chosen
int64 353
41.8M
| rejected
int64 287
41.8M
| chosen_rank
int64 1
2
| rejected_rank
int64 2
3
| top_level_parent
int64 189
41.8M
| split
large_stringclasses 1
value | chosen_prompt
large_stringlengths 236
19.5k
| rejected_prompt
large_stringlengths 209
18k
|
|---|---|---|---|---|---|---|---|
6,824,084 | 6,822,908 | 1 | 3 | 6,822,792 | train | <story><title>Fold the DOM like paper</title><url>http://oridomi.com/</url></story><parent_chain></parent_chain><comment><author>dmotz</author><text>Author of OriDomi here. Really excited to see this at the top of HN.<p>I recently pushed out version 1.0 with some new features that make OriDomi easier to use.<p>It now has an internal queueing system so you can chain up effect sequences instead of dealing with callback handlers. [1] What looks like a chain of synchronous calls will now be deferred and sequenced automatically, e.g.:<p>folded.curl(50).collapse().setSpeed(2000).stairs(-29).foldUp().unfold();<p>Secondly, OriDomi elements are now fully responsive, meaning they adapt to changing dimensions caused by media queries, window resizing, etc. You can see this behavior with the demos by resizing your browser, or on the current iteration of my personal site. [2]<p>Finally, there are two new methods that make it easy to do custom folding behavior and content manipulation, .map() [3] and .modifyContent() [4]. The former lets you pass your own function to define folding based on input angle and panel index.<p>It&#x27;s still relatively lightweight with zero dependencies and 7.6KB gzipped and minified. More than anything, a testament to what you can do with the modern browser API.<p>Looking forward to seeing what else people do with it. Check out the annotated source [5] for a look at how it works.<p>[1] <a href="http://oridomi.com/#queueing" rel="nofollow">http:&#x2F;&#x2F;oridomi.com&#x2F;#queueing</a><p>[2] <a href="http://oxism.com" rel="nofollow">http:&#x2F;&#x2F;oxism.com</a><p>[3] <a href="http://oridomi.com/#custom" rel="nofollow">http:&#x2F;&#x2F;oridomi.com&#x2F;#custom</a><p>[4] <a href="http://oridomi.com/#content-manipulation" rel="nofollow">http:&#x2F;&#x2F;oridomi.com&#x2F;#content-manipulation</a><p>[5] <a href="http://oridomi.com/docs/oridomi.html" rel="nofollow">http:&#x2F;&#x2F;oridomi.com&#x2F;docs&#x2F;oridomi.html</a></text></comment> | <story><title>Fold the DOM like paper</title><url>http://oridomi.com/</url></story><parent_chain></parent_chain><comment><author>vanderZwan</author><text>Funny coincidence, I just started a casual discussion about origami and programming with some friends yesterday:<p><i>So, my friend Torsten (who is really into papercraft and origami) explained to me the purity hierarchy within the papercraft community.</i><p><i>At the bottom is having to cut the paper and use glue in your creations. One level above that is if the form requires only cutting or tearing. Getting more and more pure is the form known as kirigami, which involves cuts but is made from a single sheet of paper as the base. At the top is origami - no glue, no cuts, only folds (although I&#x27;m not sure if there is such a thing as higher order origami), and ideally only one sheet of paper.</i><p><i>The comparison with functional programming (&quot;no glue and cuts&quot; and &quot;no state&quot;) is so obvious I&#x27;m surprised I&#x27;ve never seen it in the wild - maybe because programming has more in common with algebra, whereas origami is geometric?</i><p>Although mostly unrelated to this library, we <i>can</i> conclude that some of the effects in OriDomi should be in a section called KiruDomi. ;)<p>Actually, from a usability perspective, I see a problem with using those effects, like &quot;twist&quot; and &quot;fracture&quot;: once scrambled, it is not obvious from the shape in which way to drag to unfold again, unlike with an effect like &quot;stairs&quot;</text></comment> |
18,216,305 | 18,216,155 | 1 | 2 | 18,215,112 | train | <story><title>Will cable TV be invaded by commercials? (1981)</title><url>https://www.nytimes.com/1981/07/26/arts/will-cable-tv-be-invaded-by-commercials.html</url></story><parent_chain><item><author>plaguuuuuu</author><text>You really have a TV on each machine at your gym? This is peak America</text></item><item><author>jdofaz</author><text>My gym has guideless basic cable on the cardio machines. Anytime I channel surf I would estimate more than 50% of the 70ish channels are running commercials. Same when i stay at a hotel with cable. I’m surprised anyone is still willing pay for this.<p>Thankfully the new machines at my gym have Netflix.</text></item></parent_chain><comment><author>sumedh</author><text>&gt; You really have a TV on each machine at your gym? This is peak America<p>Some of the gyms in Melbourne Australia have TVs on all the treadmill machines. I am talking about normal gyms not some high end fancy gyms.</text></comment> | <story><title>Will cable TV be invaded by commercials? (1981)</title><url>https://www.nytimes.com/1981/07/26/arts/will-cable-tv-be-invaded-by-commercials.html</url></story><parent_chain><item><author>plaguuuuuu</author><text>You really have a TV on each machine at your gym? This is peak America</text></item><item><author>jdofaz</author><text>My gym has guideless basic cable on the cardio machines. Anytime I channel surf I would estimate more than 50% of the 70ish channels are running commercials. Same when i stay at a hotel with cable. I’m surprised anyone is still willing pay for this.<p>Thankfully the new machines at my gym have Netflix.</text></item></parent_chain><comment><author>sildur</author><text>It is common in pretty much any developed country.</text></comment> |
30,329,431 | 30,329,559 | 1 | 3 | 30,328,941 | train | <story><title>My Wife Was Dying of Brain Cancer. My Boss at Amazon Told Me to Perform or Quit</title><url>https://www.motherjones.com/politics/2022/01/i-was-an-amazon-staffer-i-finally-had-enough-when-my-wife-was-dying-and-i-was-told-to-perform-or-quit/</url></story><parent_chain></parent_chain><comment><author>gregdoesit</author><text>&quot;I felt like it didn’t matter what I said or what I did. He was going to get me out. I can’t tell if it was because of taking family leave. He basically had decided that he was going to let me go, regardless.&quot;<p>Amazon managers often have target URAs (unregretted attrition) to hit, around 6% per year in an organization. They are incentivized to fire people who don&#x27;t perform, regardless of the reason. If they don&#x27;t do it, someone else on their team might have to go. If they cannot hit URA targets, those managers could become targets to let go as URA.<p>This is a well-known tradeoff within most tech circles on the risk of working for Amazon. Unlike Netflix, who are clear about a similar policy (though without targets) Amazon does not advertise that they have internal URA targets externally.<p>I&#x27;ll also add that from the outside, this setup has worked surprisingly well for Amazon for well over a decade - based on business results and how they became one of the most valuable companies in the world. However, as this policy is more known and stories like the author&#x27;s surface, it&#x27;s starting to hurt their brand in ways that hurts their hiring and is forcing them to have to pay more to hire (&quot;would you take job A or job B that pay the same, knowing that 6% of people per year are fired at job A being Amazon?&quot;)</text></comment> | <story><title>My Wife Was Dying of Brain Cancer. My Boss at Amazon Told Me to Perform or Quit</title><url>https://www.motherjones.com/politics/2022/01/i-was-an-amazon-staffer-i-finally-had-enough-when-my-wife-was-dying-and-i-was-told-to-perform-or-quit/</url></story><parent_chain></parent_chain><comment><author>socialdemocrat</author><text>Problem with policies like this is that it creates zero employee loyalty. You will not feel bad about leaving them at a time which hurts them because you know they would never have your back. Thus you will not have theirs either.<p>Japanese managers have remarked on this problem in the US when hiring. You cannot easily invest in employees in the US. Investing in training reduce the amount of salary you are able to pay, so people leave as soon as they have training for a better paid job which doesn’t offer training.<p>Of course Japan is perhaps a bit extreme in this area but as a Scandinavia I have observed the same problem with fellow Scandinavians working in the US. Many remake on the natural loyalty you have been raised with slowly evaporating under US work conditions.</text></comment> |
10,945,797 | 10,945,563 | 1 | 2 | 10,944,795 | train | <story><title>Show HN: Super Mail Forward, an HTML email that evolves as you forward it</title><url>https://medium.com/@hteumeuleu/super-mail-forward-an-email-that-evolves-as-you-forward-it-84466596f30d</url></story><parent_chain></parent_chain><comment><author>ldom22</author><text>This is great for pranks: you send a serious looking email to someone, and then they forward it to someone else thinking they sent some chart or whatever but the next receiver instead sees another picture of your choosing</text></comment> | <story><title>Show HN: Super Mail Forward, an HTML email that evolves as you forward it</title><url>https://medium.com/@hteumeuleu/super-mail-forward-an-email-that-evolves-as-you-forward-it-84466596f30d</url></story><parent_chain></parent_chain><comment><author>shimon</author><text>TL;DR: A series of markup and styling hacks that exploit HTML interpretation quirks of various web email services can be hacked to intentionally vary message appearance between services. Coupled with forwarding, which further transforms the email using service-specific quirks, you can make a game where different paths of forwarding across services trigger different appearances.<p>Fun hack! I feel like there should be some clever practical applications but I&#x27;m drawing a blank.</text></comment> |
40,552,637 | 40,552,279 | 1 | 2 | 40,551,260 | train | <story><title>Signal: Will leave the EU market rather than undermine our privacy guarantees</title><url>https://twitter.com/mer__edith/status/1796508893822238881</url></story><parent_chain><item><author>somenameforme</author><text>That Tweet links to this [1] description which, in glancing at the text, seems to indeed be accurate:<p>----<p>According to the latest draft regulation dated 28 May (Council document 9093&#x2F;24), which is presented as “upload moderation”, users of apps and services with chat functions are to be asked whether they accept the indiscriminate and error-prone scanning and possibly reporting of their privately shared images, photos and videos. Previously unknown images and videos are also to be scrutinised using “artificial intelligence” technology. If a user refuses the scanning, they would be blocked from sending or receiving images, photos, videos and links (Article 10). End-to-end encrypted services such as Whatsapp or Signal would have to implement the automated searches “prior to transmission” of a message (so-called client-side scanning, Article 10a). The initially proposed scanning of text messages for indications of grooming, which is hardly being used to date, is to be scrapped, as is the scanning of voice communication, which has never been done before. Probably as a concession to France, the chats of employees of security authorities and the military are also to be exempted from chat control.<p>----<p>Strange times we live in. Entertaining, but strange.<p>[1] - <a href="https:&#x2F;&#x2F;www.patrick-breyer.de&#x2F;en&#x2F;majority-for-chat-control-possible-users-who-refuse-scanning-to-be-prevented-from-sharing-photos-and-links&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.patrick-breyer.de&#x2F;en&#x2F;majority-for-chat-control-p...</a></text></item></parent_chain><comment><author>astrobe_</author><text>Article 12 of the declaration of Human Rights :<p><i>No one shall be subjected to arbitrary interference with his privacy, family, home or correspondence, nor to attacks upon his honour and reputation. Everyone has the right to the protection of the law against such interference or attacks.</i><p>Bugging communications by investigators with special approval is already an exception to this principle. Government bodies that make sure that laws conform to the constitution should veto any exception broader than that, so this draft <i>should</i> basically be pointless.<p>It feels like there are social&#x2F;political mechanisms at work that allow that to however happen. They pave the road to Hell little by little, one stone at a time, and this is neither strange nor entertaining. To me, the beginning of this century has similarities with the beginning of the previous, which is quite worrying.</text></comment> | <story><title>Signal: Will leave the EU market rather than undermine our privacy guarantees</title><url>https://twitter.com/mer__edith/status/1796508893822238881</url></story><parent_chain><item><author>somenameforme</author><text>That Tweet links to this [1] description which, in glancing at the text, seems to indeed be accurate:<p>----<p>According to the latest draft regulation dated 28 May (Council document 9093&#x2F;24), which is presented as “upload moderation”, users of apps and services with chat functions are to be asked whether they accept the indiscriminate and error-prone scanning and possibly reporting of their privately shared images, photos and videos. Previously unknown images and videos are also to be scrutinised using “artificial intelligence” technology. If a user refuses the scanning, they would be blocked from sending or receiving images, photos, videos and links (Article 10). End-to-end encrypted services such as Whatsapp or Signal would have to implement the automated searches “prior to transmission” of a message (so-called client-side scanning, Article 10a). The initially proposed scanning of text messages for indications of grooming, which is hardly being used to date, is to be scrapped, as is the scanning of voice communication, which has never been done before. Probably as a concession to France, the chats of employees of security authorities and the military are also to be exempted from chat control.<p>----<p>Strange times we live in. Entertaining, but strange.<p>[1] - <a href="https:&#x2F;&#x2F;www.patrick-breyer.de&#x2F;en&#x2F;majority-for-chat-control-possible-users-who-refuse-scanning-to-be-prevented-from-sharing-photos-and-links&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.patrick-breyer.de&#x2F;en&#x2F;majority-for-chat-control-p...</a></text></item></parent_chain><comment><author>riedel</author><text>Will my email client using SMIME have to implement this? Seems kind of ridiculous.<p>Seems to be targeting platforms. Will it be illegal to send encrypted texts, what is keeping anyone from using crypto on top of existing messaging?<p>While I do not want to dive into any details on adverse effects of such stupidities, the EU seems to be actually taking a strange road to tech dependent overengineered regulation. It seems that this mostly driven by lobbyists that want to sell compliance services. Also it seems that there is more value in creating regulation rather than making sure it is enforcible.</text></comment> |
