Datasets:

parameterlab
/

scaling_mia_the_pile_00_HackerNews

Dataset card Data Studio Files Files and versions Community

Split (3)

train · 52.4k rows

text stringlengths 44 776k	meta dict
New 'Brexit Party' fails to register domain, gets claimed by pro-Remain group - ColinWright https://mashable.com/article/brexit-party-domain-pro-remain/ ====== whenchamenia Pretty clear case of domain squatting, as they do not posess the same org name and clearly did this out of spite. Clever, but not sophosticated. I can imagine they have a strong case with icann.	{ "pile_set_name": "HackerNews" }
Bashfill – art for your terminal - yankcrime https://max.io/bash.html ====== Lorin Here's a piece I threw together - Stormy beach, use as you may. [https://max.io/bash.html?zip=eDE1eTF4MjRlMXgzeTF4MzB5MXg1ZTF...](https://max.io/bash.html?zip=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) ------ chowes Pretty cool. Just a thought - maybe add an endpoint directly to the shell script? Would be cool to be able to simply `curl max.io/...` and see it ~~~ comboy Please don't. Why would you want that. Do you really want to put trust in another 3rd party (even if author is great, site can be compromised), just to see some colors in your terminal? I don't see how do we solve this problem by the way. Most people will always choose convenience over security. And they, as a user, must have some privileges. Even if you ask, they will just go ahead and say yes to get their thing. I understand that. Is there some clever technical fix for this, or do ransomware need to get popular enough to increase users security awareness? It seems to be a really hard problem. edit: Oh, I'm not very clever, no execution necessary here, just an output from curl. Realized that just after I sent it, but I'm leaving the reply for the second OT part. ~~~ yzmtf2008 This is a discussion that’s been had before and a problem that’s been solved before: [https://sandstorm.io/news/2015-09-24-is-curl-bash- insecure-p...](https://sandstorm.io/news/2015-09-24-is-curl-bash-insecure-pgp- verified-install) As a gist, here’s a quote: When you install software on Linux, no matter what package manager you use, you are giving that software permission to act as you. ~~~ saghm Most (if not all) legit package managers at least use checksums to reduce the chance of malicious packages getting installed; I'm not sure about others, but I believe pacman (the Arch Linux package manager) also refuses to install packages from unless you've imported the GPG key of the distributor. This isn't to say that package managers are completely safe (nothing is), but there are fairly significant differences between using a Linux package manager and piping a script from the internet to be executed. ~~~ ue_ The owner of the website could sign responses, and you could verify them, in addition to TLS via HTTPS. I think that can make it at least as secure as package management systems. ~~~ saghm Yep, I agree. Providing checksums for scripts to curl isn't the the norm from what I've seen, though, which I think fits in with what GP (of my original comment) was saying. Also, I'm not super convinced that most users would bother verifying the checksum; from what I've seen, most people downloading Linux distro images don't even bother verifying the checksums that are provided. ~~~ JeremyBanks I'd be great if something like hashpipe could become standard on Linux for this purpose. See [https://news.ycombinator.com/item?id=9318286](https://news.ycombinator.com/item?id=9318286) ~~~ saghm This is really cool! I hadn't heard of it before ------ SEJeff For some pretty art on your terminal (this command isn't going to delete anything): yes "$(seq 231 -1 16)" \| while read i; do printf "\x1b[48;5;${i}mHi $USER\n"; sleep .02; done Warning: pretty psychedelic colors ^^ ~~~ akgerber One can always open run this in bash running in a Docker image like so: docker run -it ubuntu /bin/bash ~~~ SEJeff True, but remember the wise words of Dan Walsh "Containers Don't Contain" in that if you run as root inside of a container without careful consideration, bad users can absolutely break out, just like in a chroot. [http://www.projectatomic.io/blog/2016/01/how-to-run-a- more-s...](http://www.projectatomic.io/blog/2016/01/how-to-run-a-more-secure- non-root-user-container/) [http://www.projectatomic.io/blog/2014/09/yet-another- reason-...](http://www.projectatomic.io/blog/2014/09/yet-another-reason- containers-don-t-contain-kernel-keyrings/) In newer docker, the defaults are really good, but even then, it is worth reading up. ~~~ akgerber Interesting. Thank you. ------ pixelbeat__ If you want to generate html, say for converting to an email you can use [http://www.pixelbeat.org/scripts/ansi2html.sh](http://www.pixelbeat.org/scripts/ansi2html.sh) For example: your_script \| ansi2html.sh --bg=dark > blah.html or your_script \| ansi2html.sh \| mail -a "Content-Type: text/html" [email protected] ------ gourneau Very cool, can we have image import feature too :) ~~~ Tenzer Perhaps you can use my command line image printer for something like that: [https://github.com/Tenzer/explosion](https://github.com/Tenzer/explosion). ------ binarymax Howdy all. I posted this on lobste.rs and it kinda took off. Glad to see it here again after all these years. Ask me anything. And feature/pull requests can be made here: [https://github.com/binarymax/bashfill](https://github.com/binarymax/bashfill) Happy bashfilling! ------ matt-attack Neat! Just wish I could draw something worth while... ------ owendaniel pretty cool, can you make the blocks smaller though improve detail? ~~~ hk__2 You can’t. It uses characters for pixels so you have either scale up your terminal or use a graphical image display. ~~~ irth You can use braille unicode characters for sub-character dots as in [https://github.com/rastapasta/mapscii](https://github.com/rastapasta/mapscii) ~~~ hk__2 Yes but you can’t use different colors for different dots in the same character.	{ "pile_set_name": "HackerNews" }
California Can Improve Housing and Transit by Preempting Local Ordinances - jseliger https://www.mercatus.org/publications/california-can-improve-housing-and-transit-preempting-local-ordinances ====== joeblow9999 what could go wrong?	{ "pile_set_name": "HackerNews" }
Ask HN: What to do when you don't have enough problems to solve? - _bxg1 Sometimes I come home from work at the end of the day and I still have the hankering for a problem that needs solving with code.<p>The issue is, if it's something that someone else has already done a strictly better job of implementing, it tends to feel empty. Now, obviously it's uncommon for an individual without a PhD or a senior FAANG position to do something that's both generally-useful and truly an improvement on what's out there already. So most of us instead occupy ourselves with solving narrower problems specific to a given organization.<p>But that still leaves the question: what problems can I <i>truly</i> solve - even small, narrow ones - in my spare time? Outside the context of a job or even a business idea. ====== WheelsAtLarge It's hard to find problems without narrowing your focus. Your goal is to pick an area and get informed and educated on it. Once you know enough you'll find areas where you can make a difference. Also, talk to more knowledgeable people in that area as they will be able to identify areas of pain. One of the fundamentals of software engineering is a needs analysis. A process where you ask a lot of questions that help you understand where and how software can help. But you need to focus otherwise you won't be able to get any usefull information to act on. ------ vlod An exercise to get you noticing problems around you, is take note of what you/or people around you complain about. If you immediate say "Why don't they do it this way..." take notes and leave it for a few days. The goal is to get in the routine of flexing those mental muscles.	{ "pile_set_name": "HackerNews" }
In Spain you have to be a hacker to be able to pay your taxes - etewiah https://redemptionthongs.wordpress.com/2015/11/05/in-spain-you-have-to-be-a-hacker-to-pay-your-taxes/ ====== moonbug And he didn't even get to mention the x509 client ceritifcates and java craplets. ------ marvel_boy Spain has the most incompetent burocreacy of west world. ~~~ etewiah And they are not ashamed of it ;)	{ "pile_set_name": "HackerNews" }
MoviePass says it will go dark for 'several weeks' to update its app - lando2319 https://www.cnn.com/2019/07/05/media/moviepass-app-temporarily-down-trnd/index.html ====== duxup That seems.... strange. >it hopes to "recapitalize" That doesn't sound like they are going dark just to update the app....	{ "pile_set_name": "HackerNews" }
AI Dungeon - TurkishPoptart https://play.aidungeon.io/ ====== theptip Note that AI Dungeon uses GPT-3 under the covers (though by default it's apparently a weaker "Griffin" variant; you can pay to get the stronger "Dragon" model.) If you don't have access to the OpenAI private beta, you can use AI Dungeon to play around with GPT-3 by starting a custom scenario and pasting in whatever prompts you want; for some ideas see Gwern's excellent post: [https://www.gwern.net/GPT-3#the-database- prompt](https://www.gwern.net/GPT-3#the-database-prompt). I'm particularly impressed with the "database prompt" experiment, which seems to suggest that GPT-3 has some level of self-referential reasoning, as you can tell it what it does and does not know in the context of a session, and it will "act out" an exchange based on that epistemology. ~~~ n_u_l_l According to Wikipedia[1], the free version of AI Dungeon uses GPT-2 and the paid version uses the GPT-3 OpenAI API. [1]. [https://en.wikipedia.org/wiki/AI_Dungeon](https://en.wikipedia.org/wiki/AI_Dungeon) ~~~ theptip Thanks, I stand corrected. ------ birdyrooster You fall to the floor and scream as you feel a sharp pain in your chest. You feel something in your chest, but you don't die. "By the gods," you moan. > You take some pepto bismol. You take the Pepto-Bismol, but it does nothing > to help you. The pain is just as bad, if not worse. > You take Tums. You take some antacids and try to settle your stomach. The > situation isn't getting any better though. "Help! Doctor Kovas! Help!" > You take mylanta. The Mylanta doesn't help your stomach, but it does stop > the bleeding from your nose. You manage to stand up and open the door to see > several of your guards dead, killed by the dark forces. ------ gundmc Twitch streamer MoonMoon has been playing this for a few days and I highly recommend watching the VODs. The videos are entertaining but the AI is extremely impressive. There were times when I was sure it was a mechanical turk on the backend because the replies were so good. Here's a clip chosen at random: [https://www.twitch.tv/moonmoon/clip/AggressiveBrightScallion...](https://www.twitch.tv/moonmoon/clip/AggressiveBrightScallionDatBoi) ~~~ webgoat What's funny is that the AI tends to be fairly terrible most of the time building the story in the way moon wants it to go, but then if he mentions anything remotely sexual it becomes an erotic fanfic literary genius. ------ birdyrooster > You shout don't shoot. You shout but he fires anyway. The bullet tears through your chest and you fall back onto the street. > You call 911. You die before the police arrive and your body is taken to a local mortuary. > You play dead. Your attempt to play dead is unsuccessful and you are taken into custody. The police arrive and find you are in possession of a small amount of cash. > You eat cash. The hospital tests you for any common diseases before releasing you with a clean bill of health. ~~~ Rebelgecko That pun at the end is probably coincidental, but you never know. The custom settings are surprisingly effective. I was able to generate some convincing Sasquatch erotica (not great, but on par with some of the shovelware stories you see on Amazon) ------ mcv Interesting, but not entirely coherent. Often it seems to prompt me to respond to something I think the system intended for "me" to have said. The drug dealer trying to either buy or sell some drugs from/to me starts talking about me in the third person, then complains that a lot of people don't know how to talk about themselves. ~~~ mcv Transcript of that: > You look at card. The number on the card points to a warehouse in the poorer > part of town. The warehouse is dark, with an old man standing in front of > it. He nods as you and Jeanette walk up. > You ask Jeannette: "Are you still here?" "Yes, I'm not done with him yet." > "Really?" "Yeah, I don't want to leave until I make sure he doesn't have > anything else. I want to be sure, you know?" > You "Who are you talking about?" "You, of course. Who do you think?" "What > do you mean? > You "You're talking to me about me in the third person. That sounds weird, > you know?" "Oh. Yeah, sorry about that. I forget that some people don't > really know how to talk about themselves." You laugh. "It's fine. So what do > you want to ask me?" > You "I want to get out of this life. I don't really need yet another drug > dealer." "You're serious?" "Yeah, why else would I come to you?" Jeanette > laughs. "OK. Well, I'm here if you change your mind. > You approach the old man in front of the warehouse. You walk up to the old > man, and he nods at you. "What can I do for you? > You show the card to the man. "I got this number. I guess I'm here to buy > something?" "Yeah, I got something. What do you want?" "Uh... do you have > anything worth buying? "Sure, we got most things." "Well, show me." " > You "Do you have anything special?" The man studies the card. "Yeah, we got some new gear that came in." "What is it? > You inspect the gear. You look at the gear. It's fairly high-tech looking, > and definitely more than what you usually buy. > You "What does it do?" The man pulls out a gun and shoots you in the throat. > You "Ow! Why did you do that?" The man shoots you again, this time in the chest. ===== Was I asking for a live demo of the gear and it turned out it was a gun? It was an unexpected twist. ------ JadoJodo Huh. Some interesting options, post-death. [https://user.fm/files/v2-f03aad33a2a3e2cc09c7f816435bd7d9/AI...](https://user.fm/files/v2-f03aad33a2a3e2cc09c7f816435bd7d9/AI%20Dungeon.png) ------ webel0 Interesting...my first few small entries were sort of neat. Then I tried creating a longer story including quotations and references to “you.” The reply seemed to be hard-coded to deal with hard case. Something like, “You think I’ll tell a story.” ------ AtlasBarfed AI Dungeon: You find a dragon. "Throw a rock to distract it". AI Dungeon: your rock you threw at the dragon missed. Close browser	{ "pile_set_name": "HackerNews" }
Flux is the new WndProc - gecko http://bitquabit.com/post/the-more-things-change/ ====== Todd I've also observed this similarity. The msg is like the actionType, the wParam and/or lParam are like the polymorphic objects that you pass with your action. The dispatcher is also not the most efficient model, where every store is registered to listen to every event. This is a bit like multiple windows on an event loop. The difference is that in Windows, messages are almost always targeted to a particular window's handle (hwnd). This doesn't make sense in Flux, since it's more of an observer pattern. The logic of interpreting the meaning of an action is left to each store, which is really just a cache. The biggest problem I have with Flux relates to this polymophism. I use TypeScript where possible and this is the one place where it always breaks down. I understand the appeal of JS objects but the only way to ensure your Flux based system is stable is to have lots of unit tests around your actions and stores. Redux is a more straightforward take on caching. I can also use type annotations on the reducers and associated store structure, so this helps ensure structural consistency. It also solves the isomorphism problem of server side rendering because each request can get its own state. There is no out of the box solution for this with Flux, since stores are singletons by default. Minor nit: stores are just caches with observers. I'm not sure why they weren't just called caches. ~~~ tracker1 I like how Redux is a pretty simple distillation of some flux concepts... In the end, I think it comes down to application scale. The "new" way of mutating models based on OO classes that tend to contain any given amount of logic tends to be much harder to reason with as you add features. More features means a linear to exponential growth in complexity and risk of side effects. With one-way workflows combined with immutable state, and idempotent components, it's much easier to log/replay/test any given scenario. ------ unoti The big idea from old school windows that is shared with Flux is the idea of little views that render themselves and manage their own state. In Windows we called those Controls or Window Classes. It is a good idea, and one worthy of preserving. ~~~ Too I haven't used a single GUI framework that _doesn 't_ have the concept of User Controls. It's not a big idea, it's the obvious thing to do. ~~~ unoti If you've ever created a user interface in HTML, you've used something that does not have the concept of user controls. Let's say that I want to make a numeric entry user control for entering numbers on a touch screen. This control will be made up of a collection of built-in UI controls that will work together to do what I need: let's say a text field, a couple of up and down buttons, an always-visible keypad, and a little slider that lets us move between min and max. In most HTML-based systems, it's not a built-in or natural thing to have such a self-contained "User Control" that I can just plop in to my user interface in 25 different places and have it manage itself, and the interaction between its own sub-components. Django, for example, completely lacks such a concept (although TurboGears does have it). This is a first class concept in classic Windows programming, and also in Flux-- although it's missing from most web- based systems. ~~~ Too Hehe, i was suspected someone would bring up HTML. Plain HTML is a markup language designed for documents, not a GUI framework. It hardly even has the concept of any interaction at all in the first place, how can it then have the concept of reusable and encapsulated interaction? (jquery is not a GUI framework either btw, its a DOM manipulation tool). I would say HTML is too low level to be called GUI framework. There are other low level graphic frameworks that also lack this, OpenGL for example which is designed for graphics only, if you want widgets you will have to build that yourself on top of the low level framework or find someone else who already did. But yes, you are right that it's quite lacking in this area on it's own. Although it's easy to find frameworks on top of html that adds this feature. Google for "HTML datepicker" and i bet you will find thousands of results. Other frameworks on top of html that does have this concept baked in are asp.net and anuglar. ------ mpweiher A couple of corrections: 1) Mac OS X does not store a bitmap for every widget, that's iOS's architecture. It stores a bitmap for every window. Having a layer (GPU-stored bitmap) was only introduced once CoreAnimation was ported to OS X. It was and is optional. 2) OS X Views also have a -drawRect: method that works the same way. 3) In fact that's how MVC works. See [http://blog.metaobject.com/2015/04/model-widget- controller-m...](http://blog.metaobject.com/2015/04/model-widget-controller- mwc-aka-apple.html) And react and frameworks like it just duplicated this, see [http://blog.metaobject.com/2015/04/reactnative- isn.html](http://blog.metaobject.com/2015/04/reactnative-isn.html) In fact, when I first read about react (non-native), my first thought was "hey, finally they came up with a good equivalent of NSView + drawRect: ~~~ mwcampbell Isn't drawRect: working at a different level of abstraction than React? In React, the view function constructs a virtual DOM tree, which can contain links, buttons, form fields, tables, etc. The equivalent on OS X would construct NSControls or NSCells, or objects that ultimately got translated into those, rather than just drawing on a canvas. ~~~ mpweiher I saw this as react choosing the obvious way to implement drawRect: inside a browser: painting with HTML. You could easily have a "graphics context" that accepts high-level objects, or a variant of drawRect: that creates subviews and then tells those subviews to draw themselves. I don't see this as being fundamentally/structurally different, though there is a slight difference in the implementation. ------ jowiar As someone who has written several things with Flux and Flux-esque architecture, I see it as a step in the middle, rather than where things are ending. It's not a large step from Flux (Stores update themselves in response to actions) to Redux (Model the entire application as reducers on a sequence of Actions) to RxJS Observables. What's shared in there is the idea that unidirectional data flow is a whole lot easier to reason about, model, and simulate than 2-way data flow. Everything else is semantics. ~~~ marknutter > What's shared in there is the idea that unidirectional data flow is a whole > lot easier to reason about It makes _some_ things a whole lot "easier to reason about" (so sick of that phrase), but other things not so "easy to reason about", like, for instance, error handling. Getting my head wrapped around the fact that asynchronous errors had to live in their own stores and be handled in the same way as all other data passed to the view was certainly not "easy" to reason about and still doesn't sit right with me to this day. You make concessions with every pattern and there is no silver bullet. ~~~ jowiar I'm not saying easy to reason about in the sense of "easy to learn because it isn't a change from how we used to do things", but rather, in that it allows one to easily answer: \- What is the current state of things? \- How did we arrive at the current state of things? \- What should the UI look like given the current state of things? It means that we can say: "Thing A happened, then Thing B happened, then Thing C happened". And then conceptualize "what should things look like after that chain of events". I've found this to make errors a whole lot easier about, because I don't need to piece together the state when an error happens -- just fire an action that says "An Error happened", then the stores figure out how to act accordingly. It's just another action. ------ ajsharp There are some great things going on in React / Flux, but the part that needs to be emphasized about Flux, that Facebook doesn't address explicitly anywhere, and that most people eager to always be on the cutting edge will never admit, is that this stuff was designed to solve problems for _very_ complex applications. Complexity is relative, and the solutions that reduce complexity and friction in the development process for Facebook may increase it for another organization. That is to say, Flux / React et al is by no means simple. Not even a little bit. But it probably simplified __a lot __of things for the Facebook team. However, YMMV for your 6 person startup engineering team. ~~~ davidrusu I'm convinced the complexity comes from the language, Flux/React are actually quite simple and I can put the core architecture together in under 50 loc of Elm. ~~~ marknutter The complexity comes from stitching everything together. You choose your router, your flux library, your build tools, whether or not to use JSX, whether or not to write your CSS with Javascript, which fancy new React specific testing and mocking library you need to use, how to organize your project, what best practices you should follow, what gotchas you will encounter because of Reacts relative young age as an OOP library, etc. You will always have to deal with complexity, it just depends on what kind of complexity you are willing to stomach. Some people prefer to deal with the complexity of stitching things together, other people prefer to have things stitched together for them and deal with the complexity of many abstractions. Both are fine choices, and we will debate endlessly with each other over which approach is the best approach. (hint: neither are). ------ estefan ...and so for those of us who aren't Windows developers, what learnings can we apply to flux to make it better? ~~~ gecko Well, first, I'd note that React and Flux are already learning from the past. For example, I absolutely think there are tons of similarities between WM_PAINT and React's DOM diffing, but there are also major, major differences. A really key one being that React effectively handles the rendering tree directly, and can therefore do high-level manipulation and performance work on it, whereas Windows paint messages forced the windows themselves to handle all of their state diffing and painting issues. This makes the React part of Flux a lot closer to things like WPF, or retained-mode 3D graphics. (In fact, it wouldn't shock me if that were the actual inspiration for React's DOM work, and that the rest of this is more covergent evolution.) I'd also note that we know that this style of design scales amazingly well. You can build and maintain applications as complex as Word, Myst, Netscape, and so on indefinitely. So we definitely know that this design has some historical precedent of working really well, and we're probably not way off track. That in turn means I think we can answer the "what learning can we apply" by looking at what worked well historically. For example, one of the things you have to do is to hide the low-level event loop. That's what frameworks like OWL and MFC did very early on, and I think what frameworks like Reflux are trying to do now. You even have some of that in the form of observers and so on in Flux itself. But I think that getting those types of things standardized, and a bit higher-level, will help a lot. I suspect, although I don't know, that ES5 was a bit of a blocker on getting that in Flux earlier, and suspect that Babel's pervasiveness will let that situation start changing, but that's entirely a guess. We also know that, for the overwhelming majority of apps that are actually written, having a GUI designer building on the underlying framework (e.g. Interface Builder, VisualAge's form designer, etc.) can both decrease development time and reduce bugs, and we know that such tools work best with certain patterns in how callbacks work in the underlying framework. Specifically, you want one-to-many observers, strongly typed events that can be exposed and described via reflection, etc. So I'd hope that implementing that kind of thing in Flux can be done in a forward-looking way from the beginning, rather than getting bolted on later. More generically, designing the framework with an eye towards making it tooling-friendly is probably a really good way to future-proof things from the beginning. I guess we'll see as we move forward. Each situation is a little different, so while there are parallels, it's hardly a slam-dunk that things will go exactly the same. But I do think that keeping an eye towards tooling is a really logical way to look forward and learn from the past. ~~~ estefan OK cool. It's not all bad news then. I think once we see react components converge across web + native we'll start to see more cross-platform tooling and designers springing up. I think things are looking pretty bright. Arguably the key insight the react team had was to treat the browser as a dumb output... and then realise that the DOM could just be one of many outputs. I did just wonder whether in the GUI world there was a major pattern that people were using today that Flux should be using instead. But apparently not. ------ jxm262 This was an awesome read. We use React and Flux daily at work so I'm going to share this with coworkers. I'm a little confused on what the author's concern is though. > I’ve just felt…well, weird. Something seemed off Is there anything substantively wrong with the flux pattern or drawbacks? ~~~ gecko _EDIT: I changed that paragraph; thanks for pointing out it no longer fit with the rest of the post._ _Original comment_ : The weakness of typing in the switch blocks. I'll alter that sentence a bit; it's a leftover from an earlier version of that article where I was going to focus very narrowly on how uMsg/wParam/lParam, like the way actions are usually done in Flux apps, are decoupled to the point where it's very easy to make typing errors. Then I described why I thought they were similar to begin with, and then axed most of the original post when the entire thing switched to showing how Flux is an old pattern we've done before. I'll see if I can tweak that sentence in a way that keeps the flow going. ~~~ DougBTX Using TypeScript's user defined type guards instead of a switch looks promising here, inside the 'if' the actions are type checked. ~~~ masklinn Or better, use Elm (or something similar) and tagged unions. That way you get type-checking and exhaustive-checking of your message types. You still have a big match (~switch/case) but now the compiler yells at you if you've forgotten to handle a message tag or if you're not unpacking the right types from it. ------ narrator So what is Angular then? Angular seems to me to be more like an ORM for the view where there's dirty checking of the model and then update events are dispatched to the external system which is the DOM instead of the DB. Is there something similar in the GUI toolkit world? ~~~ wmeddie Angular is very similar to the MVVM style of GUI programming that's popular in Microsoft's XAML-based libraries (e.g. WPF, Silverlight, WinRT and now UWP). Which I think is interesting because that's where they ended up. Modern windows programming doesn't involve writing WndProc functions anymore. ------ arijun Stemmed from this comment chain: [https://news.ycombinator.com/item?id=10379199&goto=item%3Fid...](https://news.ycombinator.com/item?id=10379199&goto=item%3Fid%3D10378684) ------ pducks32 See I think Flux is too low-level. I think it's too hard to reason about from the top level. Not that the architecture is inherently bad—people are using it a ton–but that things get out of hand way to fast. Regardless I can't wait to see web development in a year! ~~~ avodonosov Let's try to predict what it will look like? My guess: Borland Delphi. ~~~ porker I really hope so. ~~~ TimJYoung Our product, Elevate Web Builder, is essentially that: Delphi for web development. [http://www.elevatesoft.com/products?category=ewb&type=web](http://www.elevatesoft.com/products?category=ewb&type=web) ------ danellis I share the author's feeling of déjà vu. I feel like I've seen this article already. It was a comment posted on HN earlier today. It's kind of fascinating how someone's comment can get promoted to someone else's blog post in a few hours. ~~~ jessep Just to note, it is the original commenter's blog, not stolen. @gecko wrote "And the comment is now a blog post with more context for those who were lucky enough never to write raw Windows code" [https://news.ycombinator.com/item?id=10380508](https://news.ycombinator.com/item?id=10380508) ------ jsprogrammer And Node is essentially the Windows message loop [0]. [0] [https://en.wikipedia.org/wiki/Message_loop_in_Microsoft_Wind...](https://en.wikipedia.org/wiki/Message_loop_in_Microsoft_Windows) ~~~ amelius Yes, phrased differently, asynchronous programming is like non-preemptive (cooperative) multitasking from the Windows 3.1 era. ------ hoprocker I love the correlation between modern in-browser development and programming early personal computers. It's akin to how digital logic abstracts away the tyranny of E&M physics, but several layers higher, and this time just between instruction sets/runtimes. ChromeOS is _kind_ of making this leap, but I really wonder when web browser ASICs (or equivalent) will start popping up. ------ dustingetz The author does not understand React :( > React by itself doesn’t actually solve how to propagate changes It does actually - you update the state, then React propogates the changes for you through it's props mechanism. Flux is an extra layer of indirection over state changes _if you need it_ : [https://twitter.com/floydophone/status/649786438330945536](https://twitter.com/floydophone/status/649786438330945536) (edit: I regret my tone here, there is clearly ongoing work in this area and no widely accepted best practice yet) Flux is not message passing, React components do not redraw themselves, React components do not pass messages to each other, Flux only superficially looks like winapi because of the switch statement in that particular example. React provides the view as a function of state. winapi is nothing like that. React is a giant step towards functional programming. winapi is _definitely_ nothing like that. edit: Windows -> winapi ~~~ Aleman360 > React is a giant step towards functional programming. Windows is definitely > nothing like that. Err, that's not entirely true for MVVM apps, where views are just declarative markup that are rendered (retained mode) based on logical state provided by data bindings. It's been like that ever since XAML was introduced in 2006. ~~~ dustingetz MVVM makes ubiquitous use of mutable state which means model change listeners, callbacks calling callbacks etc, FP/React is about using immutable state to dodge all these problems by design. [http://www.dustingetz.com/2013/09/12/comparison-knockout- ang...](http://www.dustingetz.com/2013/09/12/comparison-knockout-angular- react.html) ~~~ Aleman360 The point is that in both React and XAML apps, you (usually) don't write code to mutate the View. In your code, the View is just a declarative construct. There's nothing stopping you from making immutable ViewModels in MVVM, other than bad perf (which React would presumably also suffer from on larger apps). ~~~ tracker1 Facebook doesn't seem to perform so badly in terms of a larger app. More varied components on a page than most applications in general. Most of the quirkiness I see in FB tends to come from how they deal with eventual consistency with their backend in order to scale to millions of simultaneous users. Most applications don't have the latter problem. ~~~ Aleman360 I bet they do a lot of shouldComponentUpdate, which kills the functional purity. XAML control properties do the equivalent of shouldComponentUpdate by default. Same ideas, just doing diffs in different places. ~~~ dustingetz > I bet they do a lot of shouldComponentUpdate, which kills the functional > purity. functional purity _enables_ shouldComponentUpdate ------ pducks32 Does anyone know of a good place to learn about these different approaches. I find this so fascinating. ------ amelius Stated more simply, React is just like "rebooting" your computer after you have changed the config files. It is, in this respect, quite ancient technology, except that the framework hits the "reset" button for you. ------ geowa4 I've never liked the comparison of Flux to functional reactive programming. It's really just good ol' object-oriented design. Actions are akin to the Command pattern and the Dispatcher feels like a Mediator. Passing callbacks instead of objects and making a mostly directed graph does not yield FRP. In my latest project, I used React with rx-react ([https://github.com/fdecampredon/rx- react](https://github.com/fdecampredon/rx-react)) and RxJS. That combination definitely made for some FRP fun. ------ sovande The big dispatcher switch in Flux is eerily reminiscent of how we used to program AWT widgets back in Java 1.0 days. This architecture was improved greatly in Java 1.1 with a delegation model. If the history is to repeat itself, as the OP so eloquent argues for, then, if you want to see where flux will be going in the next couple of years, start using knockout.js now and for once stay ahead of the curve. ------ antoaravinth What a great article. I was asking in my previous thread, what framework should I use React/Angular : [https://news.ycombinator.com/item?id=10359497](https://news.ycombinator.com/item?id=10359497) Clearly from what I have heard from HN and from this blog post is React with Flux is just the old of doing web development today! Thats great! ------ thewarrior Which is the best model to date for complex UI ? Cocoa + Interface Builder or XAML/WPF ? Have used Cocoa + Interface Builder and its quite a joy compared to web dev. EDIT : Has some thoughts on this : [http://stackoverflow.com/questions/2442340/how- does-cocoa-co...](http://stackoverflow.com/questions/2442340/how-does-cocoa- compare-to-microsoft-qt) ~~~ gecko I mean, both of those get things right. XAML/WPF tries to make the interface cleanly human editable in code, but is incredibly verbose, and the "can be human editable" constraint ends up being "is only human editable" pretty quickly. Interface Builder is a lot more intuitive and powerful, but it's more of an all-or-nothing affair, in my opinion. Beyond that, though, they have way more in common than they do different. I'm not sure it makes sense to talk of one of them as a better _model_ than the other, versus maybe a better _implementation_ of the same workflow. ~~~ thewarrior According to [http://stackoverflow.com/questions/2442340/how-does-cocoa- co...](http://stackoverflow.com/questions/2442340/how-does-cocoa-compare-to- microsoft-qt) WPF is better. ~~~ kybernetyk Well, as there's no Cocoa on Windows and no WPF on OS X it doesn't really matter. Also that SO post reads a lot like "I can't stand Interface Builder" (which is understandable if you aren't prepare to embrace it). I find the Cocoa model of not having to do anything with XML far better for my sanity. But then again I guess there are people who prefer XML artistry to drawRect overriding. :) ------ avodonosov In this line of reinventing the wheel of UI programming in web dev, I am waiting for Borland Delphi reincarnation. ------ iMark I've only looked into iOS programming a little, but is this not similar to how views are handled there too? ------ jesstaa Also, Ruby on Rails is Flux. ------ whatever_dude The writer really likes the word "idempotent". ~~~ tobr And uses it incorrectly. Idempotence is when f(f(x)) == f(x). React views take some props and/or state and return a component, so applying the view to its output would just give an error. I think the word he's looking for is "pure". EDIT: I was wrong - apparently "idempotent" can also describe a consistent relationship between the input and some state. In that sense, it's actually a very good description of how the input to a React view affects the DOM. ~~~ kgen Well, even in Wikipedia, the definition is quoted as being different for CS vs the unary operation you describe. "In computer science, the term idempotent is used more comprehensively to describe an operation that will produce the same results if executed once or multiple times." Which is more that f(x) == f(x) == f(x) for the state affected by f. ~~~ tobr Thank you for pointing this out, I was not aware that the word could be used this way. They are really quite different concepts. ~~~ matchu I'm not sure that they are. You just need to model the concept of state as the function's input/output, as functional programmers are eager to do :) If we start in state x, then apply operation f, the resulting state is f(x). If we apply operation f again, we'll be in state f(f(x)). If f is idempotent, then state f(x) and state f(f(x)) are identical. ------ underwater WndProc is how the windows manager communicates with Windows UI code. Flux is how the UI communicates actions back to the data layer of the application. They're completely different.	{ "pile_set_name": "HackerNews" }
The Physics of Brute Force (2016) - tiord https://pthree.org/2016/06/19/the-physics-of-brute-force/ ====== Qision >where 0 Kelvin is defined as a system devoid of energy This is not true, in quantum mechanics at zero kelvin (so in its fundamental state) a system has a non zero energy. See this: [https://en.wikipedia.org/wiki/Quantum_harmonic_oscillator#Ha...](https://en.wikipedia.org/wiki/Quantum_harmonic_oscillator#Hamiltonian_and_energy_eigenstates) ~~~ pif You're right. Zero Kelvin means no _entropy_. ~~~ dmarchand90 Is that true either? E.g a metastable glass structure sent to 0k probably still has an entropy? ~~~ ExThermoGuy [edit:] Third law states 0K is impossible. That's the obvious and simplest answer. So everything bellow assumes the limit as you approach 0K. I think in that case you reach a paradox because temperature is a quantity (typically) defined in thermodynamics, i.e. systems in equilibrium. A metastable glass is not in its ground state, therefore not in equilibrium, therefore not technically within the purview of thermo. This might seem like a cop out, but a similar question was asked in my qualifier. The answer, glass is not technically described my thermo and at 0K the whole thing breaks down [1] Sure we still talk about entropy and temperature of glass, but it's stretching the definitions. Another way to look at it, though, is that at 0K there is only one state available to the system (even though it is a glassy one). Therefore call the glass a new state of matter, and set S=0. If that feels weird because it's not the ground state, consider that glass' constituents, Si and O, are not in a ground state either, that'd be Fe. You don't have any problems dealing with metastable Si and O, do you? Either way, 0K makes no sense! Also, it's weird (actually wrong) to even think about materials at 0K. In classical thermo your heat capacity is zero. In modern physics your atoms' "positions'" are fully determined, therefore their "momentum" is fully undetermined. So 0K is a state that makes zero sense. [1] I forget the question. I think it was like this: the entropy of glass has a greater slope than the crystal, therefore, if you cool the glass low enough it will achieve a lower entropy than the crystal. How can a glass have lower S than its crystal state? ------ effie Of course, current computers are nowhere near capable to try out substantial portion of all 256 bit keys. It requires massive amount of energy and time to perform single bit operation, much larger than kT for room temperature T (several orders of magnitude). Not mentioning costs of trying out the resulting bit sequence for validity as a key. That should be the argument for "256 bit keys are enough". There isn't any fundamental energy cost imposed by physics here, however. Both because 1) bit flipping can be done in a logically reversible way, just go systematically from 0 to 2^256 - 1 so Landauer's assumptions do not even apply 2) Landauer's idea has been criticized for being vague/badly reasoned. Most weirdly, Landauer assumes that erasure of a bit register in general requires that thermodynamic entropy _k_ ln 2 per bit is acquired by the environment. It seems people are confused and can't distinguish information entropy and thermodynamic entropy here. In real computers, erasure of bit register decreases information entropy by _k_ ln 2 and increases thermodynamic entropy (by HW-specific amount) associated with the register. These are two different kinds of entropies. In short, real world energy costs are far higher than Landauer's limit due to current tech limitations, and possible energy cost savings in the future aren't hard limited by Landauer's limit at all. Landauer's idea is simply too problematic. Don't rely on it for any argument about real world. Finally, don't learn physics from computer science guys, even if their name is Bruce Schneier. Just as you wouldn't learn computer science from physics experts. ------ effie > _" One of the consequences of the second law of thermodynamics, is that it > requires energy to do a certain amount of work."_ No, that is a restatement of the First law of thermodynamics. Second law states that it is impossible to systematically (cyclically) extract heat and turn it completely into equivalent amount of work. ------ effie > So, we'll run this ideal computer at 2.72548 Kelvin. The record for lowest temperature is 1e-10 Kelvin and there is no theoretical limit as to how many zeroes can be added. So there is no hard limit, given good enough cooling/thermal isolation, the energy cost can be brought down. In theory, it can be brought down to zero. ~~~ SolarNet This is addressed: > To run a computer cooler than that would require a heat pump, which means > adding additional energy to the system than what is needed for our > computation. ~~~ effie That does not address it. It is true that heat has to be removed to maintain the lower temperature. But the rate at which this has to be done depends on heat generation and quality of isolation. If temperature inside is 1e-100 K, energy cost of only bit flipping becomes negligible. Energy cost of refrigeration depends then on how good the isolation is. With better and better isolation, the cost goes down, the only limit is zero. ------ murgindrag The problem is I don't need to search the whole key space. Even with very goods encryption algorithms, there are faster attacks. They're not FAST attacks, mind you, so the keys are safe, but they are FASTer. ~~~ PaulHoule I think most of the time there is some attack on a cipher which is faster than the most obvious brute force attack. Sometimes the speed-up is a little, sometimes it is a lot.	{ "pile_set_name": "HackerNews" }
App Engine SDK 1.3.5 - New Task Queue, Python Precompilation, and Blob Features - pufuwozu http://googleappengine.blogspot.com/2010/06/app-engine-sdk-135-released-with-new.html ====== kljensen The pre-compilation of python code appears to significantly decrease the time required for cold starts. That's just great. Awesome team, awesome platform. ------ floodfx Does anyone use AppEngine in production? I am not trying to troll but we've have had pretty poor performance getting data out of their datastore. We only have a couple operations apps running on it and I could not imagine running anything that need to perform on GAE. BTW - We've had slowness in both Java and Python... ~~~ melling Is anyone using Java on GAE? I love Java in general but for web dev I never found a great framework. Was considering learning Python/Django. However, the one thing about Java is that I might be able to go with Scala and/or Clojure at some point. ~~~ gtani lift on GAE: [http://distractable.net/coding/google-appengine-language- per...](http://distractable.net/coding/google-appengine-language-performance- comparison-followup/) [http://groups.google.com/group/scala- london/browse_thread/th...](http://groups.google.com/group/scala- london/browse_thread/thread/4facf58a93026d68#) ------ riobard Is Python pre-compilation just compiling to bytecode as in .pyc files, or is it compiling to native code? ~~~ rbanffy Most certainly to .pyc. Native code is the realm of a JIT runtime. ------ ibagrak Still waiting for that full text search API. I believe the ticket was 'started' in October last year. [http://code.google.com/p/googleappengine/issues/detail?id=21...](http://code.google.com/p/googleappengine/issues/detail?id=217) ~~~ joshu why is this downvoted? i completely agree. ~~~ ibagrak I didn't mean it as a complaint either. Just to clarify: I am a pretty happy user of GAE. Full text search is one thing that is missing from the feature set that could make my life as a GAE developer a lot easier.	{ "pile_set_name": "HackerNews" }
OpenID Connect spec is now there - bergie http://openidconnect.com/ ====== daveman692 This is my old first draft from last year. Others have been working on making it real over the past few months but the site hasn't been updated yet. ~~~ wmf It definitely needs some big picture explanation up front. ------ michaelchisari Hasn't this been around for a while now? It says (c) 2010, and I could have sworn I've read this spec before. ------ bergie This is where the final spec apparently lives, but seems to be down now: <http://openid.net/specs/openid-connect-core-1_0.html>	{ "pile_set_name": "HackerNews" }
Stupid Idea: Hoisting at the end (Javascript) - vjeux http://blog.vjeux.com/2011/javascript/stupid-idea-hoisting-at-the-end.html ====== benatkin I can't think of any reason why it wouldn't work.	{ "pile_set_name": "HackerNews" }
YouTube and Facebook Are Losing Creators to Blockchain-Powered Rivals - rbanffy https://www.bloomberg.com/news/articles/2018-04-10/youtube-and-facebook-are-losing-creators-to-blockchain-powered-rivals ====== Jyaif Roughly half of the content is about cryptocurrencies. The other half is stolen content (e.g. [https://d.tube/#!/c/nba- highlights](https://d.tube/#!/c/nba-highlights) ). I don't think YT and FB are sad about losing those types of "creators". ~~~ Grue3 YT wasn't very sad about stolen content when they were starting up... ~~~ kitotik They still are anything but sad about it. The amount of pirated music on their platform is mind boggling. ~~~ strictnein A lot of that is fully monetized by the copyright owners. ~~~ LordHeini Or the random person who uploaded it. ~~~ strictnein Youtube automatically identifies almost all copyrighted music when videos are uploaded and copyright owners can decide who will be the one to monetize it. Almost all of the major players have the monetization assigned to themselves. ~~~ LordHeini How do you know that? There are tons of whole albums which are definitively not "monetized" by their makers. E.g. old stuff where the band does not exists anymore or all the low selling genres where nobody cares. It is not a bad thing since i discovered a lot of cool stuff like that. ~~~ strictnein There's some long tail stuff that isn't, but the large majority is. A breakdown of how the system works (they're trying to sell music for you to use, but it's still a good writeup): [https://www.safemusiclist.com/can-use-copyrighted-music- yout...](https://www.safemusiclist.com/can-use-copyrighted-music-youtube/) ------ mrtksn You know what's interesting? A Decentralised media platform used to be huge and actually is still huge: Torrents. There's a huge community that consumes media that's not hosted anywhere particular and there are apps like Popcorn Time that offer viewing experience almost as good as Netflix. The problem, of course, is that up until now there was no way to reward the creators and almost all the media consumed on Torrents is illicit copies of copyrighted material that don't bring direct benefits to its creators. It is a huge topic in the blockchain community to find a way to reward content creators and we see early attempts that may or may not succeed at this. Another issue is the "Averagisation" of the content. The moment that you make a content that advertisers might find controversial you risk losing your reward for that content so advertising financed media fails to capture anything beyond the mainstream entertainment. This has another unfortunate outcome, which is that people who don't want to get a direct reward for their content but hoping to be rewarded with political influence can afford to continue producing content that tends to be extremist(veganism, left and right politics, racism, conspiracy theories - you name it). So we end up with extremely light content that's something between product unboxing and funny videos not touching any sensitive topic and extremely edgy content that depicts the world as black and white and if you are not one of us you are one of them. Your average monetised content on Youtube is extremely light and your average popular non-monetised conted is extremeley heavy. At this time you'll find that these new decentralised platforms are full of the extremist's stuff, as it is just another platform to spread their influence but in the long run, I believe that they will be diluted and will offer a platform where non-extremist but alternative cultures can flourish. ~~~ cornholio You certainly don't need blockchains and distributed databases to reward creators, centralized solutions like Patreon work perfectly fine. If you want Netflix style monetization, that is not a technical problem but a social one, Netflix relies on the concept of copyright. Any community that does not respect copyright will switch to the free alternative, leaving voluntary donations as the only monetization option. Maybe there is a blockchain niche where content is offered freely but ad supported, with the experience painless enough not to motivate users to switch to the ad-free alternative. The revenue would then be necessarily modest, but would be redirected to the creators almost in full, compensating the massive Youtube cut. ~~~ koonsolo I don't agree with your Netflix story. Most people don't prefer free, they prefer convenience. Spotify almost works properly as a centralized platform because almost all music is on there. But I know a few albums that aren't, and it's too bad. For Netflix, I have a subscription. But guess what I do when I want to watch the latest Walking Dead or Game of Thrones. I want it convenient, preferably legal, but most of all convenient. ~~~ ghaff How is subscribing to HBO inconvenient? It's a combination of price and convenience. There's some upper limit to the monthly price you (and everyone else) is willing to pay for content. ~~~ prepend HBO Now is a much worse experience than torrents. The navigation is slow, the updates to new episodes are poorly placed under a bunch of clicks, there are ads for other hbo shows over and over (even after I watched every single West world episode they still show me ads about a “new show”), streaming bugs (Although this improved quite a bit). It wasn’t the price that moved me away from HBONow, it was their lack of convenience compared to a torrent rig. It ended up being HBO’s design was more for themselves rather than me (“we want to show you ads” vs “you want to watch your shows”). It was still very old in its philosophy of content. Netflix however is awesome because it’s very UX focused. Ultimately, I think only OSS/pirate are closest to the use desires. ~~~ ryanianian > Netflix however is awesome because it’s very UX focused. Except for the thousands of A/B experiments that incessantly drive you to spend every ounce of attention on Netflix. E.g. the auto-playing preview that starts whenever you stop moving the active selection. It strongly encourages you to start playing the thing rather than being thoughtful about whether you actually want to or not. Personally I hate this - it drives my anxiety nuts - and I find HBO's tactics much less user-hostile (although agreed the ads for HBO's own content are outright stupid). ------ anthonybsd This article is pure clickbait. Make some half-assed, sensationalist, barely verifiable claim, sprinkle some crypto / blockchain / bitcoin seasoning on top, and to the moon you go. ~~~ sametmax Yeap. I'm deep in crypto. I have literally a company making money by providing service for masternode holders. Yet even I recognize the tech is nowhere close to be user friendly for even the most basic use. Youtube loosing anything to blockchain solutions ? Yeah, in 10 years maybe. Right now we are still working hard to figure out how to makes things work, and make money without scamming people. I mean, come on, I regularly have to compile wallets from source to make them work, sometime fixing the build process in the meantime. I have dedicated app armor profiles that I have to custom make for each one because you basically can't trust any of them. Why is this article even on HN ? Who upvote that ? Either we have a lot of new users with a completely different mindset than a few years ago, or we have PR agency pushing some agenda. And given the article is on Bloomberg... ~~~ vk23 >Youtube loosing anything to blockchain solutions ? >Yeah, in 10 years maybe. I think it's way more likely for Youtube/Google to implement some sort of blockchain based system to reward creators. ~~~ sametmax I doubt it. That would make it either way too transparent and open, or just a blockchain implementation of a centralized black box. ~~~ vk23 Blockchain implementations in centralized black boxes are more likely than not the future of blockchain. As soon as regulation gets rolled out usable blockchains will be controlled by governments and/or private companies that comply with the rules. Not that I'm not in favor of a truely decentralized solution but I doubt "they" will allow this to happen. ~~~ sametmax Well they never managed to shutdown torrent or tor, so decentralized is still alive and kicking. But yeah, we are likely to see a lot of people using the "blockchain" label for marketing reason, not using the tech for any of it's benefits. But that's silly even from a technical point of view: if you don't need decentralization and transparency, then a blockchain is a very poor alternative to a blackbox built on postgress. ------ philfrasty I see a lot of articles talking about ad revenue. For most YouTubers ad revenue is minuscule compared to what they make on product placements. Someone in the lifestyle/beauty segment with say 300k subs on YT (and similiar IG following) might make 500$ in ads a month on YouTube but 8k to 10k per product placement. This doesn't include multi-post deals (usually YT and IG combined) that will yield (from what I have seen) 40k to 60k in collaboration with e.g. big beauty brands. ~~~ mrtksn Well, product placements are still advertisement. It simply means that these ads are not managed by Google but other agencies that match Youtubers with advertisers. I wonder if Google is happy with that? ~~~ richjdsmith I doubt it. I wouldn't be surprised to see a situation that content creators would pay google for visibility (notifications, showing up in subscribers feeds etc.) in order to satisfy their product placement contracts. ~~~ wolco Youtube has been labeling these videos with a paid promotion scrolling warning. ~~~ tokai