35,773,230 | 35,772,170 | 1 | 2 | 35,771,994 | train | <story><title>Krita: A professional free and open source painting program</title><url>https://krita.org/en/</url></story><parent_chain><item><author>pmayrgundter</author><text>I used to use Gimp for photoshop type operations but it&#x27;s become unusable for me due to slowness, even with a M1 native build. No idea what&#x27;s up.<p>Tried Krita and it works great</text></item></parent_chain><comment><author>hirako2000</author><text>Same. I find gimp even lagging behind photoshop which itself can be a clog. A shame since Gimp is a fantastic app.<p>Krita is a complete replacement at this point. And, its features caters to drawing&#x2F;painting to a greater degree than photoshop, by far. The brush engine is phenomenonal and just for this has become my favorite drawing tool.<p>Two tools into one. Snappy fast even on OSX, and feels very much native visually.<p>Tip: Veikk manufactures great 8192 pressure sensitivity A4 size tablets for about 40 to 60 bucks. Packed with extra nibs and everything . Krita and this obscure made of tablets plugged onto a commodity laptop is the best value artist station for all sort of digital work.</text></comment> | <story><title>Krita: A professional free and open source painting program</title><url>https://krita.org/en/</url></story><parent_chain><item><author>pmayrgundter</author><text>I used to use Gimp for photoshop type operations but it&#x27;s become unusable for me due to slowness, even with a M1 native build. No idea what&#x27;s up.<p>Tried Krita and it works great</text></item></parent_chain><comment><author>scetron</author><text>Agreed. Just made the switch over to Krita from Gimp for some simple workflows. Everything feels much faster across Mac, Windows, and Linux. Also the tools somehow make a bit more sense out of the box.</text></comment> |
23,366,937 | 23,366,999 | 1 | 3 | 23,366,788 | train | <story><title>I Can't Breathe</title><url>https://blog.citigroup.com/2020/05/i-cant-breathe/</url></story><parent_chain><item><author>dahfizz</author><text>Pretty bold of Citi to publish something like this. I wish more companies had the balls to do something like this... Not just some &quot;Yay equality!!&quot; Tweet, but a real and specific stance. Kudos.</text></item></parent_chain><comment><author>javajosh</author><text>My cynical brain is working overtime finding a flaw in this statement, or the angle from which it is selfish, and it&#x27;s failing. One of the things I like about it is that its personal, not a company statement. Its a risk for them, though, and I am also, reluctantly, impressed.</text></comment> | <story><title>I Can't Breathe</title><url>https://blog.citigroup.com/2020/05/i-cant-breathe/</url></story><parent_chain><item><author>dahfizz</author><text>Pretty bold of Citi to publish something like this. I wish more companies had the balls to do something like this... Not just some &quot;Yay equality!!&quot; Tweet, but a real and specific stance. Kudos.</text></item></parent_chain><comment><author>brodouevencode</author><text>IDK, I’m a little more skeptical of this post. It seems more posturing than actually effecting change. CFOs have other means of doing that, in better ways than a simple blog post. This is no different than the celebrity cause du jour tweet except that it’s coming from a business leader rather than some actor&#x2F;actress&#x2F;pop star. Let’s see this CFO use their connections and influence to make things better in real ways.</text></comment> |
21,715,925 | 21,715,432 | 1 | 3 | 21,714,284 | train | <story><title>Is Arm ready for server dominance?</title><url>https://www.scylladb.com/2019/12/05/is-arm-ready-for-server-dominance/</url></story><parent_chain><item><author>derefr</author><text>&gt; I can&#x27;t pull out my visa card and go buy a (atx, microatx, mini-itx) format motherboard for an ARM CPU, the CPU itself, RAM, etc, and build a system to run debian, centos, RHEL, ubuntu whatever on.<p>The difference between ARM and x86 is that there&#x27;s no standardized ARM interface between the motherboard and the CPU—no ARM equivalent to ACPI. Every integration of an ARM CPU into a board is bespoke. So you have to buy &quot;a board with an ARM CPU on it&quot;, not just an ARM CPU and board separately.<p>But, if you relax that restriction, it&#x27;s not like it&#x27;s hard to acquire &quot;a board with an ARM CPU on it.&quot; 80% of single-board computers (e.g. the Raspberry Pi) are &quot;a board with an ARM CPU on it.&quot; You can wipe pretty much any Android device (not just phones, but also HDMI &quot;streaming boxes&quot;, which are a convenient form-factor for basing a workstation on) and install Linux on them. There are also some higher-end development&#x2F;SDK boards for ARM embedded systems, like the Nvidia Jetson. What more do you need?</text></item><item><author>walrus01</author><text>My concern about this is that with the failure of Qualcomm Centriq, there is no industry standard&#x2F;affordable&#x2F;easy to buy ARM based server platform ordinary persons and small&#x2F;medium sized businesses can acquire.<p>It&#x27;s great that Amazon has ARM based stuff, but it&#x27;s something proprietary they&#x27;re purchasing in large quantities from a manufacturer they have a very close relationship with. Undoubtedly the physical hypervisor platform and motherboard these things are running on is something totally bespoke and designed to Amazon&#x27;s unique requirements.<p>I can&#x27;t pull out my visa card and go buy a (atx, microatx, mini-itx) format motherboard for an ARM CPU, the CPU itself, RAM, etc, and build a system to run debian, centos, RHEL, ubuntu whatever on.<p>This means that, sure, you can get an EC2 ARM based server, but it&#x27;s something you can&#x27;t physically own and you&#x27;ll be paying cloud based service rates forever if you want to keep running it. There are some categories of business and government entities where not having things on-premises, or fully owning and controlling the hypervisor all the way down to the bare metal, is a non starter.<p>If the ARM platform Amazon is buying becomes truly price&#x2F;performance competitive with a single&#x2F;dual socket xeon or threadripper&#x2F;epyc, it also gives a possible competitive advantage to Amazon over any medium-sized cloud based VM provider out there currently selling (xen, kvm) based VMs on x86-64 hypervisors.<p>Based on what&#x27;s available on the market right now I see no signs of there being a viable hardware-purchasing alternative to Intel or AMD based motherboards and CPUs.</text></item></parent_chain><comment><author>als0</author><text>&gt; The difference between ARM and x86 is that there&#x27;s no standardized ARM interface between the motherboard and the CPU—no ARM equivalent to ACPI. Every integration of an ARM CPU into a board is bespoke. So you have to buy &quot;a board with an ARM CPU on it&quot;, not just an ARM CPU and board separately.<p>Not exactly true. ARM server chips do have ACPI. The trick is buying a CPU that is SBSA[1] and SBBR[2] compliant. Then most things work as expected.<p>[1] <a href="https:&#x2F;&#x2F;static.docs.arm.com&#x2F;den0029&#x2F;a&#x2F;Server_Base_System_Architecture_v3_1_ARM_DEN_0029A.pdf" rel="nofollow">https:&#x2F;&#x2F;static.docs.arm.com&#x2F;den0029&#x2F;a&#x2F;Server_Base_System_Arc...</a><p>[2] <a href="http:&#x2F;&#x2F;infocenter.arm.com&#x2F;help&#x2F;topic&#x2F;com.arm.doc.den0044d&#x2F;Server_Base_Boot_Requirements_1_2.pdf" rel="nofollow">http:&#x2F;&#x2F;infocenter.arm.com&#x2F;help&#x2F;topic&#x2F;com.arm.doc.den0044d&#x2F;Se...</a></text></comment> | <story><title>Is Arm ready for server dominance?</title><url>https://www.scylladb.com/2019/12/05/is-arm-ready-for-server-dominance/</url></story><parent_chain><item><author>derefr</author><text>&gt; I can&#x27;t pull out my visa card and go buy a (atx, microatx, mini-itx) format motherboard for an ARM CPU, the CPU itself, RAM, etc, and build a system to run debian, centos, RHEL, ubuntu whatever on.<p>The difference between ARM and x86 is that there&#x27;s no standardized ARM interface between the motherboard and the CPU—no ARM equivalent to ACPI. Every integration of an ARM CPU into a board is bespoke. So you have to buy &quot;a board with an ARM CPU on it&quot;, not just an ARM CPU and board separately.<p>But, if you relax that restriction, it&#x27;s not like it&#x27;s hard to acquire &quot;a board with an ARM CPU on it.&quot; 80% of single-board computers (e.g. the Raspberry Pi) are &quot;a board with an ARM CPU on it.&quot; You can wipe pretty much any Android device (not just phones, but also HDMI &quot;streaming boxes&quot;, which are a convenient form-factor for basing a workstation on) and install Linux on them. There are also some higher-end development&#x2F;SDK boards for ARM embedded systems, like the Nvidia Jetson. What more do you need?</text></item><item><author>walrus01</author><text>My concern about this is that with the failure of Qualcomm Centriq, there is no industry standard&#x2F;affordable&#x2F;easy to buy ARM based server platform ordinary persons and small&#x2F;medium sized businesses can acquire.<p>It&#x27;s great that Amazon has ARM based stuff, but it&#x27;s something proprietary they&#x27;re purchasing in large quantities from a manufacturer they have a very close relationship with. Undoubtedly the physical hypervisor platform and motherboard these things are running on is something totally bespoke and designed to Amazon&#x27;s unique requirements.<p>I can&#x27;t pull out my visa card and go buy a (atx, microatx, mini-itx) format motherboard for an ARM CPU, the CPU itself, RAM, etc, and build a system to run debian, centos, RHEL, ubuntu whatever on.<p>This means that, sure, you can get an EC2 ARM based server, but it&#x27;s something you can&#x27;t physically own and you&#x27;ll be paying cloud based service rates forever if you want to keep running it. There are some categories of business and government entities where not having things on-premises, or fully owning and controlling the hypervisor all the way down to the bare metal, is a non starter.<p>If the ARM platform Amazon is buying becomes truly price&#x2F;performance competitive with a single&#x2F;dual socket xeon or threadripper&#x2F;epyc, it also gives a possible competitive advantage to Amazon over any medium-sized cloud based VM provider out there currently selling (xen, kvm) based VMs on x86-64 hypervisors.<p>Based on what&#x27;s available on the market right now I see no signs of there being a viable hardware-purchasing alternative to Intel or AMD based motherboards and CPUs.</text></item></parent_chain><comment><author>floatboth</author><text>&gt; no ARM equivalent to ACPI<p>The ARM equivalent to ACPI is ACPI.<p>ACPI is not &quot;between the board and CPU&quot;, it&#x27;s &quot;between the OS and the computer&quot;. Which is actually much more important. Writing drivers for bespoke PCIe, USB and SATA controllers is not fun. ACPI standardizes configuration of these things.</text></comment> |
15,825,107 | 15,823,659 | 1 | 2 | 15,820,987 | train | <story><title>Drone Maker D.J.I. May Be Sending Data to China, U.S. Officials Say</title><url>https://www.nytimes.com/2017/11/29/technology/dji-china-data-drones.html?_r=0</url></story><parent_chain><item><author>GCU-Empiricist</author><text>Considering that China has the great firewall due to it&#x27;s government censorship I&#x27;m a bit shocked to see this as the top comment. The United States has distasteful problems with ubiquitous monitoring, but implying it is equivalent to China seems like failing to consider that there are qualitatively different levels of totalitarianism.</text></item><item><author>crappybird</author><text>All android phone are definitely sending data to United States. Why is sending data to one country better than sending data to another?<p>For US citizens, this might be irrelevant (not so much if we go by the leaks). But for everyone living anywhere else on the globe, owning a smartphone means usually owning an endpoint for one of the giant corporate data sinks which its government can easily access.<p>I understand that it is the price I have to pay for a free (sic) OS and play services. But I use it because of a lack of viable libre and open alternative.<p>And I have about as much choice as someone in the market for a decent quadcopter unwilling to send data to China.</text></item></parent_chain><comment><author>TaylorAlexander</author><text>I don’t fully understand your argument. Because China has the great firewall they’re worse? I don’t really see how the firewall relates to surveillance in this way. I agree the firewall is a human rights issue in the way that US prisons are a human rights issue, but I’d be hesitant to say that because China is bad in this one way, the fact that they perform surveillance is made worse. The US is the global leader in surveillance as far as I’m aware. We keep 0-day backdoors in computer hardware that was designed here, and there’s some uncertainty as to whether we arranged for those backdoors or only found them (NSLs make it difficult&#x2F;impossible to know).<p>Further you dismiss the parent comment as implying the US and China’s surveillance are equivalent, but I don’t see that as the claim. There is a lot of shocked surprise in the news when we find that China is doing something we don’t like with our data or computers, but we ignore that the NSA builds massive data centers for data on the global population, we kill people based on that data, and we also engage in a global hacking war. And I think it’s important to make sure that when we talk about China, we’re also willing to talk about the US. If we never talk about what we do, someone else’s bad behavior will look warped.<p>The US and China are not equivalent, but it’s hard to talk about one fairly in this context without mentioning the other.</text></comment> | <story><title>Drone Maker D.J.I. May Be Sending Data to China, U.S. Officials Say</title><url>https://www.nytimes.com/2017/11/29/technology/dji-china-data-drones.html?_r=0</url></story><parent_chain><item><author>GCU-Empiricist</author><text>Considering that China has the great firewall due to it&#x27;s government censorship I&#x27;m a bit shocked to see this as the top comment. The United States has distasteful problems with ubiquitous monitoring, but implying it is equivalent to China seems like failing to consider that there are qualitatively different levels of totalitarianism.</text></item><item><author>crappybird</author><text>All android phone are definitely sending data to United States. Why is sending data to one country better than sending data to another?<p>For US citizens, this might be irrelevant (not so much if we go by the leaks). But for everyone living anywhere else on the globe, owning a smartphone means usually owning an endpoint for one of the giant corporate data sinks which its government can easily access.<p>I understand that it is the price I have to pay for a free (sic) OS and play services. But I use it because of a lack of viable libre and open alternative.<p>And I have about as much choice as someone in the market for a decent quadcopter unwilling to send data to China.</text></item></parent_chain><comment><author>justinjlynn</author><text>As though the invasion of privacy might be acceptable depending on who&#x27;s committing the act... and how much or how often they do it and for what reasons. If it unjust, it&#x27;s unjust; it doesn&#x27;t matter if its China or any of the Five Eyes members doing it, it&#x27;s still just as wrong.</text></comment> |
19,135,016 | 19,134,649 | 1 | 2 | 19,133,026 | train | <story><title>The Psychological Trap of Freelancing</title><url>https://www.thecut.com/2019/02/why-freelancing-creates-anxiety-about-money.html</url></story><parent_chain><item><author>photoguy112</author><text>I went from hourly, to per project, to weekly billings. When I charged hourly I ended up working A LOT more than 9-5. Per project work was good but I ended up losing a lot of prospects in the quote. Since many of my projects ran into the 20-40k range, my closing rate was 1&#x2F;10 (already pre-screened, what I deemed as high quality prospects). This made me feel like crap. Instead of per project, I decided to increase the rate, so now a project may be 30-50k+, figure out how many weeks it may take me to complete it (rough idea, but this is not important) and then divide into a weekly rate. What ended up happening is me tripling my hourly rate and invoicing weekly. This was game changing for closing leads, now my rate is probably 8&#x2F;10. You get all the benefits of having to work a lot less but charging a lot more. I will be honest, some days I feel like shit (who doesn&#x27;t) and I don&#x27;t work at all. I don&#x27;t feel bad because on the days that I feel fantastic I get into the zone and knock out a TON of work and usually get ahead. Client sees progress weekly and they are happy. It helps them that they don&#x27;t have to pay a ton of money in 2-3 payments and can spread it over the course of months.<p>In terms of happiness, freelancing definitely comes in flavors. There is the grunt work, the highly paid freelancer, the consultant and the product-based business until you go full startup or large company. I have seen all tiers. Currently I am a step short of having my own product while I figure out what that will be. You definitely need business acumen and people skills to succeed in the consultant stage. For product business you gotta go a step beyond that and either do really well as a consultant to bootstrap, or just work your ass off to get it going. My advice for anyone in freelancing now, who does not have people skills and gets latched onto hourly work, you may want to reconsider your choices. Freelancing can be highly stressful and demoralizing, unless you take the steps to go into consulting or beyond. It&#x27;s a ladder, just like your corporate gig, you gotta do the work to move up or suffer where you are stuck.</text></item></parent_chain><comment><author>porker</author><text>&gt; I went from hourly, to per project, to weekly billings<p>I have tried all three, read all the HN favourites on why value pricing is the way; tried charging for roadmapping; and yet I come back to the most stressful of day-rate (hourly by any other name), unable to break this in 15 years of technical consulting.<p>Why? Because with per project billing I was losing 30-50% as client expectations were different to mine. When I added 30-50% to the prices, I didn&#x27;t win the jobs. I could write a spec 80 pages long (which no client would pay for) and still there were variances which cost me.<p>On my current $50k+ project I&#x27;ve got the client to bear the risk because he&#x27;s the worst client for cost overruns I&#x27;ve had, and it&#x27;s on a time and materials system. However because he has no more money than the top range of estimates, and because he wants everything and more, I feel trapped and as stressed as if it was fixed price (which it&#x27;s turning out to be).<p>It feels like I am missing something obvious that other developers&#x2F;consultants have got. I want to price on value so I&#x27;m not stressed about every minute&#x27;s productivity. My clients want fixed price so the risk is stacked on me; they won&#x27;t&#x2F;can&#x27;t do sprints (often because their board of directors won&#x27;t approve it, even if they say they see the benefits); and the projects are unique systems each time, so the estimation is not accurate.<p>I freelance&#x2F;consult because it pays well, but this way of working sucks.</text></comment> | <story><title>The Psychological Trap of Freelancing</title><url>https://www.thecut.com/2019/02/why-freelancing-creates-anxiety-about-money.html</url></story><parent_chain><item><author>photoguy112</author><text>I went from hourly, to per project, to weekly billings. When I charged hourly I ended up working A LOT more than 9-5. Per project work was good but I ended up losing a lot of prospects in the quote. Since many of my projects ran into the 20-40k range, my closing rate was 1&#x2F;10 (already pre-screened, what I deemed as high quality prospects). This made me feel like crap. Instead of per project, I decided to increase the rate, so now a project may be 30-50k+, figure out how many weeks it may take me to complete it (rough idea, but this is not important) and then divide into a weekly rate. What ended up happening is me tripling my hourly rate and invoicing weekly. This was game changing for closing leads, now my rate is probably 8&#x2F;10. You get all the benefits of having to work a lot less but charging a lot more. I will be honest, some days I feel like shit (who doesn&#x27;t) and I don&#x27;t work at all. I don&#x27;t feel bad because on the days that I feel fantastic I get into the zone and knock out a TON of work and usually get ahead. Client sees progress weekly and they are happy. It helps them that they don&#x27;t have to pay a ton of money in 2-3 payments and can spread it over the course of months.<p>In terms of happiness, freelancing definitely comes in flavors. There is the grunt work, the highly paid freelancer, the consultant and the product-based business until you go full startup or large company. I have seen all tiers. Currently I am a step short of having my own product while I figure out what that will be. You definitely need business acumen and people skills to succeed in the consultant stage. For product business you gotta go a step beyond that and either do really well as a consultant to bootstrap, or just work your ass off to get it going. My advice for anyone in freelancing now, who does not have people skills and gets latched onto hourly work, you may want to reconsider your choices. Freelancing can be highly stressful and demoralizing, unless you take the steps to go into consulting or beyond. It&#x27;s a ladder, just like your corporate gig, you gotta do the work to move up or suffer where you are stuck.</text></item></parent_chain><comment><author>mancerayder</author><text><i>Freelancing can be highly stressful and demoralizing, unless you take the steps to go into consulting or beyond. It&#x27;s a ladder, just like your corporate gig, you gotta do the work to move up or suffer where you are stuck.</i><p>I have one sticking point I&#x27;d love to hear what the HN crowd does to deal with it.<p>I&#x27;m freelancing and I find gigs that are long-term via recruiters &#x2F; LinkedIn. And never directly with companies. While the pay is high, the feeling is I&#x27;m just another employee, except temp.<p>How do you market your skills directly with firms, and where do you go, if you&#x27;re not the &#x27;social media broadcaster&#x27; type who&#x27;s on Twitter &#x2F; etc. all day? I DO have people skills, I DON&#x27;T spend any time doing presentations at tech conferences or blasting myself on Twitter &#x2F; social media. Do you partner with a marketing type? Or become that type?</text></comment> |
20,868,624 | 20,868,152 | 1 | 2 | 20,866,084 | train | <story><title>Firefox 69.0 Released</title><url>https://www.mozilla.org/en-US/firefox/69.0/releasenotes/</url></story><parent_chain><item><author>tasty_freeze</author><text>Fantastic news for people, like me, who spend a lot of time with $10&#x2F;GB hotspot data prices. I&#x27;d click a link to a 5KB news article only to find it streaming HD video of talking heads reading the article.</text></item><item><author>Aardwolf</author><text>&gt; The Block Autoplay feature is enhanced to give users the option to block any video that automatically starts playing, not just those that automatically play with sound.<p>Good. I know a news website that was on purpose disabling sound on videos to prevent that. So not only does it autoplay, you need to click to unmute anyway to actually hear it!<p>Why do news websites want to shove autoplaying videos on people&#x27;s throats so much, what&#x27;s wrong with playing at any time when you want?<p>And why do news websites even care about doing shoving it to the small percentage of people who actually bother to disable autoplay in their browser?<p>P.S. I already had autoplay for videos without sound disabled through about:config flags, but some videos managed to autoplay anyway. I wonder if they also fixed that issue, or simply made the about:config flag part of the settings dialog.</text></item></parent_chain><comment><author>vezycash</author><text>With ublock origin you can block loading of media above a certain size.<p>You can pair that with addon called, &quot;Image video block&quot; <a href="https:&#x2F;&#x2F;github.com&#x2F;tiborbarsi&#x2F;image-video-block-browser-addon" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;tiborbarsi&#x2F;image-video-block-browser-addo...</a><p>And finally, you can use Bandwidth hero to compress images on the fly. You need to host the server instance on Heroku. Their free tier should suffice</text></comment> | <story><title>Firefox 69.0 Released</title><url>https://www.mozilla.org/en-US/firefox/69.0/releasenotes/</url></story><parent_chain><item><author>tasty_freeze</author><text>Fantastic news for people, like me, who spend a lot of time with $10&#x2F;GB hotspot data prices. I&#x27;d click a link to a 5KB news article only to find it streaming HD video of talking heads reading the article.</text></item><item><author>Aardwolf</author><text>&gt; The Block Autoplay feature is enhanced to give users the option to block any video that automatically starts playing, not just those that automatically play with sound.<p>Good. I know a news website that was on purpose disabling sound on videos to prevent that. So not only does it autoplay, you need to click to unmute anyway to actually hear it!<p>Why do news websites want to shove autoplaying videos on people&#x27;s throats so much, what&#x27;s wrong with playing at any time when you want?<p>And why do news websites even care about doing shoving it to the small percentage of people who actually bother to disable autoplay in their browser?<p>P.S. I already had autoplay for videos without sound disabled through about:config flags, but some videos managed to autoplay anyway. I wonder if they also fixed that issue, or simply made the about:config flag part of the settings dialog.</text></item></parent_chain><comment><author>jszymborski</author><text>Or even worse (and anecdotally more common), a video that is hardly relevant or from a year-old story.</text></comment> |
39,098,943 | 39,098,530 | 1 | 2 | 39,097,150 | train | <story><title>Changes at Riot Games and the road ahead</title><url>https://www.riotgames.com/en/news/2024-player-update</url></story><parent_chain><item><author>joshuamcginnis</author><text>Minimum six months severance pay + healthcare + cash bonus. That is incredibly generous all things considered.</text></item></parent_chain><comment><author>Imz4di</author><text>Pretty decent. When I was laid off last year from a company that supposedly has a reputation for taking care of their employees, I got 1 week per year of service, which was 8 weeks.</text></comment> | <story><title>Changes at Riot Games and the road ahead</title><url>https://www.riotgames.com/en/news/2024-player-update</url></story><parent_chain><item><author>joshuamcginnis</author><text>Minimum six months severance pay + healthcare + cash bonus. That is incredibly generous all things considered.</text></item></parent_chain><comment><author>ocdtrekkie</author><text>Yeah to be honest, a half-year sabbatical with time to job hunt non-frantically is a luxury I&#x27;ve never had. I love my current job, but I would probably look at a half year severance like a vacation.</text></comment> |
6,840,549 | 6,839,473 | 1 | 3 | 6,838,299 | train | <story><title>My Roommate's a Genius</title><url>http://www.farhadg.com/post/33834177117/genius-roommate</url></story><parent_chain><item><author>uniclaude</author><text>Some responses in this thread surprise me, I thought the mindset exposed in this article was something most <i>hackers</i> shared. Therefore, after reading the post, I expected a bunch of mildly negative comments of people who built a lot of awesome things in their spare time. Well, I was wrong.<p>Anecdotal but surprising, my fellow musician friends are more prone to what I believe to be the <i>hacker</i> thinking than most of the software programmers I work with. Maybe it is because of some unfortunate psychological barrier, or the result of a strong focus on computer related things and discard for the rest, I honestly don&#x27;t know.<p>Anyways, what this roommate did is super cool, and I&#x27;d suggest everyone here to start hacking outside of their comfort zone, it can be very rewarding for some. Building things feels great, and being able to apply your hacker thinking to various things is a very useful skill to have.</text></item></parent_chain><comment><author>sigkill</author><text>Not to take away the intelligence of people but a hacker is someone who excels in situations as this - Limited time, limited resources&#x2F;cheapness to spend money, Have objects X, Need functions Y.<p><i>That</i> takes a hacker. Everything else is just a builder (be it building code, or cabinets, or robots). The core ideology of being a hacker is seeing beyond the normal functionality of the item like this roommate has seen. He looked at the wardrobe and saw a sliding table. <i>That</i> is hacking.</text></comment> | <story><title>My Roommate's a Genius</title><url>http://www.farhadg.com/post/33834177117/genius-roommate</url></story><parent_chain><item><author>uniclaude</author><text>Some responses in this thread surprise me, I thought the mindset exposed in this article was something most <i>hackers</i> shared. Therefore, after reading the post, I expected a bunch of mildly negative comments of people who built a lot of awesome things in their spare time. Well, I was wrong.<p>Anecdotal but surprising, my fellow musician friends are more prone to what I believe to be the <i>hacker</i> thinking than most of the software programmers I work with. Maybe it is because of some unfortunate psychological barrier, or the result of a strong focus on computer related things and discard for the rest, I honestly don&#x27;t know.<p>Anyways, what this roommate did is super cool, and I&#x27;d suggest everyone here to start hacking outside of their comfort zone, it can be very rewarding for some. Building things feels great, and being able to apply your hacker thinking to various things is a very useful skill to have.</text></item></parent_chain><comment><author>mercer</author><text>I&#x27;ve noticed the same thing in musician friends of mine, and I think it really isn&#x27;t so much that their mindset is different from &#x27;us&#x27; hackers, but rather that we spend so much time on virtual stuff that we don&#x27;t learn to apply our mindset to the real world.<p>In fact, a lot of us probably under-perform when it comes to real-world hacking because we&#x27;re so caught in the virtual. I know that&#x27;s true for me.<p>This did give me a bit of a new perspective on things, and makes me wonder if I should start some more real-world hacking...</text></comment> |