They do that because they have to. [https://www.out- law.com/en/articles/2016/july/digital-influe...](https://www.out- law.com/en/articles/2016/july/digital-influencers-must-disclose-paid-for- content-says-new-guidance/) ------ nafest STEEM is full of bots and content with purchased upvotes. (most articles have more upvotes than views, funny, hey?) There are only about 60.000 active users and this number is stagnating for months. No way, that Facebook or Youtube are loosing users towards this platform. ~~~ BadassFractal Was also disappointed by Steemit. I liked the concept and wanted it to work, but in practice the service was 99% people (or bots) trying to game the system uploading garbage. Any real quality content gets drowned among spam. ~~~ pjc50 Systems that promise to pay for content production create a massive, direct incentive to game the system and spam it. ~~~ BadassFractal Yep. Don't get me wrong, I really want these guys to win, but the current system is just not good enough. I don't know how exactly they'll go around solving that problem though. ~~~ ghaff There are well-established systems to pay for content. The problem is that they're very manual, take a big cut, and are relatively selective. They go by names like publishers, labels, studios, and so forth. They actually work for some definitions of work but you have to be OK with relatively high barriers to entry and with a clearly-defined gatekeeper role. ------ fortythirteen All of these "alternatives" suck. Whether you believe in censorship or not (I don't), building a no-censorship alternative to a major media platform mostly attracts the people who were censored because of truly abhorrent content. Gab and voat suck because 90% of the content is extremist bullshit. The development community needs to stop building "alternatives", with the hope that they become the next big thing, and go back to building things that we want to use ourselves. ~~~ kadenshep >content is extremist bullshit. Mainly just right+ extremists. No need to beat around the bush. ~~~ fortythirteen That's only because the left+ extremists are tolerated, if not condoned, on the SV run platforms. ~~~ kadenshep Probably because left+ extremists don't inherently have dehumanization and genocide as part of their political and moral beliefs. You can disagree with economic allocation theories, but it's really not appropriate to compare the two. ~~~ fortythirteen Yes, the only thing they have going for them is that the initial factor they use for putting someone against the wall is economic and not race based. They still put innocent people against the wall. How is this not clear to you? ~~~ kadenshep >How is this not clear to you? Because it's objectively a straw man and isn't based on anything except your ideological preconceptions? >the initial factor they use for putting someone against the wall is economic and not race based. * Huge citation needed ~~~ fortythirteen Citation? Lenin, Stalin, Mao, three generations of Kims, Guevara, Castro, Pol Pot, Ho Chi Min. All murdered massive amounts of their own people for not being communist. ------ sschueller I like peertube [1] because it is about getting the Technology working without all the crypto and money making stuff on top. Similar to mastodon [2]. [1] [https://github.com/Chocobozzz/PeerTube](https://github.com/Chocobozzz/PeerTube) [2] [https://mastodon.social/about](https://mastodon.social/about) ------ snikeris Yours.org is is my favorite example of this. Writers of articles receive Bitcoin Cash from the community. Interestingly, it costs Bitcoin Cash to upvote content and comment on things. Presumably this helps combat upvote bots and spammers. Edit: forgot to mention that if you upvote content, later upvotes of the same content earn you money. This incentivizes people to discover and promote new content they think will be popular on the platform. ~~~ wernsey I find it an interesting concept, but as with so many of these solutions I don't really see why you have to have Bitcoin Cash to make it work. They could charge your credit card for upvotes and pay you in fiat like Patreon does, and the functionality will be exactly the same from the end user's perspective. ~~~ nodja I think it boils down to payment processing fees. For patreon for example it would be super inconvenient (and expensive) to process all payments individually, so payments are made in bulk. This is why monthly payments are the standard. With crypto you can perform instant sub $1 payments with minimal fees (blocks aren't full so it's super low atm). It also saves not having to handle chargebacks, fraud, etc. ------ thisisit The article has an interesting perspective, but it doesn't answer the perennial question - How many creators exactly? Then there is this: > , a growing swath of creators have fled to sites such as DTube to avoid the > constraints. Like other upstart sites, DTube runs on the blockchain network > Steem, and users can pay creators and commenters in digital tokens. The article doesn't go beyond Dtube and Steemit at all, even though it tries to quote them as examples. So the question is - what such sites other than Dtube? Actually, on reading it closely this is a submarine piece if there ever was one. ~~~ Legogris > Actually, on reading it closely this is a submarine piece if there ever was > one. Never heard the term "submarine piece" before - care to explain its > meaning and origin? (Googling yielded nothing) ~~~ skywhopper [http://www.paulgraham.com/submarine.html](http://www.paulgraham.com/submarine.html) It's a PR piece masquerading as a news article, supported by the reporter's relationship with PR reps for the named companies. Not that it was planted or bought. It's just lazy reporting. Write up a summary of what your friends and/or acquaintances say, don't do any real background, and definitely don't be skeptical of any claims. Accept terms like "blockchain" as something it makes sense for video streaming sites to be built on. You end up with an article that took little time to write, gets plenty of clickthroughs thanks to its great headline. Another deadline met. ------ egwynn The real question is whether wider audiences of valuable consumers will follow the defecting creators. This feels like a repeat of gab/voat but for video. Neither of those platforms seem to have broken outside of their core bases of “original defectors” to become real contenders to their predecessors (twitter / reddit). ------ fbn79 Anyone remember Joost from Skype Founder? ([https://en.wikipedia.org/wiki/Joost](https://en.wikipedia.org/wiki/Joost)). ------ throw2016 We need decentralization and a multitude of platforms. A single centralized platform can't scale and no amount of automation can solve that. Human moderators are expensive and won't scale. Who is going to vet 400,000 hours of video per minute Youtube apparently gets or the volume of posts Facebook gets? It's not practically possible. Before no one really cared, but as the real world consequences of a centralized platform, surveillance and propaganda become clear the cost to free society becomes too great. The only half way measure that may work now is to stop hoovering up data, stop trying to make endless correlations and inferences to offer micro targeting. Similarly advertisers can target by location and immediate textual context but micro targeting should be disallowed. With proper legislation this can easily to enforced. ------ klez I'm not sure I understand. Are these sites paying with cryptocurrencies or is the content delivery based on blockchains? The article is a bit vague about this. ~~~ Jyaif The article is shit, that's for sure. Only the payment is via cryptocurrency. The content delivery is as centralized as ever, so this does not change anything wrt to "privacy concerns, censorship". ~~~ DalasNoin It uses IPFS for hosting, IPFS stores hashes on a blockchain. IPFS is according to wikipedia a distributed file system. ------ otterpro I like the idea of Dtube and I signed up (via steemit and took about a week to be aproved) so I can upload video as an alternative to Youtube, but it's frustrating to click on video and wait for few minutes of loading screen only to get a cryptic "Error occurred while loading video", especially videos that are older than a month old. I'm not sure why I couldn't view these videos, but my guess is that either that they were taken down by the owner or by others for violation, or that there were problems in IPFS. Anyway, it's been a very frustrating experience so far. ------ sathishvj Surprised that there is no mention of Brave and BAT in the article and in the comments so far. ~~~ rainbowmverse Whatever your perspective on Brendan Eich's views[0], anything he's in charge of is a powder keg waiting to blow up. Brave/BAT will never go far while this conflict remains. [0] Which he refused to clarify, leaving people to make heuristic decisions based on available info and personal experience with homophobia. He is, of course, free to think and feel however he wants and not share details. Others are free to decide what to invest time, energy, and money in. ~~~ maxencecornet >powder keg waiting to blow up I don't get it, what do you mean ? Is this related to his homophobia ? I don't understand why so many people can't judge Eich without pointing his homophobia, how is this even related to his tech abilities ?. The guy is a visionary, I mean he was defending privacy when privacy wasn't an even a mainstream issue, he invented in-browser scripting BAT will be mainstream, no doubt about this ! ------ maxencecornet The blockchain-based alternative to Twitter, peepeth.com is worth mentioning too I've been using it since 10 days, it's really well made ~~~ gr33nman There is also the holochain-based Twitter alternative, Clutter: [https://github.com/holochain/clutter](https://github.com/holochain/clutter) Holochain is a blockchain alternative designed to avoid blockchain’s scalability and energy consumption issues. ------ grandinj One swallow doth not a summer make ------ jacksmith21006 Google shared 1.6 billion hours consumed a day on YouTube up from 1 billion hours a year earlier. So does not look like it making a debt. ------ iamben Doesn't all this come back to "it's better until it has to play within the confines of the system"? I see so many articles about X disrupting Y, but if Y is operating within the confines of the law, half the reasons people are saying X is better are moot as soon X comes in line with Y. WRT to the article - YouTube may have clamped down on blockchain ads and extremist content, but what happens when DTube (or whoever) starting getting in to hot-water relating to the content, or the ads they're showing. Or someone decides to go hard about cryptocurrencies and taxes and they get caught up. Then it's just another YouTube without as many users. All that said, I applaud anyone that tries to compete against a monopoly. Just think the odds are very much against them. ------ kauffj Hi, LBRY CEO here (LBRY.io). If you're interested in our technology and product, everything we build is open-source and MIT licensed. Our GitHub is at github.com/lbryio There is a contributing guide at lbry.io/faq/contributing . We send cryptocurrency for all accepted PRs. ------ ruiquelhas > All three advertising-driven sites are phasing out ads for cryptocurrencies, > shielding themselves from potential legal liability if the ads are scams or > the digital coins are eventually regulated as securities. There isn't any other reason for these platforms to have any kind of usage whatsoever as of today. The creator of one of those so-called blockchains is a known scammer himself, so I guess it makes it full-circle. ------ slantaclaus The financial press is obsessed with blockchain. I’m sure there is something to that (payments? Real estate ledgers?), but this isn’t it. ~~~ maxencecornet The tech world too... All my freelance dev. friends are learning Solidity and blockchain programming. It's the latest tech trend, like noSQL/mongoDB a few years ago ------ Risse LBRY, that was mentioned in the article, has a Youtube Partner Program that pays the content creators in crypto currency for syncing their Youtube content to the blockchain. [https://lbry.io/youtube](https://lbry.io/youtube) ------ amelius If you have a Youtube channel, then how do you move your viewers over to DTube? I suspect Youtube will ban you if you simply link to DTube (or am I wrong?) What if you have your own website, which links to DTube? ~~~ Erlich_Bachman That would be really bad business practices and I haven't heard of anyone experiencing this. So yes, you should be able to post links to whatever other website you have. Many people post links to their blogs, websites, patreons, etc. This might change in the future, but so far it hasn't been a problem. ~~~ amelius > That would be really bad business practices According to stories I read, there's some dark stuff going on at Youtube, e.g. [1], discussion [2]. So I wouldn't be surprised if they'd downrank or delete your channel if you start linking to external video sites. (Note: I have no personal experience with this). [1] [https://www.maxlaumeister.com/blog/google-is-deleting- your-f...](https://www.maxlaumeister.com/blog/google-is-deleting-your- favorite-youtube-videos/) [2] [https://news.ycombinator.com/item?id=15528942](https://news.ycombinator.com/item?id=15528942) ------ homakov Something is blockchain powered when you use it as full node. Light node the very least. Dtube and steem are just websites you load in your browser. None of blockchain properties are inherited in this case. ------ kiostech I am considering to start a YouTube channel recently, dtube maybe a great alternative. However, apart from a donation, is there any other possible income source for the creator? ------ wufufufu What does it mean to be "blockchain-powered"? Your funding comes from tricking investors into thinking adding blockchain to every aspect of life is the future? ------ amelius How well do these alternatives work on mobile? And how well do they work with existing services (e.g. can I post a link to a video on Facebook, will it open the native viewer, etc.?) ------ oh-kumudo Opened the link, can't play. Guess blockchain overall doesn't suit me very well. If however, it suits them, good luck, more alternatives aren't bad. ------ amelius Is decentralized synonymous with blockchain-powered now? ------ Arzh I zoned out about half-way, are the sites actually built on blockchain or are they just using crypto currencies? ------ jeena I wanted to sign up, but they wanted my phone number. Fail. ------ tobyhinloopen Yes maybe like 10 creators ------ ForHackernews Hahahaha, no they are not. ~~~ maxencecornet How do you know that ? Are you familiar with Dtube or steemit ? As a Dtube user, It's true that there are more and more content creators everyday on the platform. The amount of content is still veeeeery far away for Youtube's, I'm pretty sure Youtube/Medium/Twitter don't really care about their blockchain-based counterparts right now, because of how small and hard to scale they are ~~~ netzone Well.. That's the point isn't it? I've never heard about it, and likely only people interested in blockchain stuff has, I would guess. On that note, are there any mainstream blockchain based sites or apps right now? Would be interesting to know. ~~~ maxencecornet >likely only people interested in blockchain stuff has Not sure, Furious Pete has moved his audience to Dtube and he is a fitness vlogger >On that note, are there any mainstream blockchain based sites or apps right now? Would be interesting to know I think that Circle is the most mainstream blockchain based app right now, because no one using it know that it's blockchain-based ! [https://www.circle.com](https://www.circle.com) [https://en.wikipedia.org/wiki/Circle_(company)](https://en.wikipedia.org/wiki/Circle_$company$) ~~~ mcintyre1994 Do you have any idea how Circle works? I guess nobody knows it's blockchain- based because it's instant and has no fees, which doesn't sound like a blockchain. Are they just making a loss and swallowing all the risk (covering fees and transfering real cash before any blockchain confirmations) or is something else going on? ~~~ ForHackernews I doubt they're doing anything on a blockchain, unless it's a "private blockchain" (aka database) ------ largehotcoffee No, they aren't. ------ notspanishflu Link without tracking [https://www.bloomberg.com/news/articles/2018-04-10/youtube-a...](https://www.bloomberg.com/news/articles/2018-04-10/youtube- and-facebook-are-losing-creators-to-blockchain-powered-rivals) PS HN should snip the tracking part in OPs automatically. ~~~ pandasun [https://write.as/b7s8ggwfu4znd.md](https://write.as/b7s8ggwfu4znd.md) Usenet post next? :P ------ gigatexal Good. ------ ebbv What a load of crap. Major channels are not giving up their enormous paychecks from Google to take a flier on blockchain powered alternatives with no audience on it. The only people switching are people who have a vested interest in everything blockchain or those who are being driven off Youtube by the ad policy changes. ~~~ dingaling But if the 'little folk' who are affected by the monetization changes find they can make money on Dtube or wherever, who will fill the lower tranches of YouTube? Other than those producing and uploading out of principle and without desire to earn anything. Unless you can ramp quickly to 4,000 hours of viewing per year, YouTube is a penniless grind. Whereas other sites offer pay-per-view right from the first viewer. ~~~ ebbv Depends on your goals and your audience. My channel is about guitar stuff, I joined an existing community and am easily finding viewers on Youtube. It might be an uphill battle for me on one of those alternative platforms, and frankly I have no interest in even giving them a shot. I know there's millions of people viewing millions of hours a day on Youtube, and I know how the game is played there. Those other platforms are unproven and frankly I don't know who's behind them. Just as Google decided to implement policies that favor their advertisers, these blockchain based alternatives may decide anyone with any tweets that can be perceived as being unfriendly towards cryptocurrencies get shut down, just as an example. The devil you know....	{ "pile_set_name": "HackerNews" }
My father, the philosopher - sajid http://thehairpin.com/2015/03/my-father-the-philosopher/ ====== lowmagnet Is it considered "ok" now to refresh a page after a few minutes just to get fresh ads? I was in the middle of a sentence and the entire page reloaded and scrolled to the top. I lost my place.	{ "pile_set_name": "HackerNews" }
Cisco Open Source on GitHub – Project Contiv Code Hackathon - kschw http://blogs.cisco.com/datacenter/cisco-open-source-project-contiv-winner-at-onug-spring ====== brobinson The open source code is available here: [https://github.com/contiv](https://github.com/contiv)	{ "pile_set_name": "HackerNews" }
Super Mario AI Competition - fogus http://julian.togelius.com/mariocompetition2009/ ====== naveensundar AI contests like this and the DARPA Grand Challenge Race encourage solutions in a single domain. AFAIK in the DARPA Challenge there was overfitting and I doubt the generalization capability of the systems involved. We need more contests in the spirit of "General Game Playing" contests where the problem domain is unknown to the programmers. <http://games.stanford.edu/>. You only get a formal description before the game and a small amount of "thinking" time which the system has to use understand the game and formulate a strategy. ~~~ apu There is a vast difference between AI for games (which are purely theoretical exercises) and AI for working in the real world. The fundamental characteristic of the real world is that there is uncertainty and ambiguity in every measurement and even your actions (did my car actually move when I pressed the accelerator?). The kinds of systems you build to tackle these latter types of problems are _very different_ from the kinds you need for the first type. Both have their place, of course, although IMHO, the latter type is more interesting, as it's a much messier area to work in. ~~~ naveensundar Well, messiness is just one part of the problem. I usually see AI as a layered system that solves a general problem. The layers are broadly: lower level sensory systems(vision, speech recognition) and higher level symbolic reasoning systems. Recently, there has a been a lot of success in the lower layers due to Machine Learning and probabilistic systems. The messiness comes in the lower layers. When dealing with the higher layers you face much harder problems. Hard in the sense of Turing uncomputable. The only formal solution proposed for general AI is uncomputable <http://www.hutter1.net/ai/uaibook.htm>. Also there is nothing which restricts real world problem solvers to a single domain. Most messy problems have a formal solution. The engineering part is what remains (but the engineering part is nevertheless hard!). Some non "messy" problems have no computable solution e.g. deciding whether an arbitrary argument in first order logic is true. They challenge the bounds on human thinking. Also "General Game Playing" is not only about games. (Like Game Theory is not only about games). ~~~ apu I don't agree that the higher level symbolic reasoning is necessarily harder, nor that the lower level is simply engineering. The problems at the low-level are still very tough, and require scientific (and not just hacky- or engineering-) approaches. As for the "single domain" issue, this was a big red herring in old-style AI (before the so-called AI winter) -- basically, it turns out that the different branches of what used to be called AI (e.g., vision, machine learning, NLP, speech, etc.) have to use quite different techniques. "General" AI systems such as logic, game players (and yes, I know it's not just about games), etc., can be used in various domains, but in general they're not very applicable to most real-world problems in the different domains. For example, I work in computer vision, and while we certainly use a lot of probabilistic analysis that can be broadly applicable to other domains, a lot of the progress in recent years has been using techniques that aren't really transferable (e.g., SIFT or SLAM). ~~~ naveensundar General AI is not applicable in real life yet. Probabilistic reasoning can be subsumed into a logic system. For example, a human(David Lowe) has originated SIFT. A reasoning system should in principle be able to derive SIFT. We are not there yet but that should be the goal. The problem with singe domain systems is none are even capable of robust inductive transfer (<http://en.wikipedia.org/wiki/Inductive_transfer>). Some reasoning problems are mathematically hard problems (<http://en.wikipedia.org/wiki/List_of_undecidable_problems>). There is no algorithm which even in principle can solve them. Among other things, you need infinite processing speed to do so. No amount of science can help here as it is in the logical domain. ~~~ apu Your statement about inductive transfer is false. There are many vision systems, for example, that use transfer learning (as it is known in our community) to use knowledge gained from one task in another. Moreover, many of these approaches are specific to vision -- they can't easily be applied in other domains. The rest of your comments about reasoning systems are either part of theoretical computer science (e.g., most of that list of undecidable problems), or in the realm of philosophy/metaphysics/80s-style AI. The former is an interesting area, but much closer to math than most other areas of CS. I call the latter philosophy/metaphysics because these are often questions that are interesting from a purely academic viewpoint, but are utterly useless for trying to make progress on real tasks. This was the big problem with 80s style AI: people hoped that they could build general systems which could "reason" about how to derive algorithms to do particular tasks. Knowledge bases were supposed to be steps in this direction. What the community learned is that this is not a valid approach, in part because it doesn't take into account the enormous amount of data people have access to from birth to adulthood (not to mention the fact that we can interact with our environment and see the results of our actions). There doesn't seem to be a good way to provide a computer system this kind of information. There are also strong biological arguments against this idea. For example, a large fraction of human brain cells are exclusively devoted to processing visual information. This is in addition to the significant amount of visual processing done by our eyes and the optic nerve. There are similar systems in the brain devoted to speech processing and language, etc. All of this suggests that a general reasoning system _cannot_ hope to solve the challenging problems in these different domains. ------ dkarl Oy, such a short timeline for a task like this! Submissions are due by August 14th or September 3. ------ apgwoz Programming video game AI is fun. I took a class at UPenn where we had to build a pacman playing agent with reenforcement learning. The gameplay was't standard pacman, but with just a few, general features and correct training it was easy to get pretty decent results. And it's not that hard to implement. Not sure how it'd work on Mario though. Anyone have any thoughts? ------ SwellJoe On a related note, one of the more interesting lightning talks at YAPC this year was about the Tactical Amulet Extraction Bot, a framework for programmatically playing nethack. Here's a blog about it: <http://taeb- blog.sartak.org/> And the code: <http://search.cpan.org/~sartak/TAEB-0.03/lib/TAEB.pm> I think it's been discussed here at HN once or twice, as well. ------ nazgulnarsil I've long wondered why the DARPA challenge for automated cars is necessary when the code could be tested using video games for orders of magnitude less money. ~~~ CGamesPlay In theory there is no difference between theory and practice. In practice, however... ~~~ nazgulnarsil crude simulations don't invalidate theories. i hate anti-scientific quips like that. ~~~ jacquesm In theory, there is no difference between theory and practice, but in practice there is. I'm quite sure that if there is one set of people that know this by heart then it is the military. Real world experience will bring out the trouble much faster than any amount of simulation. Use simulations to help you design, validate your design in the real world. Then update your simulation to reflect the lessons you learned during your real world tests and iterate. Have a look at armadillo aerospace, John Carmack is as versed as anybody in that field with simulations and STILL they find out almost every trial they do that the real world is not as clean as the simulated one. ~~~ jwhitlark Indeed. Just take a look at Murphy's laws of combat: <http://www.murphys- laws.com/murphy/murphy-war.html> ~~~ marvin Those are great, thanks :) ------ rawr I like how a hefty fraction of the algorithms use neural networks so that they get better as they watch humans play. The reason for this, of course, is that the developers just want a reason to play Mario :-) ~~~ rw Fine, yes; but you don't have to use neural networks to get that behavior.	{ "pile_set_name": "HackerNews" }
Ten Rules for Writing Cross Platform 'C' Code (2008) - nazri1 http://www.ski-epic.com/source_code_essays/ten_rules_for_writing_cross_platform_c_source_code.html ====== peapicker Rule 4 regarding unsigned long is a horrible example as Windows keeps them as 32 bits on 32/64 bit compiles while UNIXes vary between 32 and 64 bits depending on compile mode making unsigned long a disaster of portability across platforms and bitnesses. Stopped reading at that point as this article doesn’t deal with EBCDIC platform portability either... so overlooks the entire IBM main and minicomputer/OS400 market as well. And I say this as one who writes code on all of the above that does Unicode internally but one still has to interface with the OS. Anyway. There is a LOT more to portability than what is written here. ~~~ tonteldoos In all fairness, the author did specifically say the target platforms for the article are Windows, OSX and Linux. Agreed that portability beyond these platforms is a different story altogether.	{ "pile_set_name": "HackerNews" }
Interview with James Simons [video] - ernesto95 https://www.youtube.com/watch?v=QNznD9hMEh0 ====== graycat Really nice interview.	{ "pile_set_name": "HackerNews" }
The Ultimate Digital Estate Planning Guide - alejandra http://aftersteps.com/posts/168-the_ultimate_guide_to_digital_estate_planning ====== karanr Very informative. Keep up the great work. ------ aaronchriscohen awesome!	{ "pile_set_name": "HackerNews" }
Ask HN: How do you generate leads for B2B SaaS company? - Raj7k Can you share some of your actionable items to generate leads for B2B SaaS product? The product is a technical recruitment software? I am not sure about cost per lead for US demographics. ====== Raj7k Hi Everyone, need some advice no upvote :/	{ "pile_set_name": "HackerNews" }
Today is the 50th anniversary of Star Trek - TuringTest https://en.wikipedia.org/wiki/Star_Trek#The_Original_Series_.281966.E2.80.9369.29 ====== GrumpyYoungMan I'm shocked that this isn't on the front page. Has Star Trek finally faded from the public consciousness? That would be sad. (As an aside, the official Star Trek site has a nice little celebratory video from some of the actors in the various series: [http://www.startrek.com/article/happy-50th-anniversary- star-...](http://www.startrek.com/article/happy-50th-anniversary-star-trek))	{ "pile_set_name": "HackerNews" }
What To Do When A Tech Giant Decides To Eat Your Lunch - icey http://techcrunch.com/2011/06/13/tech-giant-eats-your-lunch/ ====== ChuckFrank There will always be giants ahead of you. And they will always try to eat your lunch. But with vision, determination and perseverance, the giants can be outfoxed and outwitted. One of my favorite ideas in business is that if you think you have 'no competition' than you don't know your market well enough. There is always competition. Forward competition, backwards competition, and neighboring competition. The key is to be able to think and visualize the best solution, and if that solution is better than anything else that's offered out there, and you can execute on it, then you are safe. Once that vision is lost, then the companies/products become walking dead, just waiting for the next competitor to catch up and pass them. Even the mighty fall regularly. [http://www.walletpop.com/photos/top-25-biggest-product- flops...](http://www.walletpop.com/photos/top-25-biggest-product-flops-of-all- time/) [http://consumerist.com/2008/09/the-10-biggest- chapter-11-ban...](http://consumerist.com/2008/09/the-10-biggest- chapter-11-bankruptcies-in-us-history.html) ------ peteretep Not mentioned in the article: sell your company to a competitor of the giant who's just realized one of their competitors has entered a new market place, and wants a way to catch up quickly...	{ "pile_set_name": "HackerNews" }
CodeLesson — Online Technology Learning for Professionals - kmfrk http://codelesson.com ====== jespi88 I am thinking about taking a course from them. I was hoping that I would be able to get some reviews from you guys about whether or not I should do it. Has anyone taken a course? Any thoughts? ------ enry_straker I can't speak about the site or the quality of the instructors but i have nothing but appreciation for Charles Max Wood, the instructor for the Ruby and Rails course. I think he also conducts the ruby programming language course. Check out his free online videos on rails at www.teachmetocode.com. They are free and will probably give you a good idea about the pace at which he conducts his online classes. ~~~ jeffreymcmanus Charles teaches Rails; Peter Cooper teaches the Ruby language. I'm a founder of CodeLesson and also an instructor. Happy to answer questions here or privately at my username at gmail. ~~~ YuriNiyazov How can I become an instructor? ~~~ jeffreymcmanus Most of our instructors are domain experts in the languages or platforms that they teach. Nearly all have extensive experience teaching or writing (most are book authors). A few of our courses have been suggested by users (there's a form for that here: <http://codelesson.com/courses/suggest>). We also sometimes list courses that don't have instructors yet; those course pages contain an "Instructors Need" link you can use to let us know you'd like to teach. To teach on the site, it helps us if you have a complete CodeLesson profile, including LinkedIn and Twitter links if you have them. ------ zdw Why hide the pricing behind a link that just reveals it inline? The pricing isn't bad... it's just unusual to hide it. ~~~ jeffreymcmanus We're not hiding it -- just keeping it out of the way. The principal user intention on the course page is to learn about what's in the course and who's teaching it. Most of our courses have multiple discounts; there's not always a single price. Early testing and user feedback revealed that students found a giant price list to be confusing to navigate, so the choice was to either get rid of the discounts or make the list less obtrusive. Subsequent testing suggested that we made the correct choice.	{ "pile_set_name": "HackerNews" }
Internships at any time of your life - sharpshoot http://sharpshoot.blogspot.com/2007/12/internships-at-anytime-of-your-life.html ====== myoung8 It seems like most internships are not so much a "free trial" for the internee, but an extended, interactive interview and test of skills, personality, and attitude. They exist so that firms don't get stuck with inept workers. There are also significant costs associated with interns (e.g. training, relocation) which are depreciated if the intern gets hired. Having an intern program like he describes would definitely see an increase in those costs, which makes it a disincentive for firms to have such a program. That said, I'd love to have the opportunity to intern anywhere at any stage in my life. ~~~ Tichy I thought internships are just cheap labor for the companies. At least in Europe some people do nothing but internships for years, because companies won't hire anybody for real. ~~~ davidw Yeah, at the last place I worked in Italy, my boss brought in a guy who was nice, and a hard worker, but not paid a dime. Stupid boss didn't even buy him lunch on his last day (I did out of a sense of decency). Eventually he hired him on as a 'temporary worker', which is how small firms in Italy get around the rigid labor laws. Basically, it's just another example of how the rigid labor laws take from some and give to others. ------ jamiequint The idea of companies getting free labor isn't neccessarily true, at least not for more meaningful jobs where the lead in time from hiring to productivity is longer (hence the desire for low turnover). However, I believe what this article is suggesting that if the system were to change so internships as "free trial[s]" were the norm companies would likely have better hires in the long term. Since markets with more liquidity adjust more rapidly, allowing people to move around more and allowing companies to better hire for culture fit (which may be hard to determine in a series of interviews) would ultimately result in a happier (and more efficient) labor market. Interesting idea. ------ yagibear This article focuses on the receptor side (company employing for a trial) and glosses over the donor side (organisation that loses/offers the person for trial). Universities aren't affected by students taking internships over summer breaks, and are hardly affected by students inserting internships during semesters. However candidates at later stages of life are likely to either have an employer (who is likely to incur disruption and have little incentive for allowing extended leave), or be unemployed (which makes them less attractive for receptors). ~~~ sharpshoot Your response assumes that the system operates alongside the current employment system. If every company operated that way, sure there would be disruption - but if you imagine a fluid system, no one would be disruting their 'current' position because every break can be made cleanly. Think out the box about what you've said as opposed to with the lense of how the current system works. Also if you consider the long term evolutionary impact: as people have the flexibility to try out companies a) candidates will be more experienced as they will have received training from different companies b) candidates will know exactly what roles suit them c) companies will only be populated with people who want to be there hence leading to greater productivity. Overhall the current system. As myyoung8 said - how many people want this but can't have it. This is the sign of a broken system. ------ jkush <http://vocationvacations.com/> ~~~ danw Thanks, I was desperatly trying to remmember that name! Heres an article about them: [http://www.businessweek.com/smallbiz/content/apr2006/sb20060...](http://www.businessweek.com/smallbiz/content/apr2006/sb20060412_289938.htm?campaign_id=bier_sma)	{ "pile_set_name": "HackerNews" }
Ask HN: What is your Evernote setup? - vrobancho I was wondering how you personally organize and sort your notes on evernote?<p>I have 2 Notebooks titled Sorted / Unsorted Whenever I clip or save an article on the web it goes to unsorted by default.<p>After reading I then drag the article to the sorted notebook and then to the appropriate tags. ====== filipmares I use it for everything. My notebooks look something like this Receipts (fwd via email receipts/tickets/confirmations), GTD (todos, to read, to buy, etc.), Code (html/js/css/code articles), Pulse News (my Pulse saved stories <http://pulse.me>), Work (all work related notes), Design (pretty images, design, icons). New fullscreen mode on OSX makes evernote a joy to use. Hope this helps!	{ "pile_set_name": "HackerNews" }
It’s getting harder to defend Edward Snowden - bane http://www.washingtonpost.com/news/volokh-conspiracy/wp/2014/08/03/as-evidence-mounts-its-getting-harder-to-defend-edward-snowden/ ====== greenyoda Even before Snowden, _everyone_ (terrorists included) knew that the NSA was devoting vast resources to spying on terrorists, building a huge data center in Utah to store communication intercepts, etc., etc. Quite a while before anyone had heard of Snowden, Osama bin Laden was very paranoid about his communication security because he knew that the U.S. was capable of eavesdropping on cellphone conversations. Snowden's only surprising revelations were that the NSA was spying on all U.S. citizens and on friendly governments like Germany. ------ benologist It's getting harder to thwart terrorists using outdated techniques they know are compromised. Shocked. ------ _cipher_ Because until Snowden they had so much success arresting random muslims^W^Wterrorists.	{ "pile_set_name": "HackerNews" }
Go to Microsoft.com / store / windows software - cubicle67 http://www.microsoftstore.com/store/msstore/cat/categoryID.44066700?WT.mc_id=MSCOM_HP_nav_BuyWSoftware ====== cubicle67 yeah, it's a bit silly and I'm not sure how long until they fix it, but at the moment it points to a page selling Windows 7	{ "pile_set_name": "HackerNews" }
Soros at Davos: China's social credit system and Big IT are mortal threat - _red https://www.businessinsider.com/george-soros-davos-2019-criticism-of-china-xi-jinping-ai-it-monopolies-2019-1 ====== fixermark My personal prediction for the US is that Americans will continue to rail against Chinese-style government oversight of a social credit system while supporting private institutions that de-facto create the same system without government oversight, laws to mandate the information in the datasets pass a smell-test for truth, etc. We already have financial credit reporting agencies and private organizations scraping datasets for mugshots, court cases, and legal sanctions; couple that with some social media datasets and you've got a potential employer's dream tool for candidate screening. America tends to run so hard from the risk of a Big Brother scenario that they end up smacking into Snow Crash without even realizing it. ~~~ sonnyblarney These moral/technical equivalency memes I don't think hold water. Nobody in the US is going to censor your email so that if you say something about Trump it gets magically deleted. Court cases and mugshots are _public information_ and a matter of transparency. When you murder someone, well, that's part of the deal. That's very different from the government measuring other, minute aspects of your life and making it public to everyone. If your social media posts are marked private - which is your choice - then for the most part they're not going to be available to arbitrary 3rd parties, moreover, there are definitely social media solutions you can use that don't share anything. There is an ongoing war over your information mostly for advertising by the way (not hiring) and hopefully some legislation will take care of that, and some dialogue over NSA/Snowden type things. Thankfully, there are actually laws, warrants, judges in the mix. Surely we have to judge China's actions from a completely different angle, as they have their own history, social system etc. - but the equivalency arguments just don't work. I think if you tried to text someone a message about Obama, and it was magically deleted by the US government, it would send shivers down your spine, and however political or not you were, you'd be signed up for the first protest/action - as would most of us. We all have some concerns about our system but it's manageable - what's happening in China is right out of a novel. Also note that 'it's just begun'. This is possibly only the first tranche. The de-facto objective may be to leverage tech to it's max - the result is effective total control over everyone's lives. ~~~ lustysocietyorg In our western democracies, especially the USA, not only messages are deleted but persons are. Either by lies or by harassment or by prison or by murder or by wars against entire countries and their population. Notable examples: \- Julian Assange. \- Russia, Iraq, Libya, Syria, Venezuela, ... America Has Been at War 93% of the Time – 222 out of 239 Years – Since 1776 [https://www.globalresearch.ca/america-has-been-at- war-93-of-...](https://www.globalresearch.ca/america-has-been-at-war-93-of- the-time-222-out-of-239-years-since-1776/5565946) When was the last war promoted by Russia or China where hundreds of thousands of people died ? Madeleine Albright says 500,000 dead Iraqi Children was "worth it" wins Medal of Freedom [https://www.youtube.com/watch?v=omnskeu- puE](https://www.youtube.com/watch?v=omnskeu-puE) And do not forget corruption of information by corporations and secrets services like the FBI and CIA. Whistleblower Exposes Facebook Censorship Techniques - Mindblowing: [https://www.youtube.com/watch?v=3UzFTAeEzJ8](https://www.youtube.com/watch?v=3UzFTAeEzJ8) SHOCKER: FBI Admits Sabotaging Progressive Politicians As Policy! [https://www.youtube.com/watch?v=4LYJSb-h9m8](https://www.youtube.com/watch?v=4LYJSb-h9m8) Macron vows to tighten media control because 'fake news threatens democracy' [https://www.rt.com/news/414945-macron-france-fake-news- law/](https://www.rt.com/news/414945-macron-france-fake-news-law/) Food libel laws [https://en.wikipedia.org/wiki/Food_libel_laws](https://en.wikipedia.org/wiki/Food_libel_laws) ~~~ sonnyblarney Your comments have entirely nothing to do with state regimes who monitor or coerce arbitrary citizens arbitrary communications. FYI 'Julian Assange' is wanted for specific crimes, this is normal in any nation - hopefully, if he is arrested, he'll have a chance to defend himself against specific claims. That would be a very, very public trial with a lot of scrutiny. ... and 'Russia, Iraq, Libya, Syria, Venezuela' are not 'notable examples' of anything in this context. ~~~ ghtrytttttnsa FYI Once a stubborn man is named the crime will either be found or invented. ~~~ sonnyblarney If the US gov charges someone with something, they'll have to provide evidence of a crime. It will happen in front of the world with full transparency. The US could fudge 'findings' from the CIA on Iraq, but they can't make up evidence in court. ~~~ lustysocietyorg You are very naive. Julian Assange would be free if the USA respected journalism. But the USA does not. [https://www.theguardian.com/media/2018/nov/16/julian- assange...](https://www.theguardian.com/media/2018/nov/16/julian-assange- wikileaks-have-criminal-charges-been-prepared-us) For the USA, this is about about national pride and personal revenge. Trump said that a death sentence is appropriate. The trial and accusation might be kept secret. Like in Guantanamo and similar places around the world where people are held captive without trial and where torture is normal. Do you really think the world is worried about Julian Assange because a fair trial is expected ? Do you really think that he has spent his life in the Ecuadorian embassy since 2012 because a fair trial is expected ? Do you really think that Ecuador has protected Julian Assange in the embassy since 2012 because a fair trial is expected ? ~~~ sonnyblarney Stop posting on HN. ~~~ lustysocietyorg > Stop posting on HN. I guess you are one of the US citizens who promote hate and war against Russia and China and thus want to censor free speech and messages to defend and promote your worldview. Your words from the first comment I replied to: Nobody in the US is going to censor your email so that if you say something about Trump it gets magically deleted. Your last comment proves that you are no better and you would love to have my comments deleted or having me banned from HN. I guess it is also you who downvotes my comments. You know you have nothing to say against the proofs that I linked. ------ howlingfantods I remember some weeks ago, I sent over a picture of the Chinese President as Winnie the Poo (a popular meme at the time) to some friends on WeChat. It showed up as sent in my WeChat but my friends confirm it never actually reached them. Maybe 10 minutes later, it had been deleted from the chat logs on my phone as well. ~~~ perfmode Was it a bit for bit copy of a circulated image? Or a screenshot? Because it’s possible to ship a bloom filter to detect banned images without breaking e2e encryption ~~~ hedora You can also block screenshots, scaled, noises, recolored, cropped, occluded images, but you have to send a larger model to the device. That’s not the point though. The point is that the expectation moving forward with these platforms is that you police yourself, or the machine learning algorithms will do it for you (and also ban you from mortgages, airplanes, employment, etc, if it has to intervene too frequently). Facebook does (in a very limited way) this by upranking posts it thinks will boost engagement. LinkedIn is a bit further down the slippery slope, since it’s able to influence hiring decisions (and is joined to the MS Office 365 cloud, presumably). Amazon Now had some related screwup recently where it redlined minority neighborhoods in a bunch of cities, since it used spending habits to predict they’d be less profitable. ~~~ zozbot123 > Facebook does (in a very limited way) this by upranking posts it thinks will > boost engagement. Facebook (and Twitter, and Patreon, and countless other firms) _will_ block you from posting if you post something that they regard as violating their policy. And "what is against policy" is a fuzzy enough line that "don't use Winnie the Poo pictures to make fun of the effin' President of the country" is a lot clearer than that. You may agree with the policy or not, you may think it's misguided, but WeChat is a private firm, and private firms aren't restricted by anything like the First Amendment. They provide services to you at their pleasure. ------ bawana I dont get it. We are concerned over IP theft. Meanwhile China has the Great Firewall and mass surveillance apparatus. Then you get their vice president saying ' I cannot control my unruly children who vandalize American businesses' So doesnt their IT infrastructure and super snooping ability figure out who are the transgressors? Why dont they round up ten of the worst and deport them and the assets of their companies as a show of good faith? Is it because we are doing the same? or is it because the offenders are 'too big to punish'? ~~~ koboll If you actually think China is worried about its nationals' theft of foreign IP, I have a Great Wall I'd be interested in selling you. ------ throwpromisea I think it's refreshing that finally someone with some notoriety speaks out openly against the threat of a dictatorship/authoritarian China paired with sentient technologies. Even if it's Soros. Most people are too tied to the corporation "benefits" to speak out against the evil Chinese government and its arms Huawei, ZTE and Alibaba. Even though many countries have now banned Huawei (US, Japan, UK, New Zealand, Australia, Taiwan), and others are thinking of banning (Canada, Germany, Poland), most aren't openly castigating China with exception of US and Taiwan. And even then, even though the US president is one of the few individuals that is openly confrontational with the Chinese regime, he still sometimes offers a conciliary tone. Even muslim countries like Pakistan and Malaysia that suffer from their religioius brothers imprisoned by the millions, raised a few outbursts but then went silent. ------ bb101 What's the end game for China, and indeed the world? One dystopian preview is Ma Boyong's award winning short story "City of Silence", published as part of Ken Liu's Invisible Planets. One can also read it at [https://web.archive.org/web/20120221185906/http://worldsf.wo...](https://web.archive.org/web/20120221185906/http://worldsf.wordpress.com/2011/11/29/tuesday- fiction-the-city-of-silence-by-ma-boyong/) and [https://web.archive.org/web/20120229091732/http://worldsf.wo...](https://web.archive.org/web/20120229091732/http://worldsf.wordpress.com/2011/12/06/tuesday- fiction-the-city-of-silence-by-ma-boyong-part-two/) Edit: added part 2. ~~~ joejerryronnie The end game seems to be moving more and more toward armed conflict between China and the US. I honestly don’t see both societies continuing their current trajectories without running headlong into each other. Perhaps it will just be another cold war and we’ll see who’s economic system blinks first. ~~~ boznz You mean armed conflict between some dick politicians in China and some dick politicians in the US in which everyone else but them will suffer. History has taught us nothing. ------ candiodari It's funny how privacy protections are turning out. Every week or so we see the same pattern repeat. The BIG problem with privacy is government data sharing. Medical records, police records, travel records, financial records, ... we keep hearing stories of real people really getting hurt because of these data sharing agreements. And yet all we hear about is Google data sharing, Facebook data sharing. And when it comes to problems with that, we hear about a few commercial disputes. And yet in law the situation is that we are protecting against the second case, with everywhere exceptions for the first case. And while I'm happy for such protections, I feel protections against government data sharing (especially against them sharing mistakes/inaccuracies/out of date info) would have much more positive results. ~~~ loudmax My feeling is that there will be more and more data sharing and we're going to have to reorganize our society around the assumption of transparency. Cheap cameras connected to the cloud will continue to proliferate and face recognition software will get better and more widely available. Trying to prevent big corporations and the government from using data about people is going to be an uphill battle, and probably hopeless. If you start from the assumption that massive amounts of data on people will be collected and exist, I don't see how you successfully keep it all secret without turning into a police state. The solution will be to make this data available to everyone. Not just government and the financially powerful, but everyone. Some types of activities should remain private, especially when it's practical to do so. Encryption works, so conversations can be private so long as all participants agree. Certain types of medical records should be kept private, and some types of legal records where few people are involved. But general activity that falls outside of the bands that society has deemed worthy of special protection should be considered public. Travel records? Forget it, that stuff's all over the place. As far as financial records, society has an interest when large sums of money are involved. IMHO we'd be better off if privacy and wealth were inversely correlated. ~~~ candiodari yeah but how many people are getting oocked out of the us because of a holiday in Pakistan or Iran ? ------ _bxg1 "At the center of his anti-China argument was the concept of a centralized database of personal information called a "social credit system." While Soros acknowledged that such a set-up doesn't yet exist..." But it does in China, right? I've read many articles about it and I could swear they weren't just future-looking. ~~~ howlingfantods There's currently no one 'social credit score' in China. There's some local government pilots and some private enterprise "credit scores." The ones you hear about often are stuff like Alipay's Sesame Credit, which gives you a score based on your activities in Alibaba's app ecosystem. Currently, Sesame credit is pretty harmless, and gives you discounts on online orders or financial products if your score is good. The danger is that the national government will soon get its ducks in order and hoover all this data into one overarching national credit score and use that to police behavior. ~~~ tallanvor Well, there's the one that blocks people from flying or even taking trains. ~~~ throwaway-fut So like a Chinese “No Fly List?” ~~~ _bxg1 Except instead of applying to known terrorists or criminals, it applies to people who posted something the government doesn't like on social media, or have been unemployed for too long. ------ whyever Here is a talk that looks a bit closer at the different social credit systems in China: [https://media.ccc.de/v/35c3-9904-the_social_credit_system](https://media.ccc.de/v/35c3-9904-the_social_credit_system) ------ GreeniFi We make a big hoo-ha about “social credit”, but I would argue that western financial credit scores function (or will function) in a very similar way given the amount of data some of the third party credit score providers pull and can pull in. The threat is huge because pretty much everyone needs credit to buy a home, and if you’re not a good boy or girl, that possibility will be taken from you. And here’s the dark feeling: Facebook profile and use creates a personality profile. Personality profile is valid credit-score data. That data was possibly stolen from FB. If so, your financial credit score (and by axiom social credit score) is now available to anyone who will pay for it. I’ve been particularly aware of this, because as a self-employed entrepreneur, my credit score has taken a pummeling - I think largely due to erratic cash flow. I see it as a long term threat to risk-taking. Basically, the lesson is clear: by seeking to change things, as entrepreneurs do, you’re not being a good boy or girl. ------ diminish How is George Soros perceived in USA and West Europe? Any comments? ~~~ Wohlf He's the boogeyman for people on the right, much like the Koch brothers are the boogeymen for the left, at least in the USA. ~~~ bitxbitxbitcoin That's a fair assessment whether you're on the right or left! ------ arcaster With Soros himself being the exception to the definition of a "mortal threat"?	{ "pile_set_name": "HackerNews" }
What type of investment hits are you going for? - tracecohen https://medium.com/@trace_cohen/what-type-of-investment-hits-are-you-going-for-5867d5ccd5ab#.qhn7miph4 ====== sharemywin facebook.com - college student directory. too small a market. AirBnb - share housing/couches for conferences. too small a market UBER - extra business for limo companies. too small a market. Microsoft - software for hobby computers. too small a market. Apple - computer for hobbyist. too small a market. grubhub - list of good places to eat around town. too small a market. google - were going to treat hyper links like bibliographic citations and count them and use those to rank sites. - sounds like a good phd project. good luck figuring out some hobby website from something real. If anyone of those people told me they were going to conquer the world, I'd tell them to get off the drugs and focus on something more productive.	{ "pile_set_name": "HackerNews" }
A failed takeover of T-Mobile would cost AT&T as much as $6 billion - there http://www.reuters.com/article/2011/05/12/us-mobileusa-att-breakupfee-idUSTRE74B5H220110512 ====== plusbryan In that case, who's up for some picketing?	{ "pile_set_name": "HackerNews" }
Xbox 720 rumored to be GPU/CPU powerhouse; always-on Internet required - rkalla http://www.vg247.com/2012/04/02/xbox-720-detailed-blu-ray-inside-always-on-netcon-required/ ====== rkalla As a continuation of the conversation about PS4[1], the previously rumored Xbox 720 specs that were conservative (AMD 6000-series equivalent GPU with dual or quad-core integrated design) may be invalidated by the latest leak, more specifically: 1. Dual, independent AMD GPU design (can render two scenes independently -- not Crossfire which splits 1 scene across multiple cards) 2. GPUs will be based on AMD's latest high-end 7000-series tech. 3. 4 or 6 CPU cores; 1 dedicated to Kinect. 4. I assume: integrated Kinect device. 5. Always-on internet connection for anti-piracy/DRM. 6. Blu-ray drive There were rumors a few months ago that MS was considering a no-disk device, but as other people have argued, we aren't there yet. [1] <http://news.ycombinator.com/item?id=3786624>	{ "pile_set_name": "HackerNews" }