20,455,616 | 20,455,611 | 1 | 3 | 20,454,966 | train | <story><title>Declined Proposal: A built-in Go error check function, “try”</title><url>https://github.com/golang/go/issues/32437#issuecomment-512035919</url></story><parent_chain><item><author>natefinch</author><text>Literally the first non-trivial code I wrote in go (running a bunch of goroutines to download a ton of files from a website in parallel)... I knew exactly where and how things could fail and where things were failing just by looking at the code. Coming from C++ and C# and Python, there was no comparison. I had never been so confident in the code I&#x27;d written, even though I was a newbie at Go and a veteran of the other languages.</text></item><item><author>KirinDave</author><text>&gt; Do I particularly like managing errors that way? No, but I do think that it improves the transparency and quality of a lot of Go projects.<p>So long as we can all agree that it feels super bad, I guess this is fine. But it does sort of mean that Golang approaches the Java world back with checked exceptions where principle trumped ergonomics.<p>That lead to a world where folks felt &quot;forced&quot; to use Java, and that&#x27;s a sticky label that&#x27;s difficult to remove. I think the Golang community is going to find itself growing more slowly as folks increasingly realize other options offer similar benefits without the bad ergonomics.</text></item><item><author>wybiral</author><text>This hits at something fundamental about Go, which is what I like the most about it...<p>It&#x27;s a language intended to have few primitives with an emphasis on code being transparent and errors being values, requiring you to think about what they might be at each point as you&#x27;re forced to carry them up the chain.<p>Do I particularly <i>like</i> managing errors that way? No, but I do think that it improves the transparency and quality of a lot of Go projects.<p>The same goes with the Go ecosystem and tools. You might not like how gofmt forces your code or the documentation conventions used by golint but the fact that we all use the same convention and documentation is awesome and it&#x27;s what allows things like godoc.org. I think the proverb is &quot;gofmt&#x27;s style is no one&#x27;s favorite, yet gofmt is everyone&#x27;s favorite&quot;.<p>And things like the lack of abstractions and generics are what create a community that&#x27;s less reliant on dependencies. &quot;A little copying is better than a little dependency&quot; and you can see it in stark contrast to something like the JS community with its require(&#x27;left-pad&#x27;) NPM ecosystem.<p>So, yeah, I like that they didn&#x27;t fragment the community around something as arbitrary as this. And I get that some people won&#x27;t like it, just as they don&#x27;t like the lack of generics, but there is strength in some of these approaches that isn&#x27;t immediately obvious.</text></item></parent_chain><comment><author>KirinDave</author><text>I guess then I have to ask, why would try() make that worse?<p>Because I can&#x27;t stand Golang error handling. It&#x27;s repetitive, it&#x27;s error prone, and other language features interact with it so that when you make a mistake it can be as hard as a double free to track down where the erroneous default value was introduced.<p>On the other hand, using Rust, Ocaml, F# or Haskell I understand how my code composed and I can be confident I can just use an error handling strategy. The only complexities appear, as with everyone else, when we have asynchronous code.<p>So I don&#x27;t mean to disagree with your feelings, but they&#x27;re sure not mine and they&#x27;re part of why I don&#x27;t use Golang. I was excited about try() because it at least addressed the most tedious part.</text></comment> | <story><title>Declined Proposal: A built-in Go error check function, “try”</title><url>https://github.com/golang/go/issues/32437#issuecomment-512035919</url></story><parent_chain><item><author>natefinch</author><text>Literally the first non-trivial code I wrote in go (running a bunch of goroutines to download a ton of files from a website in parallel)... I knew exactly where and how things could fail and where things were failing just by looking at the code. Coming from C++ and C# and Python, there was no comparison. I had never been so confident in the code I&#x27;d written, even though I was a newbie at Go and a veteran of the other languages.</text></item><item><author>KirinDave</author><text>&gt; Do I particularly like managing errors that way? No, but I do think that it improves the transparency and quality of a lot of Go projects.<p>So long as we can all agree that it feels super bad, I guess this is fine. But it does sort of mean that Golang approaches the Java world back with checked exceptions where principle trumped ergonomics.<p>That lead to a world where folks felt &quot;forced&quot; to use Java, and that&#x27;s a sticky label that&#x27;s difficult to remove. I think the Golang community is going to find itself growing more slowly as folks increasingly realize other options offer similar benefits without the bad ergonomics.</text></item><item><author>wybiral</author><text>This hits at something fundamental about Go, which is what I like the most about it...<p>It&#x27;s a language intended to have few primitives with an emphasis on code being transparent and errors being values, requiring you to think about what they might be at each point as you&#x27;re forced to carry them up the chain.<p>Do I particularly <i>like</i> managing errors that way? No, but I do think that it improves the transparency and quality of a lot of Go projects.<p>The same goes with the Go ecosystem and tools. You might not like how gofmt forces your code or the documentation conventions used by golint but the fact that we all use the same convention and documentation is awesome and it&#x27;s what allows things like godoc.org. I think the proverb is &quot;gofmt&#x27;s style is no one&#x27;s favorite, yet gofmt is everyone&#x27;s favorite&quot;.<p>And things like the lack of abstractions and generics are what create a community that&#x27;s less reliant on dependencies. &quot;A little copying is better than a little dependency&quot; and you can see it in stark contrast to something like the JS community with its require(&#x27;left-pad&#x27;) NPM ecosystem.<p>So, yeah, I like that they didn&#x27;t fragment the community around something as arbitrary as this. And I get that some people won&#x27;t like it, just as they don&#x27;t like the lack of generics, but there is strength in some of these approaches that isn&#x27;t immediately obvious.</text></item></parent_chain><comment><author>kazinator</author><text>Did you know where every page fault would happen, and manually check every memory access and fix the situation?<p>You didn&#x27;t have to because there is an precise, robust non-checked exception handling system which takes care of that: the hardware catches the situation, dispatches a handler in the operating system which fixes it and re-starts your program at the original machine instruction to try the memory access again.</text></comment> |
27,422,261 | 27,422,558 | 1 | 2 | 27,421,408 | train | <story><title>Show HN: Open-source alternative to Retool, Internal.io, etc.</title><url>https://github.com/ToolJet/ToolJet/</url></story><parent_chain><item><author>navaneethpk</author><text>Founder here,<p>ToolJet is a no-code platform for building &amp; deploying custom internal tools. ToolJet is built using Ruby on Rails and ReactJS. ToolJet can connect to existing data sources of companies such as databases, Google sheets, API endpoints, external services, and more. ToolJet&#x27;s drag and drop app builder can quickly create UI widgets such as tables, charts, forms, etc and connect these widgets with the data from data sources.<p>I have been dabbling with the idea of ToolJet for a while. but the real progress happened over the last 7 weeks while I was in quarantine. One of my family members tested positive for covid and then came to the state-mandated lockdown. Not being able to step out of my home has been particularly hard, but nevertheless gave birth to ToolJet.<p>I believe that the tools that require access to sensitive data should be self-hosted ( data never leaves the premises) and open-source ( modify the software to fit organization-specific requirements ).</text></item></parent_chain><comment><author>foxbee</author><text>Wow! Building this in 7 weeks is an incredible feat. I am the cofounder of Budibase - an open source alt to Retool, Mendix, Outsystems - and have been building it for around 2 years now.<p>It&#x27;s an incredible space and solves a burning problem for engineers, IT teams and business users.<p>We&#x27;re seeing major benefits of being open source, with the like of the NHS, Amazon, Deloitte and other major orgs choosing Budibase over proprietary alternatives, so I would say your decision to offer self-hosting was a good one.<p>As much as we are probably seen as competitors, I wish you well and I am happy to share notes if you would like a call?<p><a href="https:&#x2F;&#x2F;github.com&#x2F;Budibase&#x2F;budibase" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Budibase&#x2F;budibase</a></text></comment> | <story><title>Show HN: Open-source alternative to Retool, Internal.io, etc.</title><url>https://github.com/ToolJet/ToolJet/</url></story><parent_chain><item><author>navaneethpk</author><text>Founder here,<p>ToolJet is a no-code platform for building &amp; deploying custom internal tools. ToolJet is built using Ruby on Rails and ReactJS. ToolJet can connect to existing data sources of companies such as databases, Google sheets, API endpoints, external services, and more. ToolJet&#x27;s drag and drop app builder can quickly create UI widgets such as tables, charts, forms, etc and connect these widgets with the data from data sources.<p>I have been dabbling with the idea of ToolJet for a while. but the real progress happened over the last 7 weeks while I was in quarantine. One of my family members tested positive for covid and then came to the state-mandated lockdown. Not being able to step out of my home has been particularly hard, but nevertheless gave birth to ToolJet.<p>I believe that the tools that require access to sensitive data should be self-hosted ( data never leaves the premises) and open-source ( modify the software to fit organization-specific requirements ).</text></item></parent_chain><comment><author>victor106</author><text>This looks cool. What did you use to generate the documentation? <a href="https:&#x2F;&#x2F;docs.tooljet.io&#x2F;docs&#x2F;intro&#x2F;" rel="nofollow">https:&#x2F;&#x2F;docs.tooljet.io&#x2F;docs&#x2F;intro&#x2F;</a></text></comment> |
6,282,009 | 6,280,361 | 1 | 2 | 6,277,516 | train | <story><title>The greatest mystery of the Inca Empire was its strange economy (2012)</title><url>http://io9.com/the-greatest-mystery-of-the-inca-empire-was-its-strange-1198541254</url></story><parent_chain><item><author>mseebach</author><text>&quot;Explaining why communism always fail without faulting communism even slightly&quot; is a very rich genre. It is also disingenuous in failing to consider the single most likely (by way of Occam&#x27;s razor) cause of communism&#x27;s failure, which is the ideology itself.<p>But to apply some historical facts to the theory:<p><i>From its founding, the Cheka was an important military and security arm of the Bolshevik communist government. In 1921 the Troops for the Internal Defense of the Republic (a branch of the Cheka) numbered 200,000. These troops policed labor camps; ran the Gulag system; conducted requisitions of food; subjected political opponents to torture and summary execution; and put down rebellions and riots by workers or peasants, and mutinies in the desertion-plagued Red Army.</i><p>The Cheka existed from 1917 to 1922. Even if the US was scared of communism, nothing like the CIA existed to undermine the revolution in Soviet Russia. And yet, violently putting down riots by workers and peasants was necessary. It takes a special kind of ideological arrogance to blame the USA for that.</text></item><item><author>nhaehnle</author><text><i>But almost every implementation of Marxism in recent history involved totalitarianism and ignored the part about decentralization of power post-revolution.</i><p>I recently came across a very interesting thought, which is that this observation (which I also believed until coming across that thought) is induced by a kind of selection bias. The original article in which I encountered this thought is here: <a href="http://www.pieria.co.uk/articles/men_make_their_own_history_but_they_do_not_make_it_as_they_please" rel="nofollow">http:&#x2F;&#x2F;www.pieria.co.uk&#x2F;articles&#x2F;men_make_their_own_history_...</a><p>The synopsis is this: Communism tended to develop in poorer (and therefore militarily weaker) countries, and communism was <i>vehemently</i> opposed by the ruling elite in capitalist countries. The worldwide interference of the CIA is probably the clearest evidence of this. So from the start, communist countries had to defend themselves against powerful adversaries.<p>Given that communist movements were attacked quite violently by foreign interests, it stands to reason that those countries which implemented a &quot;softer&quot; approach to communism did not survive. Foreign propaganda, wars, and coup d&#x27;etats sponsored by capitalist nations killed communism in many place where it had been democratically legitimized and could in principle be sustained with the consent of the people.<p>But, to put it bluntly, the consent of the people may not be enough when what really counts is a handful of oligarchs in the US.<p>So the examples of communism that survived are those that were able to defend themselves ruthlessly against equally or even more ruthless aggressors. This defense then grew abominations like secret police and what have you.<p>The secret police was thus not a function of communism, but of the paranoia caused by foreign aggressors. Look at what secret state organizations in western capitalist countries are doing these days, and the idea that the development of secret police is related to economics starts looking a bit far-fetched.<p>I am not certain that this is the ultimate answer in this debate. However, it is a plausible enough story which has a lot of historical facts on its side.</text></item><item><author>dmix</author><text>It definitely didn&#x27;t share Marx&#x27;s original concepts of decentralized states and communal distribution. But almost every implementation of Marxism in recent history involved totalitarianism and ignored the part about decentralization of power post-revolution. So it&#x27;s a fair statement, if taken as the commonly held meaning.</text></item><item><author>PavlovsCat</author><text>Lost me at &quot;Marxists&quot;. <a href="http://en.wikipedia.org/wiki/Marxism" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Marxism</a><p>edit: this came out kinda snarky, sorry.. I found all of that very interesting and insightful, just not the very end of the ending.</text></item><item><author>vijayboyapati</author><text>A comment from a Peruvian friend of mine, who I passed the article onto:<p>&quot;This is incredibly misleading. There was no market because that culture was run by theocratic totalitarian blood thirsty central planners. The vast majority of people were a form of slave and trapped in basically a completely rigorous caste system. They were a mix of India and NK, ruled by a Mao &quot;god&quot; Inca who had total control of everything. The article gets right that people had to pay tax as labor but in some cases also as a percentage of the food they gathered, and a non-trivial percentage was stored in &quot;tambos&quot; (<a href="http://en.wikipedia.org/wiki/Tambo_(Incan_structure)" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Tambo_(Incan_structure)</a>) to support the military and state-controlled trading routes.<p>OTOH the Spanish monarchy was totally evil, purposefully wiping out millions of people and creating basically what amounts of royal satraps in the new world from which to extract cheap&#x2F;free labor and tons of gold and other wealth.<p>That said, the Incas were also primitive--no real written language and barely a minimum system for tracking amounts and numbers (<a href="http://en.wikipedia.org/wiki/Quipu" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Quipu</a>).<p>I took 12 years of Peruvian history and it wasn&#x27;t until recently that I realized how utterly terrible the Incas were. They were proto Marxists.&quot;</text></item></parent_chain><comment><author>nhaehnle</author><text><i>&quot;Explaining why communism always fail without faulting communism even slightly&quot; is a very rich genre.</i><p>Please be clear on what you mean by &quot;failure&quot;.<p>For Russia itself, communism was actually very successful economically speaking: Their economy grew more quickly than the average for other, non-communist countries that were at Russia&#x27;s level of development.<p>With this aside, and going back to what we were talking about (i.e. state violence and repression), your point is a rather weak one. During and in the aftermath of revolutionary phases, there tends to be violence. You yourself conceded that these measures were eliminated and&#x2F;or scaled down in Russia without outside intervention once things had settled down.<p>This kind of thing has nothing to do with economic organization and can be found in capitalism as well. Just look at what&#x27;s been going on in the Middle East and Egypt in particular. Those are far from being communists, and yet the cleaning-up after a coup d&#x27;etat was quite brutal.</text></comment> | <story><title>The greatest mystery of the Inca Empire was its strange economy (2012)</title><url>http://io9.com/the-greatest-mystery-of-the-inca-empire-was-its-strange-1198541254</url></story><parent_chain><item><author>mseebach</author><text>&quot;Explaining why communism always fail without faulting communism even slightly&quot; is a very rich genre. It is also disingenuous in failing to consider the single most likely (by way of Occam&#x27;s razor) cause of communism&#x27;s failure, which is the ideology itself.<p>But to apply some historical facts to the theory:<p><i>From its founding, the Cheka was an important military and security arm of the Bolshevik communist government. In 1921 the Troops for the Internal Defense of the Republic (a branch of the Cheka) numbered 200,000. These troops policed labor camps; ran the Gulag system; conducted requisitions of food; subjected political opponents to torture and summary execution; and put down rebellions and riots by workers or peasants, and mutinies in the desertion-plagued Red Army.</i><p>The Cheka existed from 1917 to 1922. Even if the US was scared of communism, nothing like the CIA existed to undermine the revolution in Soviet Russia. And yet, violently putting down riots by workers and peasants was necessary. It takes a special kind of ideological arrogance to blame the USA for that.</text></item><item><author>nhaehnle</author><text><i>But almost every implementation of Marxism in recent history involved totalitarianism and ignored the part about decentralization of power post-revolution.</i><p>I recently came across a very interesting thought, which is that this observation (which I also believed until coming across that thought) is induced by a kind of selection bias. The original article in which I encountered this thought is here: <a href="http://www.pieria.co.uk/articles/men_make_their_own_history_but_they_do_not_make_it_as_they_please" rel="nofollow">http:&#x2F;&#x2F;www.pieria.co.uk&#x2F;articles&#x2F;men_make_their_own_history_...</a><p>The synopsis is this: Communism tended to develop in poorer (and therefore militarily weaker) countries, and communism was <i>vehemently</i> opposed by the ruling elite in capitalist countries. The worldwide interference of the CIA is probably the clearest evidence of this. So from the start, communist countries had to defend themselves against powerful adversaries.<p>Given that communist movements were attacked quite violently by foreign interests, it stands to reason that those countries which implemented a &quot;softer&quot; approach to communism did not survive. Foreign propaganda, wars, and coup d&#x27;etats sponsored by capitalist nations killed communism in many place where it had been democratically legitimized and could in principle be sustained with the consent of the people.<p>But, to put it bluntly, the consent of the people may not be enough when what really counts is a handful of oligarchs in the US.<p>So the examples of communism that survived are those that were able to defend themselves ruthlessly against equally or even more ruthless aggressors. This defense then grew abominations like secret police and what have you.<p>The secret police was thus not a function of communism, but of the paranoia caused by foreign aggressors. Look at what secret state organizations in western capitalist countries are doing these days, and the idea that the development of secret police is related to economics starts looking a bit far-fetched.<p>I am not certain that this is the ultimate answer in this debate. However, it is a plausible enough story which has a lot of historical facts on its side.</text></item><item><author>dmix</author><text>It definitely didn&#x27;t share Marx&#x27;s original concepts of decentralized states and communal distribution. But almost every implementation of Marxism in recent history involved totalitarianism and ignored the part about decentralization of power post-revolution. So it&#x27;s a fair statement, if taken as the commonly held meaning.</text></item><item><author>PavlovsCat</author><text>Lost me at &quot;Marxists&quot;. <a href="http://en.wikipedia.org/wiki/Marxism" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Marxism</a><p>edit: this came out kinda snarky, sorry.. I found all of that very interesting and insightful, just not the very end of the ending.</text></item><item><author>vijayboyapati</author><text>A comment from a Peruvian friend of mine, who I passed the article onto:<p>&quot;This is incredibly misleading. There was no market because that culture was run by theocratic totalitarian blood thirsty central planners. The vast majority of people were a form of slave and trapped in basically a completely rigorous caste system. They were a mix of India and NK, ruled by a Mao &quot;god&quot; Inca who had total control of everything. The article gets right that people had to pay tax as labor but in some cases also as a percentage of the food they gathered, and a non-trivial percentage was stored in &quot;tambos&quot; (<a href="http://en.wikipedia.org/wiki/Tambo_(Incan_structure)" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Tambo_(Incan_structure)</a>) to support the military and state-controlled trading routes.<p>OTOH the Spanish monarchy was totally evil, purposefully wiping out millions of people and creating basically what amounts of royal satraps in the new world from which to extract cheap&#x2F;free labor and tons of gold and other wealth.<p>That said, the Incas were also primitive--no real written language and barely a minimum system for tracking amounts and numbers (<a href="http://en.wikipedia.org/wiki/Quipu" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Quipu</a>).<p>I took 12 years of Peruvian history and it wasn&#x27;t until recently that I realized how utterly terrible the Incas were. They were proto Marxists.&quot;</text></item></parent_chain><comment><author>int_19h</author><text><a href="http://en.wikipedia.org/wiki/Allied_intervention_in_the_Russian_Civil_War" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Allied_intervention_in_the_Russ...</a></text></comment> |
16,332,248 | 16,331,781 | 1 | 2 | 16,329,691 | train | <story><title>A todo list for new ASP.NET Core projects</title><url>https://biarity.gitlab.io/2018/02/08/asp-net-core-todo</url></story><parent_chain><item><author>jasonkester</author><text>One of the cool things about ASP.NET is how many different ways there are to get things done. There is a ton of stuff in there, and you can pick and choose the bits that make sense for your project.<p>In the old days, that meant you could toss out all silly drag&#x2F;drop, faux-stateful garbage they put in to make it so you could build webapps like they were VB6. Thus, leaving behind a really good compact MVC framework for building webapps (long before they came out with something actually <i>called</i> MVC that wasn&#x27;t as good at it). Now it means that I can read this list and not see a single technology I&#x27;ve touched at all in my 18 years of build stuff on this stack.<p>Personally, I tend to disagree with the author&#x27;s approach of pushing routine stuff out to the realm of &quot;magically happens behind the scenes&quot;, in favor of having common base classes for my page handlers that can be explicitly told to do those things with a little Initialize() method at the top of the handler. That way, when something goes wrong I get a breakpoint looking at my own code.<p>I like control, so the idea of voluntarily putting something in place that could magically shove its way in front of my code and whisk the user off to an error page just smells wrong.<p>But again, it&#x27;s cool that the stack gives us the option to do so if it fits our style.</text></item></parent_chain><comment><author>cptskippy</author><text>&gt; I like control, so the idea of voluntarily putting something in place that could magically shove its way in front of my code and whisk the user off to an error page just smells wrong.<p>I feel the same way as you however I&#x27;ve found that when working on a large code base with a lot of junior developers or contractors who lack qualities like discipline, attention to detail, consistency, and convention; it&#x27;s often easier to just wire up all of the important parts behind the scenes.<p>It&#x27;s also useful when you&#x27;re managing a number of projects that are primarily maintained by junior developers and you only drop in occasionally to do the heavy lifting.</text></comment> | <story><title>A todo list for new ASP.NET Core projects</title><url>https://biarity.gitlab.io/2018/02/08/asp-net-core-todo</url></story><parent_chain><item><author>jasonkester</author><text>One of the cool things about ASP.NET is how many different ways there are to get things done. There is a ton of stuff in there, and you can pick and choose the bits that make sense for your project.<p>In the old days, that meant you could toss out all silly drag&#x2F;drop, faux-stateful garbage they put in to make it so you could build webapps like they were VB6. Thus, leaving behind a really good compact MVC framework for building webapps (long before they came out with something actually <i>called</i> MVC that wasn&#x27;t as good at it). Now it means that I can read this list and not see a single technology I&#x27;ve touched at all in my 18 years of build stuff on this stack.<p>Personally, I tend to disagree with the author&#x27;s approach of pushing routine stuff out to the realm of &quot;magically happens behind the scenes&quot;, in favor of having common base classes for my page handlers that can be explicitly told to do those things with a little Initialize() method at the top of the handler. That way, when something goes wrong I get a breakpoint looking at my own code.<p>I like control, so the idea of voluntarily putting something in place that could magically shove its way in front of my code and whisk the user off to an error page just smells wrong.<p>But again, it&#x27;s cool that the stack gives us the option to do so if it fits our style.</text></item></parent_chain><comment><author>pc86</author><text>&gt; <i>I tend to disagree with the author&#x27;s approach of pushing routine stuff out to the realm of &quot;magically happens behind the scenes&quot;</i><p>Me too, and it&#x27;s easy to take this approach <i>way</i> too far to where you&#x27;re basically recreating your own MVC architecture in some pseudo-service layer that you&#x27;re not 100% sure how it even gets executed in the first place.<p>But I&#x27;ll admit for things you should be doing on 99.9% of calls (e.g. validating the model) it&#x27;s nice to have it done one place and one place only.</text></comment> |