Introduction to the Modeling and Analysis of Complex Systems - Schiphol https://textbooks.opensuny.org/introduction-to-the-modeling-and-analysis-of-complex-systems/ ====== troelsSteegin The book is designed to support an introductory class on systems - eg a 100 level or first year class. It's a little more technical than you might find in a typical gen-ed quantitative reasoning class, but the material is presented in a way that I think would be approachable from a STEM or non-STEM career emphasis. I trained as an engineer, so I could be overstating that... There is a pedagogical library, pyCX [0]. Overall, I like the design of the book, but would say the intended audience is someone relatively early on their analytic journey and may not serve the interests of the HN reader well. It has a much broader perspective than Allen Downey's "Think Complexity" [1], which is discrete systems (computational systems) focussed. Maybe you could think about Downey's book is a non mathematical approach to algorithms. Scott E Page's book "The Model Thinker" is more mathematical, at an undergrad engineering level, and is more of a survey of models than a taxonomic overview of systems modeling, which is what Sayama's [2] book, above, offers. A thesis of Page's book is that there can be many ways to model a problem, and multiple models help. [0] [https://github.com/hsayama/PyCX](https://github.com/hsayama/PyCX) [1] [http://www.allendowney.com/wp/books/](http://www.allendowney.com/wp/books/) [2] [http://bingweb.binghamton.edu/~sayama/](http://bingweb.binghamton.edu/~sayama/) ~~~ sn9 The intro says it can be used at an advanced undergrad to early graduate level. Depends on how much of the book one covers. ------ Scipio_Afri So is this a good open textbook? Does any open courseware or MOOC follow this book or topics it covers? ~~~ TeMPOraL Seconding the question. Also, what's the best not-necessarily-open textbook on the subject? I've been meaning to dig into the topic in depth for a while, I could use a _good_ textbook. ~~~ SurfingToad Nonlinear Dynamics and Chaos by Steven Strogatz is pretty good. Nonlinear dynamics is one of the backbones of complex systems, so it's worth delving into. Graph theory/topology is a close second. Complex Networks by Latora, Nicosia, and Russo is a nice introduction to the graph-theoretical perspective. Complexity: A Guided Tour by Melanie Mitchell is a nice and brief introduction. I can also recommend Spin Glasses and Complexity by Stein and Newman. Spin glasses are basically the "model organism" of complexity science, so it wouldn't hurt to get acquainted with them. ~~~ TeMPOraL Thank you! ------ saeranv What are some of the practical applications of complex modeling? I have a hard time wrapping my head around where something like this would be used.	{ "pile_set_name": "HackerNews" }
Is It Cheating to Have a Side Project? - ekm2 http://blogs.hbr.org/cs/2012/07/is_it_cheating_to_have_a_side.html?goback=.gde_2936203_member_133163399 ====== EvanMiller Man. This article, and the business-book morality that underpins it, is utter tripe. I heartily advocate that when it comes to managing their own time, employees do whatever they can get away with without getting fired. When it comes to negotiating compensation, companies exercise an enormous strategic advantage over employees, which they've proven completely willing to exercise in dishonest ways (cf. Apple/Google "non-poach" agreements). So when it comes to time-management, in the general case, I say fuck 'em. Get your work done, but when the door's closed, get out the clown suit and practice your torch- juggling routine if that's what you feel like doing. Of course if you actually like your boss, or you don't think your company is run by dicks, and you'd feel bad about getting clown makeup on the company furniture, then don't do it. But only YOU can decide what's right in a given situation. No one needs employment morality lessons from business book authors. ~~~ toolz I completely agree with you here. If the company leverages everything they have to keep you compensated as low as possible to keep you, then you should in turn leverage all of your work against them and do as little as possible for them to keep you. That's the only honest way to progress society. Reward good business practices with good labor. You aren't doing anyone any long term good by pretending you owe your boss anything. Provide them with the labor they pay for and nothing more. Teach employers that payment can come in a huge variety of ways. From your standard monetary compensation, ranging all the way to simply respect and healthy work environments. ~~~ crisnoble >You aren't doing anyone any long term good by pretending you owe your boss anything. The best bosses know this and will tell you as much, they will help you find out what you want to do. They realize that your first job is not going to be your last and help you focus on developing your skills. Then they hi five you when you get a better job. ------ columbo > If you do it on company time you can be fired, and quite frankly we believe > you should. Bullshit. A company can fire you for any reason. Yes, this is a perfectly valid reason to fire someone. You could also fire someone for showing up to work at 8:05 instead of 8:00. And you can fire someone because "You're the boss". Despite that, what a bullshit article. "If you aren't 100% working for your company from 8am to 5pm then we think you should be fired" is all they are trying to say. No surfing the net, no testing out new ideas, no chatting with coworkers, no personal calls and EXACTLY 30 minutes during lunch: you are hired to sit, do work, punch out and fuck off. People like this rile me up a bit... I've worked for places like that, and people like this, never again. ~~~ kamaal "Do as we say or.." kind of places are really the worst. I once worked under a guy, he had very serious problems if some checked out a new tool/language/library/framework etc at work or even tried to learn something new to him like say Haskell. Over a period of time I just figured out he was just plainly jealous that some one young would over take him. Those are the last kind of places you should work at, also they are worst team players you can ever get. ------ aaronbrethorst I've always had side projects and have always disclosed my side projects to my boss. I want to be absolutely sure there are no surprises. In one case, I let things wait almost too long and had to tell my CEO that he shouldn't be surprised to see an article about my side project in the Seattle P-I the next day[1]. That was a mistake I've never repeated. Fortunately, there were no repercussions in that case. I got lucky. Here are my thoughts: * My side projects have—without fail—made me _better_ at my day job. For instance, when I had my last 'real' job as an iOS developer for a startup, my side project was Cocoa Controls[2] (<http://www.cocoacontrols.com>), which shaved dozens-to-hundreds of hours off our development schedule. * My side projects don't compete with my employer's line of business (or potential future directions). The last thing I want is to get embroiled in a lawsuit down the road over IP theft. * My side projects never use company resources. That means no working on it at work, and no using that company laptop. * I do my best not to discuss my side projects with my coworkers. I'm happy to chat about them if they bring them up, but I don't go out of my way to discuss them. * Way back when, when I worked at Microsoft, I had to sign a moonlighting agreement that specifically spelled out what belonged to whom and what each party's responsibilities were. If your company doesn't have one, I recommend trying to introduce one. [1] [http://www.seattlepi.com/business/article/Seattle-startup- Di...](http://www.seattlepi.com/business/article/Seattle-startup-Dibspace- hopes-to-cash-in-on-1303182.php) [2] Which is now my real job. Win. ~~~ StavrosK Wait, if you don't work on it at work, why does your employer care? ~~~ rst Many employment agreements claim rights to anything the employee invents which is related to the business, whether or not on company time. And in some states, it's common for the claim to be on _all_ inventions, whether related to the business or not. (California has a carve-out in state law: an employer can't claim stuff that was not done on company time, nor with company resources, and which does not relate to the company's business. But many states, perhaps most, have no such carve-out. And even the California rules are subject to interpretation; what _isn't_ related to the company's business if the company is Google? So, it's wise to consult a lawyer regardless...) ~~~ dredmorbius Which is a very good reason for the smart kids to stick to California for their professional lives. Trying to fight your way out from under a noncompete, or lawyer up on account of a side consulting gig or independently conceived and developed idea, really stinks. And the further you get in your career the more likely you'll encounter such a situation. Such cases ultimately seriously _dampen_ both enthusiasm for the employer, and the odds of finding talent interested in working under such a regime. Of course, the ultimate negative would be for California's exceptions to be attacked by corporate interests. ~~~ gte910h >Which is a very good reason for the smart kids to stick to California for their professional lives. Georgia recently amended our constitution to make non-competes much more likely. I and much of the tech scene hugely lobbied against this effort, oh well. We didn't need to work for in state companies anyhow. ------ outside1234 I believe pretty strongly in having a side project, and working on it at work, but only when I think the side project is something that directly (20% Google model) or indirectly (skills) benefits the company. Seriously - we aren't digital coolies. We are highly paid surgeons. You wouldn't for a second fire the brain surgeon for reading about a new type of surgery that he can't put to immediate use between operations. Hell no. Its the same with node.js or ember.js or whatever you think the new hotness is that you want to experiment with. You are trying to see around corners and skate to where the puck will be. Sometimes its not obvious how node.js (or whatever) is going to help. You need to balance this against your current role, but 20% sounds about right to me. This is good for the employer. If the employer doesn't get that then you should get a new employer. ~~~ k3n I totally agree that we need continuing education, such as your analogy of the surgeon, but the article specifically mentions scenarios where the side-jobs are completely unrelated to the primary job. I've witnessed this myself, had a guy working on side-projects while on our dime. He was lucky not to get fired on the spot, because pretty much every employment agreement strictly prohibits working a 2nd paid job while you're using company resources whether that's time during the working day, or the company copier/internet, etc. If you're such a bigshot that you can negotiate the ability to work a 2nd job while on- the-clock for your day job, then more power to you, but I'm sure that's extremely rare. If you want to experiment with some new tech -- and you've been allocated the time for it by your superior(s) -- then by all means play around. But in my experience, there's typically at most only a few in each department whose formal role includes these types of projects, and they're always skunkworks- like projects that rapid prototyping or POC-like, and never a full implementation (unless you choose to go forward with it of course). This is the essence of R&D, which is there solely to make sure the business survives -- not you. ------ singular I think this whole article is a despicable example of the complete fucking subjugation of many in corporate life (the author seems to be a prominent member of this subset.) Renting my time doesn't mean you own me. Either I produce sufficiently good work for you + you continue to employee me, or I don't and you do not. Beyond that, go fuck yourself. ~~~ singular More calmly:- I don't advocate working on non-work stuff at work, it's not a fair or honest thing to do, and personally, it's not something I do. But the article goes further, it approvingly quotes:- "When people get excited about things outside of work they end showing up to work and going through motions just to get through a day. Everyone loses. The employee loses and the employer loses. People are not going to give all of themselves as they focus on their new outside interest." Which is getting into 'I employee you, so I get to tell you what you do everywhere'. Fuck that. ~~~ derekp7 Not only that -- the article basically implies that even if you aren't specifically working on your side projects on company time, that they can impact your work, because it can be distracting. So that means no dating, getting married, or having kids. No hobbies. No educational pursuits. You work, go home, maybe passively watch TV (but don't talk about last night's Seinfield at the office), sleep, and start over again. ------ kamaal Wow! This is classic exec level BS. This article clearly displays the perennial fear execs have, which is lower level employees getting rich. Well monetized side projects are scary to execs. It robs them of their financial authority which is directly related to their executive authority. No exec wants a rich low level employee who doesn't give a damn about getting fired. What that means for the exec guy is, his authority and position of advantage suffering erosion and the exec being pushed into a position where his biggest bargaining chip is lost. And not to mention the guy far lower in hierarchy may be making a good deal of money, which disturbs the advantage due to positing in hierarchy. Fact of the matter is, execs and big guys have side projects all the time. Just because they don't involve writing code it doesn't mean they don't have projects. I know a lot big guys who attend pointless conferences which they absolutely don't have to, sometimes on their own money just because their pet project is to grow their network. Or they are busy working on their next real estate project in their spare time. Or they are writing a business proposal for their own venture. This happens just all over the place, all the time. I agree that the office time should be clearly used for office work. Any other time apart from that is yours and use it the way you like it. ------ quasque This is mostly a problem of being paid per hour (or being expected to be present a set number of hours) rather than per project or task - leading to very inflexible terms of employment or contract. It's also a problem of management culture clashing with employee's expectations and desires. For example, I used to work for a place that would routinely monitor email and chat logs to make sure people were talking about work and not being overly social - even if the job was being done well with no problems. Personally I think it's important to find a balance; if a small slice of at- work, non-break time is 'spare' and being used to better oneself rather than just sit around blankly doing nothing - what is the problem? And if side projects are being done _outside_ of work, well that's none of the company's business. ~~~ dredmorbius How about being paid according to supply and demand for your talents? Tying that rate to hours worked, or pieces produced, is a negotiating tactic to focus your mind on irrelevance. What matters is 1) what value do I produce for the organization (this sets an upper limit on what you can rationally demand in compensation, not that this seems to limit the C-level set), and 2) what can you command elsewhere? Being able to negotiate from a position of strength, particularly via collective bargaining (why do you think the tech world is so deathly afraid of unions or true professional organizations) boost that through Ricardo's Law of Rent (<http://en.wikipedia.org/wiki/Law_of_rent>). ------ crisnoble I was once in an interview for a development job where I asked what the companies stance on projects outside of work was. The head honcho said, "I don't want to know about them, and in fact I don't want you to do them. You should be getting all your fulfillment from work, and if you need more pay we can work something out." In my mind the interview died right there. He didn't get it, its not about pay, but about scratching an itch, trying new stuff out. I assume that he would be okay with me watching TV at night, or running with my dog, why would my decision to blow off steam with code matter to him? ------ jeffehobbs "We think you should have a side project, unless you shouldn't, and then you should not, unless you should, which maybe you shouldn't." -this article ~~~ singular I actually lol'd at this. That sums it up very nicely! You forgot to add that you are evil if you're even thinking about it (they have IP rights on your thoughts too) ------ ixacto Employee and employer trust as of late has approached zero. There is noone outside of government that is going to work their entire lives at one corporation, that is ridiculous. There is no telling if any of the big tech companies will be here in the same form in 15 years, let alone 50. What if by 2028 POTUS goes standard-oil on google, ms goes bankrupt, apple merges with yahoo? Stranger things have happened. ------ johndavidback I believe that this entire mentality runs counter-intuitive to the web dev/tech nature of HN in general. Many web developer professionals work at firms or agencies or other web development shops that rely on client work. I'm speaking generally here, but from my own perspective client work is never enough to fully satisfy a curious and excited mind. Enterprise projects with client services, project managers, client stakeholders, C-levels, QA departments, etc, will never be satisfying in the way that rapid prototyping, direct-to-development ideation, and general 'fooling around' can be. This article is not only harmful to the modern workplace, but is irritating to web developers who thrive on creativity but work in environments where it's simply not feasible. I still have bills to pay, but am not defined by the desk I sit behind. ------ kaa2102 Having options is not immoral - it is a moral imperative. Private sector executives are willing to lay off employees for the sake of profitability. Public sector employees (even Feds #Sequester) aren't safe from layoffs or furloughs. It's not cheating to do what's in your best interest - your Employer will certainly do what's best for them. ------ stevewilhelm Check your employment contract. Some stipulate that any IP you develop while an employee is owned by the company. ~~~ outside1234 in particular Google employees, that means you. ~~~ dredmorbius Pre-empted by California state law given certain conditions. ------ singular A useful explanation from Joel Spolsky on the whole companies-owning-your- hobby-IP thing (it's v. common, they probably do, yes I'm talking to you) - <http://answers.onstartups.com/a/20136> ~~~ alok-g HN discussion: <http://news.ycombinator.com/item?id=2208056> ------ mattquiros I have a question: Is it cheating if I haven't had a task at work for weeks now and I'm using my time in the office to take Coursera and iTunes U classes on Mathematics, CS, and iOS development instead? And when I get tired I go to the gym for maybe two hours and come back and study again. Not kidding, this is a real question. I have a feeling this is technically unethical but I'm not so sure my time will be wisely spent if I just ethically sat here and did nothing. ~~~ michaelochurch Douchebag Executive answer: yes, it's cheating because you should be asking your boss for more work. That's what a good corporate citizen does. He says, "I'm done, give me more." (In reality, this doesn't graduate you to better work. Unless your boss is personally interested in your advancement, it just gets you assigned more of the same grunt work.) My personal answer: no, not cheating at all. Is your boss looking out for your career? Are you his or her protege? If you don't have a mentor, then _you_ are your mentor and you have the ethical right to manage your career as you see fit. Keep learning and carry on. ------ hotdox >The more you deliver above and beyond what your "contract" calls for, the more slack you get. The biggest BS in this article. Your delivering does not correlate to slack you get. ------ alok-g As mentioned in the article, you could be in violation of the contract you signed with your employer with side projects. See an earlier discussion on this aspect: <http://news.ycombinator.com/item?id=2208056> In my case, I have gone full-time for my (yet to be defined) project to avoid this issue and be focused 100% on it. ------ MilesTeg Well, when I am working on a side product it is better for my work productivity than when I am not. When I am working on a side project I am in the kind of mood in which I can program for 16 hours straight. Doing two projects keeps things fresh. When I am not motivated enough to work on a side project I am more likely to zone out at work and spend an inordinate amount of time lurking on HN. ~~~ cglace I agree. When I have a side project I will fly through my work so that I can get back to what I really care about. ------ hippich It is not cheating. If you are still employed - you fulfill job requirements you agreed on in exchange for money. If you are not fulfilling these requirements any company fill just fire you. Side projects are irrelevant. (Unless it is specifically said in contract and you are being paid for a chance of inventing for company something forth extra pay) ------ klinquist When interviewing someone, I ask about their side projects. If they don't have any, they aren't getting hired. In order to be a productive member of my team, you have to be passionate about technology - and that means having side projects. ------ kevinthew All of my side projects inevitably circle back and help me with my primary tasks (either through practice/learning something I didn't know already/keeping me focused). I don't see why an employer would ever discourage this. ------ carsongross Is It Cheating to Explore Outsourcing Without Telling Your Employees? Just askin' ------ sideproject That's it. I've created it. This is for all of you, SideProjectors! <http://sideprojectors.com> ~~~ benrhughes FYI, for whatever reason, trying to sign up in FF for Android I constantly got an invalid email address error. Worked fine through desktop Chrome though. ------ sigzero Not if you do it on your own time. ~~~ alok-g Since the question is whether it is "cheating" or not, the answer becomes very subjective, and yours cannot be called wrong. The best answer however would be to "Check your employment contract" as Steve also wrote. If you signed such a contract (or are not even aware that you signed one), you "could" be kidding yourself. ------ milfot Cheating == business ------ michaelochurch This is Category 5 douchebaggery dressed-up as an attempt to be "hip" to the fact that ambitious people often have side projects. It's revolting and way out of touch. Not only is the moral high horse off-putting, but the advice is impractical. Article says you should be spending 1000 hours per year looking for another career. It also says that if any of those 1000 hours occur on "company time", then (using their words) "you are stealing". This is overprivileged nonsense at its worst. How many people can fit in 1000+ hours per year on a side project _and_ the real demands of a typical day job without _some_ degree of (taken if not given) overlap? Answer: not many, but it's a good assumption that these writers have multiple maids and nannies... Of course, it's worth it to be smart about overlap. Avoid using company resources, and the writing of code that will go into production should not occur during traditional company hours. If you're going to steal time from work, use it for reading, learning, and exploration-- not product code itself. You can lose if you do that. ------ eriksank The monthly-salary system is not necessarily suitable for all programming jobs. I think it is rather an exception that the monthly-salary system correctly matches the dynamics of the situation, such as for hotel receptionists or security guards. The default agreement in programming work should be about results and not about hours present on the job.	{ "pile_set_name": "HackerNews" }
Input type=“country” - edent https://shkspr.mobi/blog/2017/11/input-type-country/ ====== Piskvorrr Keeping everyone happy and not causing major diplomatic incidents. Easy‽ Yup. Now that you've mentioned the Falklands - those should sort under "M" (for "Malvinas"), everyone* knows that, right? Don't get me started on that farce of a name that hides under the acronym FYROM, either. And, btw, some existing and recognized countries have an ISO-3166 shortname which its populace mostly considers offensive ("Czechia"). Yeah. Easy peasy. Not to mention the previous half-baked browser-specific solutions such as input=date...nope, I don't have any hope for this proposal. (Everyone in Argentina, that is.)	{ "pile_set_name": "HackerNews" }
Show HN: Instant Varnish Cache for fast static sites,WordPress,death hug and more - jjoe https://www.cachoid.com/ ====== jjoe I'm this guy who lurks in online forums and would jump in to help random people with their "server load" and "slow page loading" issues. The magic was in seeing that load drop from 100+ to single digits with snappier page loads. I knew this was something others could benefit from but also knew it was going to be a tough thing to build and scale. Challenge accepted! So I set out to build Cachoid. I paused work on it some months ago in order to finish off some other business I had started earlier. I'm bootstrapped so I'm grateful in advance for feedback, comments, things I need to improve, and things you need to see before you seriously consider using something like this. _Outline_ : 0\. Instant Varnish Cache nodes (< 10s) with ready-to-go VCLs you can spin from an _increasing_ number of locations; each node runs inside its own container 1\. Four 21-days trials. To hell with credit cards! 2\. Simple API endpoint to get page cache status, push new VCLs, purge, upload TLS/SSL certificates, push HTML files (Varnish hosted). 3\. ModSecurity rules a click away 4\. WordPress, AWS S3, Github.io, and file/static hosting (HTML-uploaded files cached inside your Varnish instance) VCLs. So Cachoid will memory-cache your "backends" and serve them like hot pancakes 5\. E2EE is a few clicks away if you have an TLS/SSL cert. It's rough around the edges but works 6\. Internal & external monitoring of nodes 7\. Google 2FA to access your Cachoid account 8\. Stripe subscription, one-time Paypal & Stripe, Bitcoin (through Stripe) 9\. Other features I haven't listed that I feel would make me sound like a car salesman like load balancing and auto resource upgrade (I almost tricked you there, see?) 10\. Check out this page if you're curious. It has screen shots and articles: [https://www.cachoid.com/support](https://www.cachoid.com/support) _Some uses cases_ : 1\. Survive the hug of death (HN, Reddit, etc) with high flying colors 2\. Cache static sites, S3 "sites", github.io, etc. Smooth out the sporadic speed issues 3\. Cache CMS sites like WordPress 4\. Cache certain API endpoints	{ "pile_set_name": "HackerNews" }
Being basic as a virtue - skellertor https://nadiaeghbal.com/basic ====== abeppu This seems as good an opportunity as any to bring up another part of the "basic" concept which feels really unhealthy: the idea that "basic" is consuming commodity, mass-market goods, and that high status is distinguishing yourself through sophisticated taste in what you consume. This mindset is problematic for at least a few reasons: \- Every choice of consumption becomes an opportunity to over-examine \- Devaluing goods because they're common lures us into a needless chain of "upgrades" as productivity improves. We can never have a post-scarcity economy if we're taught to shun whatever isn't scarce. \- All of this plays into the framing that we're first and foremost workers and consumers. Would we not all be happier and healthier consuming decent but not spectacular mass-produced and inexpensive food, drink, clothing, housing, cars, etc, instead of coveting a rare beer, or looking down our noses at people buying starbucks? ~~~ twirlock I completely agree, but I can't help but note this only sounds like a radical concept in the context of West coast liberals pretending their snobbiness is erudition. ~~~ abeppu I don't think this is specifically a West Coast thing. My supermarket has dozens or perhaps hundreds of cheeses, and so do large supermarkets all over the US. Surely that's because someone's buying the niche varieties, and going to a party and saying "oh you're still buying brie? you have to try reblochon." ~~~ dsalso Or they just like to try new cheeses? ------ obiefernandez [https://workaway.info](https://workaway.info) A site that lets you find hosts who will trade room and board in exchange for two to five hours of labor per weekday. Mostly located in beautiful/wild locations around the world. I'm currently doing three months in Europe hopping from place to place using Workaway. For instance, right now I'm at a hobby farm on top of a mountain in central italy. Super laid back. And gorgeous. Imagine the most picturesque idyllic farm you can... I'm finding that the rewards in mental health are more than sufficient to justify the astronomical opportunity cost. ~~~ opportune My browser is complaining about an expired or invalid cert ~~~ johnchristopher It's fine for [https://www.workaway.info](https://www.workaway.info) ------ Notorious_BLT Is it common for knowledge workers to fantasize about more labor intensive work from time to time? Because I definitely found myself relating to that sentiment. Usually my mind goes to construction or carpentry in those moments. My favorite part of this is the acknowledgement of the enjoyment to be found embracing the 'degenerate' as the author calls it. I can strongly relate to needing a good, stupid, socially-unacceptable laugh sometimes. ~~~ bradstewart I often find myself romanticizing the hunter-gatherer lifestyle. I'm certainly not suggesting modern society be dismantled, but there's something intriguing, attractive even, about the simplicity of that life. ~~~ prometheus76 Rule 1: Always have a plan for the day. Theorem 1: If you accomplish half of your plan for the day, you had a very unusual day. Rule 2: Be ready, at a moment's notice, to drop your plan for the day to pursue an unusual opportunity. Theorem 2: You might not always be rewarded for your enthusiasm, however. And, at first, you will see many "opportunities" that are actually distractions from the task you are avoiding. Time and seasoning will give you discernment. Rule 3: Be aware, at a moment's notice, that you will have to drop your plans and focus on an unexpected emergency. Re-build what broke so that it won't break the same again next time. Rule 4: You can start practicing now by skipping meals, or even skipping a day of eating on occasion. Also, sleep on the floor with a light blanket sometimes. Don't wear a coat to work sometimes. Take cold showers. Practice being uncomfortable. Practicing makes it easier to absorb being uncomfortable when you don't have a choice in the matter. Rule 5: While you will be met by frequent surprises and challenges, you will also be bored at times. Practice being comfortable with being bored by walking more, with no headphones, no podcasts, no music. Just you and your thoughts. Rule 6: You will always be building and re-building a plan for the day, but that plan should always be fitting into a context of the season that is coming next. What you do today makes the next season more comfortable, or at least, survivable. Theorem 3: You can judge how well you are surviving and adapting to the challenges of your environment by how long out into the future your planning reaches. Theorem 4: To romanticize this as "simplicity" is to grossly underestimate the mental fortitude and resilience required to focus on the matter at hand while continuing to rebuild a plan for the near future, all without losing your shit and giving up. Not to mention, grossly underestimating the creativity with which Nature can surprise you. (The numbering doesn't really matter, but theorem 1 is related to rule 1, and theorem 2 is related to rule 2. Mostly, it was just a way of separating my thoughts.) ~~~ bradstewart This is definitely not a response I was expecting, but it's a really good, thought-provoking one. Thanks for that. I have no doubt I'm grossly underestimating things, but I do think your ideas fit the definition of "simplicity" as I intended--simple being the opposite of complex, rather than easy or effortless. I find all of the ancillary functions we're forced to perform as part of modern life to be very complex and highly distracting. On any given day I might have to file a tax return, pay a phone bill, argue with a doctor's office over a bill I paid 18 months ago, have my car break down, deal with credit card fraud, receive a dozen spam calls, research and select a new insurance plan, find a new dentist, etc, etc. I actively take steps to reduce these distractions, but many are pervasive and effectively required. I long for the opportunity to be bored. As another comment said, this is part of what I love about backpacking: it affords the change to be bored with my own thoughts. And I'm back to romanticizing the ability to focus on a single, simple goal: survive to the next season, with all the uncertainty that brings and mental fortitude it demands. ------ skim_milk I got to experience some unexpected culture shock earlier this year taking a vacation to SF from a medium-sized city in the midwest (to probably no surprise to you reading this comment). Having forgot my clothes on the trip I got to tour all of SF for a week in cheap business casual clothing I kept on after work, which was an experience. Lovely city but damn, I had a target on my back looking like a basic tourist so I bought some more appropriate clothing and tried my best to fit in. Got home after the trip made me want to take an extra vacation day just to drink cheap beer, stare at the cows, and listen to sports on the radio. Sorry for the mostly irrelevant story, but what I'm trying to say is I think this is probably a pretty common thing even outside of white collar big city folk culture. ------ DarwinMailApp I loved this part: Being mediocre is turning down the combat difficulty on Red Dead so you can play through the game. It’s a resistance to hyper- optimization; the “courage to be ordinary”. I wholeheartedly agreed with this point as soon as I read it. I adapted this approach while building DarwinMail [1]. There have been countless email & Twitter suggestions for DarwinMail. I've always listened and asked questions until I understood what what the users core message was. However, I do not always implement what has been asked. I believe in some 'truths' when it comes to building your product while following a basic approach; 1\. Users are the core of any business. 2\. The feedback you receive from users is the most valuable feedback you will receive on your product as they are the ones actually using your product. 3\. You do not have to implement everything your users ask for. Even though you may not do everything your users ask for, that does not mean you are not listening. I believe you need to keep your features simple and easy to understand. Being basic reminds me of the saying 'Slow is smooth and smooth is fast'. To me that is one of the most important truths when it comes to life and business. [1] [https://www.DarwinMail.app](https://www.DarwinMail.app) ------ adammish “A person who thinks all the time has nothing to think about except thoughts. So he loses touch with Reality, and lives in a world of illusion.” -Alan Watts ------ hliyan Whenever I feel this way (and I do feel this way more than I care to admit), it's usually due to mental fatigue from extended periods of mental exertion. I've found that stepping away from high intensity thinking for a few weeks every six months or so helps me reset. A complete "information lobotomy" as the author suggests, may be overcompensation... ------ bch This is so personal it's beyond reproach, for decency’s sake. On the other hand, it could be overwrought romanticism that speaks to nothing but existential crisis. Who doesn’t want to be a farmer, rising at 3am to be alone with your thoughts and hot coffee, tending the fields that feed a nation, while the sun rises, signalling: this is creation; I’m driving the world! The answer is probably: farmers, who would happily say “fuck right off” to 3am starts day after day sucking dust and hoping you can keep your margins, the equipment doesn’t break, and the weather holds. I think the angst of the writing wants to push through to something more than analyzing the pedestrian, but have the ultimate enlightenment being cool with coming back to embrace the pedestrian. Ish. I’m reminded of a couple story closings: [1] Siddhartha listened. He was now nothing but a listener, completely concentrated on listening, completely empty, he felt, that he had now finished learning to listen. Often before, he had heard all this, these many voices in the river, today it sounded new. Already, he could no longer tell the many voices apart, not the happy ones from the weeping ones, not the ones of children from those of men, they all belonged together, the lamentation of yearning and the laughter of the knowledgeable one, the scream of rage and the moaning of the dying ones, everything was one, everything was intertwined and connected, entangled a thousand times. And everything together, all voices, all goals, all yearning, all suffering, all pleasure, all that was good and evil, all of this together was the world. All of it together was the flow of events, was the music of life. And when Siddhartha was listening attentively to this river, this song of a thousand voices, when he neither listened to the suffering nor the laughter, when he did not tie his soul to any particular voice and submerged his self into it, but when he heard them all, perceived the whole, the oneness, then the great song of the thousand voices consisted of a single word, which was Om: the perfection. [2] [https://youtu.be/OsDnrFBpsBk](https://youtu.be/OsDnrFBpsBk) —- [1] Siddhartha, Hermann Hesse [2] A River Runs Through It. Robert Redford/Norman Maclean ------ ken I definitely see this. There's a brand of clothing for workers that has become fashionable among trendy young people. I see people walking around with a hammer loop who I doubt have ever used a hammer. ------ invalidOrTaken I really liked this piece. I especially enjoyed the thinking<\--->tan analogy. "Intellectualism as signal for (possibly ( _likely_!) contagious) unluck" is an unfortunate, but I think real, phenomenon. ------ munificent If this article resonated with me any more strongly, I'd shatter like a wine glass. I love living on the West Coast and working in tech, and I fully appreciate the many levels of privilege it affords me. Likewise, I've learned a ton and gained countless hours of recreation from Reddit and the other social aggregators. At the same time, there is something unhealthy and unbalanced about it all. Reddit's never-ending stream of upvoted videos is a machine for showing me the best and worst of humanity. That's enriching and often hilarious. But those best videos often leave me feeling like I can't compete. Why should I practice a little guitar if I'm never going to be as good as that guy playing "While My Guitar Gently Weeps" on a ukelele? The videos of mishaps aren't any better. Anytime a video of someone doing something foolish gets a million views, I get a little more self-conscious. It reminds me of that traumatic transition in middle school when I first became really aware of social pressure and fitting in. Because I wasn't used to this signal, the gain was really high and I was constantly paralyzed by self-consciousness. The Internet is that times a million, forever. I used to feel good about my even mediocre accomplishments because I lived in a world where I wasn't constantly surrounded by the world's best X for all possible X. I'd like to get back to that state, but it's really hard to turn off that level of self awareness. Deliberately _choosing_ to be unaware is not the same as actually _being_ unaware. It's another layer on top when the goal is to strip off the inteceding layer. I can't go back to before ironic- detachment post-modernism. The best I can hope for is a "New Sincerity" _post_ -post-modernism, which isn't the same. The part about degeneracy touches a nerve too. I don't know if I've ever tried to articulate this properly, but today's progressive liberal culture is possibly the most _confining_ culture I've ever lived in. In many ways it feels like a neo-Victorian society where the expectation to follow the norms is high and the price for the slightest transgression is even higher. The _values_ it adopts are strictly better than Victorian times and many of the places I grew up in the South. Equality for people of all genders, races, ability, orientations, etc. Care for the environment. Intolerance of sexual harrassment or violence of any kind. These are _good values._ But the way progressive culture _enforces_ those values socially is pretty intense. There seems to be little room for human error, personal growth, or misinterpretation. A slip of the tongue can easily summon a career-ending mob on Twitter. (Or, at least, it _seems_ that way.) If I tell a joke, is that a micro-aggression? If I _don 't_ tell a joke, is my seriousness itself another micro-aggression? While the laws are just, the penalties associated with breaking them are Draconian. Maybe it's _supposed_ to feel this way for me now. I'm straight, male, white, able, and middle class. Perhaps I felt freer in my youth because I was in a position of implicit power where there were fewer consequences if I did or said some dumb shit that hurt someone else. And maybe I have to be more careful now because that power imbalance is being restored. But as someone who has always strived to not be racist, sexist, homophobic, etc., someone who has always had been sensitive to the discomfort of others and tried to not hurt people, it's kind of a bummer being in a culture that makes me feel even more cautious than I already naturally did. Meanwhile, there's still apparently no shortage of actual fascist, racist, sexual predator asshats out there who clearly couldn't care less about liberal culture. It feels like we're policing ourselves to the point of madness when we weren't the problem in the first place. ~~~ ehfeng > These are good values. But the way progressive culture enforces those values > socially is pretty intense. I hadn't drawn this delineation before, but I find it apt. I grew up Asian in the Midwest and while I like progressive values here, I do miss how people there tried to be _neighborly_, even if they held opposing values. I was a kid in the suburbs, so maybe I only saw the softer side, but that doesn't stop me from admiring it and hoping to emulate that particular virtue. ~~~ munificent _> I do miss how people there tried to be _neighborly__ Yes, there's a certain presumption of goodwill that seems to be lacking. I think of it as "tolerance" in the engineering sense — the idea that we each need to give a little more than 50% in an interaction to account for some slippage and human error. I do believe that micro-aggressions are a real thing, that small-magnitude interactions that are _consistently_ in a negative direction can add up to a large negative effect. But focusing on those makes it hard to gracefully accommodate the normal noise and random error in humanity. If we aren't also tracking the "micro-benefiencies", then it paints everyone who ever makes a mistake (which is all of us) as deliberately malicious. ------ scelerat To me, saying someone is “basic” is another way of saying they’re living the unexamined life. It’s an epithet that probably doesn’t apply to anyone 100% and probably everyone at least a little bit ------ strikelaserclaw It is not the thinking that is the problem, it is the constant need to be productive and for thoughts to have value somehow. There are plenty of people who can think about stuff just for the pleasure of it. I guess living in a hyper competitive place like San Francisco would kill some of that "doing something purely for the joy of it" mentality. ------ stcredzero Remember, your capacity for innovation can be optimized, but will always be finite. Apply your capacity to where the cost/benefit is optimized. ------ obiefernandez I mentioned this article to my friend Michael who is currently hosting me at his farm in Umbria, and this was his reply: "Interesting yes, too much of anything dulls the mind, even the best things can jade and wane if overindulged in. One hour outside tying up tomato vines, weeding or watering balances out 10 trading memes on FB or watching YouTube tutorials, reading about myriad things as long as they are well written. We need and crave variety, novelty and balance, while the culture nudges us towards monomania, tunnel thinking and hyper-specialisation, narrow casting in the data stream, all trees, no forest. To zoom back out you need to let go of forward motion (or better, our notion of it) and be willing to stop using our will power for a few moments and see what's behind our ego's prideful play for perfection or power. Basic thinking is a cool concept. Unwinding complexity, seeking simpler, more elegantly energetic solutions to life's challenges, first to survive then to transform quantity into quality." ~~~ fbi-director Standing at a crossroad in my life right now, your friend Michael has some really insightful quotes. Thank you. ------ your-nanny It's this new fangled meaning of basic. I have to accept it as given, but I sort of find it aggravating, maybe because I think of basic as a synonym of foundational or elementary. In the context of mathematics, calling something basic, foundational, or elementary needn't mean simplistic, stupid, or something for young children. People can add and subtract without grasping number theory. But again, just me complaining about you people's neologisms, and how basic is that? ------ sharadov I think what we as programmers or more largely knowledge workers miss is doing something which is physical and involves direct contact. Typing away on a computer in a room with dozens of others with the him of white noise is far off from that kind of experience. I like to cook, the experience of touching produce, cutting and cooking is a uniquely human experience. So, yeah get a hobby which allows you to do that. Disconnect and recharge. ------ algaeontoast I equate “basic” as a label to someone I simply find so in-interesting or dull in their personal persists or interests that I’m uncomfortable being around them. Moreso, I’m acknowledging I’m incompatible with them, to me they are “basic” in that I don’t seem to stretch my thought process around them. To others they might be interesting, but I’m not going to lie to myself or others. ------ ggg3 thankfully the shift he points out with tan/work/leisure is happening and everyone now "works" as influencer on social media being the most basic as possible. By the time the author archives his desired basicnes as a status symbol, basicnes will already be repurpose to mean that you toil all day with basic social media influencing. ------ fragsworth Listen to yourselves. Look at what you're upvoting. Is this community reaching peak arrogance? It can be rephrased as "We're so fucking smart we need to take steps to dumb ourselves down". I'm prepared for the downvotes. But come on. Really? ~~~ tjoff That's not what it is about, at all. It is, perhaps, quite telling that you would reach that conclusion to a post that ponders whether striving to perform your very best every inch of your life really is the utopia. Being "smart" wasn't even part of the equation yet you somehow ended up there. ~~~ akhilcacharya I'll be honest, I interpreted it the same way. >a post that ponders whether striving to perform your very best every inch of your life really is the utopia. I can't read it that way because _it 's not how I operate_. I don't identify as a member of the "front row"[0] even though I am middle to upper middle class. All of the things identified as "mediocre" and implicitly compared against are _normal_ to me. There's an entire caste of Americans that went to HYPSM+ and got 2300's on their SATs and feel stifled by Bay culture. I think they are supremely out of touch. [0] [https://www.firstthings.com/article/2019/06/back-row- america](https://www.firstthings.com/article/2019/06/back-row-america) ------ _bxg1 Instead of chasing the latest one-dimensional solution (or anti-solution) to The Good Life, just seek balance. Everyone needs creative space, and everyone needs something in their life that feels truly challenging. But everyone also needs meditative breaks from mental activity, and time spent in nature, and time building relationships, and time doing things that are dumb and fun and useless. This seems to be a common theme in California (at least, SF and LA): take something good - creativity, progress, art - and fetishize it until it becomes a pathology. The problem is not with any of these things - they're good; great, even! - the problem is with seeing one single dimension of life as The End-All. That is always going to end up being unhealthy, no matter what it is. ~~~ nostrademons An ironic trend among some of the Bay Area upper-middle class is taking _balance_ itself and fetishizing it. So instead of meditating for 20 minutes at home, we have 10-day silent Vipassana meditation retreats where you can't talk or touch anything. Instead of walking to the store once in a while to get some exercise, people bike 50 miles in and 50 miles back to work. Instead of having a pet, people raise a menagerie. Sometimes I think Californians should just own it and admit that this is an extreme place. Even when we do balance, we do it by switching up the obsession weekly. ~~~ esoterica Walking to the store “once in a while” is basically zero exercise. That’s an awful example of healthy moderation. ~~~ nostrademons All you need is 30 minutes of getting your heart rate up, 5 days a week. If you walk to the store 2-3 times a week, take a hike on the weekends, and jog around the block a few times on the off days, you're there. ------ malvosenior It seems as if this person is just discovering old fashioned American anti- intellectualism (unintentionally ironically presented in an intellectual wrapper). There's a reason beyond laziness that many American's look down on typical urban, liberal arts thought and discussion, and it's close to what this post posits: tribalism and in/out group signalling. The difference is that the author sees being "basic" as a signal that one is wealthy enough not to have to work creatively for a living, and the historical practitioners of anti- intellectualism are signalling a disdain for productionless thought. ~~~ kickscondor Eh, there's more to it than this. 'Basic' is also the perspective that we're really just animals working to survive. That we're all just dipshits cluttering up the world while we attempt to assemble some kind of respectable way of living. No cynicism here - I feel a real kinship to others when I'm in this mood, rather than caught up in high-mindedness - which can be fun, too, of course. I think the fact that she terms it 'basic' rather than 'anti-intellectual' makes it less reactionary - a baseline humanity that joins all of us. I think even the term 'American anti-intellectualism' is a misnomer, considering that ancient figures such as Jesus or Buddha were in this vein - preferring terse wisdom to chains of detailed jargon. They spoke in 'basic', in a way. ------ rhacker In before there's a picture of a girl with one arm in the air with short pants on butt-facing-camera and a rake in the other arm. ~~~ dang Please don't do this here. ------ whatshisface The desire to avoid the "tan back stigma" of having to think to make money has already been satisfied by snooty literature. Snooty thinking is thinking that requires a smart brain but has no economic value. If you want to show that you're smart, and you also want to show that you don't need to make money, you can produce opinions on 13th century literature or whatever else you like. So, in a sense the author's prophecy has already come to pass. ~~~ ska I suspect this take is as snooty as the caricature you are drawing. ~~~ pessimizer Accusations of elitism from people who think they're better than everyone else are a weird feature of modern culture. I think it's somehow historically related to Calvinism (the best at being of service are the saved, not the best at being smart, or the best at asking questions.) It's virtuous not to think too much, it means you aren't wasting time on things other than salvation (or making money.) Just do the obvious thing. Whatever everybody else is doing. Do it harder, though. ~~~ whatshisface The worst existential accusation that anyone could levy against the intellectual elite would be that they're engaging in the conspicuous consumption of brain time, especially so given all the fun that's made of "McMansions" and other forms of conspicuous consumption. It's probably not true of everybody, but I wonder how many people would care about whether or not they were philistines if you took away any chance of getting recognized for having good culture.	{ "pile_set_name": "HackerNews" }
James Baldwin’s Archive, Long Hidden, Comes Mostly into View - samclemens https://www.nytimes.com/2017/04/12/arts/james-baldwins-archive-long-hidden-comes-mostly-into-view.html ====== samirillian Has anyone else noticed the common application of the term 'prophetic' to minority-writers? First the New Yorker article on Atwood, now this one. We don't read great writers because they're prophetic, we read great writers because they're great writers. Like, the subtext is always that the solution to our current political issues is looking for people who we can construe as "having seen it coming." It's so silly. I doubt that the guy who wrote Giovanni's Room would particularly appreciate having the term "prophet" applied to him, as if it were some sort of award.	{ "pile_set_name": "HackerNews" }
Ask HN: Going to SXSW? Would you take "startup train" from CA to TX this Spring? - ariabov Going to SXSW? If so, are you interested in taking the "Startup Train" to the event in 2012 from California to Austin? Here are the tentative details:<p>* This would be a one way experience. Many people leave at different times, so this is the way to get there, but you are responsible for the way back. * The format will be similar to "Startup Weekend" in a lot of ways. Some will present their ideas and the teams will be formed into the groups before boarding the train. Food, drinks (beer?), supplies, Wi-Fi, etc will be provided. The trip will take 40 hours on the train. As a result, you will have ~ 36 hours to build new startup before you arrive to Austin! * We will be departing from LA as that is the only straight train leaving from CA to Austin. * We will arrive in the morning on the first day of Interactive portion of SXSW * It is going to be fun! (I envision this to be more of a laid back atmosphere with opportunity to socialize with everyone present rather than only within your team)<p>What I want from HN community is CONSTRUCTIVE feedback (like why this is not a good idea or why you would do it), questions, suggestions in the comments here AND (if you would take a train yourself and want to know more) to leave me your email via google form below:<p>https://docs.google.com/spreadsheet/viewform?hl=en_US&formkey=dGRQdG52enJTMzBMdFlSU0d3ZExMb0E6MQ#gid=0<p>What do you think? ====== ariabov Also, what did you like / dislike about other hackathons / startup weekend type events? (no name calling)	{ "pile_set_name": "HackerNews" }