16,011,498 | 16,011,479 | 1 | 2 | 16,010,943 | train | <story><title>What's Wrong with Students?</title><url>http://econlog.econlib.org/archives/2017/12/whats_wrong_wit_24.html</url></story><parent_chain><item><author>tptacek</author><text>I went to Catholic college prep high school in the 1990s. My kids, public high school (albeit: a suburban public high school) over the last 6 years. I had to write a shitload of papers. My kids have to write a shitload of papers. If anything: their education is more rigorous than was mine. If my kids get(&#x2F;got) &quot;cats&quot; vs. &quot;cats&#x27;&quot; incorrect, they&#x27;ll get dinged for it.<p>I kind of want to call bullshit on this analysis.</text></item></parent_chain><comment><author>mintplant</author><text>Yep. Relatively recent product of the American public high school system here [0], and soon-to-be product of the public university system. If anything I had to write many more papers in my high school classes than in my college ones. I don&#x27;t know what planet these guys are living on.<p>&gt; Well, the night before, I studied probably pretty close to an hour.&quot; And with that the scales fell from my eyes.<p>&gt; &quot;An hour? Do you realize that when I was in college it was common to start studying for big exams a week or more before?&quot;<p>I suspect the professor has forgotten just how much college students have on their plates at any given time. An Intro to Philosophy class may not be everyone&#x27;s top priority.<p>[0] Starting in Louisiana and finishing in California.</text></comment> | <story><title>What's Wrong with Students?</title><url>http://econlog.econlib.org/archives/2017/12/whats_wrong_wit_24.html</url></story><parent_chain><item><author>tptacek</author><text>I went to Catholic college prep high school in the 1990s. My kids, public high school (albeit: a suburban public high school) over the last 6 years. I had to write a shitload of papers. My kids have to write a shitload of papers. If anything: their education is more rigorous than was mine. If my kids get(&#x2F;got) &quot;cats&quot; vs. &quot;cats&#x27;&quot; incorrect, they&#x27;ll get dinged for it.<p>I kind of want to call bullshit on this analysis.</text></item></parent_chain><comment><author>analog31</author><text>Just want to chime in: Likewise with my kids. They&#x27;ve been writing paper after paper since middle school. Both have been taught a lot about good writing and critical thought. Other subjects are similarly rigorous. My kids study more in high school than I studied in college.<p>With that said, there&#x27;s certainly a disparity in education quality depending on where you live, and how affluent you are. In addition, for kids who attend college, there&#x27;s a disparity across departments and majors based on the high school background of the students. It is possible that for whatever reason, the author of that article ended up assigned to teaching a &quot;fluff&quot; course at their college.</text></comment> |
28,890,779 | 28,890,994 | 1 | 2 | 28,888,214 | train | <story><title>Canon sued for disabling scanner when printers run out of ink</title><url>https://www.bleepingcomputer.com/news/legal/canon-sued-for-disabling-scanner-when-printers-run-out-of-ink/</url></story><parent_chain><item><author>neilv</author><text>As many techies will probably always say anytime inkjet product shenanigans come up: just buy a laser printer.<p>And I now add: and don&#x27;t let it connect to the Internet, and don&#x27;t install proprietary drivers or software for it on your computers.<p>Also, remember the names of companies doing sketchy things, and do your part to provide negative feedback when you can, and to give positive feedback to better companies. (Example: I&#x27;ve just moved away from the Apple product ecosystem, because Apple did one too many obnoxious things, and I&#x27;ll also be pointing friends who ask to alternative solutions.)</text></item></parent_chain><comment><author>sangnoir</author><text>&gt; As many techies will probably always say anytime inkjet product shenanigans come up: just buy a laser printer<p>It&#x27;s Canon&#x2F;HP&#x2F;$MANUFATURER shenanigans - nothing inherent to inkjets. I think the better solution is to buy from more ethical printer companies, like Brother.</text></comment> | <story><title>Canon sued for disabling scanner when printers run out of ink</title><url>https://www.bleepingcomputer.com/news/legal/canon-sued-for-disabling-scanner-when-printers-run-out-of-ink/</url></story><parent_chain><item><author>neilv</author><text>As many techies will probably always say anytime inkjet product shenanigans come up: just buy a laser printer.<p>And I now add: and don&#x27;t let it connect to the Internet, and don&#x27;t install proprietary drivers or software for it on your computers.<p>Also, remember the names of companies doing sketchy things, and do your part to provide negative feedback when you can, and to give positive feedback to better companies. (Example: I&#x27;ve just moved away from the Apple product ecosystem, because Apple did one too many obnoxious things, and I&#x27;ll also be pointing friends who ask to alternative solutions.)</text></item></parent_chain><comment><author>kyrra</author><text>I had a Xerox laser printer for about 12 years, and it worked pretty well. No special drivers needed, just uses a standard pcl6 or postscript. The problem with it was toner cost. Official toner was stupid expensive, but there was decent aftermarket toner on Amazon that mostly worked.<p>I have since gone to a smarter printer with an Epson ecotank. Their ink is decent price and it works fairly well. Sadly The model I got requires custom drivers. Though they do have models that support PCL6&#x2F; postscript. The model I got also allows for larger paper sizes, but it does not handle it very well in the firmware.</text></comment> |
40,141,846 | 40,140,716 | 1 | 3 | 40,134,534 | train | <story><title>Intel Meteor Lake's NPU</title><url>https://chipsandcheese.com/2024/04/22/intel-meteor-lakes-npu/</url></story><parent_chain><item><author>int0x29</author><text>&quot;Instead of building a custom command processor, Intel uses Movidius’s 32-bit LEON microcontrollers. LEON use the SPARC instruction set and run a real time operating system.&quot;<p>Your Intel core now runs two ISAs and three OSs. Managment engine runs Minix (and used to use the ARC isa).</text></item></parent_chain><comment><author>Narishma</author><text>More than two. It has x86_64 on the main CPU cores, x86 on the ME, SPARC on this NPU and whatever the iGPU ISA is called. And I wouldn&#x27;t be surprised if there&#x27;s an ARM microcontroller or three in there as well.</text></comment> | <story><title>Intel Meteor Lake's NPU</title><url>https://chipsandcheese.com/2024/04/22/intel-meteor-lakes-npu/</url></story><parent_chain><item><author>int0x29</author><text>&quot;Instead of building a custom command processor, Intel uses Movidius’s 32-bit LEON microcontrollers. LEON use the SPARC instruction set and run a real time operating system.&quot;<p>Your Intel core now runs two ISAs and three OSs. Managment engine runs Minix (and used to use the ARC isa).</text></item></parent_chain><comment><author>userbinator</author><text>It&#x27;s always weird to see Intel using &quot;foreign&quot; ISAs, but not too surprising for something they acquired. The ME&#x27;s use of SPARC and ARC before that is more unusual; they could&#x27;ve at least used a 386&#x2F;486-class core, or even the i860&#x2F;960 if they wanted something RISC.</text></comment> |
10,764,806 | 10,764,814 | 1 | 2 | 10,764,274 | train | <story><title>Juniper: Recording Some Twitter Conversations</title><url>https://www.imperialviolet.org/2015/12/19/juniper.html</url></story><parent_chain></parent_chain><comment><author>tptacek</author><text>Stop and consider for a second how crazy this page is:<p><a href="https:&#x2F;&#x2F;kb.juniper.net&#x2F;InfoCenter&#x2F;index?page=content&amp;id=KB28205&amp;pmv=print&amp;actp=LIST" rel="nofollow">https:&#x2F;&#x2F;kb.juniper.net&#x2F;InfoCenter&#x2F;index?page=content&amp;id=KB28...</a><p>Dual_EC is a PKRNG. PKRNGs are a kind of crypto random number generator (CSPRNG). All the crypto keys in modern cryptosystems come from CSPRNGS.<p>PKRNGs are special because they embed a public key in the generator. Anyone who holds the corresponding private key can &quot;decrypt&quot; the output of the RNG and recover the generator&#x27;s &quot;state&quot;; once they have that, they can fast-forward and rewind through it to find all the other numbers (read: crypto keys) it can generate.<p>Juniper is here saying that they recognize the problem of Dual_EC --- it&#x27;s a PKRNG, and the USG may hold its private key.<p><i>So instead, they generated their own private keys and embedded them in the CSPRNGs of the VPNs they sold to customers</i>.<p>WAT?<p>But see also this thread:<p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=10764359" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=10764359</a></text></comment> | <story><title>Juniper: Recording Some Twitter Conversations</title><url>https://www.imperialviolet.org/2015/12/19/juniper.html</url></story><parent_chain></parent_chain><comment><author>unchocked</author><text>Is this going to become the primary case study on why back doors are a bad idea?<p>If so, it&#x27;s important to get a quality layman&#x27;s explanation out fast, and this is the framework of a great one.</text></comment> |
10,960,985 | 10,960,718 | 1 | 3 | 10,955,014 | train | <story><title>Organizing My Emails with a Neural Net</title><url>http://www.andreykurenkov.com/writing/organizing-my-emails-with-a-neural-net/</url></story><parent_chain></parent_chain><comment><author>tyingq</author><text>Popfile is worth looking at if this was interesting to you.<p>It is a general purpose naïve bayesian email classifier that you can integrate with almost any email system.<p>They took some of the concepts in the article mentioned here and expanded on them a bit.<p>For example, they have the idea of &quot;pseudowords&quot;[1] so that you&#x27;re working with more than just the words in the email. Like html:td for example...it expands to the number html table cells in an email, which might help with choosing a bucket.<p>[1]<a href="http:&#x2F;&#x2F;getpopfile.org&#x2F;docs&#x2F;faq:pseudowords" rel="nofollow">http:&#x2F;&#x2F;getpopfile.org&#x2F;docs&#x2F;faq:pseudowords</a></text></comment> | <story><title>Organizing My Emails with a Neural Net</title><url>http://www.andreykurenkov.com/writing/organizing-my-emails-with-a-neural-net/</url></story><parent_chain></parent_chain><comment><author>thibauts</author><text>Is it common practice to use the most frequent words as features ? It looks like they don&#x27;t carry much information, by definition. As a first naive approach, I&#x27;d rank the words by the inverse of how many categories they appear in, factor in the overall frequency, with a weight or something more clever and then take the top N.<p>Well, thinking more about it leads me to tf-idf and naive bayes (of course), at which point you pretty much already have a classifier. So it seems feature selection <i>is</i> learning in itself and defines the maximum accuracy you&#x27;ll be able to reach ? This is border philosophical but I&#x27;d love to read more about these matters. Pointers welcome !</text></comment> |
31,672,227 | 31,672,189 | 1 | 2 | 31,668,426 | train | <story><title>Sunsetting Atom</title><url>https://github.blog/2022-06-08-sunsetting-atom/</url></story><parent_chain><item><author>frostwarrior</author><text>&gt; Emacs, vim<p>Unlike VSCode, Emacs and Vim have a learning curve. And turning them into full blown IDEs makes their usage even more complex.<p>&gt; Sublime<p>Sadly, Sublime is sort of dead.<p>&gt; TextMate<p>TextMate: Text editor for macOS</text></item><item><author>shakow</author><text>&gt; Atom practically invented the kind of extensions that VSCode had<p>Let me introduce you to Emacs, vim, Sublime, TextMate, ...</text></item><item><author>quaunaut</author><text>Atom practically invented the kind of extensions that VSCode had, and even several years into VSCode&#x27;s life Atom far outstripped it in Extensions.<p>Perf became the biggest problem however, which VSCode took over.</text></item><item><author>aniforprez</author><text>IMO the killer thing that VSCode has over all the other editors is the wealth of extensions and a certain degree of simplicity. What are your plans for Zed in terms of extensibility and are you aligning more towards making something beefy and full-featured like the IntelliJ offerings or something more &quot;lightweight&quot; like VSCode or Sublime?</text></item><item><author>nathansobo</author><text>Founder of Atom here. We&#x27;re building the spiritual successor to Atom over at <a href="https:&#x2F;&#x2F;zed.dev" rel="nofollow">https:&#x2F;&#x2F;zed.dev</a>.<p>We learned a lot with Atom and had a great time, but it always fell short of our vision. With Zed we&#x27;re going to get it right. Written in Rust, custom native UI framework, engineered to be collaborative. Just starting our private alpha this week, so the timing of this announcement feels quite fitting.<p>Here&#x27;s a talk I gave last month: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;wXT73bBr83s" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;wXT73bBr83s</a></text></item></parent_chain><comment><author>nh2</author><text>&gt; Sadly, Sublime is sort of dead.<p>Sublime has ongoing development on <a href="https:&#x2F;&#x2F;www.sublimetext.com&#x2F;dev" rel="nofollow">https:&#x2F;&#x2F;www.sublimetext.com&#x2F;dev</a> and the last major release (4) was just about a year ago.</text></comment> | <story><title>Sunsetting Atom</title><url>https://github.blog/2022-06-08-sunsetting-atom/</url></story><parent_chain><item><author>frostwarrior</author><text>&gt; Emacs, vim<p>Unlike VSCode, Emacs and Vim have a learning curve. And turning them into full blown IDEs makes their usage even more complex.<p>&gt; Sublime<p>Sadly, Sublime is sort of dead.<p>&gt; TextMate<p>TextMate: Text editor for macOS</text></item><item><author>shakow</author><text>&gt; Atom practically invented the kind of extensions that VSCode had<p>Let me introduce you to Emacs, vim, Sublime, TextMate, ...</text></item><item><author>quaunaut</author><text>Atom practically invented the kind of extensions that VSCode had, and even several years into VSCode&#x27;s life Atom far outstripped it in Extensions.<p>Perf became the biggest problem however, which VSCode took over.</text></item><item><author>aniforprez</author><text>IMO the killer thing that VSCode has over all the other editors is the wealth of extensions and a certain degree of simplicity. What are your plans for Zed in terms of extensibility and are you aligning more towards making something beefy and full-featured like the IntelliJ offerings or something more &quot;lightweight&quot; like VSCode or Sublime?</text></item><item><author>nathansobo</author><text>Founder of Atom here. We&#x27;re building the spiritual successor to Atom over at <a href="https:&#x2F;&#x2F;zed.dev" rel="nofollow">https:&#x2F;&#x2F;zed.dev</a>.<p>We learned a lot with Atom and had a great time, but it always fell short of our vision. With Zed we&#x27;re going to get it right. Written in Rust, custom native UI framework, engineered to be collaborative. Just starting our private alpha this week, so the timing of this announcement feels quite fitting.<p>Here&#x27;s a talk I gave last month: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;wXT73bBr83s" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;wXT73bBr83s</a></text></item></parent_chain><comment><author>boredtofears</author><text>Sublime is very much not dead. It&#x27;s still much faster than vscode or any other heavyweight IDE.</text></comment> |
19,941,245 | 19,939,689 | 1 | 2 | 19,937,131 | train | <story><title>Spina bifida: Keyhole surgery repairs baby spine in womb</title><url>https://www.bbc.co.uk/news/health-48253477</url></story><parent_chain></parent_chain><comment><author>escapologybb</author><text>This is amazing news, it really is.<p>Slightly off topic but I would like to address the people in this thread saying things along the lines of &quot;with a medical condition is serious as this, it&#x27;s better to abort&quot;<p>Yeah, fuck no.<p>I was born in 1978 in the UK with spina bifida and Chiari malformation of the back of my brain which basically means a couple of the ventricles are being pulled by my spine out of my skull.[1] (Very basically)<p>If you look at any sort of scan of my brain and ask a Neurologist what they are looking at and they will tell you very forthrightly that the person whose scan they are looking at will definitely be uncommunicative, will have cognitive impairment, will probably be on a ventilator and will definitely have a foreshortened life. (This is not from some hypothetical thought experiment, I&#x27;ve done this over the years)<p>So, speaking as a 41-year-old quadriplegic hacker with spina bifida who&#x27;s not on a ventilator; let me say that life finds a way. I was written off so many times it&#x27;s unreal, medicine is not a science but rather a series of very very very good guesses. We need doctors, but we need lots of opinions and you don&#x27;t have to do what they say. They gave Stephen Hawking three or four years to live when he got his MND diagnosis, he lived another 30 years or so.<p>My life is great, yes I&#x27;m quadriplegic but once you get past that little speed bump I have a job, friends, a wonderful partner, family everywhere, a very serious addiction to Raspberry Pi&#x27;s and exploiting networks and I feel incredibly lucky. I am so glad I was not aborted.<p>Okay, because this is the Internet it&#x27;s time for the caveats<p>Yes I am aware I am slightly unusual and not all quadriplegics with spina bifida dodged a bullet in quite the same way I did.<p>Also, I think that the woman who is going to be carrying the baby to term has the right to decide whether to abort or not. Regardless of my opinion because I did not have to have a baby.<p>[1]: I know, eww right? :-)</text></comment> | <story><title>Spina bifida: Keyhole surgery repairs baby spine in womb</title><url>https://www.bbc.co.uk/news/health-48253477</url></story><parent_chain></parent_chain><comment><author>wincy</author><text>I’m in the US. My seven month old daughter was born with Spina Bifida. It didn’t show on the ultrasound, and it was a total shock to us. I can’t be sure but it seemed to correlate to a flu my wife had during the period that spina bifida “develops” (rather the spinal cord fails to develop fully).<p>The worst complication has to do with Chiari malformation, which affects her unconscious breathing. She gets upset or angry, and freezes up, turns purple, passes out, then requires CPR to be resuscitated. Most spina bifida babies do not have this complication.<p>We were told children with this condition die.<p>My wife obsessively reviewed the same papers the doctors had, and some others. She carefully googled every term she didn’t know. She discovered children prescribed clonidine had a MUCH improved prognosis. At her insistence and after some initial pushback and a very detailed email to the doctors, it was prescribed and my daughters condition improved substantially. She hasn’t had a single breath holding spell that’s required resuscitation since. It’s made us wary of the doctors recommendations. We feel like we have to be the experts, because if we’d blindly followed the doctors our daughter would likely be gone.<p>She’s so good natured and friendly, and she’s happy. She’s happy to be here and we’re happy to have her. If we knew there was no hope, or that she’d be permanently mentally disabled, I can’t honestly say that we’d have fought this hard for her.<p>It’s also taught me who my real friends are, my wife’s family has been so supportive while mine has retreated almost completely. People do NOT like being around tragedy if they can help it. They’ve given us “plenty of space”. My wife’s grandmother, who we weren’t close to before, has given us amazing outpourings of support and her time, visiting our daughter in the hospital almost every day. In the months leading up to our daughters birth grandma had seemed to be deteriorating due to dementia, but she has a new lease on life. I can’t say why this has happened, but it feels like a miracle.<p>One of the best things that happened to me during all this was a gray beard software engineer overheard me talking about my daughter. He took me aside and told me he had spina bifida, and we talked at length about it, and it was one of the nicest things anyone has ever done for me. It made me have hope when before I had none. I never would have known he had it. He’s lived a long and fulfilling life, a life I want my daughter to have.</text></comment> |
22,337,926 | 22,336,446 | 1 | 3 | 22,326,109 | train | <story><title>Ask HN: What job can a “jack of all trades” look for?</title><text>tl;dnr: Unhappy at my job after &gt;7 years. Love being a jack of all trades. Love learning new things. Hate being stagnant. Hate being the smartest person in the room. Need something new. What roles out there fit the skill set of someone that is good at a whole lot of things, but doesn&#x27;t feel like a master&#x2F;senior in any one of them?<p>-<p>I&#x27;ve been at the same small company for over 7 years. I started at the bottom, worked my way to the top after 3 years, and I&#x27;ve been here since. For a couple years I created new positions for myself because I hate being stagnant, but there&#x27;s nothing else to do here.<p>I&#x27;m proficient in many things and enjoy doing all of them. Development (full stack), server admin, data center management, DevOps, project management, managing teams, VoIP, routing&#x2F;switching, training, sales... the list goes on.<p>My issue is I haven&#x27;t had formal training in a lot of it, and I didn&#x27;t have any mentors or people above me to teach me more because this company is too small. I just love learning and love moving forward so I kept teaching myself new things, and then using them in the company. I don&#x27;t actually feel like I have impostor syndrome, but I also feel like someone that is filling these roles at another company probably knows&#x2F;does it better job than I can. I&#x27;m just a big fish in a small pond here.<p>So finally to my question: what role&#x2F;job title I should be looking for? All the searching I do points me to one specific roles. PHP Developer. Systems Admin. Network Engineer. Etc. Are there any other &quot;Jack of all trades&quot; out there that can tell me what your job title is, and what I could be looking for?</text></story><parent_chain><item><author>akcreek</author><text>I have a wide-ranging self-taught skill set as well that I&#x27;ve developed over the last 14 years of running my own businesses. I&#x27;ll share what I&#x27;m doing from a high level as it might not be the most common path.<p>I&#x27;ve been acquiring small but promising businesses that don&#x27;t have the right team in place to move them forward. I bootstrap them on my own and replace my roles as the business can afford staff. Once enough roles are replaced, I&#x27;m able to start looking for the next business. I&#x27;m on my fourth business now. Sold the first two, the third is a productized service netting seven figures, and I just acquired the fourth, which is a SaaS business that I believe has great potential.<p>Currently, I&#x27;m formalizing this method and will build a team that can execute it much more quickly than me alone. I&#x27;ll be shooting for a new business every 12-18 months to build a portfolio. We&#x27;ll have a group of partners and a small staff that will be focused on getting these acquisitions straightened out and growing, then we&#x27;ll install a team to run them full-time and we&#x27;ll go on to the next one.<p>So just taking what I&#x27;ve been doing for years and everything I&#x27;ve learned from it and scaling it up to reduce the timeframe from acquisition to growth and then operation of the business.<p>If OP or anyone else who identifies themself in a similar manner wants to chat, email is in my profile. I&#x27;m actively looking for people like us to work with.</text></item></parent_chain><comment><author>fxtentacle</author><text>I support this approach. I learned a lot about online marketing and selling physical products by purchasing a struggling online shop. There&#x27;s even dedicated web pages like flippa.com or empireflippers.com</text></comment> | <story><title>Ask HN: What job can a “jack of all trades” look for?</title><text>tl;dnr: Unhappy at my job after &gt;7 years. Love being a jack of all trades. Love learning new things. Hate being stagnant. Hate being the smartest person in the room. Need something new. What roles out there fit the skill set of someone that is good at a whole lot of things, but doesn&#x27;t feel like a master&#x2F;senior in any one of them?<p>-<p>I&#x27;ve been at the same small company for over 7 years. I started at the bottom, worked my way to the top after 3 years, and I&#x27;ve been here since. For a couple years I created new positions for myself because I hate being stagnant, but there&#x27;s nothing else to do here.<p>I&#x27;m proficient in many things and enjoy doing all of them. Development (full stack), server admin, data center management, DevOps, project management, managing teams, VoIP, routing&#x2F;switching, training, sales... the list goes on.<p>My issue is I haven&#x27;t had formal training in a lot of it, and I didn&#x27;t have any mentors or people above me to teach me more because this company is too small. I just love learning and love moving forward so I kept teaching myself new things, and then using them in the company. I don&#x27;t actually feel like I have impostor syndrome, but I also feel like someone that is filling these roles at another company probably knows&#x2F;does it better job than I can. I&#x27;m just a big fish in a small pond here.<p>So finally to my question: what role&#x2F;job title I should be looking for? All the searching I do points me to one specific roles. PHP Developer. Systems Admin. Network Engineer. Etc. Are there any other &quot;Jack of all trades&quot; out there that can tell me what your job title is, and what I could be looking for?</text></story><parent_chain><item><author>akcreek</author><text>I have a wide-ranging self-taught skill set as well that I&#x27;ve developed over the last 14 years of running my own businesses. I&#x27;ll share what I&#x27;m doing from a high level as it might not be the most common path.<p>I&#x27;ve been acquiring small but promising businesses that don&#x27;t have the right team in place to move them forward. I bootstrap them on my own and replace my roles as the business can afford staff. Once enough roles are replaced, I&#x27;m able to start looking for the next business. I&#x27;m on my fourth business now. Sold the first two, the third is a productized service netting seven figures, and I just acquired the fourth, which is a SaaS business that I believe has great potential.<p>Currently, I&#x27;m formalizing this method and will build a team that can execute it much more quickly than me alone. I&#x27;ll be shooting for a new business every 12-18 months to build a portfolio. We&#x27;ll have a group of partners and a small staff that will be focused on getting these acquisitions straightened out and growing, then we&#x27;ll install a team to run them full-time and we&#x27;ll go on to the next one.<p>So just taking what I&#x27;ve been doing for years and everything I&#x27;ve learned from it and scaling it up to reduce the timeframe from acquisition to growth and then operation of the business.<p>If OP or anyone else who identifies themself in a similar manner wants to chat, email is in my profile. I&#x27;m actively looking for people like us to work with.</text></item></parent_chain><comment><author>chirau</author><text>This business of buying and selling businesses, I have heard a bit about it here and there but i don&#x27;t even know where to start looking for people who are either selling or who are buying. I&#x27;d love to look into it as I think I would quite enjoy it. Any resources you could point to?</text></comment> |
9,402,716 | 9,402,747 | 1 | 3 | 9,401,860 | train | <story><title>JVM Internals (2013)</title><url>http://blog.jamesdbloom.com/JVMInternals.html</url></story><parent_chain></parent_chain><comment><author>sorokod</author><text>Perm. Generation was removed in Java 8<p><a href="https:&#x2F;&#x2F;www.google.co.uk&#x2F;url?sa=t&amp;source=web&amp;rct=j&amp;ei=zoczVejCEvK07QbUyYHABw&amp;url=https:&#x2F;&#x2F;blogs.oracle.com&#x2F;poonam&#x2F;entry&#x2F;about_g1_garbage_collector_permanent&amp;ved=0CC0QFjAF&amp;usg=AFQjCNF4QzNUlcnBz2m1O3iiJuiP5Mqebg&amp;sig2=uwZeba7-exlnPKskw4p3lQ" rel="nofollow">https:&#x2F;&#x2F;www.google.co.uk&#x2F;url?sa=t&amp;source=web&amp;rct=j&amp;ei=zoczVe...</a></text></comment> | <story><title>JVM Internals (2013)</title><url>http://blog.jamesdbloom.com/JVMInternals.html</url></story><parent_chain></parent_chain><comment><author>pjmlp</author><text>While a very interesting article, and it provides a broad overview of what is to be expected by any JVM implementing the &quot;JVM Specification&quot;, not all JVMs are made alike.<p>For example, JikesRVM, Aonix, IBM Websphere Real Time, OS&#x2F;400 JVM (which makes use of OS&#x2F;400 kernel JIT and TIMI) and many others.</text></comment> |
9,055,208 | 9,054,288 | 1 | 2 | 9,053,149 | train | <story><title>The world's slowest Linux PC</title><url>http://www.extremetech.com/extreme/124287-the-worlds-slowest-linux-pc</url><text></text></story><parent_chain></parent_chain><comment><author>stragulus</author><text>This reminds me of the dial-in server I built in our student home back in &#x27;97-&#x27;98. It was a 386sx 16Mhz with 2MB of memory and a 40MB hard drive that you had to preheat in the oven or it wouldn&#x27;t spin up. That was realistically the lowest spec&#x27;d hardware you could actually get to run linux on.<p>It took half an hour to boot, but that was okay since it was always on anyway. It took about 5 minutes to set up a ppp connection using a dial-in modem, and then the whole house had internet access through its network adapter. Unless someone had tripped over the coax cables again of course..</text></comment> | <story><title>The world's slowest Linux PC</title><url>http://www.extremetech.com/extreme/124287-the-worlds-slowest-linux-pc</url><text></text></story><parent_chain></parent_chain><comment><author>voltagex_</author><text>Previously: <a href="https://news.ycombinator.com/item?id=8791812" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=8791812</a>, <a href="https://news.ycombinator.com/item?id=5581851" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=5581851</a></text></comment> |