Break up Google - monfrere https://apps.bostonglobe.com/opinion/graphics/2018/06/break-google/ ====== fatjokes I'll be the devil's advocate. I miss the old Ma Bell. Its monopoly meant that AT&T Bell Labs had no financial pressure which allowed it to pursue pure research and crazy ideas that won several Nobel Prizes and laid the foundation of the 21st century. It's impossible to say what would've been. Would it really have been worse than the miserable choices of telcos in their current form? Verizon, AT&T, etc. Similarly, Google's ad revenue allows it to pursue incredible advances in AI and driverless cars that would otherwise be unprofitable. ~~~ marcodave > Similarly, Google's ad revenue allows it to pursue incredible advances in AI > and driverless cars that would otherwise be unprofitable. yet at the same time, they can decide what's "in" and what's "out" (figurately) overnight. They could declare that driverless cars "are not worth it" or that AI research "has to be reorganized", and who would be there to counter them? ~~~ profunctor Facebook, Amazon, Apple, Tesla, Microsoft, Uber etc etc. Google have a very powerful position but its not like they don't have formidable competitors in every field except maybe search. ------ Sylos I never understood in the first place, why governments let advertising become such a big business. Yes, there's the informational aspect to it, Farmer Joe needs to know that there's a new tractor that fulfills his needs, but we're long past that. Nowadays advertising mainly tries to sell things that people don't need. They can't use these like Farmer Joe to produce new value. Instead it harms the economy when people buy them. There is of course something to be said about having luxury goods available as reward for people that do well economically, but it should not be the case that the poorest families feel like they need to buy overpriced Adidas shoes to be accepted in society. It's nowadays central to advertising to build a brand image, to convey a feeling, to always play the same jingle. Which is psychological warfare, it carries essentially no informational value. ~~~ fwdpropaganda > (...) why governments let advertising become such a big business (...) > Nowadays advertising mainly tries to sell things that people don't need. > (...) Free market fundamentalists (I'm not one of them) would tell you that no one can judge better than the individual themselves what they need or don't need, and that if an individual says they're willing to part with their money to buy X, then that's them saying they actually need it. Even though I don't buy this view because the world is more complicated than the binary cause-attribution that it implies, I do think it brings up the question of who decides who needs what. If I believe Axe deodorant will get me "the hottest babes" and I decide really need it, would you have the government override my decision? ------ yuhong I wonder if Eric Schmidt left because of this debacle: [https://www.nytimes.com/2017/08/30/us/politics/eric- schmidt-...](https://www.nytimes.com/2017/08/30/us/politics/eric-schmidt- google-new-america.html) ------ bsaul I’m surprised this opinion hasn’t got more traction historically. It seems so obvious... ------ spacemanmatt Break up Microsoft and Apple, too ~~~ spacemanmatt Hello, Intel	{ "pile_set_name": "HackerNews" }
Commit 15 Minutes to Help a Student Break Into Your Industry - jontonsoup http://projectxpresso.com/hackernews ====== onedev This is awesome. We should help people around us achieve the same successes many of us have been fortunate to achieve. At some point we must all realize that this (for various values of "this") isn't some sort of race to the top (if a "top" even exists), this is about pulling _everyone_ up with us. I'll give you an example. When Dr. Dre was shooting the "Welcome to California" video in his hometown of Compton, the whole community was ecstatic, seeing their idols in action in real life. The same idols that provided many of them hope and the opportunity to dream. A large part of those people surrounding the scene were kids, of all ages. One of those kids was Kendrick Lamar, whose dad (or uncle?) had put him on his shoulders so his kid can catch a glimpse of the amazing scene that was taking place. Fast forward to today, Kendrick Lamar is one of the biggest artists in the world right now. He was able to make it out of Compton, California and become bigger than what his environment told him he can be. He represents the voice of the newer generation. When he started getting big and started working with Dr. Dre, he told Dre "I was there, I one of those kids that was watching you!". I think it's a truly beautiful story and to some extent we are all capable of inspiring and helping those around us, either through our own actions or spending 10 or 15 minutes to give someone advice, or responding to an email. We are not that important that we cannot spare 15 mins to someone who looks up to what we do and is inspired by what we do. ------ zebra Interesting - I already gave 2-3 hour introduction to two kids - 14 and 16 y/o. Next week one mother will bring her son for lessons. Btw the 14 y/o is already prized in his school for programming knowledge. I do it for free, because I like the idea of giving bright future to these young minds. ------ jacalata That looks interesting, but I'd like to know a bit more about who is running it and how/why before I put my contact info in. ~~~ jontonsoup We're a DreamIt Ventures company-- you can find our bios on our other site: [http://www.tradeup.io/team](http://www.tradeup.io/team) ------ gnarmis This is great! "office hours for the tech industry" explains itself. ------ BlackDeath3 "I'm a Professional" \- cup of coffee. I find that hilarious. ~~~ JealousCat *espresso ~~~ BlackDeath3 That's what I'm talking about.	{ "pile_set_name": "HackerNews" }
The Technium – A Conversation with Kevin Kelly - Futurebot http://edge.org/conversation/the-technium ====== jal278 While somewhat obvious when you think about it, this point is rarely addressed: > You can't learn calculus just hanging around people who know calculus, you > actually have to study it. It may be that for us to really master the issues > of attention management, critical thinking, learning how technological > devices work and how they bite back, all this techno-literacy may be > something that we have to spend several years being trained to do. Maybe you > can't just learn it by hanging around people who do it or else just hanging > around trying to learn it by osmosis. It may require training and teaching, > a techno-literacy, and learning how to manage your attention and > distractions is something that is probably going to require training. ~~~ wallflower Yes, the ability to focus is one of the most important traits of successful technologists. How do you teach it? I think it has to be more a case of lighting the fire with-in. Any successful program has to have the learners start to ask and answer their own questions (sometimes with guidance, sometimes with the all-important persistence of focus) - not be guided by rote teaching. [http://en.wikipedia.org/wiki/Flow_(psychology)](http://en.wikipedia.org/wiki/Flow_$psychology$) ------ dsplatonov Quite interesting, but there are only facts, no recommendations how to avoid new issues, that may appear in future	{ "pile_set_name": "HackerNews" }
Show HN: 3cosystem – biggest tech and event calendar in your city - sheraz http://www.3cosystem.com ====== bbcbasic Its nice. I will use this to keep an eye on events in Sydney. ------ tckr You are just aggregating Meetup and Eventbrite. How do we get other events listed? ~~~ sheraz Right, but it seems that meetup and eventbrite are about 90% of the events in any place. So chasing that last 10% is not part of the MVP. That said, I've been thinking on this question. I see two easy ways: 1\. a Webform with email verification / admin verification 2\. (My favorite) - Make a calendar invite to [email protected] and I can have Mailgun handle the request to my API. 3\. Submit your URL to an iCal/Gcal and I scrape it on a daily cron. Any other thoughts?	{ "pile_set_name": "HackerNews" }
Python logging 101 - alonswartz http://plumberjack.blogspot.com/2009/09/python-logging-101.html ====== alonswartz More in-depth information is available at: <http://docs.python.org/library/logging.html>	{ "pile_set_name": "HackerNews" }
The History of Dental Braces - tintinnabula http://www.theatlantic.com/health/archive/2015/07/braces-dentures-history/397934/?single_page=true ====== lukifer I don't have the link handy, but I watched an interesting video from an orthodontist describing the root cause of most crooked teeth being due to poor diet (partially from insufficient nutrients, but also not enough hard-to-chew foods to build jaw strength), and poor posture, which causes everything else to grow in the wrong directions and proportions over the course of years. I am unqualified to comment on the validity of these ideas, but it certainly seems likely that these kinds of subtle, year-after-year health issues would get overlooked by the scientific and medical community, compared with a lucrative fix after the fact. EDIT: Found it: [https://youtu.be/NvoX_wEtwDk](https://youtu.be/NvoX_wEtwDk) ~~~ JoeAltmaier Its caused in America partly by a mix of jaw sizes and teeth arrangements. We're mixing genes that haven't mixed every, and we can get small jaws and big, prominent teeth that inevitably are crooked. Often some have to be pulled to make room for the rest. No way is that caused by diet. ------ lucozade Oh those kinds of braces. I thought it was a history of BCPL derived languages.	{ "pile_set_name": "HackerNews" }
The Official Website of America - eupharis http://officialwebsiteofamerica.com/ ====== alttab Freedom? Freedom to vote for two candidates that were all but preappointed, freedom to be spied on, freedom to be indefinitely detained, freedom to pay for the poor decisions of others through taxes, freedom to have less rights than corporations, freedom to be unreasonably molested in airport security, and freedom to be penalized for not having health insurance. Gotta love that freedom. ~~~ eupharis This link is perhaps the single least likely starting point for a serious discussion of liberty in the twenty-first century in general, and America in particular ;) ~~~ alttab I know I got a downvote but I feel better now. ------ ddd1600 Runs great on the iPad!	{ "pile_set_name": "HackerNews" }
Google founders trade research chores for Moffett landing rights - gibsonf1 http://www.sfgate.com/cgi-bin/article.cgi?f=/c/a/2007/09/12/BUDJS3IOT.DTL ====== create_account Why does this have so many votes? Ok, the Google guys are wealthy and have lots of privileges. We already knew that.	{ "pile_set_name": "HackerNews" }
Covid-19: Why Aren't We Randomly Sampling? - giardini Individuals want to be tested for Covid-19 but only a limited number of testing kits are available. We can't test everyone.<p>Shouldn't government officials randomly sample populations rather than testing whomever volunteers? What use is testing if we don't stick to proper statistical sampling methodologies? How can we know how good or bad the situation is if we don't have decent statistics? We _do_ want to know how good or bad the situation is, don't we? ====== el_dev_hell > Shouldn't government officials randomly sample populations rather than > testing whomever volunteers? Governments are prioritizing tests for people with symptoms or close encounters with confirmed infected people if they're in a high-risk pool. > How can we know how good or bad the situation is if we don't have decent > statistics? We _do_ want to know how good or bad the situation is, don't we? Tests on the ground don't give a fuck about the macro (and I'd argue they probably shouldn't). When you have a micro-crisis (such as a suspected case in a nursing home), it's very hard to argue for random sampling for the greater good of "better data". ------ WheelsAtLarge There is not enough testing capacity, so tests are being done where they can do the most good such as testing at hospitals, to determine treatment, or whether a person needs to isolate to keep from spreading the virus. The U.S. will eventually need to go to random testing(maybe 10% of the population) to get a handle on the pandemic but it's a hard test to administer, it also needs to be done regularly, and it costs over $50 per test, so widespread testing will be hard. ------ rayhendricks Because the government evidently does not have the tests due to incompetence/bureaucracy. Amazon is assembling a lab and will start randomly sampling employees [https://www.cnn.com/videos/business/2020/04/17/amazon- covid-...](https://www.cnn.com/videos/business/2020/04/17/amazon- covid-19-test-jay-carney.cnn-business/video/playlists/business-tech/). MSFT will probably copy this strategy for its workers. Give it 6 months and I can imagine corporate COVID testing labs for most large companies coming online. Damn this is a weird timeline. ------ ThePhysicist Some countries are, there were e.g. random tests in Germany and Austria to study the general prevalence of Covid-19. There are other ways to cleverly increase test capacities for "explorative" testing by e.g. combining samples from individuals, testing them as a whole and performing binary search on the positive results. Germany plans to roll out antibody tests in May to find out who is already immune, building up the test capacity for that seems to be a complicated process though. ------ ghastmaster > How can we know how good or bad the situation is if we don't have decent > statistics? We cannot make good judgement without decent statistics. > We _do_ want to know how good or bad the situation is, don't we? Define "we". I certainly do. Politicians and media have other priorities than I do.	{ "pile_set_name": "HackerNews" }
Google App Engine to support SQL - scorpion032 http://groups.google.com/group/google-appengine/browse_thread/thread/9740dd2a8bdf4206 ====== ultrasaurus Reading between the lines, this shows that App Engine is a growing & responsive project, and makes me less nervous about building on it. ~~~ grandalf I'm trying to feel that way too... but the fact is there are people on the app engine team who could write SQL support for app engine in a few days in their spare time. The problems with app engine and the datastore have shown that there was a high level misunderstanding underlying the core design of the datastore... and how it would function in the context of lots of simultaneous users. So I'd feel a lot more confident if Google addressed this concern other than with the high availability datastore... ------ ShabbyDoo Look at this from the perspective of Google Apps corporate users. Imagine that the IT intern has just completed the corporate cafeteria's lunch menu system, and it's time to deploy it. While it's then least significant application the IT department manages, there's still a high fixed labor cost for infrastructure roll-out and management. The DBA must provision instances across dev, QA, and production environments. Onto which servers will the application be deployed? Must they be procured? Even if the lunch menu app is deployed on a VM instance, that OS image still requires security patches and other upgrades. The cost of deploying the intern's work likely exceeds his/her salary for the summer. With SQL on AppEngine, corporate developers can build apps like this without learning how to use NoSQL for persistence. Even if GAE's SQL doesn't allow scale-out sufficient for SaaS vendors and such, it will fill an important niche in Google's apparent goal of moving corps onto their cloud. As another commenter here suggested, the bar for perf/scale in many cases may be no higher than that provided by a MSAccess DB hosted on a Windows fileshare. ------ hpaavola We are living weird times. Multitasking, copy/paste, SQL support, these things are old, but still newsworthy when added to new platforms/services. ~~~ scorpion032 There is a difference between humans speaking and monkeys speaking. For hundreds of thousands (if not millions) of people that use the datastore API, this is a big thing. ------ jjm This could help out those who are building projects using Django &/or Django- nonrel. ~~~ zoomzoom Kind of kills one of the main reasons for the nonrel branch to exist, no? Wasn't django-nonrel an outgrowth of efforts to put django on appengine? I think that the nonrel project has utility on other places (redis, mongo, etc...) but ABP (all buttons pressed, creators of nonrel) was pushing django on GAE alot, IIRC. ~~~ jjm I agree. Don't forget that work has begun for a Cassandra driver as well. Truth be told however, Django and a SQL based system aren't all that bad. No matter what, it will be a long time before Django gets full 1.0 support for NoSql in any shape or form. That means, 100% Django coverage. ------ callahad So long as the performance is reasonable, this will go a long way towards removing lock-in barriers with AppEngine. ~~~ tantalor "The datastore is high-latency and extremely unreliable" \- <http://www-cs- students.stanford.edu/~silver/gae.html> ~~~ pjscott I've found that, if you want to make responsive apps on GAE, you must use memcache. At any scale. Personally, I gave up and left for better options. The generous free quotas aren't worth the trouble. I hear they've improved latency since I left, so take this with a grain of salt. I'm still not going back any time in the next few years, though. ------ netmau5 Hopefully this is the real deal and not an abstraction on the current datastore. When using the datastore in a relational way, you get some pretty horrid performance. ~~~ Strom It is the real deal and it will scale, and I quote, "as well as SQL scales". ~~~ scorpion032 The "free scaling" using appengine datastore is nothing more than theoretical at this point. The service has severe datastore latency problems and non trivial downtime. Looks like using RDBMS, solves both these issues for now, while Google can ponder around long term solution for the bigtable access. ------ Stormbringer I rather got the feeling that the datastore was much better for certain kinds of things than SQL. However, unless you are an expert in both SQL and the use of BigTable, how would you know when to use the one over the other? Okay, so obviously SQL is 'designed' to be good at transactions (whether it is or not is an exercise for the readers), and BigTable is really good for fuzzy search. I'm guessing that SQL is actually going to be more useful for anyone doing e-commerce (hence transactions) or anyone with familiarity with traditional SQL based persistence (even - shock horror - JDBC). SQL is bland, BigTable is sexy. But another word for bland is mature... ------ redstripe Nice feature, but not super important for new projects. I suppose it will make porting some existing projects over. I didn't remember seeing SQL on the roadmap however so I had another look ( <http://code.google.com/appengine/docs/roadmap.html> ) and I'm very excited to see it as been revised with a few awesome enhancements. I've had several projects I wanted to try on app engine which were impractical because of GAE limitations like no full text search, no programmatic access to blobstore, no bulk export/backup, no mapreduce. The future is looking a lot brighter for GAE. ~~~ ibejoeb Why isn't it important for new projects? I have a ton of projects that I can't do on GAE precisely because of this. GQL is _extremely_ limited. ~~~ URSpider94 At the risk of re-hashing a number of previous discussions, GQL appears limited when compared to SQL because Google's database is designed to scale to extremely large datasets and massive numbers of concurrent users. The features that are missing were removed intentionally because they don't scale. If you can re-think your database use to be consistent with this new paradigm, then you'll have a much more scaleable app when you're done. ~~~ scottbessler The end goal for every app doesn't have to be scaling on the order that GAE's original design provides. People have lived for years creating apps that use Excel or Access as a datastore. Being able to use SQL on GAE will allow more widespread use of GAE for things besides "the next twitter". ------ Kilimanjaro Google should buy a SQL engine like Postgres now that mySQL is in oracle's hands. People will need SQL databases till the end of times, and coupled with BigTable that can be a killer in the database space.	{ "pile_set_name": "HackerNews" }
Ask HN: My first programming job, no college degree, need advice - TbobbyZ I've taken some CS classes at a community college (Java & C++). Dabbled in different programming languages through Udacity, Team Treehouse, Codecademy, etc (Ruby, Python, JavaScript, Swift, PHP). Read a couple books on making websites. I don't have any projects I can claim as my own. Everything I've made have been slight changes from course projects. In general, I can figure out the tools needed to make something and morph existing code to build stuff.<p>I got a big break working as a Salesforce developer. Lots of new stuff, learning every day. Been working there 3 months. I'm pretty much getting paid to study and learn new tech for 4-6 hours of my shift.<p>Advice that I need. What are things I MUST do so I don't squander this opportunity?<p>Also, I work Uber/Postmates at night for 3-4 hours because I'm only getting paid $35k a year. As soon as I'm profitable and have the talent I've been promised $60k-$70k a year and the flexibility to go back to college to finish my CS degree. Is there anything I can do during my downtime of Uber/Postmates drives that will help in my developer journey? ====== jonny_storm I think the only thing you "must" do to not squander the opportunity is be passionate, which implies following your interests. Anything you can latch on to in your studies will help you make progress. As for your secondary work, use that time to think or simply rest your brain. Your subconscious requires downtime to solve problems and integrate what you learn; never underestimate the value of regimented idleness. Above all, enjoy! In the worst case, you'll learn a great deal and move on. ~~~ TbobbyZ Great point on resting my brain. Thank you! ------ jacalata Why do you need a second job on $35k per year, are you supporting a family or something? ~~~ TbobbyZ Yup. Wife and two kids.	{ "pile_set_name": "HackerNews" }
Launch of ProGamer.app to let gamers earn real prizes - dfortu https://www.progamer.app/post/welcome-to-progamer-app-play-esports-games-and-earn-money ====== davidtdev I already tried it and it works good. However, it still needs more users to play with ~~~ skybax_gamer which games it has? It has Brawl Stars for Android? ------ gabrielddl I think they are also developing a version for iOS, waiting for it. ------ gabrielddl It works good! I already receive some profits from it. Good job	{ "pile_set_name": "HackerNews" }
All Websites Look the Same - brownie http://www.novolume.co.uk/blog/all-websites-look-the-same/ ====== 21echoes (Most) all websites _should_ look the same. Most browsers look the same. Most car dashes look the same. Most newspapers look the same. Most books look the same. The web is not art. At least, not most of the time. Websites should only look markedly different with good reason. For most clients, there is not a good reason. ~~~ Spivak Of course, then the question should be why most websites settled on this particular style originally. ~~~ mc32 It's probably dictated to some degree by some aspect of culture. When you visit the websites where another culture dominates, one might find things to be different from what we're used to but similar to others where that other culture dominates the design. ~~~ kagamine A very good point I think, the web in your language is not always the same as the web in other languages, for example sites like nicovideo.js do tend to be different and carry a lot more information per page than American or European sites. ~~~ loco5niner nicovideo.jp, I assume? ~~~ kagamine An easy mistake to make as s and p are right next to one-another on the qwerty um ... I might not be paying attention. ------ unicornporn Aaand... Looking at their landing page[1] I can see they've chosen to go with a horizontal page layout. Because they use a non standard page layout they have a black stripe bumping in and out of the viewport instructing the user that they can/should scroll. This is quite a common layout among artsy portfolio themes[2]. Has anyone ever tried to sidescroll a web page lately? On my Yosemite MBP with latest Firefox/Chromium I just get a jitter and no movement. Sometimes the scrollbar moves in the wrong the direction and then dies. Moral: what is tried and tested usually works very well. [1] [http://www.novolume.co.uk/](http://www.novolume.co.uk/) [2] [http://demo.koken.me/#boulevard](http://demo.koken.me/#boulevard) ~~~ kalleboo > On my Yosemite MBP with latest Firefox/Chromium I just get a jitter and no > movement So turns out you have to scroll up/down to get it to scroll left/right. That makes total sense. And the speed is way off so the first time I tried it it just flicked straight to the end... ------ mattkevan > At times I think back to when websites were produced in Flash. For all its > downfalls (and there were a lot) one thing was always true. Flash sites > rarely looked the same. The author clearly doesn't remember what it was actually like to arrive on a Flash site, and play the fun games of 'where has the designer hidden the navigation today?' and 'oh crap, how do I turn the sound off?'. Design patterns are there to ensure that functionality works in a roughly consistent manner across different sites, so instead of having to spend ages figuring out an inscrutable interface, the user can easily buy a product or find the information they want and get on with their day. This is not a trend. This is lots of people slowly figuring out how content should be structured for maximum usability in a web context. Layout conventions will develop over time, as new ideas are incorporated and technology changes, but that's a good thing. As has been pointed out, books have looked roughly the same for the last few hundred years, but design innovation has only increased, as technology and our understanding of the conventions involved has improved. The visual design area is more susceptible to trends - a few years ago everything was glossy, then with 'Flat UI' everything became dark blue and a sickly shade of green. But that's ok too. Except for the green, that was horrible. The danger is with 'cargo cult' design. That's where the complaint against generic themes is valid – a style is used because it's popular without thinking about whether it's actually the best fit for the content and what's to be achieved. ~~~ mreiland I fucking.hated.flash websites. HATED. With a passion. Even when it was being done it was a stupid tech trick from jackass developers, it was never a designer driven thing except as a means of doing layouts that were you couldn't do in html at the time. and it was NEVER about usability. I hated that trend and thank god it didn't last very long specifically BECAUSE it threw the users under the bus. ~~~ mattkevan Most Flash sites were pretty bad (the first site I made was Flash, and it was bad), but it was also used to create possibly the finest website ever made. [http://superior-web-solutions.com/](http://superior-web-solutions.com/) Turn the sound up, and definitely do not skip the intro. It'll bring a tear to your eye. ~~~ angelofm I enable flash to watch this, I will never get back this 5 minutes of my life, DANGER DO NOT VISIT One thing is for sure, it brought a tear to my eye. ~~~ mattkevan Oh come on, it's not that bad - it's not like it set fire to your computer or anything. It's just an amazing example of what you can do with Flash, and why you shouldn't. ------ dpcan I could not disagree more. Don't fix what isn't broken (anymore). I believe that after years of designing websites, we found something that works, and works well. Consumers land on sites and see something familiar. It makes for a comfortable and easier web. I'm all for this "standard" in web design. ~~~ onion2k Just like we didn't need to fix the infinite-scrolling-homepage before it, or the top-navigation-with-drop-downs design before that , or the left-side- navigation-fixed-width design before that, or the fluid-width-with-header-and- two-sidebars before that. The current design trend is exactly that - _a trend_. Something else will replace it in a year or two. The current state-of-the-art full screen background image site is no more a standard than any other design in any other field. Design is a living, breathing thing that evolves as our technology evolves - it moves with the times. However... _I believe that after years of designing websites, we found something that works, and works well._ You don't need to 'believe'. If you aren't testing your designs and gathering actionable metrics you're really missing out. ~~~ tikhonj Testing is great, but tends to involve small local modifications. It'll get you a site that looks the same in a different way, but won't help if you want something a bit different. Even if people did run tests on significant redesigns, I suspect results would be dominated by methodological issues and a lack of power, leading to little more than noise. ------ avodonosov It's just one example of fashion in tech. Around ten years ago there was another fashion for web sites - all the panels had rounded corners (and it wasn't supported by CSS, so people created the rounded corners from pieces of images - very unproductive waste of time). Non-tech people, when ordering a web side, often just don't accept things which look different than other web sites they have seen. At that times it was difficult to convince people rounded panels with borders are not necessary. People often are unable to judge themselves, so they rely on what others do. There are many other examples of such unhealthy fashion: Spring framework in Java, XML, SOAP, gray text on web pages (even despite it violates W3C accessibility recommendations), not using tables in markup (even if I want tabular layout), etc, etc On the other hand I agree that uniformity can help people to consume information, and also inventing unique design is often a waste - the content is the most important part. Still, there are many cases of harmful fashion. ~~~ kagamine Don't want to nit-pick but, >gray text on web pages (even despite it violates W3C accessibility recommendations), the W3C don't recommend against grey text at all, they recommend that designers consider the _contrast_ of text colour versus background colour, and to not use _light_ grey on white. It's a matter of contrast and not a blanket rule. I do think it is important that we don't start making new silly rules about dos and don'ts in web-design. ~~~ avodonosov Contrast, you're right. And also, there are good examples of gray (low contrast) texts - some auxiliary elements. But when the main text - e.g. an article body - is published in low contrast so that I need to inspect HTML and disable the color to be able to read it, such cases make me sad :((( :) ~~~ kagamine I hear you, disable colour, ctrl+, ctrl+, ctrl+. OK, now I can read this! ~~~ smoe I'm way too lazy for that, I simply close a page as soon as anything interferes with my reading experience. Whether it is small, low contrast text, survey or region selection popups seconds after initial page load, text jumping once the over sized inane stock photo in the header is finally downloaded, etc. If the information contained is of any importance it will show up in a readable form somewhere eventually. ------ mholt For that matter, all books look the same too. And yet everyone knows how to use books. You hand someone a book and they never look at you funny asking how to get to Chapter 1. His article is negative, but I for one have been able to traverse websites more quickly and easily because they adhere to some now-common conventions. Of course websites need to be original but not SO original that they require the user to adjust their assumptions about what to expect from site while it's loading. ~~~ kagamine Unless the book is a manga, in which case you will find chapter 1 at the back, and how many of us tried to read our first manga in the early 90s only to be really confused? I mention it not be a pedantic fool, but because the web also has global regional variations and the linked blog post deals solely with the western web and its layout. There is a marked difference in design and quantity of information (and quality, both positive and negative) of the web _we_ use and the web in other regions. ------ BinaryIdiot Honestly I'm fine with most websites sticking to a similar layout as it helps me navigate it faster plus it's just trendy right now so that'll pass like all web design trends before it. Having said that this specific layout is garbage, in my opinion and not because of its design but because of the way it's used. It's so incredibly rare to see a company use this type of layout without filling in every single space with utter bullshit about generic buzzwords and it just takes up so much space. I can't count how many start-up websites I go to and I have to scroll down for pages just to figure out what they even sell because everything up front is large, generic images that don't mean anything followed by lots of very general phrases and buzzwords. ------ Phlow I think it's safe to say, at least from my view, that Bootstrap is the reason for it. Bootstrap made this format easy and clean, and it works well with mobile. Websites will look like this until someone comes out with the next thing that's easier and/or cleaner and/or works better in mobile and then a couple years later THAT will be the format you're seeing everywhere. I don't think this is a bad thing. At least it's clean and works well on mobile... ~~~ flockonus Bootstrap didn't invent such websdesign, it was experimented with, learned and improved collectively. If anything, the library implemented these (almost) standards that were wildly used. ~~~ mreiland He didn't say they invented it, he said they made it easy to do. ------ pun_Krawk I take issue with the current 'standard' design, but only indirectly. I feel like giant home screens give companies the freedom to create a great looking webpage without any actual content - like a giant landing page. Since they all look the same, it's easy to compare and contrast. I can recall a number of times scrolling through the entire home page for a company, only to still be confused about what the product actually does. I see a huge banner image, coordinating colors, tons of whitespace, very high-level text content...but little that says, "Our product will specifically do this, that, and the next for you!". I have to click around to find that out. By that time, I'm quite annoyed, and I'm not sure if your product is worth my effort. Maybe my expectations of a home page are wrong though. ~~~ analog31 I find it's often easier to find out what a company does by doing a quick Google search, than to figure it out from their website. ~~~ TuringTest Me too. If the company is notable enough to have a Wikipedia page, usually the article's first paragraph tells you what you want to know of the company much better than its landing and About page. ------ trymas If mentioned style works is simple, and represents/introduces product/service well, then why not. What annoys me is when designers/developers over do it, e.g. scroll hijacking, lots of heavy JS which introduces horrible lag, and unnecessary pop which ruins user experience. Sorry, but `novolume.co.uk` is stepping into the the category of over doing it. Huge, and super low contrast arrow buttons to switch articles. Why? Italic serif slim and narrow font, from which my head hurts, eyes are twitching and is not readable (and some characters are unrecognisable, e.g. '&'). AFAIK, serif font is more readable then sans-serif, but this is not the case. Custom scroll bar, why the hell do you need to replicate a perfect native widget my browser has (and this seems to be a new trend, probably replacing scroll hijacking)? Crazy tilted, on hover shape and colour changing (and low-res) social buttons, why make it so complicated? At least `novolume.co.uk` loads and renders fast, is responsive and does not have lagging UI. ------ sdoering He's even got a little follow up on what happened after he posted his content: [http://www.novolume.co.uk/blog/stolen- success/](http://www.novolume.co.uk/blog/stolen-success/) ------ jpswade >At times I think back to when websites were produced in Flash. For all its downfalls (and there were a lot) one thing was always true. Flash sites rarely looked the same. This is the take away line. There's a reason why we now have beautiful looking websites to a fairly uniform standard and that after the 2000s, the usage of Flash on Web sites declined. The fact that "all websites look the same" should be celebrated in as much that we've found a formula that is practical for consuming content and for the most part, works. ------ orthoganol He's right that most _bootstrapped_ startup websites look the same, because they don't have designers on their team, their founders aren't trained in design, and they don't have the money or time to really flesh out the design. They just follow easy examples that are passable or in vogue. Or worse, maybe they just buy a template. But OP is wrong once you talk about startups that get money. I mean for some well known ones, just look at Stripe, Mattermark, Branient, Mixpanel, Filepicker, Buildzoom... these sites aren't the same at all. If you spend time studying the design of hundreds of YC startups you'll see what I mean... almost to the point where I wonder if YC specifically instructs their startups not to copy other YC startups. ~~~ erik14th Those you listed all look like the layout in the article. ------ websitescenes After reading the comments the debate seems to be creativity vs utility. There has to be a balance between the two. Acknowledge what works best now and then adjust when something better comes along. With that said, specifically in websites, I think utility should come as a first priority. If your doing a band or artist website I can see bumping up the creativity factor though. ------ s_dev I found this on Intercoms blog post entitled "Some Things can't be Wireframed". This picture reflects the meta design of many websites. [https://blog.intercom.io/wp- content/uploads/2014/02/SquareSp...](https://blog.intercom.io/wp- content/uploads/2014/02/SquareSpace-Frame.png) We've arrived with this design from years of design evolution and no one person is responsible. All products seem to ultimately converge on some optimal universal archetype. Websites, books and radio towers are no different in this sense. The same will be true of mobile Apps someday but I don't think its the case at the moment. [https://blog.intercom.io/things-cant- wireframed/](https://blog.intercom.io/things-cant-wireframed/) ------ fsloth As in "All the books looks the same"? I see nothing wrong with finding optimal ways to present information. ------ thenomad So in summary, most websites have settled on a design with: \- Headline / key attention-grab in the most visible size possible \- Subhead / attention -> interest converter right below that \- Attractive visual element providing emotional context occupying as much screenspace as possible \- Benefits propositions right below those, exactly where you'd expect them to be if you're familiar with a Web browser Sounds like a damn good approach to me. I mean, I'd be happy to see an even more efficient design that measurably increased conversion rates for most products, but if there's nothing currently out there, I'm OK with the state of the art :) ------ totemizer All websites should look the same, but they don't. Sadly. It's all just information in some kind of format. A video as an mp4 or some text as... well text in whatever way your machine stores it, but mixed with a bunch of irrelevant other text. But then there is "design" and then you get stuff like inconsistent search, inconsistent site layout, you never know where to look, what to look for, you miss things because they are placed somewhere where you are not used to look. It's a mess. All websites should look the same. ------ callum85 All _startup websites_ look the same. They all use this template because it perfectly addresses their goals (grab your attention, explain a new kind of product, convince you to sign up) while also being familiar and repeatable. That doesn't concern or surprise me. Other kinds of web page with a standard design style include: shopfronts, forums and Q&A sites, search engine result pages, shopping carts, calendar apps, video sharing sites. Trying to look irregular just for the sake of it is bad. ~~~ JustSomeNobody >Trying to look irregular just for the sake of it is bad. Looking irregular because your designer can ... actually design is good. Looking irregular because there's a better way to present your site to the public is good. ~~~ callum85 I agree. But startups shouldn't be expected to do this. Startups are experiments; you want to quickly determine if there's a market for the product (and fail fast if not, so you can alter the product or move onto something new). Being conservative with design is the perfect approach for this. If you experiment with unproven layouts, and it fails, how do you know if the problem was the product or your layout? Interactive new stories, artists' portfolios, design agency websites, web apps, and websites that are themselves art - these are all good places to push boundaries in design. Not startup product promo pages. ------ dfragnito It so happened I was given 5 different pens over a course of a week. Each pen had a different interface twist, pull, slide, press, not one was of the traditional variety of clicking the top. The following week I had to go to the bank to sign something. The banker handed me a pen, I pulled, twisted, pushed, and could not figure it out then I realized it was of the tradituinal variety, and sheepishly clicked the top. ------ mjsweet I think it's important to not mess with the customers mental model. In particular the shopping cart pattern was created over a period of time to make the eCommerce user experience as frictionless as possible. So when someone wants to get through the cart, you would want as few surprises for the customer as possible. The hamburger icon is a great example of how a UX pattern has taken a long time to filter down into the the collective mindset of users... "oh.. this is the menu". I still get clients asking when the funny stack of lines are and end up adding "Menu" right next to the icon. So my question is this: is it safe to try new things, or is it better to stick with existing patterns we know work? Or is there a blend of both? Is it better to let larger operations (Facebook, Google, Apple etc) to forge the way with mass assimilation of UX patterns? I do think my first instinct is right (first sentence), but I would love to know the experiences of other UX people about integrating new and fresh UX patterns. ~~~ FilterSweep Great comment. I'm finding it one answer of your ? To be more and more a "depends on your project." I do theoretically find a website to be a form of "artistic expression" but unlike most other medium, there is a technically "right" few ways and many "wrong" ways to "implement" your art. When you see a website posted here that takes a bit of artistic liberty in its design, you will _undoubtedly_ have some HN commenters criticize the way they did such and such. Despite the fact the page load time is only affected by one millisecond, that "incorrect" implementation is reason enough for some to trash the designer and deem his "solution" inadequate. What we then see is a world full of TALENTED designers often too afraid to try something new. But, isn't that the point of art? It's meant to be polarizing. This is just personal opinion, but I'm finding it more and more necessary for the designer of the modern web to have _multiple, concurrent projects_ as opposed to completing one project and moving on to the next. Currently I'm working on an athletics site which uses your now "bread and butter" design which the OP gripes on, but I'm also working on a payment web app which has a design that harkens to someone filling out a clipboard. I've just this week also accepted a project to showcase a fashion designers portfolio, and I'm swinging for far left field on that one. If I was not working on these projects concurrently, I would not have learned that each design has advantages and disadvantages, and I would be pidgeonholing myself _if I didn 't give myself room to fail_ We are all still learning and growing in web development. And our consumers are growing too. One interesting thing you mentioned is that users are steadily growing more accustomed to the hamburger button - a quick google search will tell you that the Hamburger wasn't so tasty in AB testing, however, users learn. I've been a part of a reason site redesign which found the extra click of a dropdown menu was better liked (and had more click through) than the link bar, despite our demographic was relatively older users! And The hamburger menu is a great case study as it has become commonplace in modern design. You could go with the triple bar, or do Apple's approach of a double bar that rotates into an "X" ( [https://apple.com](https://apple.com) ), or you could do Google's three circles arranged vertically in their mobile Chrome browser, but the concept is essentially the same. Now, there are very talented developers on HN that _despise_ the hamburger, and perhaps rightfully so, but you often hear crickets when an alternative is proposed. Certainly the tabbed interface at the bottom with a "More" button works, but it doesn't work for every case. So sure, you will have some projects where you have to go with what is known, but try some other projects to challenge a different approach out of you to build up your chops. ------ MrJagil earlier discussion: [https://news.ycombinator.com/item?id=10124078](https://news.ycombinator.com/item?id=10124078) ------ ohthehugemanate Nytimes.com Brookings.edu Reddit.com JustinBiebermusic.com Facebook.com Spotify.com Google.com Websites Fall into functional categories. Sites within a given category look the same. Sites about a product need a powerful visual "grabber" element that communicates key brand points along with their name, then they need to provide key informational points on am easy to digest manner, often segregating the audience by interest. The big banner, three subtopics layout is a popular way to achieve this. But not all websites are about introducing a product. Some are about getting immediate social interaction. Some are about exposing deep information in a set of categories. Some are about hierarchical display of the newest possible information. They don't tend to use the banner/three subheadings layout. ------ drikerf I believe it's a good thing. When websites follow some kind of blueprints it makes it a lot easier for the user since they can recognize it. The negative side is of course that it might slow innovation, although slow isn't always bad. ------ inDigiNeous Who cares about the looks, really? The looks are there just to present the content, in a way that fits all the devices that are used to view it. Sure, you can do some artsyfantsy pantsy stuff now and then, but then again, it's about the content too, just that the whole artsy website is the content. And this guy has the most generic looking blog structure also, so why is he blaming the guilt on somebody else. I'm so glad I don't have to go through these "designed just because design" flash websites anymore and try to figure out different structures for each page. ------ skaplun Most organizations pick designs based on competitor research. Sometimes there's a project manager in the middle to preach ux. Either way the site comes out like the rest, and at times its usable ------ Kiro Definitely prefer that layout compared to the one used on novolume.co.uk. ------ pmontra All "normal" stairs, windows, roofs, tables, chairs look the same. There are good reasons for stable architectural patterns. There are good reasons for web design patterns too. Go back to the 90's and early 00's. There were so many different styles. A few won and became the ancestors of today's styles. Many more lost and got extinct. Sure, there are other styles that nobody thought about that are better than what we have today. They'll get created from time to time, copied and refined. ------ awjr The designer seems to be harking back to a time when pretty much the only browser was one on a laptop and you could reliably assume 764pixel width. These days, you have no idea what is browsing your website and more than likely it is somebody on a phone. So priorities change. Content makers want their message in front of as many people as possible. To achieve this, you make it work on a small screen. This brings good design constraints and stops design for the sake of design. ------ cm2187 Let's make website like architects make buildings. It's more important to be original than beautiful or functional. Let's put the navigation menus at the bottom of the page and the disclaimer at the top. Let's randomize the order of the links and elements so that every user has a unique and original experience on every visit. In fact why use english? That's so boring. Let's use hieroglyph! ~~~ noir_lord > Let's use hieroglyph! [https://fortawesome.github.io/Font- Awesome/](https://fortawesome.github.io/Font-Awesome/) I get that your comment was a joke (clearly) but there is a nugget of truth in it. ------ oneJob I've often thought that porting a game engine to the browser with a suitably robust object library and hyper-intuitive developer interface would be just what is needed to jump-start a move away from rectangles and columns. And doubly so now that VR is about to hit its stride. I want what "The Lawnmower Man" promised me, dang it! ------ jbb555 Most websites are _aweful_. My monitor is almost 2000 pixels wide and they insist in packing their whole text into about a 10cm little strip of it. I see so many websites that want me to read about 5 words in a row when there is space for about 30 if they weren't too lazy to use the whole screen. I guess they prefer arty over practical. ------ AndrewKemendo The internet is a giant A/B test. If something works, people adopt it. Once it stops working, people move on to what works then. Wash, Rinse, Repeat. I'm starting to think that the tech community at large doesn't understand that it's also part of humanity, and thus falls to the same cognitive traps as the rest of society. ------ js4win A Website needs to convey an idea in the most convenient form possible. Due to a rise in smartphones, most websites have trended towards a mobile-first layout - scroll to view the entire content without any redirects between multiple pages. I would be interested to see a professional designer's perspective on this. ------ hkmurakami _> Generic wins out every time._ Frankly, unless you are a company where design differentiation is paramount, it is much safer to do what everyone else is doing and be "good enough". It's cheaper, faster, and possibly on average better for visitors to glean the messages you want them to hear, compared to more daring designs. ------ mdpm "All these pants have 3 holes, some sort of fastening/cinching mechanism, and the layout's basically the same in each case!" ------ starikovs The good side of this is that users, not hackers, can feel conmfortably when they deel with something known and predictable. ------ task_queue It is a current design trend, it will be different in a few years just as it was different a few years ago. ------ desireco42 I would say, this is good part, common elements, creativity is in the content or other solutions. ------ kenOfYugen All websites look the same because they rely on 'best practices'. If you have a 'better practice' go ahead and implement it, thus inspiring the best practices to come. That's how the human world evolves, slowly blending the old with the new. ------ gopowerranger A lot of posts here are mixing "look the same" with "function the same". Familiarity is fine when it comes to function but to look the same is boring.	{ "pile_set_name": "HackerNews" }
Amazon Fires Missile At Book Industry, Launches 70% Kindle Royalty Option - icey http://www.businessinsider.com/henry-blodget-amazon-fires-torpedo-at-book-industry-launches-70-kindle-royalty-option-2010-1 ====== sjunkin This is brilliant. Anything which streamlines distribution has always helped the consumers and producers while increasing overall efficiency. Redfin is a good example, this looks like it will be another. ~~~ cnunciato Not always. Redfin, maybe, since the middleman in that case is really more like an obstruction between buyers and sellers. Publishers aren't an obstruction in that sense. Sure, some of them could probably run leaner operations and give more money to their authors, but the publishing industry as a whole serves a very valuable purpose we don't necessarily recognize, because we're so used to it. ~~~ runevault Depends, there is some use like content filtration. However the user ratings could fill in for a lot of that on amazon. Also, as came up in another branch of the article's discussion, this could cause certain things like freelance editing to get a real boost from potential increased customers. ------ cnunciato Personally I love the idea of authors earning more for their efforts, I think that's great, but there are so many unintended (by consumers, anyway) costs of Amazon using its reach for this kind of thing -- publishers get squeezed, so they produce fewer books, bookstores get squeezed, so more of them close up shop, commerce flows ever more directly to Amazon, choice gets limited... I just don't like it. I buy a ton of stuff from Amazon, but I'm starting to think maybe that's such a great thing anymore, in the long run. ~~~ iron_ball Your comment was gray when I saw it, so I restored it to >0, but I disagree. This move makes it easier for authors to get their product into readers' hands, gives them a better cut than the publishing industry generally did, and provides better value for the user. Amazon can't cause "less choice," because for one thing, they have effectively unlimited inventory; and for another, if there's an untapped demand, a competitor will arise. Sure, nobody else can publish to Kindle, but the next few generations of smartphones, netbooks, and possibly tablets are very likely to make that a nonissue. ~~~ petercooper _Sure, nobody else can publish to Kindle_ That's not true, is it? I'm sure I've seen publishers like Pragmatic Programmers selling Kindle stuff that doesn't go through Amazon. I don't have a Kindle though, so I'm not going to state this with 100% confidence ;-) ~~~ shawndumas They do indeed. I have a number of titles in epub format from them. ------ greyman The article suggest that the Kindle business is a big money-loser so far? That surprised me. Why it should be a money-loser, when the Kindle itself is rather expensive and the e-book copies cost virtually nothing(?) ~~~ gchucky There was an article a few months back that stated that Amazon loses $2 for each book sold on Kindle. Publishers won't sell e-books for less than the publishing price. [http://www.tbiresearch.com/e-readers-should-drive-profits- fo...](http://www.tbiresearch.com/e-readers-should-drive-profits-for-both- distributors-and-book-publishers-2009-11) is the original document, as far as I can find right now. ~~~ etherael Is this genuinely a case of "We have commercial control of a lot of physical book manufacturing commodities and in order to leverage the value of these commodities we want to artificially inflate the price of the competition"? That... seems... well, it doesn't taste good, let's put it that way. ------ Mark_B This is a totally exciting and great idea, but the down side the cynic inside of me sees coming is the spam/ads saying "Work from home as an author and make $$$" and junk Kindle-only books flooding Amazon. ~~~ potatolicious > _"and junk Kindle-only books flooding Amazon"_ I actually think this would be a great idea - so long as it does better than the App Store in terms of filtering for the best. Amazon's recommendation/review system has always been pretty strong, though. Democratization of publishing, of content distribution and production, is one of the chief reasons why the internet has been the most important invention in recent memory. ------ ShabbyDoo So, am I correct to assume that authors mainly need publishers for printing, distribution, and marketing? Will we see more self-publishing as a result of the Kindle/Nook/etc? ~~~ msg The main benefit I receive from publishers is filtering. Even the worst publisher printing unbelievable shlock is light years ahead of the garbage in the publishing anteroom, the slush pile. With that, the greatest blog post on publishing of all time, "Slushkiller": <http://nielsenhayden.com/makinglight/archives/004641.html> ~~~ tjic > The main benefit I receive from publishers is filtering. The main benefit I receive from my friends is filtering. Now, the question is: do publishers or my friends do that job better? ~~~ msg Or a deeper question, are the publishers making your friends' lives easier by doing it first? Do your friends read thousands of self-published books to provide you with recommendations? Or is all their action applied after the mainstream publishers' filter? I'm sure there is self-published stuff out there that is worth my time. Unfortunately, I don't want to read the literary equivalent of MySpace to find it. A good publisher has a quality bar I can trust, and they've taken on the burden of reading unsolicited submissions. And as the blog post says, 75% of it is unreadable crap, 24% is readable but not worth your time, and 1% or less is quality and publishable. That's a lot of hours you and your friends would have wasted. ------ xcombinator :-D I'm waiting for the Apple tablet info the 27 of January. It seems too much coincidence that Amazon changes her policy now just at the same fees that Apple Apps Store charges. They must know something that we don't and want to be first... ~~~ runevault There have been rumors/leaks that Apple is making content deals with various forms of publishing including book, which if true this does make more sense. ------ j_baker While I sympathize with the Publishers, they're beginning to sound a lot like the RIAA. For capitalism to work, dinosaurs have to die. And it's beginning to look like the publishers are turning into dinosaurs. Personally, if I were to publish a book, I'd be tempted to just cut out the middle man and forego the big advance (which I hear usually isn't that big anyway).	{ "pile_set_name": "HackerNews" }
The Math Problems from Good Will Hunting, with Solutions - agiri https://medium.com/cantors-paradise/the-math-problems-from-good-will-hunting-w-solutions-b081895bf379 ====== agiri From Wikipedia: "Consider a system of n linear equations for n unknowns, represented in matrix multiplication form as Ax = b where the n × n matrix A has a nonzero determinant, and the vector x = {x_1, x_2, ..., x_n}^T is the column vector of the variables. Then Cramer's rule states that in this case the system has a unique solution, whose individual values for the unknowns are given by: x_i = det(A_i)/det(A)" ------ wso How do you 'calculate the inverse of (I − z × L) using Cramer’s rule'?	{ "pile_set_name": "HackerNews" }
Donate hair to help contain oil spills - shawndumas http://www.matteroftrust.org/programs/hairmatsinfo.html ====== jacquesm <http://www.kolotv.com/home/headlines/92913319.html>	{ "pile_set_name": "HackerNews" }
Highest Paying Tech Companies of 2019 - z0a http://levels.fyi/2019/index.html ====== senordevnyc If you're a software engineer in a city where these companies employ folks and you're thinking this doesn't apply to you, I'd encourage you to at least give it a shot. It's not only the absolute best of the best who get these jobs. I recently decided to do a round of interviews after 10+ years as an independent web / iOS dev, having _never_ had a professional software dev job. I'm also a self-taught developer with a business degree from a no-name state school. Despite all that, I've been really surprised and happy with the market reception here in NYC. I got interest from the bigger guys like Amazon, FB, and Twitter, as well as smaller companies like Dropbox, Stripe, Square, Coinbase, etc. Last week, I got a very good senior / staff offer from one of the smaller public companies for around $400k in first year comp. With bonuses, promotions, refreshers, etc, that could easily average $500k - 600k per year over the next few years. And I had no competing offers. Some of the other companies I'm in the loop with will almost certainly offer quite a bit more, although I love this company that made the offer and I'll probably just drop the other interviews and take it. Comp isn't everything. All this to say, if you're interested in making more $$ and these companies are hiring where you live, don't pass it up because you think it's only for hotshot 22-year-olds coming out of Stanford. ~~~ geebee Have you studied extensively for the technical exams? I've tried, and I've gotten interviews at several of the FAANGs as well as some desirable mature startups, but I fail at the technical screeinging stage. Not sure if I've tanked it or was close, but I get the "no hire" call or email after take-home projects or whiteboard exams. Btw, to give you sense of it, I'd have no trouble finding a loop in a linked list, printing all permutations of a set, or searching a tree recursively. I'd have to puzzle a bit to figure out how to do DFS vs BFS, but I'd get there, I don't have it loaded into memory. I wouldn't be able to implement merge sort on the spot, I'd need to look it up, though I could probably get it frontloaded. All I can say is dayum those interview exams are hard, what I described is a pre-req, nobody will just ask you to permute a set, but if you can't, you'll never solve whiteboard the problem they ask you in 45 minutes. For take-home projects, one (a rails app) was rejected because I used named routes rather than using the more conventional methods (I know this wouldn't be good to do in a production app... guess I just wasn't thinking about routes, it was a demo app, so I just threw some names routes in there for demo purposes, it was a take-home), along with some "duplicated" code that I thought was justified but never got to explain (I personally think extracting this into another method would be a pre-optimization that would need to be undone when the methods diverged, something I thought would be likely under the admittedly fabricated business requirements). I did have what I though was good testing, the reviewers did complement that along with some aspects of the app in their review. Sorry, don't mean to give you my sob story, I just... I'm at the point where I wouldn't mind a crack at these jobs but just feel like maybe it's not an effort that's going to pay off (I mean, how much more time do I really want to spend on the kind of problems in cracking the coding interview? I actually feel like I got something out of studying it and preparing, but going back over and over, nah... maybe other people retain this stuff better than I do, and you know, maybe that does actually say something about suitability for these jobs). ~~~ senordevnyc How many tech screens and interviews did you do? I cast a pretty wide net to start, so I was in the loop to some degree at a bunch of companies over the last ~7 weeks, which was exhausting. But I didn't really think I had much shot at these bigger tech companies, honestly, so I interviewed at a ton of NYC startups too. The practice was really helpful. I haven't totaled up my stats, but this is roughly how things went: 1\. Once I got a recruiter on the phone, I had a 100% chance of going to next stage 2\. For take-home projects, I had a 100% pass rate (did 3-4 of these) 3\. For online assessments, I had a 50% pass rate (did 2 of these) 4\. For live coding screens, had about a 60% pass rate (did 10-12 of these) 5\. For onsites, I had a 50% offer rate. I did 4 of these at NYC startups, and 2 at bigger tech companies, one of which made an offer. Still waiting to hear from other one, but not hopeful. I'm still in loop at 3 big tech companies. The point is, it's pretty random. I flopped a couple of tech screens pretty badly because the interviewer was just difficult. Some give easy questions, some give hard. Some you click with, some you don't. And you get better at this over time too. _(I 've also been amused to watch startups give more challenging interviews than the big tech companies and then make offers that are 1/2 as valuable)_ In terms of prep, I took a data structures / algos class at Harvard Extension a couple years ago that was really helpful, and then I've been doing some Leetcode and CTCI problems the last couple months. Not enough though, honestly. I also went through some mock interviews with Interviewing.io and TripleByte, both of which were helpful. By far the most helpful thing though is that _both_ of the big tech companies where I did onsites actually tested me on mostly real world iOS dev, not generalist whiteboarding algorithms. And the other tech companies where I'm in the mix have also been a little more flexible. Twitter for example offered me the option of a take-home iOS project or a traditional 1-hour generalist tech screen. Although their onsite is still whiteboard coding algorithms from what I understand. Sigh... ~~~ geebee Thanks for your reply! Your pass rate is quite a bit higher than mine - I'm 0/2 on projects, probably 2/5 on interviews (I'm only counting the in-person interviews, don't have a problem with phone screen level). Some were much easier than others. I think my most recent interview was a couple years ago, though, haven't done much of it lately. I do agree with you and the other reply (mdocherty) that it is a bit random and you only need to connect once. That said, it's not totally "free", there's no real point (for me at least) in going into these without substantial prep. At my google interview, I asked for 3 weeks. My lunchtime "interview" (this one is unscored, just a chat) told me that he had requested and studied for 6 months! Seriously. Now, some of that may seem nuts, but if you really don't know much about data structures, algorithms, binary arithmetic (or are very very rusty on it), I can see how a stretch of studying would be good for you. But once you have, it starts to feel like re-studying for your midterms. Still, for $250k and up, with growth potential... yeah, I can see why people are willing to keep going through the washing machine. Lastly, I suspect you're just a little better at this than I am. I think I'm in range, but it's a little more of a stretch. ------ chimeracoder Looks like they're including RSUs for private companies as equivalent to cash, which _dramatically_ skews the data. For private companies, RSUs aren't liquid, and ISOs actually _cost_ money to exercise, so they arguably have negative value. Treating them as cash- equivalent makes these rankings very misleading. ~~~ oarabbus_ They would be remiss not to include this when making a statement about total compensation. ~~~ chimeracoder > They would be remiss not to include this when making a statement about total > compensation. Ideally they would be separated out. But if you have to make a single ranking, it's way more misleading to include RSUs/options for private companies than would be to ignore them. ------ memn0nis These salaries are incredibly high for someone who never worked at a tech company in the valley. What's the general consensus on whether these salaries will increase, decrease, or stay the same in the medium term (i.e., next 5-10 years)? ~~~ doublement With nothing to back me up except the general impression I have, these numbers look out-of-whack even for the highest-paying employers in the Bay Area. ~~~ senordevnyc I know I'm just a random internet commenter and thus you could be forgiven for thinking I'm making things up, but I just got an offer from a smaller public tech company for a senior / staff level position making almost $400k in first year comp. I'm pretty confident that after negotiation we'll land a little over $400k. And recruiters at several other tech companies where I'm interviewing have told me they can match or exceed this offer. I think FB or Snap would pay more than $600k at this level, but I don't want to work for either of them :) To be fair, I have 12 years of experience, 9 of that in mobile dev, but _all of it is self-employment experience_. Comp is just insane at the top companies. ~~~ pascalxus If you can get 600K at FB or Snap, you must be a top 3% candidate, according to FYI.levels, right? ~~~ senordevnyc I mean, I don't know? To be fair, I have not gotten an offer from either of those companies. Maybe I never could. But I did get an offer from a company that competes with them for talent and it's roughly at the L5 level at Snap and E6 level at FB. Looking at levels.fyi, I'm seeing $550k - 575k, and given that the offer I got was about $50k higher than the data levels.fyi has for the company in question, I don't think hitting $600k is crazy, especially if you have competing offers. ------ hotdogs What's in Pittsburgh driving the median so high? I know Carnegie Mellon is there, but I was not aware of any sort of commercial tech hub. ~~~ Zaheer Zaheer from Levels.fyi here. Argo AI & Duolingo are based out of Pittsburgh. Uber & Google also have a decent sized presence. Some more context on their tech scene here: [https://www.reuters.com/article/us-pittsburgh-tech/a-tech- bo...](https://www.reuters.com/article/us-pittsburgh-tech/a-tech-boom-in- pittsburgh-brings-hope-and-angst-idUSKCN1MM13Y) ~~~ hotdogs Huh, it's been about a decade since I last visited Pittsburgh, I had no idea. Thanks for sharing. ~~~ crw5996 Pretty much all the big tech companies have a presence here. From what I can remember, Microsoft (Azure Storage), Amazon (ML Alexa Teams), Google, Uber (ATG), Argo AI, Aurora, Facebook (Oculus), Duolingo, and Apple are all have offices in the city. In the suburbs I think Netapp and Oracle have offices. ~~~ Zaheer Significant concentration of AI & ML teams probably raises the median (thanks to CMU). Some of the hottest skills in the market today. ------ swat535 As a Canadian Software Engineer with 10+ years of experience.. I think this list is comical.. I've managed to barely squeeze 120k-130k CAD (90-100k USD) out of big companies here (e.g Shopify). I'm not sure if having free medicare is worth losing 2-300k... Oh and I've tried applying for remote positions in the US and I get the good ol compensation skewed based on COL mantra. ------ grammarxcore I feel like this list is skewed by cost of living. The top four cities are also very expensive cities to live in and around. 200k in the bay area is scraping by whereas 100k in the Austin area gets you a house in a reasonable amount of time. Are there any plans to provide adjustments like that? ~~~ throwawaymath Can we please stop with the hyperbole? $200k in the bay area is emphatically _not_ scraping by. You can live on your own, without roommates, save money _and_ have a social life if you have a $200k income in SFBA. What people (especially on HN) think "scraping by" looks like is getting a little nuts. Just because you can't have an opulent lifestyle and a cheap five bedroom house doesn't mean you're struggling. $200k in SFBA is well beyond the point where all your basic needs are met. ~~~ pascalxus it all depends on your situation. Sure, as a single person 200K is doing well. But, 200K with a family of 4 (2 kids and a wife) is definately scraping by on the penninsula or SF. The only way that's not scraping by is if you bought your house over 20 years ago (or during 2010-2012 housing slump) OR you got yourself a Rent controlled apartment. Other than that, You ARE scraping by. In SF, day care is almost 3K per month per child! On the penninsula/SF, if you rent a 3 bedroom apartment, it'll cost 4k-6K or so per month or more, that's 60K of your 130K take home pay. ~~~ txcwpalpha >But, 200K with a family of 4 (2 kids and a wife) is definately scraping by on the penninsula or SF. Lol. No, it isn't. It is absolutely mind blowing what the general tech industry thinks "scraping by" means. The _median_ household income in SF is less than 100k. At 200k, you make more than twice that. If you're just "scraping by" with 200k, then I can't even imagine what people making less than the median are doing. ~~~ geebee Child care in San Francisco, the kind that goes from 8am to 6pm, runs over $2500 a month. That's not ultraluxe, that's pretty standard fare, and my estimate is probably on the low side. A 3br house in an unfashionable but largely safe part of town is probably well over $4000 in rent. Again, that's not a high estimate. If you have 2 kids in daycare and are paying a mortgage or even just renting, you're looking at $9,000 a month in these expenses alone. Wealth in San Francisco is more measured by when you got into the housing market than what you make, salary-wise, unless you're quite a ways up. Now, a two income family with tech jobs is likely going to have at least 300k in family income (though even with the expensive 8am to 6pm day care, expect lots of phone calls coordinating who will scramble over to day care before 6). These families are not "scraping by", and I agree we need to be careful with hyperbole. But the median household income may not reflect the cost structure for new arrivals to the housing market who lack the family structure that would cushion the blow of daycare costs. ~~~ camgunz Being able to afford 8 hours of child care for multiple kids every weekday, and a mortgage/rent on a 3br house, is way above what most Americans consider scraping by. Americans who are scraping by use family, friends, and spouses for child care (or just hope for the best), and they live in low-cost housing often in pretty bad neighborhoods with bad schools that are far away. They also have trouble affording health insurance, they often share a single car (if they even have a car), have debt, and aren't saving. ------ senordevnyc Is this getting flagged? It's currently near the bottom of page 4, and should be in the top 10 of page 1. Are HN'ers just bitter / skeptical of these numbers? ~~~ doublement I don't know why it's falling away from the front page, but as far as skepticism goes, numbers that surprising raise more questions than answers. Your anecdotes have been very informative by the way. ------ umvi Obviously San Francisco and New York City have the highest salaries... they have the highest cost of living. Can we get a list adjusted for cost of living? ~~~ lhorie Depends on who you're living with. When I first moved to SF, living in a dorm downtown w/ shared bathrooms/kitchen among some ~50 people, I was paying $1.8k/mo. Then my wife and kids joined me, and we moved to a "proper" place in outer richmond. The cost for 2 bed + 1 kid in preschool went to 6.5k/mo. If you're single, you're probably looking in the range of 3.6 - 4.5k for a 2 bed rent, or half of that if you can get a roommate. Transit runs you about $80-100/mo. So if you're young and cheap, there's a lot of opportunity to build up a bank. On the other hand, If you are married w/ toddlers and your spouse is on a non- work visa, you're gonna have some tougher luck w/ COL. ------ libso How is the level mapping between various companies decided? ~~~ Zaheer Within a company, levels codify the hierarchy, scope & responsibility of employees. The question we try to answer with our mapping is: "If an employee at company X were to switch to company Y, which level would they come in at?". The answer then is: what is the equivalent scope / responsibility across companies. There's several other factors (company size, interview performance, etc) that go into actual leveling when you switch companies and thus we really emphasize that this is a _rough_ guide. I think we've settled on something that's generally agreeable for most folks. We constantly take feedback though and adjust based on what we hear from users switching between companies. ------ crispyporkbites Is there data on the UK / London available? ~~~ oarabbus_ Honestly if you're a software engineer in the UK and you're concerned about salary... you should move to the United States. ~~~ IneffablePigeon Who isn't concerned about salary? Who is _only_ concerned about salary? Like most software engineers in the UK, I could almost certainly make at least triple by moving to the US but I don't consider it worthwhile for me. Many people do - there's no right answer. ------ Trias11 Can we separate salary from stock-based comps? ~~~ rcpt Why? They're all reported the same as income on your taxes ~~~ electricslpnsld Compensation from stock grants is significantly more volatile than base salary or bonus targets, but otherwise I don’t see a major difference. ------ zer0faith Does this data include Cyber Security type jobs? ------ einpoklum These salaries is kind of obscene. But then, the conduct and social impact (in the US or outside of it) of many of these companies is also kind of obscene: Lyft and Uber employ pseudo-freelancers for very low effective wages; AirBnB are keeping apartments out of the regular rental market in favor of jacked up per-day prices; Facebook tracks everybody and shapes (to some extent) their consciousness and knowledge of the world; and so on.	{ "pile_set_name": "HackerNews" }
Google Tells ITC Judge: Microsoft Revealed Our Secret Source Code - joelhaus http://paidcontent.org/article/419-google-tells-itc-judge-microsoft-revealed-our-secret-source-code/ ====== jdp23 Hmm, it seems to be more about objecting to the specific expert witness they're using: "In April, Microsoft sent Google a subpoena asking for a variety of information, including confidential source code.... In its motion for sanctions, Google says it should have had a chance to review the credentials of the expert in question, Dr. Robert Stevenson, and it should have had a chance to object. The motion notes that Stevenson has done consulting work for Microsoft and Hewlett-Packard (NYSE: HPQ), “both direct competitors of Google.” Now Google wants the ITC judge overseeing the Microsoft v. Motorola case to stop Stevenson from testifying." ~~~ kenjackson The real issue is that Google has the right to review the experts that look at Google confidential code. MS is supposed to disclose these efforts to Google. MS disclosed this expert to Motorola, but not to Google, hence the problem. From what I can tell Google has a good case on this, but it's far less controversial than the title would lead one to believe. MS will probably have to get a new expert and light smack on the hand for not following protocol. These types of things happen all the time in court cases. ------ CurtHagenlocher I believe in situations like this that it's customary to give the code to be evaluated to an outside expert in order to protect both parties from the risk of theft of intellectual property. Is Google's main objection that they would have wanted to approve of the expert witness first? That seems unusual. (Disclaimer 1: IANAL) (Disclaimer 2: I work for Microsoft, but I know nothing about this matter.) ------ tzs Wait...Google objects to the outside expert Microsoft hired to look at the source code because he's worked for Microsoft before on legal cases? Surely Google doesn't expect that every time a company needs an outside expert to look at source code (which they have to hire an outside expert for because they are not allowed to see it themselves) they need to find a new expert? ~~~ wtallis If the outside expert is supposed to be an _outside_ expert, then there needs to be a way for Google to object to the expert on the grounds that they're not really that independent.	{ "pile_set_name": "HackerNews" }
25 Years After Junk Science Conviction, Texas Admits Sonia Cacy's Innocence - finid https://theintercept.com/2016/11/04/25-years-after-junk-science-conviction-texas-finally-admits-sonia-cacys-innocence/ ====== seibelj This is something I find extremely scary, because an unusual series of events (accidental fire, accidental drowning, suicide) could be framed to look like something entirely different (arson, murder), which could drag any one of us into a nightmare. If you don't have the money to hire your own experts and a strong legal team, potentially bankrupting yourself, you are at the mercy of a motivated prosecutor with nearly unlimited resources. In 2009 a scathing report was released by the National Academy of Sciences that essentially says that blood spatter, handwriting, hair, fingerprints, and bite mark analysis are all junk science[0]. If two "experts" can look at the same evidence and come to entirely different conclusions, how is this science? It's opinion wrapped up as scientific fact. Who knows how many people are innocently convicted. It's terrifying. An excerpt from WikiPedia about hair analysis: _The outcry from defense attorneys has forced the FBI to open up on disputed hair analysis matches since 2012. The Justice department began an "unprecedented" review of old cases involving hair analysis in July 2013, examining more than 21,000 cases referred to the FBI Lab's hair unit from 1982 through 1999, and including as many as 27 death penalty convictions in which FBI experts may have exaggerated the reliability of hair analysis in their testimony. The review is still in progress, but in 2015, it released findings on 268 trials examined so far in which hair analysis was used. The review concluded that in 257 of these 268 trials, the analysts gave flawed testimony that overstated the accuracy of the findings in favor of the prosecution. About 1200 cases remain to be examined._[1] [0] [http://www.nytimes.com/2009/02/05/us/05forensics.html?pagewa...](http://www.nytimes.com/2009/02/05/us/05forensics.html?pagewanted=all) [1] [https://en.wikipedia.org/wiki/Hair_analysis#Microscopic_hair...](https://en.wikipedia.org/wiki/Hair_analysis#Microscopic_hair_analysis_in_forensics) ~~~ cstross Something I really _don 't_ understand about the American system (I'm British) is why _anyone_ could possibly think it's a good idea to make Prosecutors and Judges elected offices! The whole "tough on crime" narrative is toxic when it plays into electoral politics because it gives prosecutors an incentive to pick fights they know they can win (targeting vulnerable people with limited resources to hire an effective defense) and it rewards judges for portraying themselves as the vengeful defenders of the wronged by imposing unduly harsh sentences. Seriously? Other countries do just fine with prosecutors and judges who are unelected civil servants, and don't seem to have quite the same track record of excessive victimization of the vulnerable. ~~~ s_q_b In the United States, we do things a tad differently. The Federal government here is not a government of general jurisdiction. It operates on the principle of a social contract which reserves powers not specifically given to the Federal government to individual provinces. While this principle is far degraded these days, election of state officials is still fully reserved to the states. Many states have decided that judges are best chosen through election, and their constituents permit such action through the democratic process. In the Federal system, judges are appointed by the executive. Following the same reasoning as you, Hamilton noted in the Federalist Papers, a series of editorials published anonymously which outlined the reasoning that shaped the constitution, that the executive appointing judges was the best method, because the executive lacks the power of both the "purse and the sword." Only when states act so egriously as to breach the United States Constition, rather than state law, does the Federal government step in. Our most serious problem is that we generally cannot sue law enforcement officers, prosecutors or judges due to sovereign immunity, which provides almost absolute protection from civil suit. I believe we inherited "sovereign immunity" from a rather incorrigible previous government. They believed that some sort of divine mandate somehow exempted their highest government official from the law, a particularly absurd idea which has had rather unfortunate consequences for several billion people. ~~~ raattgift Funny that you should mention the system in what was then Great Britain; the Constitution of the modern U.K. and its antecedents in English law are very much part of a live constitutional crisis in the question of the power of the executive versus the power of the legislature. The ruling below contains in it an extremely fair overview of some of the issues you mischaracterize in your last paragraph. I think it's understandable that you got it wrong; comparative constitutional law is not an especially popular thing, and there are further reasons I'll return to below. Two of the most senior judges (by rank) in the UK and likely the most highly regarded (by the legal profession generally) public law judge, wrote this ruling that was handed down Thursday. The judges are also justices of the Supreme Court of the United Kingdom, which will hear the appeal, although nobody seriously expects that the UKSC will overturn the judgment unless the parties agree to ask the Court for permission to consider some matters listed in the judgment as "common ground" as in dispute. The parties are the national executive (through a head of the new department for exiting the European Union) and a mechanism which allows public interest cases to be brought against the government by concerned citizens and residents; several individuals are effectively the true claimants. I'm going to make references to several numbered paragraphs in the ruling, which you can read in full here. Unfortunately the source-text-with-markups version is not yet online, but that will follow in due course as is general practice. The parties agreed that drafts of the rulings would not be made in advance because of the risk of leaks that might harm either party's interests, and that they would agree to a true copy that would go online first, so that there could be no question about the exact wording of the ruling, because the matter was (and is still) virtually certain to be considered by the Supreme Court in December. [https://www.judiciary.gov.uk/wp- content/uploads/2016/11/judg...](https://www.judiciary.gov.uk/wp- content/uploads/2016/11/judgment-r-miller-v-secretary-of-state-for-exiting- the-eu-20161103.pdf) The judicial review of executive authority is not novel; this judgment refers (at paragraphs 26, 27, and 28) to case law established in the 17th century. Just prior to the American Revolution the "Intolerable Acts" complaints made frequent reference to the English Bill of Rights (1688) and most of the American leadership made it abundantly clear before the Revolution began that the unrest was founded in their desire to protect their rights as Englishmen. What was eroding their rights was not the monarch (again, this was established in the civil wars of the 17th century, and the Glorious Revolution (judgment, para. 26)) but factional politics in the British Parliament. Rival factions were vying for power, and the largest groups coalesced around Frederick North and Charles James Fox. The former was strongly supported in the countryside by rich land owners (with their wealth being generated by tenant farmers) and professionals, merchants, and other cityfolk in the urban centres of the day. As is common even today, the "country" party was highly conservative both socially and economically, while the "city" party was keen on progressive reforms to governance, extension of the franchise, and -- crucially -- equity for Englishmen living outside England. The economic conservatives were trying to preserve the balance of accounts available to the government in the ongoing war with France and its allies and a few other parties (the Seven Years War, which in U.S. history lessons tends to be called the French & Indian War) and were hostile to spending money garrisoning the western frontier of the colonies unless paid for locally, and they were thus intractably opposed by interests in the colonies that favoured expansion Westward into the river valleys that had been won from France, but knew there would be violent opposition by the people already living there who had been France's allies. The Foxite Whigs were very close with many Americans, especially Benjamin Franklin, and were keen on breaking deadlocks in the British parliament on this and other common matters. They essentially propagandized against the Northites' insistence that the elected legislatures in each of the colonies was the appropriate venue for discussing grievances and raising petitions to the North-led government, with Charles James Fox himself proposing a system whereby Englishmen living in the colonies could elect Members of Parliament directly without owning land directly in metropolitan Britain and without being physically present to cast a ballot. The Northites were intractably opposed to this, as the Colonies would almost certainly provide the Fox faction and its allies a clear and possibly even huge majority in the House of Commons. The only way the King was involved at all is that he stupidly -- or perhaps because of the porphyria which clouded his mental faculties from time to time, sometimes seriously enough that he went through periods of being called "mad" \-- was playing favourites in pressing North to choose personal friends to head up government departments. He even more foolishly pressured North to formally recommend the appointment of a handful of his favourite courtiers as (mostly, but not wholly, ceremonial) colonial governors. However, that was essentially a Revolution-enabling error of judgment: Fox and Franklin exchanged letters agreeing that because enough non-Englishmen were living in the colonies, and had moved there to escape actual tyranny by properly absolute monarchists -- especially in the German states -- they should caricature the conflict as between Colonists and the King rather than political factions jostling in the elected House of Commons, and engage them as allies in the escalating political conflict, especially as outright armed rebellion seemed likely. (There was of course a substantial history of armed rebellions just prior to the English Civil War, and riots and other civil disturbances in London in economic downturns as the one caused by the expense of the Seven Years' War and preparing for the likely resumption of hostilities with France, Spain and the Dutch Republic). George III was also the monarch of a German state (Hannover), and that was used to further convince immigrants -- especially German ones -- to support the Revolution. The North government's decision to hire mercenaries from Hesse-Kassel and other German states rather than draw down on reserves of British soldiers -- it was essentially a cost-saving measure, and was quietly opposed by the King because it significantly enriched German princes that were in competition with his family's interests -- played right into that characterization. (cf. Franklin's 1777 work, "The Sale of the Hessians"). So, the "sovereign" was at the time Parliament, and it was too factionalized to protect itself from challenges in the courts, and that somewhat stayed the hand of the North government -- and especially George Germain and the Earl of Sandwich, who were the government officials in charge of dealing with the rebellion in the Thirteen Colonies. However, it did in 1773-1774 make it even more difficult to bring a lawsuit in a court against the government, so to some extent you are right that 'sovereign immunity' was in play, although not especially successfully. Had open warfare not broken out, it is very likely that the North government would still have collapsed (resulting in a series of uneasy coalition governments), that the Court of Appeal would have held that the ex parte cases for relief against the British executive were in fact valid (the British government mostly defaulted, deliberately, on several court actions brought by Americans). Additionally, one of the live constitutional issues -- especially in Massachusetts -- was the primacy and authority of the executive of Britain backed by the British parliament over the legislative assemblies of the colonies. The Northites and their country-conservative allies were already losing ground, with Parliament taking powers from the British executive and delivering them to executive councils and legislative councils i many colonies, starting with the Québec Act (1774). Essentially the American Revolution was triggered by ineptitutes and reactionary decisions taken by a weak proto-Tory government in a very divided Parliament during a brief pause in a world war and in a period where trans- Atlantic trade in raw materials was crucial to their pressing economic needs. (By 1780, the British were again in active warfare, and without allies, against five European powers, with fighting on four continents; they chose to stop fighting in the American Revolution rather than risk losing possessions elsewhere, especially the sugar and rubber plantations they controlled and were fighting to protect from the Spanish and Dutch). It was the failure of a government which barely controlled the elected House of Commons, and yet was unable to bring itself to share power - even temporarily and tactically - with other factions both in England and in the English colonies. ~~~ s_q_b That's a lovely bedtime story for children at Old Exeter, ending with a British strategic withdrawal rather than humiliating defeat, but we prefer to teach actual history on this side of the pond. I think you're very confused about what sovereign immunity actually _is._ Sovereign immunity, also known as crown immunity, is the common law right of the monarch not to be sued, from which judicial and investigative immunity descend. My comment had nothing to do with the American Revolution, except to note that the British imposed this terrible concept across their now-defunct empire. ~~~ raattgift Willion v Berkley(1561) 1 Plowden 223, 75 ER 339 (K.B.), "[it is a] difficult argument to prove that a statute, which restrains men generally from doing wrong, leaves the King at liberty to do wrong" (Brown J), with Dyer CJ concurring. Bracton, De legibus et consuetudinibus Angliae (c. 1235): "Quod Rex non debet esse sub homine, sed sub Deb et Lege". Case of Ecclesiastical Persons (1601) decided in Parliament, "the king is bound by act of Parliament although he not be named in it, not bound by express words; and therefore all statutes which are made to suppress wrong, or to take away fraud, or to prevent the decay of religion, shall bind the King." 1615) 11 Co Rep 66, 72a, 77 ER 1235, Crown immunity from statute is confined to what in modern terms is the Queen's Consent and the Prince's Consent, and that there is no immunity from judicial review except with respect to the monarch personally (i.e., it is a personal protection rather than a corporate one). Pawlett v Attorney-General (1688) Hardres 465; 145 ER 550, while consent of the monarch (sua sponte or under formal ministerial advice) is required for suits claiming money judgments against the monarch personally, equitable remedies against the Crown do not require consent. Pawlett remained the law of England through the American Revolution. Even though there has been statutory reform recently, this is still reflected in English law, and is one of the reasons why the recent headline constitutional case was listed as R. (Miller et al.) v the Secretary of State for Exiting the European Union. Canadian law, incidentally, developed differently in the 19th century, and so it would have been listed as Miller et al. v The Queen of Canada. Indeed the British badly mishandled the fighting in the American colonies, however that doesn't make your claims about the legal system of what was then Great Britain was correct, and your recent argument on that front is not supportable in English law of the time (and Scots constitutional law was not effectively in play during the American Revolution). Neither could whatever developed in the British empire after the Revolution was settled. ------ mabbo > In an exceptional move by the notoriously conservative panel, the BPP agreed > that Cacy should be paroled, just six years after she was convicted. She served 6 years before parole, not 25 years behind bars I'm far more concerned with Cameron Todd Willingham. Governor Perry had this evidence, that much of the state evidence being used was junk science, and did nothing while an innocent man was put to death. Shameful. ~~~ nostromo The amount of junk science we allow in American court rooms is truly alarming. I wish more people knew about the case you're reference. Here's an excellent article: [http://www.newyorker.com/magazine/2009/09/07/trial-by- fire](http://www.newyorker.com/magazine/2009/09/07/trial-by-fire) And here's a good description about how it's quite common for a "fire expert" (which may simply be a normal firefighter) to misclassify an accidental fire as arson, implicating innocent survivors as murderers: [https://californiainnocenceproject.org/issues-we- face/fire-i...](https://californiainnocenceproject.org/issues-we-face/fire- investigation/) ~~~ yuhong I also have been thinking of other examples. Imagine someone sued a vaccine manufacturer claiming that the vaccine cause autism. Imagine also that years later it turns out that vaccines can "cause" autism, but only in case of things like leaky gut. Was the court and legal system designed for cases like this? ~~~ ceejayoz > Was the court and legal system designed for cases like this? Yes. There's even a law that sets up a _specific_ court with special expertise and powers in vaccine cases. [https://en.wikipedia.org/wiki/Vaccine_court](https://en.wikipedia.org/wiki/Vaccine_court) ~~~ gizmo686 The fact that vaccines have their own court specifically specified by law suggests that the legal system is not designed for that type of case, and special provisions needed to be added to handle the more common instances. ~~~ ceejayoz So the legal system's ability to adapt as necessary is thus evidence of the legal system's inability to adapt? OK? ~~~ gizmo686 The legal didn't adapt in this case. The legislative system applied a patchwork fix. Further, the fix is narrowly narrowly tailored to vaccines, meaning that the legal system is still not equiped to deal with the same kind of issue if it does not involve vaccines. ------ rdtsc "Expert" witnesses for US courtrooms is a special kind of a parallel voodoo- science world. Especially when it comes to arson. Prosecutors like to pick the same people to testify as "experts" and their top qualification is that they have testified before as "experts". I imagine many have optimized putting up an act and throwing around fancy terms to make it seems really precise and scientific. Their future employment depends on that. ~~~ tzs In civil cases, where both parties often have a significant budget for hiring experts, the experts often actually are top people from their fields but who are retired. I watched a patent trial, and an important part of one of the claims was that certain data from a hard disk was cached in a RAM cache. The side that wanted to see the patent invalidated brought up some earlier patent that involved caching some data on a hard disk, and claimed it was prior art that should have been considered. Their expert said that "RAM" stands for "random access memory", and a disk is random access and it is memory, so that any programmer or engineer who read the patent that called for using a RAM cache would understand that caching that data on a hard disk would count. That, of course, was one of the most ridiculous things I'd ever heard. However, the expert certainly was a real expert. He was a professor emeritus and former head of the computer science department of a top CS school. In fact, he had been the one who _started_ the CS program there and brought it to its position as a top program. He was a fellow of the IEEE, and his published papers back from when he was an active researcher were some of the seminal papers from the beginning of the modern semiconductor and VLSI era. So how the hell did this guy think that "RAM cache" is commonly understood to include a cache stored on a hard disk? I asked the lawyers for the side that was defending the patent, and their expert (another retired professor emeritus, IEEE fellow, yadda yadda...) about that. They explained to me that experts in a trial like this will get paid $50-100k or more to testify in this kind of trial. They basically have to just spend a few hours reading a patent, and then come up with an argument for the side that is paying them that will sound good to a jury and that is not provably a lie. Then they have to come and spend maybe a week at the trial location, being there to help the lawyers out and to spend maybe an hour on the stand. So basically $100k for a couple of weeks of not too strenuous work, two plane trips, and a week in a hotel. They don't have to worry that colleagues will find out about the dumb things they said at trial and hold it against them or that it might tarnish their legacy or reputation, because everyone in the field knows about these expert witness gigs. When they hear that Professor Soandso said something really stupid about RAM cache at a trial, they just think, "Oh...I guess Professor Soandso wanted a new RV" or "Professor Soandso wanted a new boat". (In the case of the expert for the patent owner, it was to be one of the earliest to own a Tesla). ~~~ SilasX I think you're being too uncharitable to the expert. It sounds like his point was that caching on disk is _conceptually similar_ to caching in RAM, and that therefore, for purposes of prior art, you should probably list inventions that cached in this (similar) way. IOW, an engineer reviewing the literature should have included inventions that cached on disk if they were otherwise similar. Remember, prior art is intended to demonstrate the extent to which your idea is new. It makes a big difference whether the inventor thought of caching _at all_ vs whether they just used an existing caching scheme and swapped out the implementation for a faster one. Posters on HN make a big deal about obvious patents being granted because someone took an existing invention and added "...on a computer/the internet". Well, it's a similar problem when someone takes an existing mechanism and says "... but on a faster storage medium instead". ------ garyclarke27 Similar junk in the UK has put many innocent parents away for "shaking baby syndrome" just based on a theory, not proven by scientific evidence. Expert witnesses who don't agree with the consensus establishment, have even been banned from practicing medicine, thus most now refuse to testify. ~~~ DanBC You might want to read the papers those banned doctors refer to, because the doctors often mangle the science. Here's one case of a doctor who had been struck off by the GMC. The judge overturned that decision, but has maintained the ban on her acting as an expert witness because she mangles the science so badly. [https://www.judiciary.gov.uk/wp- content/uploads/2016/11/squi...](https://www.judiciary.gov.uk/wp- content/uploads/2016/11/squier-v-gmc-protected-approved- judgment-20160311-2.pdf) ------ geff82 The nightmare is also that in some countries, when the police knocks on the door to arrest you, you might get killed in a gruel archaic ritual called "execution" at the end, even if you did nothing wrong, just the odds were against you. Here in Germany I do not have to fear the police. If if the judges wrongly sent me to jail "for life", at least I'd have some hope that one day I can convince them they were wrong and get to freedom again. ~~~ zeveb > If if the judges wrongly sent me to jail "for life", at least I'd have some > hope that one day I can convince them they were wrong and get to freedom > again. Is your German government any more able to restore your lost decades than my government is able to restore lost life? For some crimes execution is unjust; for others it is just. It is just as unjust to allow someone who deserves death to live as it is unjust to execute someone who deserves life. ~~~ bzbarsky > It is just as unjust to allow someone who deserves death to live as it is > unjust to execute someone who deserves life It's long been a general principle of criminal law, at least in the US, that convicting someone who is innocent is in fact more unjust than acquitting someone who is guilty. The sentiment has been expressed by Voltaire, Blackstone, Ben Franklin, and a good number of others, going back to at least the 18th century. This is why (again in the US) conviction requires proof "beyond a reasonable doubt". ------ rmchugh The other case mentioned, the Willingham case is even more horrifying. A man was convicted of murdering his children and sentenced to death on bogus evidence. When presented with evidence to the contrary, the state of Texas under Rick Perry ignored it and allowed the man to be executed. This is state sanctioned murder of an innocent man. Why is the Governor not on trial for this? ------ draw_down We need a pretext for what we want to do, which in America is to lock people up. If we can fool ourselves with something that sorta looks and smells like science, that fits the bill perfectly. ~~~ aero142 I don't think it's fair to say we "want to lock people up". We need to believe that we can make ourselves safe from criminals. We need to believe can do some science magic and tell the difference between the criminals and the regular people so we can sleep at night. Admitting we can't calls in to question the whole premise of locking the bad people up. A judge or politician can't come out and say, "we have no reliable way of deciding guilt or innocence." That is reality but we can't allow ourselves to admit it. ~~~ draw_down All I have to say is, look at our prison population vs any other country's. ------ metafunctor Is junk science in court rooms a root cause or just a symptom? ~~~ notgood I always despite this question so much; mainly because everything is a cause of something and a symptom of something at the same time; there is nothing isolated in this world. So you have to give a lot of context to see if -in that context- it is a cause or an effect. I'm this particular case you could say stupidity is the root cause, but saying so it's too abstract to be usefu/actionable. ------ Tloewald This reminds me of a New Yorker article on the same topic (covering an even greater injustice, also in Texas -- in fact referred to in this article) [http://www.newyorker.com/magazine/2009/09/07/trial-by- fire](http://www.newyorker.com/magazine/2009/09/07/trial-by-fire) ------ johnhattan Got a friend currently doing time in Texas for basically the same thing. Here's hoping this gets the case some notoriety. [http://thearsonproject.org/case-studies/curtis- severns/](http://thearsonproject.org/case-studies/curtis-severns/) ~~~ Hondor Wow. 27 years for burning down your business and claiming insurance, even when it doesn't kill or seriously injure anyone, and the value is only ~$200,000. Guilty or innocent, that's a completely obscene sentence! How can anyone in Texas safely make an insurance claim for fire when the risk of misunderstanding is so great? In this particular case, it all seems to hinge on people's opinions of whether a flying can could have jumped over some barrier or shot a plume of flame in some direction and other subtle details about the scene that can't possibly be known without actually reconstructing or simulating the whole thing. ------ finid Somethings the main qualification of some so-called experts is a certification from a 6-hour or 6-week class. From then on, they are eligible to testify as an _expert_ in serious criminal cases. ------ edblarney Question is: what is considered 'junk science' at the time it was used in court? Because I'm sure we are using some 'junk science' we just don't understand at the present time. ------ lanius Gerald Hurst and Chris Connealy are true heroes. ------ gourou Making a Murderer season 2 ~~~ mason240 Except this person appears to be innocent. ~~~ hueving Uh, the whole point of making a murderer was to show that he could potentially have been innocent as well. ------ yuhong Anti-discrimination laws are even worse in that discrimination can happen with no evidence at all. One of the methods used to enforce them (particularly in things like hiring) is statistics, most of which assumes employees are interchangeable commodities. They were designed back in the 1960s for things like manual labor jobs. I am willing to suggest a compromise to limit them to these kinds of jobs. ~~~ charonn0 I think you meant to reply to a different post.	{ "pile_set_name": "HackerNews" }
Gatwick Airport: Drones ground flights - happy-go-lucky https://www.bbc.com/news/uk-england-sussex-46623754 ====== adamiscool8 I genuinely don't understand how it can be a 24+ hour operation just to take out a drone. Don't jets regularly get scrambled in response to less disruptive intrusions? Doesn't the battery die at some point? Can't they follow it to where it lands and take it out of commission? Couldn't someone have woven a giant net by now? ~~~ matthewmacleod As I understand it, the drone(s) have been vanishing then reappearing at various points throughout the day. While it seems quite easy to deal with the issue at first glance, I can see why this would be difficult to deal with. A drone strike at takeoff could be pretty catastrophic, so there is rightly an attitude of erring on the side of safety; flights are unlikely to resume until the authorities are fairly certain the drone is gone. But they are pretty small, so it doesn’t seem like it would be terribly easy to track them. The operator may be using multiple drones, and could potentially be quite far away from Gatwick - I’m no drone expert, but I understand 6-7km range with a 30min flight time is feasible. That’s quite a wide area to search. Honestly I’m surprised that we haven’t seen this happen before now; it seems like such an easy attack. I would guess that we might even see a rash of copycat attacks. ~~~ adamiscool8 I totally understand why they'd have to err towards caution on the initial appearance, but the drones aren't teleporting away when they vanish. The combined power of the authorities can't follow a drone for 30 minutes and capture it? Something just seems off. ~~~ alasdair_ A few autonomous gps-guided drones are all that is needed. No one would need to come back to get them. $200 could shut down an airport for hours ------ jnellis Someone posted a topdown photo of Gatwick from about 3000ft on reddit this morning. I was wondering how they got that picture. [https://www.reddit.com/r/CasualUK/comments/a7za4i/this_photo...](https://www.reddit.com/r/CasualUK/comments/a7za4i/this_photo_i_took_of_gatwick_this_morning/) ~~~ Gaelan I think that's a stock photo (jokingly implying that they were responsible) ~~~ solarkraft I see now. My first thought was that they're responsible, but from the text the photo appears to be a PR photo and the post tounge-in-cheek. ------ sgroppino Affecting 100K passengers... how come this is not top 10 in HN? ~~~ gandalfian It's the main national news in the UK. Whether it is developing into mass hysteria or an agitant is really using industrial sized drones to cause chaos is impossible to know. As one of the main hubs in and out of europe a lot of people are getting very worried for holiday gatherings. ~~~ jackpeterfletch By the end of friday 250,000 people will have been displaced. I dont know how you really deal with that! ------ opwieurposiu Half the time these "Drones" are just birds or plastic bags. [https://arstechnica.com/information- technology/2016/04/drone...](https://arstechnica.com/information- technology/2016/04/drone-that-hit-british-airways-jet-was-likely-a-plastic- bag/) ------ pjc50 Conspiracy theory: a lot of people have pointed out that no pictures of the alleged drone are circulating. This comes at the end of a week in which the government is moving towards no- deal Brexit. Is this some kind of test of the emergency response? ~~~ pbhjpbhj Unlikely. My "conspiracy" theory would be that there's been an active terror threat, that they're handling but don't want to go pubic with. The UK government must have anti-drone measures, surely? It also seems possible that opposing forces could organise this to flush out details of drone responses, you can't exactly hide your countermeasures when they're in the open at Gatwick. ------ codeduck I wonder how long it will be before airports need to run point-defence lasers to interdict things like this. ~~~ solarkraft Automated interceptor-drones must be a thing by now. I know for certain there's a german company specializing in drone-defense, but I think their competency lies mostly with detection/jamming. ~~~ pbhjpbhj They're going to have a full order book!	{ "pile_set_name": "HackerNews" }
Show HN: First ever MQTT and XMPP dual-protocol server - f055 https://blog.process-one.net/first-ever-mqtt-and-xmpp-dual-protocol-server-ejabberd-business-edition/ ====== MattJ100 There has been an MQTT module for Prosody for ~5 years: [https://modules.prosody.im/mod_pubsub_mqtt.html](https://modules.prosody.im/mod_pubsub_mqtt.html) I'm not aware of anyone using it in production, or asking to - so it's not received a lot of attention. For my own projects I've tended to prefer bridging to XMPP in other ways, but it was fun to work on. I found a number of things surprising in MQTT, for example the lack of errors in response to commands (such as publishing), with the only solution to be just closing the connection entirely. ~~~ f055 Didn't know about the Prosody module. However, MQTT in ejabberd is at the core level, not module, so it is able to access all the performance and scalability features used by XMPP - and in that sense, ejabberd MQTT is production-ready. I think the surprising behaviours of MQTT are its strength - it's minimal and perfect for low-energy devices. For heavy lifting, there's XMPP. ~~~ MattJ100 Not sure what you mean by "at the core level", exactly. Prosody is quite modular, and everything is implemented as a module with access to the same APIs. Modules do not have performance limitations. I know ejabberd's architecture less well though. Our internal XMPP pubsub (XEP-0060) support has a native code API designed for use by internal modules, so there is no need to marshal everything from MQTT into the appropriate XMPP stanzas for example, it's a direct mapping from MQTT to our internal API. ~~~ mickael When you talk about MQTT and IoT, scalability and clustering is the deciding factor. When you deploy an IoT stack, it is common to have to manage hundreds of thousands or millions of devices. The stack is leveraging ejabberd clustering and scalability. ------ kolargol Is this the holy grail of IoT infrastructure or is everyone just using WebRTC nowadays? ------ mickael I’m the CEO of ProcessOne and lead on ejabberd, ask me anything :) ------ f055 Also, at mqtt.fluux.io you can test one of the few first public brokers that supports MQTT 5.0 spec - there are instructions using Mosquitto in the announcement.	{ "pile_set_name": "HackerNews" }
Deleting the /r/golang subreddit - siddhant https://groups.google.com/forum/#!msg/golang-nuts/XoOhzUClDPs/jgSWxng7CAAJ ====== 4ad Dupe (no comments): [https://news.ycombinator.com/item?id=13035027](https://news.ycombinator.com/item?id=13035027) Let's see which thread survives.	{ "pile_set_name": "HackerNews" }
Did Churchill Cause the Bengal Famine? - curtis https://winstonchurchill.hillsdale.edu/did-churchill-cause-the-bengal-famine/ ====== basicplus2 TLDR: No The truth—documented by Sir Martin Gilbert and Hillsdale College—is that Churchill did everything he could in the midst of world war to save the Bengalis; and that without him the famine would have been worse.4 4 Martin Gilbert, ed., Winston S. Churchill: The Churchill Documents (Hillsdale, Michigan: Hillsdale College Press, 2006 and ongoing).	{ "pile_set_name": "HackerNews" }
Does packed struct hurt performance on x86_64? - arunc https://attractivechaos.wordpress.com/2013/05/02/does-packed-struct-hurt-performance-on-x86_64/ ====== acqq Argh, one more "works on my computer" article. The answer is dependent on the processor. Intel Cores that are recent enough don't take perrformance hit for unaligned access. But when you compile the code you compile it for every user not for those with the same computers like you.	{ "pile_set_name": "HackerNews" }
We’ve long blamed carbs for making us fat. What if that's wrong? - roarktoohey https://www.vox.com/2016/7/6/12105660/do-low-carb-diets-work ====== geezerjay Taken from the article: > But before we throw out the low-carb approach to weight loss and load up on > a bowl of linguini, let’s be clear: This study had some important > limitations, leading some researchers to react more cautiously. It lacked a > control for comparison, and while the baseline diet was designed to keep > participants at about the same levels of energy burn they experienced > outside of the study, the participants started to lose weight on that diet > too. So they were already slimming down by the time they started their low- > carb month. Essentially the study took obese participants and placed them in a controlled environment, forcing a change in their real baseline diet, and decided to define the newly enforced diet as the baseline. Yet, apparently researchers failed to account for the fact that enforcing the baseline diet was already leading the subjects to lose weight, and thus decided to register the initial weight loss as the baseline. So, in the end they compared the weight loss caused by the low carb diet with what researchers decided to consider the baseline result (the transition period to the new diet which was already causing weight loss in subjects). Then, as the weight loss observed during the low carb diet hadn't accelerated that much when compared with the weight loss observed during the diet transition period, they somehow concluded that low carb diet isn't that effective.	{ "pile_set_name": "HackerNews" }
Oracle exec: Open-source vendors locking down licences proves 'they were never - pplonski86 https://www.theregister.co.uk/2019/01/17/oracle_exec_opensource_vendors_locking_down_licenses_proves_they_were_never_really_open/ ====== planck01 Oracle is not the bad guy because of being closed source. Oracle is the bad guy because they will stop at nothing to screw their customers over and extort the hell out of them. I've experience with them taking out functionality we were using out of their enterprise edition (replication) and then trying to sell it in a separate product for millions. And then their start offer is 10 times the eventual agreed figure because of us being 'loyal customers' , which means they first try to get a 90% to 95% margin at least. I have experienced them buying software company of a software product we were using and then greatly increasing the prices while they are unable to support the product, because they laid of all the original engineers. Also no upgrades ever anymore. Even though they have some good products (well: the database and their gis capabilities), much of what they touch turns into shit. Also given their extortion methods, I nowadays try to avoid them as the plague. That's why they are the bad guys. Never mind their licenses. ~~~ tabtab Yip, I've heard many complaints about them. They seem more concerned about tricking customers into coughing up cash than establishing a longer-term relationship. Why would you buy more from somebody who keeps screwing you? It's best to have at least two DB vendors in your shop, and remind them of this when they get difficult.	{ "pile_set_name": "HackerNews" }
New Google Chrome Builds Show Greasemonkey Support - qhoxie http://mashable.com/2008/10/19/google-chrome-greasemonkey/ ====== andreyf I'm hoping Chrome innovates on script-sharing... if it were easier to see/edit/share scripts for a page you're visiting, Greasemonkey would become an entirely different product. Also, if GM scripts could expose API's to each other. ~~~ shawndrost I think the most interesting choice would be automatic usage of some scripts, subject to certain criteria (popularity, manual review, etc). It's a problematic idea, but it would have really interesting effects if it were widely used. ------ sidsavara Cool. Firefox add-ons in general is the reason why I temporarily used Chrome but went back. The fancy each tab is its own process is cool, but I love Greasemonkey, Delicious, Firebug,Adblock,Flashblock,Noscript... Basically, by blocking all the offensive scripts to begin with, my browser doesn't crash as often as it probably ought to ;). ~~~ sant0sk1 With how pervasive JavaScript has become on the web, I find an add-on like NoScript to be onerous. You basically have to allow every web site you visit before it will appear correctly. FireBug was what was keeping me in FireFox until I started running Webkit nightly builds and saw how great the Inspect tool is. ------ jamongkad I hope they make a version for Linux! I would very much like to run it. FireFox's one giant process is getting on my nerves.	{ "pile_set_name": "HackerNews" }
The Future of HHVM - mwpmaybe http://hhvm.com/blog/2017/09/18/the-future-of-hhvm.html ====== TazeTSchnitzel Given HHVM is already being dropped from PHP packages because of its lagging compatibility, announcing that they're not targeting PHP compatibility any more might be the nail in the coffin for HHVM (and thus Hack) as a viable “upgrade” from PHP for _existing_ codebases. I mean, it's great that Hack will work for new Hack code and existing Hack codebases, but there aren't a lot of those. It makes sense for Facebook — why waste your efforts on maintaining part of your runtime that you don't need? — but I wonder if this will consign HHVM to irrelevance in the long term. Maybe Hack is a compelling platform for new code, but then, why use this obscure proprietary Facebook thing that's a bit better than PHP when you could use any of the numerous other languages out there that are also better than PHP but have much better ecosystems? Personally this makes me sad because I wanted to see a standardised, multiple- implementation PHP language. Facebook did, even. They paid someone to write a spec: [https://github.com/php/php-langspec](https://github.com/php/php- langspec) Maybe someone will write a new PHP implementation to take that idea forward. Or maybe we'll be stuck with Zend forever. The future is strange. ~~~ muglug It makes me sad that, as a Mac-based developer, installing & updating HHVM takes half an hour (via Homebrew). I imagine that has taken the wind out of many people's sails, when contemplating migrating/updating codebases to HHVM's (superior) syntax. ~~~ fredemmott Sorry, I know this is a pain; I'm hoping to fix it by the end of the year (along with bringing back nightly debs, and supporting more recent versions of debian/ubuntu). For homebrew build times, there's [https://github.com/hhvm/homebrew- hhvm/issues/5](https://github.com/hhvm/homebrew-hhvm/issues/5) In the short term, docker works rather nicely. ------ muglug HHVM & Hack solved two big problems that made PHP difficult for Facebook and other large companies with large existing PHP codebases: Speed, and the lack of type checking Now the PHP ecosystem is more mature – PHP 7 eliminated the speed differences between HHVM and PHP, and a bunch of static analysis tools find 95% of the bugs that HHVM's typechecker finds. It makes sense that this would be an inflection point for the future of HHVM. I hope that more features from HHVM make it into PHP core – especially property types and generics – because, whatever FB decides to do with HHVM, PHP is here for the long-haul. ~~~ jimktrains2 > HHVM & Hack solved two big problems that made PHP difficult for Facebook and > other large companies with large existing PHP codebases: Speed, and the lack > of type checking At what point do you stop using the hammer to put in a screw and just use a screwdriver? ~~~ muglug When the cost of buying screwdrivers for your entire workforce would likely bankrupt the company. ~~~ jimktrains2 I'm not sure what you're analogy is here. You wouldn't switch every nail to a screw in the same moment. ~~~ muglug Right, but you're still investing time in doing that switch. No matter which way you cut it, you're still replacing every single nail. "We'll just update as we go", you say. That's fine, but it means that some parts of the house – normally the oldest and most integral to the entire structure - will use nails for years to come. And your developers will need to be trained in both hammers and screwdrivers to be able to work on the house in totality. ~~~ jimktrains2 Sure, but if those nails are also causing structural instability, then it might be prudent to do the investment. It seems now, no one will be using your type of nail anymore either, so now you have to have them custom made at expense. ~~~ cwyers Sometimes those nails are doing just the opposite, they're holding the foundation together, and if you try and pull them all out the whole thing might collapse. ~~~ VeejayRampay This is why I use Krazy Glue for everything, so I don't have to think about what's the nail, the screw and the hammer in this long-winded analogy about PHP and its shortcomings. ------ rrdharan This is fascinating. It's a well-written post and their plan makes sense to me, but I imagine there's a tough choice ahead for framework authors (the Laravels and Drupals of the world) about whether they want to fork their communities, stay with PHP7, or try to target both with the same codebase (in the near term or long term)? At any rate at least the fact that the HHVM folks are communicating the strategy effectively and transparently should help everyone involved make reasonable decisions. ~~~ HugoDaniel That and PATENTS: [https://github.com/facebook/hhvm/blob/master/hphp/hack/PATEN...](https://github.com/facebook/hhvm/blob/master/hphp/hack/PATENTS) ~~~ zimbatm If Facebook had released the code under BSD then nobody would have complained. But this basically gives a BSD plus patent grant, and reverts to BSD if there are any patent litigations. And now people are complaining. ~~~ s73ver_ Because it is them saying, "We can take all of your patents, but if you sue us for it, then you don't get to use this." ~~~ jbergens IANAL. I think that is a common misunderstanding of the clause. If you sue them for react patents you can still use HHVM, or vice versa. [https://medium.com/@dwalsh.sdlr/react-facebook-and-the- revok...](https://medium.com/@dwalsh.sdlr/react-facebook-and-the-revokable- patent-license-why-its-a-paper-25c40c50b562) ------ bepotts How is Hack? Has anyone built anything with it and would like to share their thoughts? How's the HHVM community? I've always thought that PHP was an underrated language that got a bad rep due to whacky design choices and PHP developers being seen as "less skilled" (a stereotype I know, but it is prominent) than others. Object Oriented PHP and frameworks like Laravel were a nice change of pace in my opinion, and there's plenty of good PHP coders out there if they had the right experience and stuck to a good coding guideline. Alas, I confess I stepped away from PHP due the stereotypes against it, but HHVM always seemed promising. I haven't heard much about it over the years though. What's the toolchain for HHVM? ~~~ kmavm I'm chief architect at Slack, and we migrated to Hack from PHP 5 throughout 2016. The toolchain for HHVM is all installed as a single big deliverable, which gives you the language engine and supporting runtime libraries itself, an in- address-space web server (Facebook's Proxygen), a debugger in the form of hhvm -a, and the Hacklang toolchain accessed via hh_client and appropriate editor/IDE integrations. I share your intuition that there is actually a glittering core of "stuff- that-makes-you-successful" hiding in the incidental complexity of PHP, and we wrote this blog post trying to put some substance behind that intuition: [https://slack.engineering/taking-php-seriously- cf7a60065329](https://slack.engineering/taking-php-seriously-cf7a60065329) ~~~ sneak Wouldn't it make more sense to take the parts of the PHP runtime environment that enable rapid prototyping and figure out how to implement them in a language that has a working == operator rather than trying to graft type safety on a language that has both strpos() and str_rot13()? Remember BML, bradfitz' attempt to do this with Perl? I would love to see someone do something similar for Python. ~~~ Can_Not > a language that has a working == operator == has always been working in PHP. I know maybe that optional type coercition trips up some noobs occasionally before they made any effort to learn the language (hint === doesn't coerce types for equality), but how low effort does a complaint have to be? Type coercition is actually pretty cool when you're not really sure what the browser or client is about to http at you and you just want it to work. It's much better than crashing at runtime because '12' isn't a number. If you're input isn't sane, throw an exception or use a validation library. Now if we're talking about a good type system that can be enforced at compile time like rust, Scala, etc. Sign me up. But if it's run time, it's run time, we gotta keep going. ~~~ sneak > It's much better than crashing at runtime because '12' isn't a number. something something yell at you for breaking their door ------ ryangordon Here's the interesting thing about all this; HHVM will always be developed because it's important to Facebook's bottom line and Open Source because it only benefits them to keep it out there and have other people testing it and improving on it. Now that they're getting rid of direct PHP support, HHVM is only going to get better. This will unlock a whole host of language improvements that HHVM couldn't otherwise make. HHVM is faster relative to PHP now, and it will only get faster with these changes. Typing is an important part of making JITed code fast and unless PHP ever decides to fully add it, it will never have the potential to catch up. This is important to PHP-based companies as they grow and want to optimize on cost and development efficiency. Undoubtedly, this split will be painful initially for those of us who are bought into the symbiosis of the HHVM and PHP ecosystem together. How painful it is to split will just be a question of where members of the PHP community want to go (or both). The nice thing is that converting something from PHP to HHVM isn't terribly hard; not anywhere near like converting from PHP to Golang. For HHVM, it's mostly just adding type annotations. ~~~ nkozyra > HHVM is faster relative to PHP now While this is probably still true[1], it's certainly less of a concern now than it was with 5.x. Would (often negligible) performance boosts be enough for someone with a 5.x PHP codebase to choose Hack over PHP 7.x? I can't see that for most cases. [https://kinsta.com/blog/the-definitive-php-7-final- version-h...](https://kinsta.com/blog/the-definitive-php-7-final-version-hhvm- benchmark/) ------ sunseb I'm excited! :) PHP is IMHO the most productive and easiest platform for web development: \- a request \- a response \- templating \- no shared stated And that's it! But the language syntax has so many quirks. So it's cool if Hack redesign the language and make it more beautiful and consistent. Many developers switch to Ruby or Python because these languages are better designed. I think Hack could attract a lot of these developers who want more beauty in the tools they use. ~~~ dna_polymerase Oh boy they really got you! Have a look at Python & Flask! There is nothing easier than that! ~~~ geofft Flask is really good (and my preferred web framework, and full disclosure, I have forgotten how to write PHP), but it fails very badly at "no shared state," and depending on what GP meant by "a request" / "a response", it fails at that too. A Flask process handles an indefinite number of requests and responses; the built-in server handles them serially, and doing otherwise brings in either threads (and shared state) or multiple processes. The Slack article posted elsewhere in these comments [https://slack.engineering/taking-php-seriously- cf7a60065329](https://slack.engineering/taking-php-seriously-cf7a60065329) has some excellent arguments about why PHP's approach is different in interesting ways. ------ ankyth27 Parse, react and now this. Why would I now learn any new Facebook tech? ~~~ cdelsolar what happened with React? ~~~ hibbelig BSD+Patents license. ------ maxpert I am way less sad about HHVM now (specially after React license debacle). I think Facebook now has opportunity to think about this fork as a fresh take on PHP and maybe make the language awesome both from syntax/performance perspective. I don't think living with a weird hybrid with current language landscape is an option. ------ philippz Sad. Facebooks involvement by utilizing PHP and pushing the language by extending it was a good sign for the PHP community. Would have loved to see that they align with PHP7 or even further, push their engineers into improving PHP itself. PHP has such a huge ecosystem. I wouldn't risk to bet on Hacks future. ~~~ COil Agree, that's a pity. Instead of having one top language, we will have 2 "now- incompatible-great-languages". ------ pbiggar > Eliminating references. PHP references have unusual semantics, where the > function specifies the binding of parameters with no indication at the > callsite. I feel like I called this one in [https://circleci.com/blog/critiquing- facebooks-new-php-spec](https://circleci.com/blog/critiquing-facebooks-new- php-spec): > This is interesting because they’re changing the definition of the language > through a sort of back-channel. They’re allowing breaking changes by > effectively deciding that other implementation choices are equally valid. > I’ll give you an example, which I’ll get into more below. There’s a little > known bug in the Zend engine around copying arrays that contain references. > IBM wrote a paper about this bug in 2009. Basically, this bug was necessary > in Zend to make copying arrays fast, and IBM figured out a way to do it in a > way that was actually correct, for only a 10% performance penalty. ~~~ smsm42 I get why they want to get rid of references. If I would be designing PHP from scratch, that's probably the first thing I'd do - most hard to fix bugs in the engine and most security woes of features such as unserialize() stem from references. Unfortunately, _TONS_ of code uses them, and there are some data structure things that would not work without it unless alternative solution is provided. So it could not happen in PHP. But it'd be interesting to see how it works for Hack. ~~~ fredemmott we're currently leaning towards out/inout parameters, with copy semantics, not byref (and in most cases, we'll probably be able to optimize away the copy); not certain yet though. ~~~ smsm42 Would be nice to hear what comes out of it and how it works! ------ dcgudeman I wonder what this means for wikipedia? Will they be migrating to a hack only stack now? ~~~ zeitg3ist MediaWiki runs on more than 25k websites [1] other than Wikipedia, so I don't see them switching to Hack only. Also, I run a pretty big MediaWiki site and the last time I tried moving everything to HHVM (~6 months ago, I think) stuff appeared to be working initially but randomly broke from time to time (probably because of Scribunto or some other extension; couldn't manage to pinpoint the exact reason). PHP 7 didn't give me any problem at all; it's fast enough (way faster than PHP 5) and most pages are served by the Redis cache anyway. I suspect that Wikipedia will consider a move back to PHP, they're moving the most expensive logic to Lua modules anyway... [1] [https://wikiapiary.com/wiki/Main_Page](https://wikiapiary.com/wiki/Main_Page) ------ foxfired I think HHVM was equivalent to what jQuery was to JavaScript. jQuery forced JavaScript to be better, and the better JavaScript becomes, the less jQuery is needed. So if we get to a point where HHVM is completely irrelevant, it simply means "Mission Accomplished". ~~~ VeejayRampay In terms of language, jQuery didn't innovate in anything though. It was a great framework mind you, but there's nothing special about it that influenced the choices in design for the more recent versions of JS. ~~~ Kiro Not even querySelector? ~~~ VeejayRampay I think querySelector and querySelectorAll are simply more generic versions of the traditional approach of using getElementById and getElementsByTagName, but it's possible that the greater versatility of $ influenced the later design of querySelector, indeed. Then again, it was not a jab at jQuery, which proved to be a fantastic tool for a decade in the field of web development. ------ the_duke Has Hack actually gotten meaningful adoption outside of Facebook? I never hear about anyone using it... ~~~ muglug Slack does, and some (all?) of MediaWiki. Outside of that, I don't think it's enjoyed the sort of penetration of other OS projects from FB ~~~ smsm42 MediaWiki doesn't use Hack. Wikimedia Foundation servers (which run Wikipedias and other sites) do use HHVM, but the code is 100% PHP-compatible and still runs fine on standard PHP. ~~~ appleflaxen this is a really helpful distinction that isn't made on the other comments that address HHVM and MW; thank you! ------ krapp Well, this is disappointing. I really like Hack and I was hoping it would take off, but judging from this thread it seems unlikely the language is going anywhere worth following. I guess it's lucky that I only have one project written in it...that I now have to convert back to PHP. I'm really going to miss XHP. Native XML support has ruined me for templating frameworks. I never want to write HTML as concatenated strings ever again. ~~~ fredemmott For completeness: Sara Golemon started porting Facebook's old PHP5 implementation of XHP to PHP7 - you can find it here: [https://github.com/phplang/xhp](https://github.com/phplang/xhp) \+ [https://github.com/phplang/xhp-lib](https://github.com/phplang/xhp-lib) ------ tiffanyh This is pure syntax sugar but will Hack now clean up the PHP inconsistency with function naming and return values? E.g. FunctionName() vs function_name(). Or E.g. return 5x20; vs return "5"x10; ~~~ fredemmott Function naming: We're moving towards functions_like_this(), instanceAndStaticMethodsLikeThis(), and async functions like foo_async() and methods like fooAsync(). We're unlikely to change the PHP builtins, but we're fairly likely to build replacements - for example, Hack Arrays are best used with [https://github.com/hhvm/hsl](https://github.com/hhvm/hsl) instead of the PHP array functions, and this also provides replacements for common string operations that are consistent and fit well with the Hack type system (e.g. nullable or throw an exception instead of falseable). For return values, I'm not sure exactly what you mean - could you give a full example? If I take your example verbatim, it's a syntax error in both Hack and PHP - if I go for "5"*10, it's a Hack error ([https://gist.github.com/fredemmott/90c5f8eca17d1d4e1204f0085...](https://gist.github.com/fredemmott/90c5f8eca17d1d4e1204f0085cc120f5)) ~~~ tiffanyh From the blog post: HHVM will not aim to target PHP7 If you don't plan to support PHP5 anymore and HHVM is not targeted at PHP7 ... then my ask is to just make a better language and drop ALL of PHP baggage. When you say: We're unlikely to change the PHP builtins That concerns me. Because why even break support from PHP7 if you don't plan to change (fix) the builtins? ~~~ mxawng As fredemmott said above, we're hoping to build replacements for the various PHP builtins that we want to be a core part of Hack. I think that replacing the functionality provided by PHP builtins will be a less confusing transition experience than retrofitting them with modified behaviors would. Once we do have a compelling and comprehensive Hack Standard Library, I wouldn't be surprised if we dropped PHP builtins in favor of that. ------ thatonechad I tried out Hacklang a bit and I really enjoyed it. However I could not get xdebug or any type of debugging to work with it. Also the lack of an editor on the calibre of PHPStorm (atom is not great at all) made me give up. I am just hoping for PHP7 to move in the right direction. ------ crescentfresh First I'm hearing of Hack! Didn't realize HHVM had under it's wing _two_ languages. ------ ecesena What are the best framework for web dev on top of hack/hhvm? Last time I used PHP I was using yii (yes-it-is). Wondering what framework can someone use today if she has to start from scratch on hack. ~~~ fredemmott [https://github.com/hhvm/hack-router/](https://github.com/hhvm/hack-router/) and [https://github.com/hhvm/hack-router- codegen/](https://github.com/hhvm/hack-router-codegen/) power docs.hhvm.com and some of our other users; they do have problems such as extremely lacking documentation, which I'm going to be addressing soon. This is definitely an area we're planning on working on - and this post is meant to be announcing the start of this work, not that it's ready :) ------ royge If HHVM(Hack) will drop all the inconsistencies and weirdness of PHP in their implementation the better since it's no longer be compatible with PHP anyway. ~~~ rurban That's the plan. Break the old nonsense, like the one they mentioned: refs and refcount. Everybody should switch to Hack, it's a much better and safer language. ------ fiatjaf [removed language flame war] ~~~ grzm There are plenty of places where you can view arguments for and against PHP alone and in comparison to Python and Ruby on the internet. This submission is specifically about HHVM. Asking people to justify the use of PHP in such a context is just inviting a language flame war. Please don't. ------ ohdrat Guess I'll mosey on back to OCaml then... ------ merb I wonder why they just don't deprecate HHVM altogether and maybe create a HACK version on top of GraalVM. This would probably be way more performant and probably might be better for integration into other systems. ------ memracom I think that these changes mean the death knell for PHP in any version, for small companies. There is still a place for Hack or PHP7 in very large operations, but startups, and businesses that run at smaller scale, really should walk away from PHP entirely as soon as possible. Two reasonable directions to choose are Python Three with a framework like Flask (lighweight) or Django (heavy duty). Or go to the JVM with something like Grails framework (heavy duty) on the Groovy language. Ratpack is a lightweight framework for Groovy and there is also an interesting option to use Vaadin 8 which lets you put your GUI code into the main app rather than writing separate Javascript code. When making your decision, be sure to consider the huge JVM ecosystem that integrates quite easily with Groovy including development tools like Jenkins and SOAPUI that can be scripted with Groovy. And the Python side also has a fairly extensive ecosystem of libraries as well. The skill level of Python and Java/Groovy developers tends to be higher than PHP which has always attracted people who would learn just enought to get by. The software dev community has gone through an explosion of diversity in the past 2 decades and that has enabled a lot of experimentation with new ways of doing this. There is a lot of good in this. But now we are in a period of contraction. Some of this is manifested in the spread of functional capabilities via libraries such as reactive extensions and functional features being added to languages like Java and Javascript. Another manifestation is the fading of PERL from prominence, and this is now happening to PHP as well as Ruby. This is evolution. Embrace it or face your personal extinction as a software developer. ~~~ muglug > This is evolution. Embrace it or face your personal extinction as a software > developer. Woah there Mr Hyperbole. The reason PHP is still in use, and not dead or dying, is that it's one of the simplest languages to write server-side code in. That means it's remarkably easy to hack something together quickly, with no compilation step to get in the way. Unless that changes in a drastic fashion, projects will continue to get started in PHP, and PHP's user base will continue to grow, and (hopefully) the language will continue to improve to accommodate that growth.	{ "pile_set_name": "HackerNews" }
10gen Announces Strategic Investment from Intel Capital and Red Hat - mschneido http://www.10gen.com/press/10gen-announces-strategic-investment-intel-capital-and-red-hat ====== saosebastiao Good luck to them. I wouldn't invest in any company that has Intel Capital as a primary investor. As one of the largest VCs in the world (by fund size), their success stories list is remarkably short. Intel has found their formula for innovation, and they tend to inadvertently strangle anything that might have a slightly different innovation culture. ------ josh2600 Can anyone hazard a guess as to why they'd conceal the amount raised? Genuinely curious as to what the justification might be. ~~~ jpdoctor A better question might be: Why would you advertise how much money you have in the bank to your competitors? You're providing info so they know exactly how much to cut prices and strangle you. ~~~ josh2600 Does cutting prices have a lot to do with which how much money you've raised? I hear what you're saying, but disagree with your premise that it's a better point. I think pricing and funding are different conversations. BTW: Looks like they raised 7.6M, which is definitely a 'strategic' investment when looked at in contrast to the 70+M they've already raised. [http://techcrunch.com/2012/11/14/intel-capital-and-red- hat-i...](http://techcrunch.com/2012/11/14/intel-capital-and-red-hat-invest- in-10gen-bringing-total-to-76m-for-the-nosql-database-company/) ------ malandrew How does 10Gen make money besides support services? The valuation and money raised so far appear awfully rich for a pure support services play or are support services really that profitable and scalable? ------ JJRTaylor Great news!	{ "pile_set_name": "HackerNews" }
Show HN: Nomad List 2.0 – Find the best cities to live and work remotely - pieterhg https://nomadlist.com/?v=2.0 ====== pieterhg Hi HN! I launched the first version of this on HN 6 months ago [https://news.ycombinator.com/item?id=8107222](https://news.ycombinator.com/item?id=8107222) Nomad List indexes the best cities where you can go to live and work remotely. I started with 25 cities and 100 data points, and now have 500+ cities and 50,000+ data points. From cost of living and internet speed, to how safe and fun a city is. I've also added 25,000+ places you can work (coffee shops, coworking spaces) and sleep (hostels and hotels). And it's integrated with my Slack group #nomads, which lets you meet other travelers in every city.	{ "pile_set_name": "HackerNews" }
The Muen Separation Kernel - englishm http://muen.sk/ ====== Zuph "The Muen Separation Kernel is the world’s first Open Source microkernel that has been formally proven to contain no runtime errors at the source code level." This doesn't really jibe with seL4's claim: "The world's first operating- system kernel with an end-to-end proof of implementation correctness and security enforcement is now open source." [http://sel4.com/](http://sel4.com/) ~~~ c_moscardi The issue here is the spec - no runtime errors at the source code level is, as I understand, a completely different specification than end-to-end implementation correctness. In particular, the Muen Kernel report itself [1] explains: _By implementing the kernel in SPARK and proving the absence of runtime errors, we have shown that the kernel is free from exceptions. While these proofs provide some evidence to the correctness claim of the implementation, the application of these particular formal methods do not provide any assurances beyond the error free execution of the kernel. Proving functional properties such as the correspondence of the scheduler to a given formal specification is necessary to further raise the confidence in systems based on the Muen kernel._ In other-words, we don't yet have formal confirmation that this thing actually does what we might expect it to - just that its execution is bug-free. [1] [http://muen.codelabs.ch/muen-report.pdf](http://muen.codelabs.ch/muen- report.pdf) ~~~ vilhelm_s But in the other direction, it seems that end-to-end implementation correctness implies absence of run-time errors. The seL4 authors write[1]: > IMPLICATIONS [...] a functional correctness proof already has interesting > implications for security. If the assumptions listed in Sect. 5.5 are true, > then in seL4 there will be: No code injection attacks [...] No buffer > overflows [...] No NULL pointer access [...] No ill-typed pointer access > [...] No memory leaks [...] No non-termination [...] No arithmetic or other > exceptions [...] No un-checked user arguments [...] Aligned objects [...] > Wellformed data structures [...] And this was already done in 2009. So I don't think Muen is the first microkernel to prove absence of run-time errors. (Maybe they claim that Muen is the first open source run-time-error-free microkernel in the sense that they did the verification after seL4, but before seL4 was open-sourced?) [1] [http://ssrg.nicta.com.au/publications/nictaabstracts/3783.pd...](http://ssrg.nicta.com.au/publications/nictaabstracts/3783.pdf) ~~~ hga I would guess so, seL4 was open sourced in August 2014 and the first public preview of Muen was December 2013, per a quick check with Google. On the other hand, I've read that if you want to do serious SPARK/Ada work, you've got to buy AdaCore's tools or benefit from their academic program. seL4's verification down to binary was done using generic GCC (a clever way was found to meet the higher level proofs with stuff generated from the binary; they first tried CompCert (a verified C compiler that is free for non- commercial use) but I gather that suffered from an impedance mismatch). ~~~ nickpsecurity Misleading. AdaCore provides Ada and SPARK IDE's in full under GPL if you release your software under GPL: [http://libre.adacore.com/comparisonchart/](http://libre.adacore.com/comparisonchart/) Lots of free guides, tips, libraries, etc. You get _way_ better tools in terms of testing, inspection, analysis, etc if you buy them. No doubt. The base platform, good enough for Muen or IRONSIDES DNS, is free. You can replicate their work easily plus create safer variants of established software such as Nginx, etc. Whereas seL4 relies on Haskell, Isabelle, several proof frameworks/tools, C, and GCC. They achieved a lot more but with a lot more tools, time, and expertise. Those of us that were interested couldn't even check the verification stuff, especially the C-related tech, until late 2014. Using them would be... non-trivial to say the least. :) Good that they open-sourced as that will allow (is allowing) others to build on the work. I know it's already getting integrated into Genode OS. ~~~ hga As I was told in a HN discussion that non-educational "for GPL" version doesn't supply the same runtime, and the run time supplied is not very good. Maybe it's OK, but with all those restrictions and limitations it just didn't sound like an ecosystem I want to mess with. Plus I prefer to be able to develop and release software with less restrictive open source licenses. WRT seL4 vs. Muen, I wouldn't be surprised if seL4 does less for you, it's only 9,000 lines of C code, and some of it is artifacts from the manual Haskell -> C translation. ~~~ nickpsecurity Ahhhhhh. Wasn't aware of that. Will have to check with them. Muen uses the zero-runtime profile. Not sure about IRONSIDES. Far as those using a runtime, if that's the case, I'd recommend some FOSS people create an alternative one that is good. Then they get the language, toolset, etc benefits without that issue. Recreating _those_ will be much more difficult. "WRT seL4 vs. Muen, I wouldn't be surprised if seL4 does less for you, it's only 9,000 lines of C code, and some of it is artifacts from the manual Haskell -> C translation." That's not what I meant. seL4 is a separation kernel: they're supposed to do almost nothing. The thing is that once a modification occurs, it can invalidate the whole security claim. So, the person modifying it needs to be able to correctly use whatever its assurance depended on. That will be _much easier_ for Muen given a domain expert only needs to learn Ada/SPARK vs all that went into seL4. Now, Muen certainly has less assurance in that it doesn't have formal models of design, security policy, etc. Most FOSS types won't do all that, though. So, just requiring a language that knocks out errors and maybe learning Design-by-Contract is a nice alternative that might get more people involved. That it's Ada... might get less people involved. Who knows. (shrugs) ------ nickpsecurity It's interesting work. It's what my niche would call medium assurance software: a regular development approach that selectively uses higher- assurance tech or practices to produce stuff with fewer defects or risks. Aside from issues in x86 or security policy, the other big risks it will face are how it handles error states, how much apps can affect its internals with function calls (static helps), covert channels (esp timing), and what effect compiler has on it. I recall IRONSIDES was "provably immune" to single-packet DOS and correct W.R.T. specification thanks to SPARK... until a compiler bug decided differently. ;) Ada really needs a compiler like CompCert C or FLINT ML for safety/security use-case. Good news for people wanting to try it out is that it's been integrated into Genode OS per recent newsbite: [http://genode.org/documentation/release- notes/15.08#Genode_o...](http://genode.org/documentation/release- notes/15.08#Genode_on_top_of_the_Muen_Separation_Kernel) They claim it's also ready for day-to-day albeit still early so problems will happen. Patient, early adopters and contributors are target audience. Have fun! :) ~~~ pgeorgi I agree that the toolchain is large, unwieldy and insufficiently proven itself. However, given that it competes with other software compiled with random (usually GCC) compiler versions (what, do you think all seL4 drivers that eventually set up DMA will be verified?), the compiler issue is not a problem unique to Muen. Xen has the same problem (and by extension Qubes), and even seL4 has it for all purposes that exceed running the kernel and sigma0. The big innovation here is probably the easy general availability of a practical Separation Kernel system. And the other (not quite as big, but still significant) innovation is having a Separation Kernel that you can fix yourself, if anything looks off to you: Many of the commercial offers in that space are held together by lots of duct tape, it's just hidden by means of binary-only releases, certification procedures and sales reps. ~~~ nickpsecurity "However, given that it competes with other software compiled with random (usually GCC) compiler versions (what, do you think all seL4 drivers that eventually set up DMA will be verified?), the compiler issue is not a problem unique to Muen." There's how good it is relative to what it competes with and how well it meets its goals. I'm talking about potential issues with the latter. And drivers have nothing to do with what I said about the kernel. There's other methods/tech for handling them. "the compiler issue is not a problem unique to Muen" I have a certified compiler for C. Most separation and microkernels use that. Some use a C++ subset which can be easily converted to C. I don't have one for Ada or SPARK. So, of open kernels, the problem is indeed unique to Muen. AdaCore has commercial tech to handle it in a labor-intensive way but I'd also consider making an equivalent C system side-by-side. Then, can use SPARK proofs, C verification methods (eg Frama-C, Astree), and certified translation to object code. Meanwhile, that the very-complex compiler can destroy the security argument is worth remembering and possibly testing/inspecting for. I'm working on the concept for an easily-built, robust Ada compiler. Once I'm done, I'll pitch it to the AdaCore people to see if they'll do it or assist an external project in doing it. "Xen has the same problem (and by extension Qubes)" Yes, it's why I call it low assurance. I told QubesOS team, "secure" appliance vendors, etc about alternatives with low TCB and strong security. A glimpse at the market will show how many people bought that. ;) "even seL4 has it for all purposes that exceed running the kernel and sigma0" They admit it. They also have many parallel projects ongoing at NICTA to fix that. They solved the compilation part recently in an unexpected way. Others they're currently working on are here: [https://ssrg.nicta.com.au/projects/TS/](https://ssrg.nicta.com.au/projects/TS/) The seL4 team and Gernot Heiser were more clear on assumptions and limitations of their tech than most I read. There were certainly no attempts to mislead. Refreshing compared to the marketing crap I had to deal with from likes of Green Hills. "The big innovation here is probably the easy general availability of a practical Separation Kernel system. And the other (not quite as big, but still significant) innovation is having a Separation Kernel that you can fix yourself, if anything looks off to you: " I agree. I said the same in another comment here to 'hga.' It's why I promote and bring attention to Muen elsewhere so more people review, try and contribute to it. Medium assurance is certainly better than low and might get replaced with high given time. ------ minthd This relies on Intel's Vt-d , but there are some issues with Vt-d : [http://invisiblethingslab.com/resources/2011/Software%20Atta...](http://invisiblethingslab.com/resources/2011/Software%20Attacks%20on%20Intel%20VT-d.pdf) ------ amluto x86 has some really weird ISA quirks that can lead to exceptions and, frequently, security holes. I wonder how good their ISA model is. ~~~ nickpsecurity Exactly. They'd need to model the correct, known error, and likely error states (eg errata inspired) of the processor. After validating that model, they need to model, test, and implement their kernel operations against it. Only then can we believe its implementation will be bug-free. At least until another flaw is discovered on Intel's side. ;) Note: This was approach taken in the FM9001 and Verisoft bottom-up verification programs. Those were for correctness whereas Rockwell-Collin's AAMP7G processor also verified security (eg isolation). Personally, I don't trust anything on x86 as it's too flawed. SPARC would be my choice given it's cleaner, an open standard, and has OSS implementations (eg Gaisler LEON, Oracle T1/T2). ~~~ amluto On extremely brief inspection, they avoid a bunch of the problems by not actually running user mode (CPL3) code. That means no SYSRET garbage, no weird IRET states, no SWAPGS, etc. On the other hand, using virtualization for everything means that you pay a full host/guest switch cost every time you context switch, and that's _much_ more expensive than SYSCALL + SYSRET. Their exception handler asm looks highly questionable, but maybe they really never have exceptions :) ~~~ nickpsecurity The point was that they both created models of hardware, software, error states, and so on to use to ensure correctness of the software at every state. They even designed a safer, C variant and compiler to attempt to knock out that risk. Past that, they used microkernels and modular software (esp privileged) to further reduce risk + ease analysis. So, the takeaway was that whatever code you're looking at better represent what's actually going to happen on the machine when it works and when it doesn't. Bottom-up verification methodologies like the above help to achieve that. Merely coding what you think works and proving that code has no common defects isn't enough. ------ vectorEQ the site is marked as high risk >.> [http://www.mcafee.com/threat- intelligence/domain/default.asp...](http://www.mcafee.com/threat- intelligence/domain/default.aspx?domain=muen.sk) just sayin' :) not trying to imply anythin'. apart from that my gateway doesn't let me on it :P ~~~ saganus Same thing happened to me on the corporate network. Not sure why this happens. I would imagine the domain was previously owned by someone that got it into the banned list? or perhaps a blanket ban for certain registrars or something like that? ~~~ api It's probably because it's a "security related" product, which caused some moronic knuckle dragger to classify it as a "hacking tool." This happens a lot for things related to networking, security, virtualization, etc. Corporate IT is a low circle of hell. ------ j2kun And here I thought this was going to be a new kernel for machine learning :)	{ "pile_set_name": "HackerNews" }
An Introduction to Geometric Algebra - ingve https://bitworking.org/news/ga/2d ====== macawfish I LOVE Clifford algebra. It has been a gateway for me into multilinear algebra and abstract algebra, among other topics. If a computer were able to do Clifford multiplication in a single process, it'd be able to do some NP tasks in polynomial time. Clifford algebras are a sweet intersection of combinatoric and geometric thinking. Edit: didn't even read the article, just upvoted because of the topic. ~~~ petters Which NP tasks? ("Some" NP tasks are already possible in polynomial time) ~~~ trashtoss Seconding the question because I want to see the encodings. Intuitively this makes sense: in the GA formalism a "single" term requires 2^n fields (where n is the spatial dimension), and "simple" operations like addition and multiplication thus require 2^n (or more) operations to evaluate. If you could instead somehow do those operations in O(1) time you would clearly pick up a rather nice speedup, but again I'm curious what the problems and encodings (as GA) actually look like. ~~~ trashtoss Actually easy to find, for example here: [https://members.loria.fr/RSchott/staceyredujanv08.pdf](https://members.loria.fr/RSchott/staceyredujanv08.pdf) . ~~~ macawfish Yup, that's what I was thinking of. ------ pizza There's a library called versor that might be handy for folks that want to use geometric algebra in programs. [https://github.com/wolftype/versor](https://github.com/wolftype/versor) [https://github.com/weshoke/versor.js/](https://github.com/weshoke/versor.js/) ~~~ grondilu Perl 6 users should also check out my library inspired from versor. [https://github.com/grondilu/clifford](https://github.com/grondilu/clifford) It's not as well optimized but it's much easier to use. ------ ajamesm > Similarly, to rotate vectors you have to create matrices, which don't exist > in ℝ2, and apply them to vectors through matrix multiplication. You don't "need" matrices, they're just one way to represent linear functions that map vectors, and the complex field is another (for R^2). Coincidentally, most of the concrete implementation described for operations in G^2 here are applications of Euler's formula. This article drops off in extending the lessons from R^2 to R^3. Comparatively, matrices excel for comprehensibility in this regard -- if you know how to apply matrices in R^N, you can apply the same knowledge to R^N+1. ~~~ Koshkin > _You don 't "need" matrices, they're just one way to represent linear > functions_ Is there another way? ~~~ ianai As vectors, as algebraic formulae, as a graph, etc ------ contravariant Please don't conflate sets with algebras. Strictly speaking the tuple (R^2, +, ·) (where · is multiplication by a scalar) is a linear algebra over R, R^2 is just a set. Now I know mathematicians often refer to spaces by their underlying set, but the notation G^2 doesn't really make sense (for starters R^2 = R x R, what is G?). Calling it the Geometric Algebra over R^2 would be fine. You can even refer to it as just R^2, as long it's clear that you're using the geometric product (and what metric you're using). ~~~ ajamesm You're right, it's not really the product of some set "G" with itself but hooooo boy a programming/hacker forum is probably the wrong place to be defending the syntax of mathematical notation ~~~ catnaroek If anything, programmers should (and often do!) complain that mathematical notation and terminology _isn 't_ defined rigorously enough, and that the main justification for many design decisions is “hysterical raisins”. By comparison, even the wackiest programming languages are the parangon of consistency - after all, they have to be interpreted by machines that can only follow rules. ~~~ ajamesm I'm reading a disagreement in your phrasing, but I think we're saying the same thing: Math notation is the wild west, dressed in the veneer of consistency but indignant at any untoward implication. Programming languages are praised by their elegance and economy, even when they're wacky. Any theory (programmatic, mathematical, scientific) benefits from those qualities, because theories like to be axiomatic and terse. But any primer or intro or lesson is made MUCH better through repetition and redundancy. Computers don't need the rule of three, people do, and there's an mismatch. ~~~ catnaroek Yes, there's a disagreement. contravariant's complaint about the notation G^2 is completely justified. ~~~ ajamesm I would object too, but I don't see how that could be confusing moreso than any whiteboard "you get what I mean" pseudocode. The reader's walking in with knowledge of the product-based construction of N-dimensional space, and we readily admit that "R^2" is (a set literally, but) taken to mean the space equipped with whatever operations appropriate for whatever algebra. I'm being kinda sophist on this. "G^2" isn't meaningful. I agree. But given the convention of naming a set with the implication of whatever topology/metric/norm, the notation is already under harsh torture, right..? ~~~ catnaroek In my reply to contravariant, I explain why I don't think R^2 constitutes abuse of notation: [https://news.ycombinator.com/item?id=13241874](https://news.ycombinator.com/item?id=13241874) . ------ yk Read it first as algebraic geometry, was confused that I understood some of the words. ------ yequalsx It's hard to understand why he complains about vector operations that require stepping outside of R^2 but then introduces a 4 dimensional vector space. The justification needs to be reworded in my opinion. ~~~ dpwm It really doesn't help that in 2D you can't do much that you can't do with complex numbers. I'm not a mathematician and I really struggle with just accepting the mathematical definition. I've found it helpful to think of the geometric algebra as an extension of the R^2 to contain scalars and geometrically well- defined imaginary numbers. In R^2, the dot product maps to R. You can't store this in R^2. You can store this in the corresponding geometric algebra. For R^3, the corresponding geometric algebra forms an 8-dimensional space: 1 for the scalars, 3 for the vectors, 3 for the bi-vectors (planes formed by the 3 basis vectors) and 1 as the geometrically meaningful imaginary part. And yet in 3D and beyond, geometric algebra provides a really elegant framework for rotations in a way that is consistent, self-contained, and readily extends to higher dimensions. ------ divyekapoor Thanks for the clear and concise exposition. It was quite useful.	{ "pile_set_name": "HackerNews" }
Ask HN: Do you test your webapp's front end code? How? - silver_arrow I was thinking about testing my frontend code. After looking at couple of frameworks, it appears that as a developer, I think its a much bigger and complicated task to setup and maintain the framework as compared to testing the backend code (Mocking responses, check DOM manipulations, running tests in various browsers). Generally speaking, how many people do it in the wild and how do they do it? ====== bryanrasmussen I tend to test with cucumber ( the ruby version as opposed to the js version because the dsl seems nicer to me - although haven't looked at js version in more than a year so maybe off-base on this) Cucumber can then drive different browser libraries including selenium. ------ mcdevhammer Full integration tests (I.e. click a button in the UI, check that something was updated in the database) with Fluentlenium in Java and unit tests for directives/controllers/services (Angular) using Jasmine. ------ mattkrea Pretty sure most people are still using [http://docs.seleniumhq.org/](http://docs.seleniumhq.org/) ~~~ cauterized Selenium is ok for automating click-thru testing, but it's a pretty miserable unit testing platform. Last front-end project I worked on we did unit testing with Jasmine	{ "pile_set_name": "HackerNews" }
Ask HN: What are your favorite quotes about new ventures? - meisterbrendan Which quotes motivate you to get started on a new project, or sustain you when you are feeling discouraged? ====== quackerhacker "Get err done!" :: I'm a programmer, (more abstractly a trial & error and cut & paste expert), but I feel a quote doesn't really help when feeling discourage or a lack of motivation. A quote to me is no different than an Ansel Adams poster with a simple headliner, with the hopes of sparking an epiphany. "Just do it!" :: The quotes that I state above are what I tell my self while I blast 949 or itunes as I type away on Dreamweaver, and occasionally check HN for a distraction from the monotony. In other words, FOR ME, a quote can't encapsulate motivation, but MY WIFE can lite a fire under my ass (my best boss lol).	{ "pile_set_name": "HackerNews" }
Why 3D Printing Will Go the Way of Virtual Reality - mrsebastian http://www.technologyreview.com/blog/mimssbits/27526/ ====== jeffool I sometimes suspect the same about 3d printing, but I think the comparison to VR is funny given recent rumors about the next Xbox being shipped with the next version of the Kinnect as standard. Sure, we're not wearing goggles, but otherwise...	{ "pile_set_name": "HackerNews" }
Ponzu – An open-source HTTP server framework and CMS in Go - wilsonfiifi https://github.com/ponzu-cms/ponzu ====== patrickmn > Automatic & Free SSL/TLS A couple of years ago, I wouldn't have believed we would be seeing essentially zeroconf TLS/PKI in software anytime soon. Letsencrypt, the "encrypt everything" movement, and people like Steve, Ponzu's author, have improved internet security tremendously at a time when it is critically needed. ~~~ nilslice Thank you, but all credit is due to the Let's Encrypt team. It is an amazing thing they have done. ~~~ srcmap Steve, Quick question, must the server use "Let's Encrypt" be public on internet to use it? Like: Can I use private ip (10.1.1.x) behind the NAT and still use "Let's Encrypt" \+ your CMS/server? Thanks ~~~ nilslice Sort of. If you're OK with manually updating the certificates after initially fetching them from L.E., then you can use them. However L.E. must be able to communicate directly with the server via HTTP to prove authority and send you the certificate. There are other tests that the ACME protocol can do to determine authority over a domain name, but Ponzu's implementation doesn't handle them. Sorry if that doesn't fully answer your question. ------ nilslice Hi all - Ponzu's author here. I was pleasantly surprised to see this post today. I'm reading through comments and will be releasing some video content as an overview of the CMS and server shortly - hoping to address any questions I see here. If you get a chance to try it out and have questions or issues, I'm in the #ponzu channel in the Gopher's slack org: [https://invite.slack.golangbridge.org/](https://invite.slack.golangbridge.org/) feel free to ping me there or open an issue on Github. Steve ------ bketelsen Nice to see Ponzu getting some attention. I used Ponzu to create the GopherCon 2017 site this year (gophercon.com) and really enjoyed how easy it was to put content up quickly. I created Go helpers -- only useful if your website is in Go: github.com/bketelsen/ponzi && github.com/bketelsen/ponzigen Overall A+ to Ponzu. I'm on my 6th ponzu site now, still love it. ------ wyc Looks spiffy. I like the approach of keeping even the database as part of the application. I think it makes projects a lot more like appliances, which can really be more plug-and-play. I see a lot of databases moving towards the application layer (CouchDB, Firebase), but it's interesting to see applications going the other way. Lastly, here's to the hope of an exploit named "Pwnzu" never getting released! It's simply too good of a name. ------ tyingq Does look pretty slick, but I imagine the flat nature of the content items will be limiting. In the example, song has an artist. But artist is a string vs a related content item. I can't tell if that's an MVP type decision and will change later, or a design decision that won't change in the future. ~~~ nilslice Hi - you can make a relationship using the built in addon package, github.com/bosssauce/reference The reference is stored as a string (or []string if you opt for a reference.SelectRepeater input func), but the value stored as a reference is actually a URL path to the content as it would be accessed via the Content API. This becomes very powerful when you enable HTTP/2 Server Push, and declare the referenced content to be pushed when it's parent content is requested. The underlying data looks like this: Song id: 1 title: "Take Me Home, Country Roads" artist: "/api/content?type=Artist&id=2" If you enable H2 Server Push by implementing the Pushable interface (add a Push method that returns a []string of the JSON field names to push), the server will know to make a response for the referenced Artist field and push it down to the client when the parent Song is requested. ~~~ tyingq Ahh, okay. That seems straightforward. Might be good to reference that in the main documentation. ~~~ nilslice Definitely will -- thank you for taking the time to read through.. it's hard for me to know where the docs are too light sometimes. (besides generally everywhere) ------ jordanlev Kudos to the creators for getting the CMS field definitions right by allowing arbitrary amounts and types of fields! It's so annoying to me that so many CMS's and static site generators start out with the assumption of 1 big rich text / markdown "body" for content and treat everything else on the page as miscellaneous stuff (meta-fields, yaml front- matter, etc). ~~~ devmunchies Sorry, I've never used a CMS or managed a blog... but I'm curious about the use case and benefits of having arbitrary fields. Is it for meta information about a post? Are those fields injected into a post somehow? How are those fields used? (I'm ignorant of CMSs) ~~~ chickenfries Imagine the case of a generic news article: the body of the post can contain text, photos, pull quotes, videos, a slideshow, audio content, etc. The CMS needs to enable users to add all of that content and expose via the API to multiple clients (web, mobile, feeds, etc). ~~~ justincormack I always thought that fields are generally poor for that - html is pretty good and has ways to structure all those things, and they can be extracted and styled for different clients. ~~~ CognitiveLens HTML as a data entry format is error prone, and HTML as a cross-platform data source requires a lot of tooling and unreliability compared with a properly- structured field-driven JSON API ~~~ rapind If you have the luxury of convincing your users to learn markdown instead of structured fields you'll have a far simpler and extendable solution. Obviously rarely the case, but worth having the conversation. ------ chickenfries Looks interesting, it would be nice if the ”Why?“ section contained comparisons to other CMSs. ------ epynonymous havent looked at the reqdme or rtfa, but ponsu, if i'm not mistaken, is a sauce in japan used for dipping, it consists of soy sauce and citrus/lemon/lime flavoring, great with raw, grated daikon radish. in terms of this project, excellent, i actually wrote a lot of web apps using golang and found the main deficiency to be the templates, tried amber, ace, and even the default mustache/handlebars, but still think jade and haml beat those hands down. i did see a few ports of jade, but wqsnt certain about the stability or completeness of it. ~~~ ppodsfkk I spoke to a Japanese programmer friend on his opinion on projects named after Japanese words. His personal take was that many were at cringe level. Not just him, his group of friends regularly chat about the "cringiness" in their line group. I promptly shared my project based on a Japanese name and provided entertainment for a few mins. ~~~ tomcam Go visit Japan and check out English usage on their T shirts ------ tenken Boltdb sounds neat, but I swear no off-the-shelf tooling supports it. ~~~ jaytaylor I was apprehensive about BoltDB too, at first, but after giving it a shot I've really taken to it and come to appreciate the reliability and flexibility it offers. It's not well-suited for all cases, just those where dropping in high- performance transactional persistence into an app meets your needs. As it keeps gaining traction and popularity, more and better tooling will inevitably be created to scratch itches :) ------ dozeone [https://github.com/ponzu-cms/ponzu/issues/113](https://github.com/ponzu- cms/ponzu/issues/113) Thats my question... ------ whizzkid Couldn't see any authentication system in Readme, Is there any auth mechanism that can be used for API usage? ~~~ daenney According to the README it depends on golang.org/x/crypto/bcrypt and github.com/nilslice/jwt so it seems likely to have authentication on board and a way of using JWT tokens for API access. ~~~ tshawkins How hard do you think it would be to add SAML/OAUTH2 authentication? ------ sAbakumoff Indexing - why don't u use bleve? ~~~ nilslice It's actually almost ready! Check out the ponzu-dev branch or look at the compare between it and master for the implementation. I would love to get some feedback as a first time Bleve user. ~~~ sAbakumoff Well, I am not affiliated with bleve, but actively use it in my project where the data are in BoltDb but index is stored separately in bleve. It's really awesome package. ~~~ nilslice I agree :) sorry I wasn't more clear, but I have indexing already added with Bleve - it's in the ponzu-dev branch of the repo now. If you get a chance to browse the code lmk if you spot anything I have done incorrectly! ------ delblues as a web server, can I use this with an Ruby on Rails application? ~~~ nilslice Sure! Just think of Ponzu as a JSON web service and fetch/put data from your controllers or models. ------ vlgk looks interesting	{ "pile_set_name": "HackerNews" }
Ask HN: Why does everything break immediately when starting a new language? - inputcoffee Many years ago, when I started python, nothing would compile or install. It took many hours to get used to the virtual environment, different versions of python (2 and 3), and then the libraries to get hello world working reliably.<p>When I first started ruby, the rvm on the machine had not been updated. Got everything up and running, and then a new update in rails broke the hello world example.<p>When I started VueJS, npm simply would not install everything I needed. It kept telling me it was broken. I finally realized that it was running a slightly older version of nodejs and that changed everything.<p>Why does it take so many hours just to get the first basic hello world up?<p>Sure, after you've played with it, you know exactly what happened so well that you ignore the issue.<p>Its not the bother of learning it, it just seems something is fundamentally wrong with development if our tools are like this. ====== PaulHoule I think many developers have a "macho" attitude that things are supposed to be hard; if you are smart you can handle the complexity of C++, Kubernetes, etc... Python is a special case. Python was easy long ago but the Python 2 to Python 3 transition was brutal, particularly because many Linux distributions used Python as a scripting language for system scripts. Thus "python" had to be python 2, and a generation of programmers got python 2 as a default and wrote more py 2 code when they should have been writing py 3. ------ asynch8 I've had plenty of these situations aswell, and now a days I don't even bother if the process setting something up is too painful. That is why I highly enjoy writing scripting languages so much, because they are generally just out of the box ready to run after a small install. No extra thought required to begin developing.	{ "pile_set_name": "HackerNews" }
Unexpected Senate Action on NSA Reform Bill - uptown http://thecable.foreignpolicy.com/posts/2014/11/13/unexpected_senate_action_on_nsa_reform_bill ====== uptown "If the bill is passed, it would likely end the political debate about NSA surveillance of American citizens." I can't say I agree with that.	{ "pile_set_name": "HackerNews" }
Ruby Metaprogramming Simplified - cheind http://cheind.wordpress.com/2009/12/18/ruby-metaprogramming-simplified/ Here is an approach to ease unleashing the power of Ruby’s metaprogramming. ====== tptacek Changing the behavior of an existing class or method isn't really what people mean by metaprogramming, is it? ~~~ jeremymcanally Well no not really. I guess you could use this lib for metaprogramming (code generation etc.), but I don't really see much benefit. This just seems to be an odd wrapper that doesn't make things more apparent (though that may be because I already know a good bit about Ruby and can't see with "n00b eyes"). ------ petesalty I'm sure someone spent some time on this but I fail to see how things makes things easier or clearer. If anything it just muddies the waters. I know that metaprogramming can be hard to get your mind around sometimes, but you're much better off running through the existing material. If you keep at it eventually everything just clicks into place and you have that "ah-ha" moment. Takes a while but it's worth it. Check out this link for some great resources (this has been posted on HN in the past): <http://ruby-metaprogramming.heroku.com/> ------ jamesbritt This is nuts. So, instead of learning the correct syntax to add behavior to a class or to an instance, you learn some library syntax instead?	{ "pile_set_name": "HackerNews" }
Google will kill Microsoft Silverlight in Chrome by disabling NPAPI plug-in - bedroomfireflys http://www.theinquirer.net/inquirer/news/2383624/google-will-kill-microsoft-silverlight-in-chrome-by-disabling-npapi-plug-in ====== greggyb Silverlight's end of life has been announced. Microsoft is even phasing it out of its own product offerings. The example I am thinking of is their data visualization tool, Power View, which is taking the helm as their dashboard design platform. It was originally developed with Silverlight, but pretty much all current development is in the HTML5 fork in PowerBI. On the Netflix front, Chrome has had HTML5 streaming since late last summer. I think the bigger news is killing NPAPI, not specifically Silverlight. Edit: Typoes. ------ hatred I haven't gone reading the article in detail. What happens to the streaming providers like Netflix etc that use Silverlight ? Would they stop working too ? ~~~ joshstrange Netflix is already moving to HTML5 video [http://9to5mac.com/2014/06/05/yosemite-finally-allows- netfli...](http://9to5mac.com/2014/06/05/yosemite-finally-allows-netflix- subscribers-to-wave-goodbye-to-silverlight/) ------ zo1 And everyone is silent... But if it was Microsoft trying to use it's weight to kill off some net technology it doesn't like/own. ~~~ joshstrange I think we can all agree killing off NPAPI is the right choice. As google said it's ancient tech and it's holding them back. Netflix is the only thing I ever use that uses NPAPI, via Silverlight, and even they are moving to HTML5 video [0]. Also MS already killed off Silverlight [1] and other plugins. This is where we WANT to go with the web, a plugin-free world is goal... Let's not try to make this a "If MS did this everyone would be up in arms" issue because that's not what it is. The article is super click-baity as Google isn't saying "Fuck You" to MS but to ALL of NPAPI which has outlived it's usefulness IMHO. [0] [http://9to5mac.com/2014/06/05/yosemite-finally-allows- netfli...](http://9to5mac.com/2014/06/05/yosemite-finally-allows-netflix- subscribers-to-wave-goodbye-to-silverlight/) [1] [http://www.itworld.com/article/2736986/enterprise- software/m...](http://www.itworld.com/article/2736986/enterprise- software/microsoft-kills-silverlight-and-other-plug-ins-in-windows-8.html) ~~~ hatred I think Amazon Instant Video is also on Silverlight ? ~~~ joshstrange Yes, I think they originally used Flash then switched to Silverlight. Not sure if they still support the flash player though. That said I'd bet they will be moving to HTML5 soon. ------ dlu Oh thank goodness. We should be celebrating the end of NPAPI	{ "pile_set_name": "HackerNews" }
X/HTML 5 Versus XHTML 2 - pg http://xhtml.com/en/future/x-html-5-versus-xhtml-2/ ====== danielha Reminds me of a quote: "The nice thing about standards is there are so many to choose from." There _are_ cool additions to both, and that's the problem. Two sets of standards that set out to accomplish the same goal. Anyhow, there will be some time to kill before browsers (read: IE) start incorporating the best stuff.	{ "pile_set_name": "HackerNews" }
Hundreds of Nude Photos Jolt Colorado School - DanielBMarkham http://www.nytimes.com/2015/11/07/us/colorado-students-caught-trading-nude-photos-by-the-hundreds.html ====== makecheck I never understand why parents push so much responsibility to school administrators. When something is not happening _at_ school, during school hours, related to education, why is the school expected to do anything at all? If use of a phone app causes interruptions _in class_ , you respond by setting rules _in class_ such as "put your phones away". Otherwise, it's _COMPLETELY_ outside the boundaries of the school. The police shouldn't be involved unless a charge has been levied by someone (e.g. "this person took pictures without my permission"). Bringing them in did nothing to help the children, it only further increased exposure. Oh, great: the police are going to "try to identify" the children in the naked pictures; well, how, exactly, without making the situation far worse for everyone? Parents need to be parents. Train children about the risks of trading pictures or anything else of a personal nature (pictures are not guaranteed to be seen only by the person you send them to, pictures can be used as blackmail, etc.). Show kids why they should think twice before doing these things. And yes, commend them for the sensible steps that were taken, e.g. guarding things behind a password instead of leaving them completely in the open. ~~~ aikah > When something is not happening at school We don't know that. We don't whether some pictures were taken or traded inside the school. And if that's the case, the school administrator are responsible. But I'm more concerned about the destinations of these photos which may likely end up in child-porn sites on the internet. edit: ok it seems some pictures were actually taken in the school. ~~~ lmitchell The article does imply that we know that. > The photo-sharing, some of which took place in school, ------ StavrosK Isn't it clear that this is not child porn, and that the law is wrong, when teenagers are sexting? It's just almost-adults discovering their sexuality, how can they be prosecuted without anyone in that process thinking that something is wrong? ~~~ DanBC It depends a bit on the ages and intent of the teenagers. A 17 year old who has no sexual interest in other 17 year olds but who does have sexual interest in 13 year olds is possibly worrying, especially if they've managed to gather nude photographs of 13 year olds. (Not saying anything like that happened here though). But even ignoring the child sexual abuse images aspect: It's a pretty unhealthy culture where children assign point values to naked photographs of other children. That's not normal exploration of childhood sexuality. In cultures that have much more open sexuality we see reduced sexual activity in children (eg, less sexually transmitted infection; fewer unplanned pregnancies). The UK / US seem to have a problem with this and just telling children to stop doing it doesn't seem to be working. (Fully agree that prosecuting a child for taking an image of themself is a bad idea) ~~~ makecheck Although laws seem to only consider age, this makes little sense given the wide variety in puberty. Some 19-year-olds look 15, and some 13-year-olds not only look 17 but they have probably matured over their peers to the point of being _physically_ closer to the average 17-year-old than the average 13-year- old. It is certainly possible for a 17-year-old and 13-year-old to seem physically similar and be attracted normally to one another. Society shouldn't be able to auto-condemn a relationship at one point in time, and magically become OK with it 5 years later (when the two people may not even look that different). It gets even worse when absolute age is considered. It's insane that two 17-year-olds can meet and date and want to have sex, yet people come with pitchforks to prosecute the first one unfortunate enough to turn 18!? ~~~ StavrosK I actually think Greece got this pretty right, the age of consent is 15 and if the people involved are within 3 years of age from each other, it's legal. The one dark spot here is that the age of consent for homosexual relationships between men is 18 for both participants, but here's hoping that will go away soon too. ~~~ anotherevan I had half written a post about how the laws in Australia are similar to what you outlined for Greece. I certainly agree that they make a lot more sense than no (legal) consent being considered possible for adolescents. But in the end I dropped it because it struck me that while the legal ramifications of this situation may be considered stupid, the far overriding worry to me is how unhealthy this situation is: for those involved, for their community, and their culture. The focus should be on the far more difficult problem of changing that. While legislation may be a part of that, I doubt if that alone is the solution. How do we fix this? ------ Others I'm torn about whether or not sexting is a legitimate problem... Very many teens do it with mutual consent, and for older teens it really shouldn't be illegal at all. But I do think that, to some extent, younger teenagers need to protected against themselves. They just don't have the maturity to recognize the consequences of their actions. I think that really, what really is important is fixing sexual education. America doesn't have rigorous guidelines for sex-education, and that means schools often take a DARE like approach to it. I think that the federal government might need to implement a national standard for sex-education, focusing more on the reality of sexual activity and the risks involved. I'm not sure that is ever going to happen though, it is probably far to left wing for social-conservatives in Congress. Whether or not we reform sexual education, the legal system needs to figure out a better way of handling sexual activity among minors. Filing child porn charges on minors exchanging nude pictures is ridiculous. I'd support an exception to current child porn statues to protect minors from being falsely labeled "sex-offenders", sort of like the Romeo and Juliet clauses in most statutory rape statues. That would be a good step towards actually recognizing that people don't wait until they are 18 before developing sexuality. (Although they really should, because as soon as you turn 18, all the reasoning and maturity that makes you an adult comes in at once...) ------ jMyles There will be a movement to "decriminalize sexting," or perhaps even "decriminalize youth," which will grow rapidly in the coming years. It will be interesting to see how it fares against the rhetoric about child porn (and child safety generally) that characterizes the current political climate. ------ triangleman As always, the underlying problem of parents' sheepish deference to authority (be it school administrators in this case, but also police, government, and "experts") will not be questioned by the New York Times. Look at the article's treatment of the parent who went to the school counselor about a photo she found on her daughter's phone. All it says is she was "heartbroken" by the school's response and eventually decided to home-school her child. Did the parent take away her daughter's cell phone? Where there other reasons for pulling her daughter out of the school (perhaps the toxic culture in which a majority of students are trading nude photos of themselves)? What did she expect the school to do anyway? We will not learn the answers to these questions, only that in some way, _the school_ failed, not the parents. The fact that parents are continually ceding responsibility for raising their own children to whoever will take it, is not at issue here. That point is taken for granted whenever one of these cases comes up. I wonder what would happen if schools started banning cellphones entirely. Why do kids need them anyway--they can always make a phone call from the principal's office. I suspect parents would complain about their heavy-handed tactics (but in reality the problem is that it makes their job harder). It seems like our culture is continually interested in passing the buck to someone else, until something goes wrong, at which point "something" must be done. Rinse and repeat. ~~~ DanBC This parent found a nude image (and so was checking the phone?) and took action - she told the school and was told the school wasn't going to do anything; she pulled her child out of school and homeschooled. I don't understand how you read that and say that she was giving all responsibility to the school. (And the school acts in loco parentis - they're supposed to be responsible for the child for the 6 hours a day the child is there.) ------ tomku The article talks about "safe sexting" education as a solution, but I'd like to suggest that such a thing does not and perhaps will never exist. It's great that you trust the person you're sending the pictures to not to share them, but you also have to trust: 1) That same person with that same responsibility even after you break up, including when they're at their most angry with you. 2) That nobody (your school, your ISP, your government) is eavesdropping on your communication method. 3) The software that's being used to both send and receive the photo. 4) That the recipient will keep their phone or PC physically secure so that random people can't just click "Photos" and view them. 5) That the recipient won't get "hacked" and have your photos uploaded online somewhere without their knowledge. There's a lot of parallels with DRM and copyright - once you've converted something into an easily-copyable form and sent it across a network, it's very, very hard to make sure that it never gets copied again. We should be telling teenagers (and maybe some older people too...) the truth - that if they sext, no matter how much they trust the other person, they're taking a risk that their photos might end up shared more widely. ~~~ DanBC You assume that "safe sexting" doesn't teach 1, 2, 3, 4, and 5 as reasons to avoid sexting? And that safe sexting doesn't try to move children to posting clothed instead of unclothed images but with sexual text instead of sexual images? Here's a canadian thing talking about it, and about the difficulties of abstinence only approaches: [http://www.macleans.ca/society/how-safe-is- sexting/](http://www.macleans.ca/society/how-safe-is-sexting/) > For Lauren Dobson-Hughes, president of Planned Parenthood Ottawa, it’s > important to teach teens about the criminality of sexting alongside the > topic of consent, and offer guidance, should they choose to do it anyway. > “If you tell youth not to do it, simply that it’s illegal, they hear, ‘Don’t > get caught,’ and it doesn’t help them understand the actual risks involved > in sexting,” she says. That’s why her organization is taking a risk- > reduction approach to sexting in the sex education workshops it provides to > young students in local schools upon request. This means accepting that > sexting is part of teenage life. “There’s an upside to this, or they > wouldn’t be doing it,” says Dobson-Hughes. “We would rather youth talk about > consent in an age-appropriate way, throughout their lives, so they > understand that sharing a picture without someone’s consent isn’t right.” And we've had years and years of abstinence only approaches to reducing teenage unplanned pregnancy, or to reduce HIV/AIDS, and we _know_ it just doesn't work. ~~~ tomku I think you've severely misread my comment. I'm absolute NOT proposing any kind of "abstinence only education" regarding sexting. I support what you said about teaching the risks and safer alternatives. If that's what "safe sexting" initiatives are teaching, great! However, that wasn't the impression I got from reading the article you linked - it talked a lot about the legal risks, a bit about trust and consent and a bit about taking "safe" sexy pictures that people won't be able to identify you in. My point in the comment above was that even if you do all of that, a lot of the risk is simply outside of your control. That's fine - people do risky things all the time, it's part of life. I just don't like taking an approach that's essentially harm reduction and calling it "safe". ~~~ DanBC > I think you've severely misread my comment. Sorry! It's a bit late here. I think we agree. ------ intrasight This is a technology problem, and I expect that we'll find a technology solution. I bet there are dozens of bright young things working on image processing algorithms to detect various undesirable states of undress and the exposure of sexual organs, and that these algorithms will be baked into the terms of service of the Internet as we know it, and that said Internet will be a much more user friendly place without such images. ~~~ maxmcd This is a solved technology problem[1]. A technical solution has not changed the fact that people do not want all of their pictures scanned by a third party. 1\. [http://www.ibtimes.co.uk/microsoft-launches-free-cloud- versi...](http://www.ibtimes.co.uk/microsoft-launches-free-cloud-version- photodna-help-detect-child-pornography-1511390) ------ superplussed Wouldn't it be relatively easy to have each owner of a phone enter their birthdate upon setting up the phone, and then do image-detection so the phone would just block the saving of any photo that contained nudity until the owner was over 18? Of course, technology can be circumvented but this would be a start. ~~~ DanBC We have facial recognition technology that recognises black people as gorillas, and other face recognition technology that ignores black people. Nudity recognition is going to be really hard to detect. Since these children were using "vault apps" those vault apps would probably start to include bypass techniques. And this ignores the sexual health stuff that children can validly search for. You don't want to block images of how to check your testicles for cancer, for example. (Although photographs are probably not helpful blocking the images would be counterproductive.) ~~~ SolarNet The last one at least wouldn't apply. Only pictures the phone _takes_ would be blocked. Assuming this is some sort of OS/Administrative app, I doubt the vault apps could get around anything preventing the camera service from returning an image without, basically, rooting the phone. Other than that, the facial recognition stuff is a fair point.	{ "pile_set_name": "HackerNews" }
Faster - Why Constant Stress is Part of Our Future - jmorin007 http://www.readwriteweb.com/archives/faster_constant_stress_future.php ====== tomjen This need not be the case - most newspapers suck because they all try to out compete CNN, which only leave time for a small part of the story with 70% of the facts wrong anyway.	{ "pile_set_name": "HackerNews" }
Jaws: HTML5 Javascript game engine / development library - ukdm http://jawsjs.com/ ====== lukev Not saying this isn't awesome... but don't there seem to be more HTML5/Javascript engines/libraries/toolkits than there are actual decent products or games? ~~~ bermanoid The problem is, none of the engines so far even come close to the quality of decent game engines on other platforms. They've all got seriously rough edges, bugs, missing features, etc., to a point where there's not even a clear winner yet where further community development efforts get funneled. Until there's a clear "winner" in the space, I'm happy to see more engines come out, maybe one of them will finally get close enough to a general purpose game engine that it will see some community involvement. ~~~ WesleyJohnson What are your thoughts on impactjs? I know it's not a general purpose game engine, but I'm just curious to see what people think it's missing. A lot, I'm sure, in terms of general purpose gaming, but how could it be improved for it's target games; tile-based platformers and top-downs? ~~~ boneheadmed I've created a couple of games with ImpactJS and have really enjoyed it. I think it's great for tile-based platformer games in particular. But (with enough programming skill), you can bend it to make virtually any type of 2D game. The code is very well thought out and organized. It's a pleasure to work with generally. Haven't used any of the other HTML5 engines though. ------ wwweston Sigh. No sound. I kindof understand why. If my recent forays into in-browser audio are any indication, it's kindof a mess. You need Flash fallbacks for older versions of IE, there are latency/seeking problems on browsers that do support the audio element, mobile support is even sketchier and limited to a single element, and that's just for playback of pre-generated media... ~~~ portmanteaufu The documentation briefly mentioned supporting audio assets [1], but I haven't been able to find obvious examples of how to use them once they've been loaded. One of the provided sample games [2] had a soundtrack, so I dug through the source [3] a bit and discovered that there is an "Audio" class and some other undocumented functions that can be used with an "Assets" object to achieve playback. Looks like he's just coding to fast to keep everything written down. :) [1] <http://jawsjs.com/docs/symbols/jaws.Assets.html> [2] <http://ippa.se/webgames/unexpected_outcome/> [3] <http://ippa.se/webgames/unexpected_outcome/game.js> ~~~ ippa HTML5 audio is kind of weaksauce atm yes. To support all major browsers I need to ship both oggs and mp3s for example. Jaws creates instances of Audio() for each sound, loading them by setting the src-attribute and listening for the canplay event before making the asset as fully loaded. Just google the Audio-tag, you have play(), pause() etc. ------ ippa Ah, I was wondering where all the new github watchers were comming from, now I know. JawsJS is very much alive! I've had sort of a pause from development after working _A lot_ on it for a period. I'm always fixing bugs and accepting patches. I got documentation at <http://jawsjs.com/docs/index.html> but I know it could be better. I've tried to make up for it with tons of examples.. I know I personally love examples when learning new stuff. About sound, I would say it's HTML5 weakest point. I think both chrome and ff are working on new sound APIs so this might change. JawsJS now support basic playing of sounds through the Audio()-element. Last time I checked in safari there was a delay though, making it slightly sucky for shooting-sounds and so on. ------ tommi The "Jaws is very much work in progress, so expect big changes within the first months of 2011." is outdated or has a typo. <https://github.com/ippa/jaws/commits/master> appears to have active development. ~~~ ippa Ye, github, the source and the examples is where it's at. The homepage has become less relevant. Thanks for reminding me to remove that line. ------ jamesflorentino Looks nice! The code looks easy enough to get started. And I love the setup(); update(); draw(); game state methods. That's how I used to do it in ActionScript3 before. I'm actually now diving into HTML5 game development as well and I was wondering what's the advantage of Jaws.js over Easel.js? ~~~ Impossible Looking over the documentation for the two libraries it seems like they have different goals with minimal overlap. Easel.js is basically a clone of a subset of the Flash API, while Jaws.js is a small game engine for building HTML5 platformers and is comparable to Flashpunk. It has classes for tile maps, parallax, etc. ~~~ jamesflorentino Thanks for the reply. I just checked Jaws' documentation, and it seems to be perfect for my little turn-based strategy game. I've had experience using EaselJS before but the problem is that I'll also need to build something on top of it to make it work as a game. ------ justbeast Myself (and a couple others) used JawsJS to do our first Ludum Dare (<http://www.ludumdare.com/compo/ludum-dare-22/> ) entry. It's a great basic framework -- the examples on the site is what sold it for us. ------ noduerme StrikeDisplay, <http://strikedisplay.blogspot.com> went to version 1.0 today, with a lot of capabilities, filters, multiline text justification, etc. It's not so much a game engine as an all-purpose interactivity kit/screen graph, with a display/event model based on AS3.	{ "pile_set_name": "HackerNews" }
The Gun Lobby Is Down to Its Last, Unconvincing Excuse - ourmandave http://www.rollingstone.com/politics/features/taibbi-gun-lobby-is-down-to-its-last-unconvincing-excuse-w506851 ====== theyregreat Depending on the state, getting a Destructive Device tax stamp and local law enforcement approval, Americans can currently privately own _fully-functional, diesel-powered traverse, towed, anti-aircraft 40 mm auto-cannons_ if they were made before some treaty (I can’t remember which one). They’re several hundred thousand dollars and the shells are hundreds of dollars each. That’s right: moderately rich people can own their very own artillery in some states like Arizona. [http://youtu.be/BcJEFosXfFQ](http://youtu.be/BcJEFosXfFQ)	{ "pile_set_name": "HackerNews" }
Cyber Risk Isn’t Always in the Computer - larrys http://www.wsj.com/articles/cyber-risk-isnt-always-in-the-computer-1443125108 ====== larrys To pass the paywall: [https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&c...](https://www.google.com/url?sa=t&rct=j&q=&esrc=s&source=web&cd=1&cad=rja&uact=8&ved=0CB8QqQIwAGoVChMIqt3sieGSyAIVgqkeCh2ZRQs_&url=http%3A%2F%2Fwww.wsj.com%2Farticles%2Fcyber- risk-isnt-always-in-the- computer-1443125108&usg=AFQjCNHpXi0PNKaqqjV4H2IHIy19MVePNQ) ~~~ tracker1 I use the Referer Control chrome extension for that.	{ "pile_set_name": "HackerNews" }
Amazon face recognition falsely matches 28 lawmakers with mugshots - georgecmu https://www.theguardian.com/technology/2018/jul/26/amazon-facial-rekognition-congress-mugshots-aclu ====== eboyjr Amazon's response to this report: [https://aws.amazon.com/blogs/aws/thoughts- on-machine-learnin...](https://aws.amazon.com/blogs/aws/thoughts-on-machine- learning-accuracy/)	{ "pile_set_name": "HackerNews" }
Walking Truck - colinmegill https://en.wikipedia.org/wiki/Walking_truck ====== ckastner > _The stepping of the robot was controlled by a human operator through foot > and hand movements coupled to hydraulic valves._ > _The walking truck was one of the first technological hardware design > applications to incorporate force feed-back to give the operator a feel of > what was happening._ This might sound primitive in today's autonomy-driven mindset, but in contrast to autonomous robots, this is a technology that could be delivered today (or was already delivered in 1965, according to the article). So if infantry really does need hardware to move stuff from A to B, the 1965 approach -- primitive as it is -- might be the simplest solution. ~~~ icebraining I'm sure that approach is simpler, but from what I can tell, the (semi?) autonomous technology can also be delivered today: [https://www.bostondynamics.com/ls3](https://www.bostondynamics.com/ls3) ~~~ ckastner I thought of that example, too, but thought that it had been cancelled as unsuccessful. Turns out it was cancelled for mainly other reasons. Quoting [1]: "By late 2015, the Marines had put the LS3 into storage because of limitations with the robot including loud noise, challenges in repairing it if it breaks, and how to integrate it into a traditional Marine patrol" [1] [https://en.wikipedia.org/wiki/Legged_Squad_Support_System](https://en.wikipedia.org/wiki/Legged_Squad_Support_System) ~~~ taneq Turns out the marines don't really need a loud, expensive, fragile machine to haul their gear when they can just use a quad bike. Robots are awesome but integrating practical robotics with mission critical operations is really _really_ hard, especially because you're automatically competing with battle-tested best in class solutions. ~~~ Mvhsz Actually turns out Boston Dynamics had a good idea and over-engineered it. LM built a cheaper, wheeled, semi-autonomous troop support vehicle that ended up selling pretty well. [https://defense-update.com/20070529_smss.html](https://defense- update.com/20070529_smss.html) ~~~ taneq That thing looks an awful lot like a quad bike with two extra wheels. ~~~ steverb AKA a "6 Wheeler". At least that's what we called them when I was kid. They use differential steering, which makes them a good fit for automation. Don't have to worry about turning a steering column, just shift the power around which the off the shelf ATV already handles. ~~~ taneq Yep, there were ads for them in the back of Popular Science magazine. They were fully amphibious too and could float. Don't get me wrong, I love my fellow kinematically-complicated meatbags but I do kind of think wheels win this round. ~~~ cr0sh There are still a couple of companies that sell 6WD (and 8WD) vehicles like these - Argo is one of them (and that machine up-thread looks like they just strapped some stuff to one of those): [https://argoxtv.com/](https://argoxtv.com/) The other kind of "extreme off-road differential steered" ATV that people both want (and then seemingly want to sell soon after - almost like a boat) is the Russian Sherp: [https://sherpatv.com/](https://sherpatv.com/) I'd love to have one of those - but they are a bit out of my budget (and my wife would probably divorce me if I brought one home, even if I could afford it). ~~~ taneq I love the Sherp! Also the roughly-equivalent bike version: [https://canadamotoguide.com/2016/08/03/russian-2wd-bike- is-a...](https://canadamotoguide.com/2016/08/03/russian-2wd-bike-is- apparently-now-on-the-market-and-its-not-a-ural/) ------ alex_young Video: [https://www.youtube.com/watch?v=ZMGCFLEYakM](https://www.youtube.com/watch?v=ZMGCFLEYakM) The thing looks a little top heavy to me. I wonder if there are airbags :) Also - external hydraulics seems like quite a limitation. ~~~ beardog Between the old footage (minus the basic color), music, and narration this feels like it could be a scene from the twilight zone or a doctor who episode ------ bwaine Interesting, perhaps the inspiration behind the walking battle machines[0] in my favourite table top board game "Scythe"[1]. Interesting to see a real life Mech! [0] - [http://www.heavymetal.com/news/these-amazing-paintings- raise...](http://www.heavymetal.com/news/these-amazing-paintings- raised-1-8-million-for-a-board-game/) [1] - [https://stonemaiergames.com/games/scythe/](https://stonemaiergames.com/games/scythe/) ------ retSava > It alternatively bore the name of "CAM", an acronym for "cybernetic > anthropomorphous machine" now that's a seriously cool name! The pic makes me think of Strandbeests and derivatives: [https://www.strandbeest.com/](https://www.strandbeest.com/) ~~~ Hitton It's the opposite of cool name. Anthropomorphous means resembling human being, this was nothing like human, it was quadruped. ~~~ Insanity That just makes it an incorrect name but not necessarily not a cool one. The Death Star isn't a star but the name is cool. ------ booleandilemma They look vulnerable to snowspeeders. ~~~ HenryKissinger That armor's too strong for blasters. ------ globuous The reminds me of this video [1] where the guy builds these out of wood and paper and powers them with wind. Increadible. [1] [https://m.youtube.com/watch?v=LewVEF2B_pM](https://m.youtube.com/watch?v=LewVEF2B_pM) ------ PinkMilkshake That thing looks amazing! A similar concept was these walking harvesters [https://www.youtube.com/watch?v=2pJwDZXasKU](https://www.youtube.com/watch?v=2pJwDZXasKU) ~~~ Animats That was an interesting idea. Deere acquired them, and built a prototype.[1] But Ponsse's approach[2] was more practical. The dual chassis articulated 8-wheel system is unusual but very effective. A big problem with those heavy legged machines is very low road speed. The Ponsse machine is much faster when you aren't in difficult terrain, so you can get it to the job under its own power. Deere copied that and now makes those, too. [1] [https://agmetalminer.com/mmwp/wp- content/uploads/2012/04/wal...](https://agmetalminer.com/mmwp/wp- content/uploads/2012/04/walking_harvester_large.jpeg) [2] [https://www.youtube.com/watch?v=PE1f1GydafQ](https://www.youtube.com/watch?v=PE1f1GydafQ) ~~~ DoctorOetker The Ponsse machine: it would be cool if they could recover the gravitational potential energy of the tree for the cutting operations, say by storing the energy in a flywheel ------ jonah There was a walking logging machine developed by Finnish company Plustech Oy in the mid-nineties and later bought by John Deere who tried to commercialize it but it didn't meet much success. "[It] was designed with sensitive or by other means harder to reach terrain with minimum impact on the environment in mind." [https://www.youtube.com/watch?v=2pJwDZXasKU](https://www.youtube.com/watch?v=2pJwDZXasKU) [http://www.theoldrobots.com/Walking- Robot2.html](http://www.theoldrobots.com/Walking-Robot2.html) [http://www.unusuallocomotion.com/pages/museums/museum-of- lus...](http://www.unusuallocomotion.com/pages/museums/museum-of-lusto-in- finland-forest-machinery.html) (Near the bottom) ~~~ cr0sh The was also the OSU Adaptive Suspension Vehicle: [http://cyberneticzoo.com/walking-machines/1984-osu-asv- adapt...](http://cyberneticzoo.com/walking-machines/1984-osu-asv-adaptive- suspension-vehicle-mcghee-american/) [https://library.osu.edu/documents/university- archives/subjec...](https://library.osu.edu/documents/university- archives/subject_files/Adaptive%20Suspension%20Vehicle.pdf) ------ dmix I’ve always wondered how much money consultants made off the “cybernetics” buzzword in the 60s and 70s. ~~~ PhasmaFelis Was it a buzzword at the time? Stuff like this is actually closer to the original definition--very roughly, a system that uses continuous feedback loops to keep itself in a stable, functioning state--than to the way we use the word now. ------ timonoko Why are these walking machines always so slow? I think Neal Stephenson described a skateboard with hundreds of tiny feet, moving faster than wheels on any surface. I want to see that. ~~~ krapp Progress takes time, and ambulatory motion is a finicky, delicate nightmare that only seems simple in humans and animals thanks to millions of years of evolution. CAM was created in the 1960s[0], but BigDog[1] and other recent Boston Dynamics quadrupeds that aren't designed for human passengers are much faster[2], but still awkward. Also remember these are expensive prototypes designed to test things other than speed. Making them faster only guarantees that they break themselves harder when they run into a wall or trip over a cliff or something. [0][https://www.youtube.com/watch?v=ZMGCFLEYakM](https://www.youtube.com/watch?v=ZMGCFLEYakM) [1][https://www.youtube.com/watch?v=W1czBcnX1Ww](https://www.youtube.com/watch?v=W1czBcnX1Ww) [2][https://www.youtube.com/watch?v=3OKZ_n8QW4w](https://www.youtube.com/watch?v=3OKZ_n8QW4w) >I think Neal Stephenson described a skateboard with hundreds of tiny feet, moving faster than wheels on any surface. I want to see that. I am neither Neal Stephenson nor a physicist but I'm pretty sure the friction caused by the increased surface contact of "hundreds of tiny feet" versus wheels would still make the wheels faster and more efficient. Geckos and things can stick to vertical surfaces and move quickly because they're lightweight. Anything capable of sticking to an arbitrary surface _and_ supporting human weight is going to be slow. And if moving downhill, wheels don't really need to do work - gravity does the work. Something with "hundreds of tiny feet" either has to slide or "walk." ~~~ timonoko I disagree. Centipedes and other many-legged critters can move very fast. Every leg is just a tiny lightweight thing with its own balanced dynamics, just a part of a wheel basically. First thing that came to my mind is a plastic brush with flexible back. If you move a rollers along the back the bristles extend downwards and move backwards in a walking motion, just like a sea urchin does. Scale that and you have a walking machine moving amazingly fast. Tiny bristles yield and conform to any surface. ~~~ Qworg CWU's "whegs" are much in this vein: [http://biorobots.case.edu/projects/whegs/](http://biorobots.case.edu/projects/whegs/) ~~~ cr0sh I could also see Brook's Genghis platform being extended to "centipede" multiples of legs and probably working well. [https://en.wikipedia.org/wiki/Genghis_Robot](https://en.wikipedia.org/wiki/Genghis_Robot) EDIT: fixed mistake - put "Dante" but meant Genghis... ------ t0astbread It had force feedback. Did it have any sort of protection in the case of rapid movement of tge legs? ~~~ cr0sh I personally don't know if it did - I've never seen any information on operator safety of this machine, though I have read a lot about it and Ralph Mosher over the years. He's also the guy behind the GE Hardiman exoskeleton: [https://en.wikipedia.org/wiki/Hardiman](https://en.wikipedia.org/wiki/Hardiman) ...which was another system much like this truck. For that one - and I don't know how true it was - it was said that it could get into a feedback loop that could cause injuries to the user, but it wasn't clear if that was for the entire "suit" or for the mounted arm test assembly (they had built a single arm up to the shoulder and mounted it on a stand to test it separately from the "suit"). GE was heavily into this field of what they called "man amplifiers" \- several of the later ones spearheaded by Mosher: [http://cyberneticzoo.com/man-amplifiers/1953-g-e-o-man- manip...](http://cyberneticzoo.com/man-amplifiers/1953-g-e-o-man-manipulator- american/) [http://cyberneticzoo.com/man-amplifiers/1958-9-ge- handyman-r...](http://cyberneticzoo.com/man-amplifiers/1958-9-ge-handyman- ralph-mosher-american/) [http://cyberneticzoo.com/walking-machines/1962-64-ge- pedipul...](http://cyberneticzoo.com/walking-machines/1962-64-ge-pedipulator- ralph-mosher-american/) [http://cyberneticzoo.com/man-amplifiers/1965-g-e-lifting- boo...](http://cyberneticzoo.com/man-amplifiers/1965-g-e-lifting-boom-edwin-e- ziegler-ralph-mosher-american/) [http://cyberneticzoo.com/teleoperators/1969-g-e-man-mate- ind...](http://cyberneticzoo.com/teleoperators/1969-g-e-man-mate-industrial- manipulators-ralph-mosher-american/) This was also the same time period as Hughes Aircraft's MOBOT systems - which were meant as remote manipulators for working in nuclear research, underwater repaid, and similar harsh environments: [http://cyberneticzoo.com/teleoperators/1959-mobot-1-hughes-a...](http://cyberneticzoo.com/teleoperators/1959-mobot-1-hughes- aircraft-american/) [http://cyberneticzoo.com/teleoperators/1962-underwater- mobot...](http://cyberneticzoo.com/teleoperators/1962-underwater-mobot-hughes- aircraft-american/) [http://cyberneticzoo.com/teleoperators/1963c-mobot-hughes- ai...](http://cyberneticzoo.com/teleoperators/1963c-mobot-hughes-aircraft- american/) [http://cyberneticzoo.com/teleoperators/1964-%e2%80%93-mobot-...](http://cyberneticzoo.com/teleoperators/1964-%e2%80%93-mobot- mark-ii-%e2%80%93-hughes-aircraft-american/) What we now know as "ROVs" (and UAVs, UGVs, and other names) all stem from a lot of this research back then (and earlier). Hughes' system was actually kind of innovative; there is a paper you can dig up (in fact, I think it's linked on one of the above articles) that detail how these systems were controlled: They needed to control a lot of various servo and other actuators, but they couldn't use a long cable with tons of wires - they needed the cable to be flexible and not weigh a ton (which is still an issue today). But they didn't have the modern electronics we have today to accomplish it. What they ended up doing was using a synchronized motor-switching system that had two rotary switches driven by synchronous motors on both ends. There was a mechanism in place to keep them "in sync" so that the switch connected on one end would be the same as on the other end. The controller at the transmitter would thus be connected to the proper motor or actuator at the other end, many times a second, and the umbilical only needed a few wires (plus wires for power - which IIRC was AC and served as part of the sync system - plus wires for video feeds). In a way, it was an early form of electro-mechanical multiplexing. It quickly gave way to more electronic methods (likely things more closely resembling serial PPM, used in hobby radio control systems - once reliable transistors became common; while such a thing could have been done with vacuum tubes, it wouldn't have been reliable on such machines and environments) - but reading that paper was an interesting insight on how to do things differently! In fact, it's similar in scope to how Westinghouse did something similar for telemetry monitoring and control back in the 1920s and 30s - and showcased in their "robot" Electro - by using sounds and tuning forks, in a similar was to electrical coherer systems - they could control relays remotely using tones sent down telephone lines. Why Hughes didn't use a similar approach is a mystery - could have been patent reasons, or reliability issues or something of that nature. It's a fascinating period of history in robotics, control theory, computation, and more in my opinion (also at this time, you have a large interest going on in artificial intelligence - such as it was in those years - and deep behind the scenes, there was certain interest in so-called "artificial neurons" \- hardware implementations of the McCulloch-Pitts neuron model. At one time, around 1956 IIRC, RCA even made a "frog's retina" model using similar models - when you look at it and how it was wired and works - it really looks like a CNN made of hardware for image recognition... ~~~ t0astbread Hey, that's very cool. Thank you! ------ shireboy Discontinued when they realized the enemy could just fly around it’s feet with a tripwire. ;) Inspiration for the AT-AT? ------ bischofs Is this better than a Driving Truck? ------ rishabhd Metal Gear? : )	{ "pile_set_name": "HackerNews" }
Le Paper Globe: a do-it-yourself terrestrial globe - drewda http://joachimesque.com/globe/#1 ====== nekgrim EN link also available: [http://joachimesque.com/globe/index.html.en](http://joachimesque.com/globe/index.html.en) ~~~ oneeyedpigeon Site read my Accept-Language heading perfectly. ------ yellowapple Very nice! I'll have to try this out when I get home. ------ bengali3 very cool ! what are some of your ideas on customization? your ancestry/family tree overlayed? travel logs? historic airline route maps? Early explorer journeys? WW2 troop/invasions? starmaps? ------ bezaorj great activity to do with the kids! ------ Eleutheria Oh, beautiful! Can it be done with hexagons and pentagons like a soccer ball? It may get more rounded, but probably harder to assemble. ~~~ Luc It works rather well with triangles: [http://en.wikipedia.org/wiki/Dymaxion_map](http://en.wikipedia.org/wiki/Dymaxion_map)	{ "pile_set_name": "HackerNews" }
LSD — My Problem Child by Albert Hofmann - b-man http://www.psychedelic-library.org/child.htm ====== DCoder Late Syd Barrett of Pink Floyd was into LSD when his career went off the tracks. Such a shame, he was amazingly good. Another British band, Porcupine Tree, explored LSD in their early works, from "Lynton Samuel Dawson" to the amazing "Voyage 34", which includes the following remark: They're not drug addicts Wandering around, not knowing where they are They're your most creative, most courageous And like it or not, they're going to build you A new civilization...	{ "pile_set_name": "HackerNews" }
Google to Acquire Nest - coloneltcb http://investor.google.com/releases/2014/0113.html ====== MrZongle2 Am I the only one who thought "well, good for the Nest guys" followed by "too bad, it looked like a good product"? ~~~ psbp Yeah, motorola products have completely gone down the toilet after that acquisition. They were so great before with fast updates and a wonderful skin of android, and now they're either non-innovative or way too overpriced for the value. ~~~ arikrak Yeah, and like Android and Youtube. Sarcasm aside, Google has actually done pretty well with acquisitions compared to other companies. (Say ones that begin with "M" or "Y"). You can see the list in wikipedia: [http://en.wikipedia.org/wiki/List_of_mergers_and_acquisition...](http://en.wikipedia.org/wiki/List_of_mergers_and_acquisitions_by_Google) ~~~ Steko YouTube was fine when Google wrote checks and got out of the way. Now Larry and co. have their hands all over it and YT is slowly going to shit... from the G+ spam to the annotation spam and of course you need to sign in to keep them turned off (lol maybe!), to "hey let's make you rebuffer the whole video you just watched" to just horrid performance drops in general to "hey we found a way to make YT comments even worse". I can't feel that we'd be much better off if MS had decided to lose billions on YouTube along with Bing and Google had pressed ahead with Google Video as a legitimate competitor. ~~~ teh_klev "hey we found a way to make YT comments even worse" Could they get any worse? Seriously does any normal thinking person really participate and contribute comments in that quagmire? I sometimes I thank Google and Yahoo for creating those honey pots for the internet brain-dead to vent their steam and vitriol, keeping them well away from stuff I like to constructively participate in. ~~~ snogglethorpe Actually the comment quality on the videos I watch seems to have improved markedly since the G+ integration... Coincidence? No clue... Still, all the "OMG G+ will destroy youtube!1!" whining is looking pretty stupid... ~~~ jsight I agree... it is still horrible, but it seems to be slightly less horrible now. ------ tghw Given Google's history with acquisitions, as a Nest owner, I'm not thrilled to hear this. Hopefully they let it run as independently as possible. ~~~ VLM Google always shuts stuff down. Which is just a big laugh when its an internet application, but not so funny when its your thermostat. Anyone know what happens when GOOG shuts off the Nest system? Hopefully the thermostat reverts to at least a simple dumb mode rather than shutting everything off? ~~~ cloudwalking I doubt Google would shut down a $3,200,000,000.00 acquisition. ~~~ sliverstorm Please don't include decimals on that kind of number, it's intellectually dishonest. ~~~ Karunamon ? Only if you're incapable of telling the difference between commas and periods, I suppose. ~~~ sliverstorm It isn't _factually_ dishonest, because it is an accurate number, and anyone can make sense of it. I say it is _intellectually_ dishonest because it reads to me as a clear attempt to make the number appear more impressive. Borrowing from Wikipedia, "intellectual honesty": Facts are presented in an unbiased manner, and not twisted to give misleading impressions It would still be accurate to say it was a $3,200,000,000.000,000,000,000 valuation, but I hope you will agree this is misrepresenting information. ~~~ Karunamon Eh, guess we're going to agree to disagree there. Dollar figures having two decimal places at the end is pretty much a standard. If they included 3, yeah, that would reek of shiftiness. On top of that, all of the press releases I see don't even include the full amount written out, just "$3.2B". ------ nostromo I'm happy for Nest but sad for myself, given the smoke detector was my Christmas gift last year. Previously I would look to YouTube as an acquisition done right. But after the kerfuffle around G+ integration, I no longer feel that way. If I have to sign in with my G+ account to manage my smoke alarm, it's going directly into the rubbish bin. If Apple had bought Nest, on the other hand, I'd feel very differently. ~~~ Sanddancer Had Apple bought nest, you'd have to log into your icloud account to manage it, via your idevice, with no other management abilities available. Apple is absolutely horrible at playing well with others. ~~~ nostromo I'm ok with that. My issue with Google isn't Single-Sign-On, it's forcing every product into a social-network mold. Although I'm a happy user of Facebook and Twitter, I think SV's social obsession has largely been fruitless. Social does not improve most products and can actually harm them. And now I'm worrying about how "social" is going to be slapped on to my fire alarm. ~~~ Sanddancer You missed my point. If apple controlled nest, you'd almost certainly only get notifications if you were using an idevice of some sort. Apple's terrible about working with others to create industry standards; the AppleTV for example would be a lot more useful if it used DLNA for streaming instead of Apple's proprietary format. ~~~ ilyanep I think you're missing his/her point. The problem nostromo has is not proprietary formats but social networks. I think the worry is updates like "John Doe turned the temperature in his house to 75!" (and while that fear is overstated, it's not unreasonable to not want products that can detect the presence of humans in your bedroom connected to social networks). ~~~ psbp Google+ doesn't really have to be a social network. There's nothing social about my use of G+, and I use it pretty frequently. ------ jmduke The cynic in me shudders at the possibility of Google adding even more real- world data like temperature preference and lifestyle factors to their massive data portfolio. The idealist in me is incredibly excited at the possibility of Nest's fundamental strengths being bolstered by Google's coffers. ~~~ Karunamon Am I the only one that doesn't get chills up their spine whenever Google breaks into some new market? I see very little possible misuse of temperature preference (of all things...) and very great possible gains. The more intimately a service knows you, the more personalized and relevant data it can bring. And another thing, I am really sick and tired of tempering or being told to temper my enthusiasm for some new technology or some novel use of existing technology just because it might be misused. Just about every technology that's wide-reaching enough has abuse potential. That is not an excuse for ludditism! Deal with the abuse instead of hamstringing the tech. ~~~ chrisrhoden What about the ability to know when someone is in your home and when someone is not? If Google records that data (say, to be able to provide you with a handy chart of your energy use and some ways to improve it), the potential I am more worried about is the fact that the data exists makes it possible to subpoena. ~~~ wyager Exactly. I don't care if the government knows when I'm home (they can already figure that out), but imagine if Google's database of Nest info got leaked. Burglars could look at the database and say "Oh hey, look, no one's home right now." ~~~ vdaniuk Do you really think burglars could not get their hands on leaked government agency database? This is just another excuse to throw feces at Google, and HN commenters just don't miss any possible opportunity to do that. ~~~ diydsp strawman and goalposts. PP said google's database, not government databases. google data breach in last 30 days: [http://money.cnn.com/2013/12/04/technology/security/password...](http://money.cnn.com/2013/12/04/technology/security/passwords- stolen/) inside job at home security company in last year: [http://www.wbng.com/news/state/198129651.html](http://www.wbng.com/news/state/198129651.html) ~~~ sneaky_ruds Calling that a Google data breach is a pretty big misrepresentation; keyloggers installed on user machines collected passwords typed into a number of websites, including Google's. (disclaimer: I work for Google, have no special knowledge of the incident in question) ------ minimax "Google Inc. (NASDAQ: GOOG) announced today that it has entered into an agreement to buy Nest Labs, Inc. for $3.2 billion in cash." Can that be right? $3.2 billion? That's a crazy huge sum. ~~~ ActVen They have paying customers. It matters. ~~~ dangrossman Nest has customers who have paid it, it does not have paying customers. There is no ongoing fee despite every device Nest sells being connected to its servers 24/7/365\. It takes no more than ~3 seconds for any changes you make on their web/mobile apps to reach the thermostat, so it has to be at least checking in with a server constantly. ~~~ nknighthb Surely the updates are sent via some form of push. Polling on that scale would be obscene. ~~~ dangrossman Yet that's what I believe it does. Every few seconds, Nest sends an HTTP POST to their servers with its serial number. If there are any commands waiting for that thermostat (change temperature initiated from an app for example), they get sent in response, otherwise the connection is closed. ~~~ cbr That's the client pulling, not the server pushing. Pushing would be "when the owner makes a change on the website, notify the appropriate thermostat to change its settings". This would be way more efficient, but too many Nests aren't going to have suitable internet connections. ~~~ dangrossman Perhaps you misread "yet" as "yes". I'm curious if there's a power issue as well. I don't know how fast wifi can turn on/off and reconnect to a network. Nest has to be low-power as its only power source is one of the tiny wires from the HVAC system and that doesn't supply enough to run the device offline, let alone online. It uses that wire to charge an internal battery instead. ~~~ cbr I did make exactly that misreading; sorry! ------ k-mcgrady Very surprised Apple didn't purchase this. Headed by Tony Fadell, brilliant design, I thought it would fit and be a nice diversification for them. However it will be very interesting to see what Google does with this. If I put away the cynic in me for a moment: the more data Google has on me the better their services are for me. I could imagine the Nest thermostat integrating with Google Now and the location data Google has on me for example to better now my comings and going. ~~~ crucifiction Perhaps Google bought them because Apple did try to make a bid. Hence the inflated price... ~~~ easyfrag Apparently Google was the only serious bidder and Apple was not in the mix. Source: [http://recode.net/2014/01/13/google-acquires-nest- for-3-2b/](http://recode.net/2014/01/13/google-acquires-nest-for-3-2b/) ------ bradly Seriously not trying to troll, but could someone help explain where Google might see 3.2 billion dollars of value in a company that pretty much just sells a successful thermostat? ~~~ ctdonath Google's core competency: know everything. Look at anything Google does from that perspective. Each Nest will feed data (anonymized, of course / _cough_ /) back to Google so they'll know home heating patterns, heck, home usage patterns (it watches activity and proactively & predictively adjusts for when people are/aren't around). Feed vast amounts of that data into the cumulatively large (no adjective does it justice) data mining process and they'll know that much more about [m\|b]illions of people & locations. US$3.2B? In the USA alone that works out to $0.003 per person per day over 10 years (assuming everyone has a Nest device in the long run; optimistic calculation, but sets the ballpark values). ~~~ Daishiman Integration with Google Now would seem like the logical next step. ------ toddmorey Please, please Google... don't spam me about starting a Google+ account when I'm just trying to turn the temp down a few degrees. I beg you. ~~~ patrickaljord And I beg all HN users to stop doing Google+ jokes as they're just as unfunny as they're unoriginal. ~~~ ilyanep I'm not convinced they're as much jokes as real concerns by people who have already been burned by this (see: YouTube -- I'm not going to argue about whether or not G+ integration has made these products better, but it's not unreasonable to not want your real-name associated with comments you made under a pseudonym, and to be so annoyingly pestered to do so!) ~~~ aniket_ray Google+ is Google's social layer. Commenting is an inherently social activity and it makes sense to have a common layer i.e. G+ here to handle them. Changing the temperature is not a social activity. So no the jokes are not real concerns and are mostly silly intellectually lazy exaggerations. ~~~ taybin God forbid ------ callmeed FYI Google Ventures participated in 2 of Nest's funding rounds, including leading their series C last year. I can't say exactly if/how this affects the acquisition but it does feel like some of the money is just traveling in a circle. ------ uptown Smart buy in my opinion. The connected home has enormous untapped growth potential, and they just acquired a company that managed to take something as mundane as a thermostat and make it cool. ~~~ robg At least there's a cost savings angle to an intelligent thermostat. The connected smoke alarm as a cool object really amazed me - it's where new business models are made. ~~~ smackfu Exactly. Walk the aisles at your local home improvement store. Find every product that you interact with that is under $20. You can probably make that amazing for $50-100. And what's that in terms of how much people spend on houses? ~~~ robg It would be a fun list. Humidifiers have always annoyed me. ------ badclient Someone at google is thinking of ways to use Google Plus to fuck up Nest. ~~~ caprad Has google hired a lot of MBA's recently, because it look an awful lot like they are trying to cross-pollinate their main business lines, to improve vertical integration and uptake. ~~~ iamjustin It sure does. Hopefully they can find a way to optimize the backwards overflow which is sure accompany these changes. ------ agperson Argh, I was just about to buy some Nest Protects, but I don't want Google sensors built into my house. ~~~ mikeg8 Agree. sometimes it feels there is no escaping google's watch ------ ChuckMcM It's awesome for the folks at Nest, but the first thought through my head was this : I am so starting a smart lawn sprinkler controller company! ~~~ interpol_p Oh please do. Irrigation systems have the clunkiest, most error prone interfaces I have ever used. ------ mikegreen $3.2b makes me think there has to be some awesome technology that they own or pipeline, as I can't get excited about the thermostat. It is a great idea, and played with one a bit, but it isn't solving any large HVAC issues - the thermostat is simply an on/off switch for the real working hardware in your basement/outside. So, what else do they do that makes Google want to pay $3+ billion (pinkie to lip) for Nest? ~~~ maxerickson They have figured out how to do marketable home automation devices and how to navigate getting them certified by UL and the like. ------ jffry Coming soon: audio ads, broadcast throughout your home via your Nest Protect. Since it knows if you're moving, it can wait and play the ad when it knows you're there, allowing Google to charge a higher cost per impression. ~~~ smackfu Sounds silly, but people pay Tivo a subscription fee every month and they pack that thing full of ads. ~~~ Karunamon The only ads on Tivo that I can remember is a single line item on the home screen, and this was almost always for some VOD service. There was also the thumb integration (you could thumbs-up some ads from either live tv or your recordings, which would pull up a new page with info about whatever was being advertised, occasionally a video), but this is about as unintrusive as it gets (a small icon on the top right whenever a compatible ad is played). Has this changed in the newer revs? I'm honestly curious. ~~~ smackfu Yep. Here's the ad sales page which goes through all the various options, including showing ads on the pause screen and including ads when you delete a show and in the menu that lists your episodes of a show. It's gross. [http://www.tivo.com/tivoadvertising/](http://www.tivo.com/tivoadvertising/) (Your ad blocker may stop that page from working properly.) ~~~ Karunamon Auugh.. thanks for the heads up. I can cross a new Tivo off the list of things I want, then. Part of the reason I bought that device was to _skip_ ads... ------ hoopism The Nest UI (web and mobile) is laughable horrible. Only has about 2 weeks historical data. Doesn't record what means a temp was adjusted (web? Phone? Nest?). Doesn't do any sort of trending long term or historical analysis. Charts overlay clicking points so you can see some data. Doing my own analysis it ended up using more energy than my manual changes. So I don't even use autoschedule. ------ loganu It's not a talent acquisition. It's not a move towards more government monitoring. It's not meant to increase G+ sign-ups or sell ads for more efficient furnaces. It's a play into the growing "connected product" / smart home segment. When you combine google's resources, their current software and hardware products, and the type of products Nest is likely to move on to, you get some strong synergies that Google would be dumb to ignore. A little more discussion on where things could go from here (that doesn't touch on the NSA or government subpoenas) would be really refreshing. ------ molecule Coming Soon: Google+ Integration w/ Your Nest Thermostat ~~~ badclient No heat for you if you don't upload a profile pic. That will drive up engagement I bet. ~~~ sliverstorm _I 'm sorry Dave, I'm afraid I can't do that. Only users who use their real name on G+ are allowed to change the temperature_ ------ mesozoic The real winners are DST Global and the others who bought round D and got what looks like a 50% return on $150 million in about 2 weeks. ------ ThomPete For once I can understand the pricing and think its in fact cheap. 1) Nest has a realistic potential to be in "every" home if not the actual hardware then the underlying intelligence. 2) Nest has a business model that works. People are paing for it and they love it. 3) Combining Google data with Nest access points I can only imagine the awesome things they can come up with and improve. Perhaps the first glimpse at an intelligent grid system. 4) 3.2 is a steal and given that its cash its a good sale. ~~~ notacoward The only way Nest will have on in every home is by aggressively enforcing bogus patents against everyone who makes anything even remotely similar. We should cheer for that? ~~~ ThomPete I think you are missing the bigger picture here. It's not about the thermostat its about the ecosystem its part of. And I did write "every" :) ------ nodata Oh come on this has to stop. How much would it have cost Google to build Nest from scratch? Not 3.2 billion dollars. ~~~ angersock It's not the tech, it's the install/customer base. ~~~ pgrote How large is the installed base? It appears to be small for smart thermostats and even smaller for Nest. [http://thinkprogress.org/climate/2013/11/02/2877211/smart- th...](http://thinkprogress.org/climate/2013/11/02/2877211/smart-thermostats- poised-major-market-growth/) ------ outside1234 I'm really surprised. I thought Nest was Tony Fadell's vehicle to make it back into Apple. I am going to sit here with a bemused expression on my face thinking of Tony Fadell at data driven Google. I put it 6 months before he is out of there. ------ figital There's been a product on the market for several years called "TED" ... something seemed fishy when Google killed the data monitoring service ... [http://www.google.com/powermeter/](http://www.google.com/powermeter/). Still ... you have the power (so to speak) to meter your own appliances. Yes you. Mine is still in the box :(. ------ belgianguy smart phone > smart car > smart house > ... ? ... > smart human I for one see great areas of improvement and possibilities inside the common house. Not that I'd wire up _every_ appliance with a Wi-Fi sensor, but some data _can_ be useful, if only for safety (falling asleep with the oven on: here a sensor could cut the power at a certain condition, or trigger the fire alarm, or ring up the firefighters). Or you left the house and realise you left some of the lights on, just tell the in-car console to open the domotics app, and tell it to shut the lights off. And the smart fridge, if RFIDs or its successor ever become cheap enough to be able to be printed on a milk carton, you could have your fridge's contents with you wherever you go, just open the app, look what's about to go off, or have it remind you to get extra supplies when you're near a point of interest. If they'll let me I'll hook up a Nagios server to my coffee machine. ~~~ MartinCron I know this makes me sound like a terrible luddite or hipster or both, but I've been thinking about all of these smart devices and services and how they may have a somewhat infantalizing impact on people. I recently met with some people behind a startup built entirely around generating meal plans for you. I understand that it's a useful service (for some types of people). But I worry about the implication that we are now a species that _can 't even figure out what to eat_ for ourselves. ~~~ pgcosta We can figure out what to eat. But it takes time. Imagine that you want to personalize your diet. Take certain ammounts of protein, calories, fat, etc... It would take lots of time if you would prepare a weekly plan for yourself. Thats a good Idea. But I do feel what you'r expressing, like we need an app to do everything. But I much rather live with these little apps and have lots of good information than to live completly oblivious to everything like my grandads (kind'of. I still have my hippie moments). ~~~ MartinCron I don't know, it might be nudging you to being oblivious in a different direction. Encapsulation is generally about ignorance, and if you have a robot designing your macro-nutrient intake for you, then you can wind up oblivious to what is actually in your food. ------ jcampbell1 The only possible way this acquisition make sense is that Nest has some truly amazing product in the pipeline. It is impossible to justify 3.2 Billion for a team or thermostats. My guess is they wanted to get acquired because some future product make sense to have Google's brand and go to market ability. ~~~ venomsnake A friend is currently working for an intrusive home management solution that certain telecoms are to unleash on the unsuspecting Germans. All internet of things stuff, all remote. It will be sold with internet subscription. The root capabilities will be in telco and not the home owner. I am willing to bet a lot that Nest have either something similar or that google wants to spearhead this market and are scrambling with whatever the cost the know how. ------ wil421 So will they shut it down like they did when bought sparrow or bump? I thought sparrow was great for iOS and OS X. Googles gmail app is not as stable. Lately I've been concerned about google and privacy this make make me change my mind and just buy a competitors version of a "nest". The price is what has been keeping me away. ------ throwaway420 I wish we lived in a world where Google can be trusted with all of this personal data because they could do lots of interesting things to make lives easier and create more wealth for everybody. But I have every expectation that this data, if not right away, could someday be sent to the criminal gangs that wear suits and ties that are looking for new targets to loot and plunder. Just knowing the temperature in your house, cross-referenced with other data about you as well as electricity bills, could be enough for a future police agency to argue probable cause that you're running a drug growing operation and have them do all kinds of raids and intrusive searches and harassment. This shouldn't be an issue, but Google has earned absolutely zero trust with its obvious non-denials of NSA activity and other negative conduct. ------ dengar007 Now you can +1 your temperature! ~~~ mikeg8 oh jesus ------ ehfeng Google should have negotiated for a $3.141 billion price. ~~~ YokoZar The 60 million dollar joke. ------ lowlevel I have a feeling I'll be ripping the Nest off of my wall in no time. ------ angersock "We've noticed that you're currently freezing your toes off...would you like to search instead for 'HVAC'?" Fucking creepy. ~~~ sixothree I find this creepy as well. The fact I was considering purchasing one gives me an ill feeling now. ------ jusben1369 I think folks are too focused here on Google caring about the temperature in your house. I suspect Nest's hw/sw/design chops will come in very handy when putting together say the experience of a self driving car? ------ matmann2001 Great. Now I'll have to listen to an ad before my fire alarm goes off. ------ ck2 Do they own patents or something? Because with a $10 android chip, any Chinese plant could churn out Nest clones in a few months. ~~~ smackfu The tricky part is getting it on the shelves at Home Depot or Lowes. Nest threw a lot of money at Home Depot, if the dedicated end caps I've seen for the last couple of years are any indication. ~~~ tanzam75 Home Depot and Lowes both sell private-label home automation products. They could buy the equipment from the Chinese and slap their own brands on it. ------ 14th ... I'm glad I haven't bought one yet. Now I need to figure out how to build an open source one. ------ badman_ting Google offers you 3 billi, you take it. That's what I always say. ~~~ evanmoran You wouldn't take 3 billion from someone else?=) ------ Fogest Nest has a post on their blog about this as well if you're interested: [https://nest.com/blog/2014/01/13/nest-google-and- you/](https://nest.com/blog/2014/01/13/nest-google-and-you/) I am not sure why people always say Google makes companies suck. This may be the case sometimes, but it is that way for most companies who buy things if they try to make changes. Just look at YouTube. It has become quite successful, despite some poor decisions. ------ FiddlerClamp I'm relieved that Apple didn't buy them. In that case, they'd have certainly either a) discontinued the Android version, or b) created a cross-platform app like iTunes. ------ cmos Nest has built an expensive thermostat that is engaging. It certainly doesn't take $80 Million to do that. So perhaps they also spent their money developing a cheaper version after proving that people like it and more importantly proving it can save money and eventually pay for itself. I would spend a ton of money putting everything on one chip, getting the cost down to $5 or $10 for the same user experience. Maybe put in a cheaper display if needed. Now this wireless device in the house can pay itself off in very short amount of time, making it a super easy decision for consumers. The current offerings of thermostats are clunky and have horrible user interfaces that require modes and buttons and such to program.. forget about daylight savings time! If people can buy Nest functionality for $50 then google will have a solid foothold in people's homes. From that they can sell camera's that show up through your google TV device and get into the security market. The dial on Nest is a universal interface, as the original ipod has shown us, perfect for scrolling through menu's and long lists and for changing volume or choosing music. Might as well put a microphone in so people can ask the internet things. Still not quite sure it's worth $3.2Billion.. perhaps there was a bidding war? ------ bluthru Ugh, our industry needs more owners, not less. ------ smackfu Well, that should resolve their patent issues. ~~~ callmeed Elaborate? ~~~ smackfu Honeywell sued them. Google must have enough defensive patents to use against Honeywell to make them go away. Terrible, of course, but that's the way the world works. ------ suprgeek $3.2 BILLION All-Cash offer. Is that Color-level valuation for a Thermostat company? Or more like Instagram-level... Holy Moly! ~~~ cududa Nest has great hardware designers (which Google lacks) and engineers. Nest first built a hardware/ software platform that enables them to in the future build other smart appliances and home automation tools. The thermostat was simply the first product. ------ pessimizer I don't know a lot about Nest, but I understand that requests to the thermostat are made from the phone app indirectly through a central server? What possible consumer benefit could that indirection have? edit: The reason I ask is that I'm trying to figure out why an exact copy of Nest except that it didn't leak data and didn't require other people's servers to work wouldn't eat Nest's lunch. ~~~ ceejayoz I used that indirection to turn the heat up for my cat while on vacation, knowing that a big ice storm was coming. Couldn't do that if it only worked on the LAN. ~~~ mdda Actually puzzled : Why would the cat need it warmer indoors if there's an ice storm? Isn't keeping it at the same temperature enough? Or is the problem because the heating switches off overnight, so you feel that it needs a boost during the day to compensate? Isn't that something that a smart thermostat should cope with? ~~~ ceejayoz Boosting it means if the power goes out for a few hours and the temperature drops 20 degrees in the house it goes from 70 to 50, not 50 to 30. Protects the pipes, too. ------ pinaceae well, stick in a fork in Nest then. wonder how bad their financials were when they're already selling. fucking SnapChat refused a FB offer, but Nest just rolls over and dies. ~~~ clarky07 What you meant to say was that nest isn't run by idiots that are stupid enough to turn down a 3 billion dollar offer. ~~~ pinaceae well, but for a moment it seemed that fadell really wanted to build something great and lasting, building his own vision. turns out it's just another boring let's get rich story. ------ achy This might be a minority opinion, but I think more than home data collection (which they probably have a lot of already from phone / computer usage), that this is about acquiring a company that has cache and a 'cool' factor within both the design world and more importantly the market sector of young tech inclined home owners - a hugely lucrative market. ------ ivv Theoretically, Google could now be remotely adjusting your room temperature to maximize (or minimize) the effectiveness of advertising. [1] [1] [http://anzmac.info/conference/2013/bestpapers/anzmac2013-364...](http://anzmac.info/conference/2013/bestpapers/anzmac2013-364.pdf) ------ abvdasker I hate to be that guy, but I think if Google's plan really is to tackle tech in the home, it probably isn't going to work out. The attempt to better integrate technology with common household devices and appliances is nothing new [1]. Most of the previous attempts over the last 20 years have have been met with limited success. The biggest obstacle is and has been that most of the utilitarian devices in homes already do their jobs pretty well. They're also inexpensive. What does Nest/Google have to offer that won't be more expensive and will present some life-changing advantage over a conventional stove/thermostat/garage door opener? [1] [http://www.internetnews.com/xSP/article.php/1489021](http://www.internetnews.com/xSP/article.php/1489021) ------ sdoowpilihp This will give Google access to a very idiosyncratic data set no other major tech company has. It will be interesting to watch how they influence the product line over the coming years, as well as what they do in terms of integration with other google services. ------ noonespecial In a not-so-strange way this fits well with their recent robotics acquisitions. It really feels like lightning could strike a second time for google so long as they don't middle manage themselves out of it. ------ andrewhillman Wow. This weekend I was talking about Nest with my dad and I said Google will end up buying them. Interesting to see that it's an all cash transaction. I guess all cash makes the deal cheaper for Google. ------ dorfsmay So that means you'll have to have a google plus account, older than 13, and use an interface that use a protocol that replaces snmp but that is propriwtary to google, just to change the twmperature? ------ deeviant So perhaps being able to dissect nearly every aspect of a users online life is not enough for Google, now they want to offer a range of devices that can start recording the minucia of everyday home life. ------ lauradhamilton As a Nest owner this creeps me out. Google should NOT have always-on sensors of any type. ------ keithg Finally a tech company with enough good sense to realize that if you get a buyout offer that starts will "b" and ends with "illions", you take the money! ------ ericcumbee On one hand google having more information is unsettling but at the same time it could lead to some interesting possibilities. In the summer my nest kicks the AC on at about 4:45 assuming that I will get home sometime around 5pm. But say I go afterwork to have a beer or drink coffee and stay out until 8pm. Nest knowing where my phone is means it could be smart enough to not turn my AC on until I am headed home. ------ cocoflunchy $3.2 billion? ~~~ samsnelling Yep. Think of it as 3.2 instagrams. ~~~ bandris Or 2 youtubes. ------ jmuguy Hmm, I wonder if this will make a security system (like canary [http://www.indiegogo.com/projects/canary-the-first-smart- hom...](http://www.indiegogo.com/projects/canary-the-first-smart-home- security-device-for-everyone)) more or less likely. I assumed that would be the next product from Nest. ------ BIair On the face, appears to be a huge valuation for an overpriced thermostat and smoke alarm. But combined with their recent robotic acquisitions I wonder if this signals a move beyond the smart phone, and smart car, to the smart home? If Google engineers want to build the Star Trek computer, surely they want to build the Jetsons home. ------ granttimmerman Well, I guess that's one reason/excuse why Nest turned me down a summer internship when I applied last November. ------ outside1234 When do we start getting ads on the Thermostat? Or ads on our browser asking us why we are spending so much time at home? ------ jerdavis This doesn't make a whole lot of sense to me. Besides the fact that Nest is a great product (But so are Triscuits), why would Google buy them? The Nest _does_ know when you are home. If Google starts to use Nest data to target adds at me, I'm going to rip it out, set it on fire, and mail it to Larry. ------ HorizonXP All I can say is that KPo is a beast, and he's totally why Google paid such a large sum of money for Nest. ------ callahad Time to add thermostats and smoke detectors to all those blog posts about "de- Googling" your life... ------ fudgy73 $3.2 BILLION?! Was Nest Labs making a profit? Seemed to me like they made cool devices that no one bought. ~~~ dangrossman They were shipping 50k thermostats a month over a year ago. Combine a heat-up in home automation interest this year with some very fancy endcaps they've placed in Home Depot (the thermostat and smoke detector, with interactive demo videos), they're probably selling much better today. ------ protomyth I was hoping Honeywell would buy them an experience a bit (at the division level) of a NeXT-Apple replay. I really am not sure about buying one given the implications of the data from this device being given to advertisers or used in advertising analytics. ------ mikeg8 "To change the temperature of your master bedroom, please create a google+ account." ------ Cub3 Maybe we'll finally see Android @ Home become a reality [http://techcrunch.com/2012/06/24/what-happened-to-android- at...](http://techcrunch.com/2012/06/24/what-happened-to-android-at-home/) ------ Luke-Jr Maybe Google will push Nest to comply with the GPL terms? They're currently missing the (required by GPLv2) build/install stuff from their source code releases... I've been unable to get root on mine so far :( ------ bitwize Oh great. You have set a temperature of 65°F. Share your climate preferences your Google+ circles? ------ cleaver My thought on the topic, after being shocked at the price, was that Apple must have some home automation products as their next big thing. 3.2B to head off Apple from creating the "iPod of home automation" is still a bargain. ------ tsenkov Was there anything similar (as an amount of cash in the deal) in the last 10 years? Probably Microsoft's acquisition of Nokia's phone division? Is there a list somewhere, that would be interesting to see. ------ eyeareque "It smells like you've burned your dinner. Would you like to order Dominos for delivery?" I love my nest. I hope they do good things with the brand. I'll admit.. I am fearful for what they'll do with it. ------ rhythmvs Well, then we should have a better look at [http://www.loxone.com/](http://www.loxone.com/) and maybe so keep our actual real-life data out of black box data centers. ------ vikas5678 With all the data google already has on me, as a new homeowner, I think I'm terrified of buying this product. What kind of profile would this allow Google to build on individuals? ------ blueskin_ Suddenly I no longer want one. I loved the idea when it was a simple way to save on power bills, but I wouldn't have google spy on me even if I was paid money to use it. ------ subndes Google now able to collect more data points about your home too! ------ abhi3188 After a look at Google's smart house experiment in London, I think it's safe to say, their next lot of acquisition targets will be home automation companies. ------ dpeck Woohoo, I look forward to it disheartening into Mountain View and only being used to control the HVAC at HQ and be shown off to board members on their quarterly tours. ------ jyz 3.2 billion is an insanely large number. But then when you step back and see Snapchat being offered the similar amount, you kind of feel sorry for Nest for selling. ------ spiderPig Nice acquisition, but $3.2 bn?? Really? Just unbelievable. ------ WWKong This proves that the market for "better mouse trap" is huge. Look around the house. Pick something. Anything. Create a better version. ------ jd007 what a great way to force g+ on users even more. "too cold and want to increase your temperature? add 3 friends to your circles!" ------ baweaver So YouTube didn't work as a G+ promoter, so now we'll have to log into our houses with it. Well played Google, well played. ------ benwerd Do other large tech companies not realize what Google's up to, are they unable to try to compete, or do they just not care? ------ pgcosta I understand why this is a good aquisition, but still 3.2B... The valuation was 'only' 2B. That escaleted a lot! ------ pirateking I look forward to well designed Nest competitors that support connections and logging to user specified endpoints. ------ elwell "OK Google, flush the toliet." ------ kgarten I guess in future I'll need a google+ account to adjust the temperature in my house ... :) ------ regnum Good thing the Google founders have grown up and don't need adult supervision anymore. ------ oscargrouch a sign that google is horny for the "internet of things" :) ------ andyman1080 Is it known how much equity Faddell had? Is he a billionaire now? ------ sushirain Google + Nest + Boston Dynamics + Ray Kurzweil = Domestic Robot? ------ baweaver So will I need to sign into my house with a Google+ account now? ------ sidcool Isn't Google trying to spread too thin? I feel so. ------ jpswade Great. Now there's another Google product that will never hit the UK. ------ forgotAgain Google with (new) data sources in my house: hmm. ------ aaronpeck Remember Sparrow? ~~~ everydaypanos sure ------ michalu Yes, now we can have even more relevant ads!! ------ ffrryuu Bailing out the VC already? ------ skizm You must now login with your G+ account to turn on your thermostat or smoke detector. ------ jgalt212 oh, no. there's definitely no bubble. ------ mmuro Bummer.	{ "pile_set_name": "HackerNews" }
Guess What? Everyone Was Wrong About Tesla - booleanbetrayal https://www.forbes.com/sites/enriquedans/2018/10/28/guess-what-everyone-was-wrong-about-tesla ====== rurban Current talk is that Musk's (Boring) LA Tunnel project is mostly hypeware, that he cannot hold the promised date at all. Opening should be December 10. That should have been the 2 mile Hawthorne along Interstate 405 to Westwood segment, but it looks like it's just a short 3/4 mile segment to the Dodgers stadium. [https://electrek.co/2018/10/22/elon-musk-boring-company- laun...](https://electrek.co/2018/10/22/elon-musk-boring-company-launch- tunnel-december/) Will see how that will affect Tesla and SpaceX.	{ "pile_set_name": "HackerNews" }
Ask HN: How do I learn functional DevOps as a cofounder? - muonic I am in the very early stages of developing a venture with a colleague in my PhD cohort (in computer science). He works in CS theory and lacks a lot of actual functional tech skills (he only took one programming internship during his undergrad), whereas I am only slightly better off (my research is in machine learning; I have approx. two years of full time experience at FAANG companies and regularly write Python code for my research).<p>Essentially, we are planning to try to package a recent development in our research as a B2C (web)app. Neither of us have any experience in this type of development; I currently do most of the coding on the research end of the code, whereas he has been handling more of the nontechnical aspects. We are planning on hiring a developer to build the webapp but personally I would have qualms with not having strong knowledge of both the webapp stack as well as the deployment, so I am currently on planning on learning some basic devops so I can oversee deployments and infrastructure as we slowly scale.<p>I have a few questions that I would really appreciate anyone's insight into:<p>(a) Would it be a mistake to outsource the development of our webapp for a long period of time (say, ~6 months) without anyone on our team acting in a CTO role? I will be continuing to develop the backend core of our product in Python, but I know nothing about web development and have no desire to learn.<p>(b) Can anyone recommend good resources for someone looking to handle the devops of their product? Is this too ambitious of a task for someone with no experience in such things? I know my way around Git pretty well, but have never properly worked with CI tools, AWS/GCP/Netlify/etc, or anything of that nature. ====== de6u99er Good DevOps are people with lots of experience in software development, architecture, and infrastructure automation (and the lack of automation). This can not be learnt quickly. IMHO you're looking for someone like me who would rather work for one week day and night on automating something than investing a couple of hours every once in a while to do or have someone else doing it with manual interventions. Just so you understand what I mean by that. I have 20 years of professional software and data engineering experience, had to manage my own infrastructure when I was working for a small consulting company, or had to cut (or circumvent) lots of red tape at a big pharma company when dealing with infrastructure admins to automate my projects, built my onpremise software defined compute and storage cluster. And I learn programming languages as a hobby. Nevertheless, here's some links that might be a good starting point: [https://about.gitlab.com/devops/](https://about.gitlab.com/devops/) [https://www.dummies.com/business/operations- management/devop...](https://www.dummies.com/business/operations- management/devops-for-dummies-cheat-sheet/) [https://landscape.cncf.io/](https://landscape.cncf.io/) (I might add more as reply to this comment) ------ de6u99er My other comment was about your second question (b). About your first question (a) I think it would be a mistake to just outsource it without good oversight. An Austrian saying which IMO answers your question best comes to my mind "Wer nichts weiß, muß alles glauben!" which translated to English means "Who doesn't know anything, has to believe everything.". Means you want to know if good decisions are being made. ------ nelsonic Hi @muonic, this is a great question many people tech founders face. The short answers to your questions are: a) Don't hire someone else to build the "core" of your App; only you know _exactly_ what you want/need. If you have Python skills, build it yourself using the tools you already know (e.g. [https://www.djangoproject.com](https://www.djangoproject.com) ) Deploy it to Google App Engine [https://cloud.google.com/appengine](https://cloud.google.com/appengine) and side-step the DevOps learning curve. b) Decide which Platform as a Service (PaaS) is right for you given the type of App you are building and learn that _after_ you have a working demo of your App. Longer explanation: If you hire someone _inexperienced_ (i.e. "cheap") to build your App, you can almost guarantee that you will need to scrap and rebuild it much sooner. Inexperienced developers will skip fundamental software engineering principals like automated testing, following security best practices or documentation and code-reuse. Build the MVP yourself and then bring someone onto your team once you have a good setup in place and need to add features. When you are building an "MVP" of an App, you _really_ don't want to be thinking about infrastructure; it's a distraction. Use Heroku, Google App Engine or Firebase to handle everything for you and focus on the _features_ of your App that users will want (and ideally pay for). As @de6u99er noted, DevOps is not something you can learn in a hurry. There isn't one _single_ book you can read to learn everything you need to know. There are too many unknown-unkowns when you combine creating an App from scratch and thinking about the infra. If you can ask a friend or former work colleague to help you with DevOps _after_ you have built the MVP you will have a much clearer idea of what is required. You can share an App running on your localhost with people online using a tool like Ngrok see: [https://github.com/dwyl/learn- ngrok](https://github.com/dwyl/learn-ngrok) And when you are ready to deploy it, ask the Internet how to do it (people on HN are very helpful) and you can learn that specific subset of DevOps. Write a _log_ of everything you learn e.g: [https://github.com/dwyl/learn- devops](https://github.com/dwyl/learn-devops) so that everyone on your team knows how your system works. Once you out-grow the _manual_ approach to DevOps, consider automating it. But right now, DevOps is very much "YAGNI" [https://en.wikipedia.org/wiki/You_aren%27t_gonna_need_it](https://en.wikipedia.org/wiki/You_aren%27t_gonna_need_it)	{ "pile_set_name": "HackerNews" }
Question for all Riders... - CanDoco Where do you storage your bicycle at home? ====== nmcfarl Now I have a walk in basement, it’s leaning against the wall. In my old place, a second story walk up, it hung from the wall in the hallway, between the bedroom and the bathroom. In my wife’s old place, she had her’s chained to the porch railing, and mine joined it when I stayed over. \-- I’d curious as to why you want to know…. ~~~ CanDoco I just wanted to recommend a cool gadget I got for the wifey, called the Click-Base. being married to a woman who collects bicycles like stray dogs it really made a difference in our bike storage. (www.bicyclick.com) ------ dagw My apartment building has a locked bike room. ~~~ CanDoco Sweet!	{ "pile_set_name": "HackerNews" }
I Hate Voicemail - pitdesi http://thoughtcatalog.com/2011/i-hate-voicemail/ ====== decode I know some people like the author, people who never listen to their voicemail. I call and leave them a message and they call me back without listening to it. When they do this, they are communicating to me that their time is more important than mine. I am often just conveying information and I have to say it twice if they don't listen to the message. That's fine if it's a salesman cold-calling you. If it's a friend or family member, that's insulting. There are a number of other reasons to use voicemail: 1) Everyone can speak faster than they can text. If you have a significant amount of information to convey, texting sucks. Voicemail can be very efficient. 2) Many people don't have unlimited texting plans and texting can get expensive quickly. 3) Texting is dangerous and illegal while driving in many places, while speaking and listening on the phone are often not illegal and definitely less dangerous. ~~~ dlsspy > 1) Everyone can speak faster than they can text. If you have a significant > amount of information to convey, texting sucks. Voicemail can be very > efficient. Voicemail is potentially efficient for the sender at the cost of the recipient's ability to understand what you're rambling. My phone lets me SMS via voice. I can send a concise, planned message. The recipient can receive something that uses his time most effectively. > 2) Many people don't have unlimited texting plans and texting can get > expensive quickly. I turned mine off in favor of a data plan and use that for SMS. > 3) Texting is dangerous and illegal while driving in many places, while > speaking and listening on the phone are often not illegal and definitely > less dangerous. Speaking and listening to a phone while driving is dangerous and illegal without digging out and hooking up a headset, while waiting until you stop is not illegal and definitely less dangerous. ~~~ stevelosh > Speaking and listening to a phone while driving is dangerous and illegal > without digging out and hooking up a headset It's still just as dangerous, even with the silly headsets. Multiple citations in the first paragraph of the "Handsfree device" section here: [http://en.wikipedia.org/wiki/Mobile_phones_and_driving_safet...](http://en.wikipedia.org/wiki/Mobile_phones_and_driving_safety#Handsfree_device) ------ kovar You lost me with the first line: "Leaving someone a voicemail message on someone’s cell phone in 2011 is not only misguided, it’s selfish." If you don't want to get voicemail, don't offer it as an option to your callers. I get really bent out of shape by people who expect that everyone trying to reach them by <insert communication medium here> will follow their personal, and unpublished, rules. We all use <insert communication medium here> in different ways, and most of the mediums are designed to be flexible, thus appealing to more users. Don't attribute malice, or selfishness, to other users of the medium who are using it in the way it was designed. If you don't want people to leave a VM, say so. If you don't listen to your VMs, say so. If you don't want people to leave a long VM, say so. ------ wewyor Just as an alternative point of view: I probably won't call you back just because of a missed call if you don't leave a voicemail as I'll think whatever you were calling about wasn't important or if it was you will call back later. I use Google Voice on my android phone and though it doesn't always update right away it does mean I don't have to call a voicemail number and log in to hear my messages I just press play. ------ jerrya I don't listen to voicemail, but it is rude not to accept it just as it is rude to leave long messages on voicemail. The caller has already connected with you, for you to tell them to then hangup and try again with a txt or email is pretty obnoxious and arrogant. I don't listen to voicemail, because I have googlevoice. ------ darklajid I agree fully. First of all 90% of my voicemail messages suck and follow this universal script: \- "Oh.. Erm.. It's XXX. I tried to reach you" \- Babbling, most are not used to a one-sided talk and get lost \- After listening the conversation could've been compressed to half a text message. Unfortunately the business phone I have is required to support a voicebox. Worse: German carriers tend to abuse these things to milk their customers. The cheaper the carrier, the more certain you can be to have a mandatory (no way to turn it off. Calling your own box costs money..) mailbox that answers after X rings, where X is usually small enough that I can reach my wife only on the second try (before she pulls out the device the voicebox answers). What a rant. I guess I have a deep sympathy for all people that hate this voicebox thing.. ------ Flemlord I'm notorious for never returning voice mails for the exact reasons expressed in this post. But two months ago I signed up for Google voice it largely fixed the problem. The text recognition is bad, but I can usually figure out who called me and that's all I need. The only outstanding issue is that my phone (WP7) doesn't always update the Google Voice tile that lets me know I have new messages. Not sure if that's an issue on other phones. ------ bconway While I agree with the premise that voicemails that provide no additional information are not useful, the author is an elitist jerk. That being said, callers generally have no idea if you aren't answering because you're not near your phone, or because your phone is off/without reception/on a plane, in which case the call notification would never appear. Google Voice does a good job of solving this by includes notifications for missed calls, but everyone else has no way of knowing they missed a call. ------ pronoiac I wonder if there's a way to deconfigure voicemail completely. Someone noticed that on a friend's phone & sort of envied them having "one less inbox." [1] [1] [http://a.wholelottanothing.org/2011/04/three-phone-tips- for-...](http://a.wholelottanothing.org/2011/04/three-phone-tips-for- antisocial-people-like-me-that-hate-phones.html) ------ lukejduncan Personally, even if I get voicemails I tend not to listen to them - just return the call. If my phone rings I find myself feeling a little stressed. I'm usually in the middle of something that I don't want to be pulled away from for more than a minute. Phone calls always imply they will last longer than you want. ------ tomjen3 I don't hate voice mail - I hate people who use it without understanding how to. Half my messages are .... crackling .... dut dut dut ------ paul9290 I agree voicemail is pointless. Just send me a text message, email or Instant message. ------ ChrisArchitect while reading this I was afraid of what conclusion the author was going to reach -- but a vm message that says 'txt or email me' is great -- amen! ~~~ pavel_lishin That seems redundant. If I get a voicemail that says, "text or email me" - isn't that basically saying, "i was trying to get in touch with you, please reciprocate" - which is already made implicit by the fact that you have a missed call because someone was trying to get in touch with you? At that point, don't even leave a voicemail. I never do - they'll see that they missed a call and call me back, or I'll try again later - or I'll send them a text or an email! ~~~ stevelosh I'm pretty sure the OP is taking about having the RECEIVER'S message mention texting/emailing, e.g.: ring... ring... ring... "Hi, this is Steve. I'm not here right now. If you could text or email me instead of leaving a voicemail that would be much appreciated." ~~~ ChrisArchitect yep really I find VM is just a 'medium' choice, and one that I don't prefer, but maybe my callers would at the time. Sometimes it's just easier to ramble on about something instead of typing. But VM is by no means instant, don't expect a reply in any soonish timeframe. That's what IM/txt is for. Email and VM might as well be the same...non-current issues. ------ the-kenny In soviet russia, voicemail leaves messages for you.	{ "pile_set_name": "HackerNews" }
ICANN delays .Org sale approval, calls for more transparency - patrickdavey https://domainnamewire.com/2019/12/10/icann-delays-org-sale-approval-calls-for-more-transparency/ ====== CaliforniaKarl I suggest changing the post URL to be the source ICANN post, [https://www.icann.org/news/blog/org- update](https://www.icann.org/news/blog/org-update) The only content added by the original URL ([https://domainnamewire.com/2019/12/10/icann-delays-org- sale-...](https://domainnamewire.com/2019/12/10/icann-delays-org-sale- approval-calls-for-more-transparency/)) is a link to the webcast meeting referenced in the PDF letter linked in the ICANN blog. It is [https://domainnamewire.com/2019/12/10/video-watch-the-qa- wit...](https://domainnamewire.com/2019/12/10/video-watch-the-qa-with-ethos- internet-society-and-pir/) ------ tinus_hn Now ICANN can show its true colors. Is this just more smoke and mirrors just so they can absolve themselves of responsibility while still sheepishly approving this heist when the drama has had time to die down? Or will they act and relieve PIR of the stewardship of the .org tld?	{ "pile_set_name": "HackerNews" }
Google: warlord in a world of bandits? - razorburn http://whimsley.typepad.com/whimsley/2010/01/google-as-warlord.html ====== andreyf One has to appreciate, however, that Google seems to seek out economic positions which allign their interests with the overall social interest. Surely, that isn't just happenstance. ------ mynameishere Google: World-class PR. That's it. When something really hits their bottom line they will literally have no choice but to behave like every other corporation. ~~~ BerislavLopac Actually, they already do. I've read an interview with their CFO a while back, and he said that a large majority of the company does traditional, non-cool corporation stuff. It is only trhe production department that does things in a hip way, and they're doing everything they can to publicize that, as you say. ------ berntb The fascinating idea here, is to consider the model of "warlord" as applied to a political party in elections.	{ "pile_set_name": "HackerNews" }
Income tax on stock for original founders? - markcray2 A scenario:<p>Person launches startup, takes seed funding from angel investor at creation of company. Angel owns 60% for their capital contribution, Founder owns 40% solely for their future sweat contribution, no cash upfront.<p>Yes or No: The IRS sees the 40% ownership of the new company for the Founder as taxable income because the units are being given to the founder as payment for services being rendered...?<p>If Yes (which is what my advisors are telling me) — how do people deal with this tax liability? Do most founders put themselves (if their angel doesn't care one way or another) on a vesting schedule just to help spread out the tax burden over a few years?<p>Or is there some strategy of legal avoidance that I'm unaware of? ====== mlinsey First - founders should always be on a vesting schedule, just like everyone else. This schedule should be laid out in the founder's agreement. This isn't for tax reasons but in the case you have multiple founders and one of them leaves. Second: giving 60% to an Angel investor is way too much, but I presume you picked a random number as an example. If you plan to raise a larger round later (from a VC etc), you should get a convertible note, where the Angel doesn't get a set amount of shares but rather the right to convert the note into $(amt invested) * (discount rate) at the time of the next round. Third: Yes, you need to pay taxes on your stock as it vests. You should talk to your attorney about what's called the 83(b) option to mitigate this tax liability. Given that your stock is worth very little you should have minimal liability. Fourth: I presume you just stated this scenario as a hypothetical and you haven't actually started a company and done this, much for the above reasons and what other comments have said. Do your advisors have experience launching/guiding a successful startup company before? ------ tlrobinson Let me preface this by saying I really have no idea what I'm talking about. But... Equity is not considered "income". The only time you get taxed is when that equity is sold, in which case it's taxed as capital gains (if you've held the equity for longer than one year). Capital gains tax in the US is 15%, so it's a pretty good deal. The bigger problem I see here is the angel taking 60-freakin-percent of the company! That's a huuuge chunk of the company for an angel investment. At the end of the day, you're not going to be left with much. ~~~ ojbyrne As previously mentioned, the 83(b) election is the key thing. It just means you elect to get taxed on the stock when it is sold rather than when it's received. ------ epi0Bauqu _I am not a lawyer, so don't listen solely to me._ No. 1) You shouldn't be giving up 60% in an angel round. 2) If the company is brand new, the shares should be worth essentially 0, which means you should be paying like $1 for them. 3) Your situation isn't entirely clear, but it seems that there is no taxable income here. You will have to pay capital gains taxes when you sell your shares, however. 4) If it is restricted stock (e.g. vesting), there is a tax issue. It is simple to deal with, however. Like others' have pointed out, you need to do a an 83(b) election. It is a simple one page thing, but you have to do it in a timely fashion. So look into it now. If you don't, you will get taxable income as your stock vests, which in most cases, is not what you want. The reason you don't want this is you will have to pay taxes on "phantom income," i.e. on taxable income that isn't associated with associated cash flow. ------ markcray2 I apologize if some things were not clear. The situation described is hypothetical; while I appreciate everybody's concern about my giving away too much, the numbers here are made up, no deal has gone through, etc. I think the 83(b) election is what I was looking for here. And yes, I'm _definitely_ on the hunt for a new financial advisor/CPA, my current one is not up to snuff here. (The simple fact that they didn't mention the 83(b) possibility raises red flags.) Asking the question here is simply to get some unfiltered, unbiased advice so that I have more to go off of when evaluating advisors, because yes, this is my first time taking on outside investment. Where people are stating that the company value is essentially zero; if anybody has any links to throw out regarding how to value a company that has only taken a angel round, I would appreciate it. The "equity is not income" argument; I've been told that my equity has to be given to me in exchange for something—just being the "founder" doesn't cut it. Since they're given to me in exchange for my services, it's considered taxable income. Thanks for all the great feedback/conversation, I really appreciate it. ------ dcurtis You gave an angel 60% of your company? You don't know if you will be taxed on your 40% contribution, and yet you already went through with the deal? Your advisors are unable to answer your fairly simple questions? Something is wrong here... ~~~ wright It's probably family, not a formal investor. ------ sohail You're doing it wrong. Talk to a real-live accountant. ------ paul9290 Yes that is way too much of a percentage of your company to give up! Anything below 50% you lose the majority vote (try to keep 60% or more, if possible) and your idea due to you being a minority may get changed. In turn and in the long run your startup becomes a job rather then a passion!	{ "pile_set_name": "HackerNews" }
Show HN: An optimized and ergonomic image annotation platform - gingahbread31 https://www.picsell-ia.com/ ====== fonfon31 Looks good, is the usage of the tools unlimited ? ~~~ gingahbread31 Annotations are unlimited and you got 1000 calls of the tools for free during your trial ! ~~~ fonfon31 Ok thanks	{ "pile_set_name": "HackerNews" }
Show HN: My first Wordpress template in 5 years. Feedback, please? - astrowilliam http://www.wilwaldon.com/claire ====== astrowilliam I consider this a basic blogger template, nothing too fancy, just good and solid. This thing has been sitting on my "to do" list for a while and I decided to crank it out to get it out of my head. Any feedback would be appreciated, thank you. ------ DrScump [http://wilwaldon.com/403.shtml](http://wilwaldon.com/403.shtml)	{ "pile_set_name": "HackerNews" }
Drone Strikes Hamper Apple Watch Deliveries in Pakistan - herbig http://www.nytimes.com.clonezone.link/apple_watch_drone_strikes ====== _comlag I fell for this...	{ "pile_set_name": "HackerNews" }
Software for Programming Microbes - jcr http://www.technologyreview.com/printer_friendly_article.aspx?id=27025 ====== jcr For those interested, the linked _Nature_ article has more details. [http://www.nature.com/nature/journal/vaop/ncurrent/full/natu...](http://www.nature.com/nature/journal/vaop/ncurrent/full/nature09565.html)	{ "pile_set_name": "HackerNews" }

Subsets and Splits

No community queries yet

The top public SQL queries from the community will appear here once available.