4,372,981 | 4,372,884 | 1 | 2 | 4,372,563 | train | <story><title>Why Explore Space? A 1970 Letter to a Nun in Africa.</title><url>http://launiusr.wordpress.com/2012/02/08/why-explore-space-a-1970-letter-to-a-nun-in-africa/</url></story><parent_chain><item><author>dmlorenzetti</author><text>When Bill Gates' wife began pushing him to work on issues of third-world health, this was more or less his argument against it. She dug up the statistics to show that this idea, while intuitive, is not supported by fact. As health improves-- and in particular as child mortality goes down-- birth rates fall accordingly.<p>As we all know, Gates got on board, and now funds a lot of health research and on-the-ground initiatives.</text></item><item><author>jxcole</author><text>I don't know if this makes me cruel, but whenever people talk about donating money to starving children in Africa, I always imagine the following: If I were to donate some amount of money to starving children in an impoverished nation every year I could, theoretically, bring some of them out of starvation. However, these children would then grow into adults, and then these adults would have children of their own. The number of these new children would almost certainly be higher than the number I originally helped bring out of famine, so at that point there would be just as many if not more starving children than we had to begin with. So in my mind the question really goes the other way, how does donating money to buy food for starving children in Africa improve Africa's condition in the long term? What problems caused these nations to produce more children than food and what is being done to eliminate the source of these problems, rather than just the symptoms?</text></item></parent_chain><comment><author>sliverstorm</author><text>As I understand it, Gates funds <i>health</i> related research, e.g. clean drinking water or malaria. Your parent was discussing the simple provision of free food.</text></comment> | <story><title>Why Explore Space? A 1970 Letter to a Nun in Africa.</title><url>http://launiusr.wordpress.com/2012/02/08/why-explore-space-a-1970-letter-to-a-nun-in-africa/</url></story><parent_chain><item><author>dmlorenzetti</author><text>When Bill Gates' wife began pushing him to work on issues of third-world health, this was more or less his argument against it. She dug up the statistics to show that this idea, while intuitive, is not supported by fact. As health improves-- and in particular as child mortality goes down-- birth rates fall accordingly.<p>As we all know, Gates got on board, and now funds a lot of health research and on-the-ground initiatives.</text></item><item><author>jxcole</author><text>I don't know if this makes me cruel, but whenever people talk about donating money to starving children in Africa, I always imagine the following: If I were to donate some amount of money to starving children in an impoverished nation every year I could, theoretically, bring some of them out of starvation. However, these children would then grow into adults, and then these adults would have children of their own. The number of these new children would almost certainly be higher than the number I originally helped bring out of famine, so at that point there would be just as many if not more starving children than we had to begin with. So in my mind the question really goes the other way, how does donating money to buy food for starving children in Africa improve Africa's condition in the long term? What problems caused these nations to produce more children than food and what is being done to eliminate the source of these problems, rather than just the symptoms?</text></item></parent_chain><comment><author>mynameishere</author><text>Health generally improves with the underlying economy, not because of charity. The underlying economy is going to correlate with damn near other statistic one way or another.<p>More credibly, the "War on Poverty" was an abject failure in every way.</text></comment> |
25,791,515 | 25,791,598 | 1 | 2 | 25,789,603 | train | <story><title>Tell HN: Dropbox now requires access to contacts for Google login</title><text>I remember I was using Google login to login to my Dropbox and in the last year or so Dropbox started asking me to access my contacts in Google. I would always deny access and still manage to successfully login. Yesterday I tried the same but with no luck. I contacted Dropbox support and this is their reply:<p>&gt; I&#x27;m afraid that is not possible at the time. I apologize for any inconvenience this may cause.<p>Interesting that they chose this route when users are getting more and more privacy-aware.</text></story><parent_chain><item><author>jjbinx007</author><text>Ads on Amazon Prime are infuriating. And I can&#x27;t help think how annoying it must be for people with disabilities.<p>My other bugbear are the auto playing videos on Netflix and the use of massive spoilers in episode thumbnails.<p>As a single consumer in a vast ocean I don&#x27;t think my opinions will ever be listened to. Right now it&#x27;s worth putting up with this crap as the benefits outweigh the cost but if it gets any worse I&#x27;ll be unsubscribing.</text></item><item><author>KingOfCoders</author><text>Same with the ads for Amazon videos on Amazon Prime. They are ads and I don&#x27;t want ads. But they don&#x27;t see it that way (don&#x27;t get me started on the forced watching of texts on Blue Rays).</text></item><item><author>Ensorceled</author><text>I left dropbox when they changed the full page upsell to &quot;dropbox business&quot; so that I couldn&#x27;t easily figure out how to skip it and get on with my work.<p>I had a paid pro account at the time.<p>I actually had a conversation with a product manager; I checked the yes you can contact me when I cancelled my account. They simply refused to admit that an upsell was a advertisement and that disrupting my workflow on my paid, professional account for an ad was wrong.<p>The other interesting thing about that conversation, they could not understand how a sole proprietor would see no benefit from collaboration tools and kept making up bizarre scenarios where I could use them.<p>I actually asked them if they were a product manager or a salesperson at one point.<p>To Dropbox&#x27;s credit, that product manager didn&#x27;t try to retain me, they were genuinely trying to figure out why I had quit; they just couldn&#x27;t grok the reason.</text></item></parent_chain><comment><author>jonpurdy</author><text>This is a great example of why I still prefer torrenting films and TV shows as opposed to using my wife’s Netflix sub: the pirated media is better!<p>Netflix and Hulu and competing with easier to use and more flexible pirated media, whether they like it or not. The consistency and flexibility of the VLC interface (or whatever media player you choose) is vastly better than whatever features a Netflix PM is trying to push to juice their metrics.<p>(I won’t even get into unskippable screens on Blu-Ray discs which are removed on the pirate version.)</text></comment> | <story><title>Tell HN: Dropbox now requires access to contacts for Google login</title><text>I remember I was using Google login to login to my Dropbox and in the last year or so Dropbox started asking me to access my contacts in Google. I would always deny access and still manage to successfully login. Yesterday I tried the same but with no luck. I contacted Dropbox support and this is their reply:<p>&gt; I&#x27;m afraid that is not possible at the time. I apologize for any inconvenience this may cause.<p>Interesting that they chose this route when users are getting more and more privacy-aware.</text></story><parent_chain><item><author>jjbinx007</author><text>Ads on Amazon Prime are infuriating. And I can&#x27;t help think how annoying it must be for people with disabilities.<p>My other bugbear are the auto playing videos on Netflix and the use of massive spoilers in episode thumbnails.<p>As a single consumer in a vast ocean I don&#x27;t think my opinions will ever be listened to. Right now it&#x27;s worth putting up with this crap as the benefits outweigh the cost but if it gets any worse I&#x27;ll be unsubscribing.</text></item><item><author>KingOfCoders</author><text>Same with the ads for Amazon videos on Amazon Prime. They are ads and I don&#x27;t want ads. But they don&#x27;t see it that way (don&#x27;t get me started on the forced watching of texts on Blue Rays).</text></item><item><author>Ensorceled</author><text>I left dropbox when they changed the full page upsell to &quot;dropbox business&quot; so that I couldn&#x27;t easily figure out how to skip it and get on with my work.<p>I had a paid pro account at the time.<p>I actually had a conversation with a product manager; I checked the yes you can contact me when I cancelled my account. They simply refused to admit that an upsell was a advertisement and that disrupting my workflow on my paid, professional account for an ad was wrong.<p>The other interesting thing about that conversation, they could not understand how a sole proprietor would see no benefit from collaboration tools and kept making up bizarre scenarios where I could use them.<p>I actually asked them if they were a product manager or a salesperson at one point.<p>To Dropbox&#x27;s credit, that product manager didn&#x27;t try to retain me, they were genuinely trying to figure out why I had quit; they just couldn&#x27;t grok the reason.</text></item></parent_chain><comment><author>ballenf</author><text>Ads on Prime on kids content is <i>especially</i> frustrating.<p>My biggest goal with kids is to help them with their focus and limit exposure to &quot;infinity pools&quot; of content. It&#x27;s not that I have a problem with the content of the ads, it&#x27;s that they train kids&#x27; brains to want to switch quickly between content the moment a show has a lull.<p>It creates that FOMO that they might not be watching the most exciting show right now because the ad always makes the other show look way better.<p>Youtube is of course the epitome of this issue, although disabling the mini-player on kids content helps a little.</text></comment> |
22,860,399 | 22,860,308 | 1 | 3 | 22,859,938 | train | <story><title>California, Oregon and Washington announce western states pact</title><url>https://www.gov.ca.gov/2020/04/13/california-oregon-washington-announce-western-states-pact/</url></story><parent_chain><item><author>RandomTisk</author><text>He wanted to shut down travel from China in January, something he got reamed for politically by the media and the left. Damned if you do and all that.</text></item><item><author>danhak</author><text>Yes, he wanted to dodge responsibility for the unpleasant job of shutting things down. Now he wants to enjoy positive publicity for opening things back up.</text></item><item><author>throwaway_USD</author><text>Ironically Trump refused to &quot;shutdown&quot; the States a decision he deferred to the Governors.</text></item><item><author>aazaa</author><text>Possibly relevant:<p>&gt; President Trump tweeted Monday that the &quot;decision to open up the states&quot; following shutdown measures taken to stop the spread of the coronavirus lies with him, not governors.<p><a href="https:&#x2F;&#x2F;www.axios.com&#x2F;trump-coronavirus-reopening-governors-states-3ce510ff-cd94-4b4a-89b8-58d8bca5d69f.html" rel="nofollow">https:&#x2F;&#x2F;www.axios.com&#x2F;trump-coronavirus-reopening-governors-...</a></text></item></parent_chain><comment><author>standardUser</author><text>That is one tiny step in response to a crisis that requires dozens of quick, bold steps. If he gets one point for decisive action and 20 points for delaying, deferring, muddling and contradicting, how much credit has he really earned?</text></comment> | <story><title>California, Oregon and Washington announce western states pact</title><url>https://www.gov.ca.gov/2020/04/13/california-oregon-washington-announce-western-states-pact/</url></story><parent_chain><item><author>RandomTisk</author><text>He wanted to shut down travel from China in January, something he got reamed for politically by the media and the left. Damned if you do and all that.</text></item><item><author>danhak</author><text>Yes, he wanted to dodge responsibility for the unpleasant job of shutting things down. Now he wants to enjoy positive publicity for opening things back up.</text></item><item><author>throwaway_USD</author><text>Ironically Trump refused to &quot;shutdown&quot; the States a decision he deferred to the Governors.</text></item><item><author>aazaa</author><text>Possibly relevant:<p>&gt; President Trump tweeted Monday that the &quot;decision to open up the states&quot; following shutdown measures taken to stop the spread of the coronavirus lies with him, not governors.<p><a href="https:&#x2F;&#x2F;www.axios.com&#x2F;trump-coronavirus-reopening-governors-states-3ce510ff-cd94-4b4a-89b8-58d8bca5d69f.html" rel="nofollow">https:&#x2F;&#x2F;www.axios.com&#x2F;trump-coronavirus-reopening-governors-...</a></text></item></parent_chain><comment><author>danhak</author><text>I&#x27;m not able to find examples of that. Can you point to any mainstream media outlets &quot;reaming&quot; him over that decision?</text></comment> |
32,476,401 | 32,474,643 | 1 | 2 | 32,472,412 | train | <story><title>Twilio incident: What Signal users need to know</title><url>https://support.signal.org/hc/en-us/articles/4850133017242</url></story><parent_chain><item><author>jamespwilliams</author><text>The attack Twilio suffered is almost identical to the recent attack against Cloudflare: <a href="https:&#x2F;&#x2F;blog.cloudflare.com&#x2F;2022-07-sms-phishing-attacks&#x2F;" rel="nofollow">https:&#x2F;&#x2F;blog.cloudflare.com&#x2F;2022-07-sms-phishing-attacks&#x2F;</a> (even down the wording of the text messages, which are nearly identical). Cloudflare’s use of security keys prevented the attackers getting access to any accounts in that case.<p>These attacks are sophisticated and are capable of bypassing TOTP or mobile-app-based MFA. If this is widespread, I’d be surprised if we didn’t see a massive influx of breaches soon. The vast majority of companies are not well defended against this.</text></item></parent_chain><comment><author>hn_throwaway_99</author><text>&gt; These attacks are sophisticated and are capable of bypassing TOTP or mobile-app-based MFA.<p>To be honest, I wish people would stop parroting that these attacks were &quot;sophisticated&quot;. In my opinion, I&#x27;d call something like Pegasus spyware &quot;sophisticated&quot;. I don&#x27;t think these attacks were that sophisticated at all - they were just standard issue, MITM attacks using targeted text messages - and they just took advantage of what is always the weakest link in security: people. I think of myself as a general middle-of-the-road software developer but I think I could have easily replicated this attack myself.</text></comment> | <story><title>Twilio incident: What Signal users need to know</title><url>https://support.signal.org/hc/en-us/articles/4850133017242</url></story><parent_chain><item><author>jamespwilliams</author><text>The attack Twilio suffered is almost identical to the recent attack against Cloudflare: <a href="https:&#x2F;&#x2F;blog.cloudflare.com&#x2F;2022-07-sms-phishing-attacks&#x2F;" rel="nofollow">https:&#x2F;&#x2F;blog.cloudflare.com&#x2F;2022-07-sms-phishing-attacks&#x2F;</a> (even down the wording of the text messages, which are nearly identical). Cloudflare’s use of security keys prevented the attackers getting access to any accounts in that case.<p>These attacks are sophisticated and are capable of bypassing TOTP or mobile-app-based MFA. If this is widespread, I’d be surprised if we didn’t see a massive influx of breaches soon. The vast majority of companies are not well defended against this.</text></item></parent_chain><comment><author>maerF0x0</author><text>to be clear they are not able to &quot;bypass&quot; TOTP or mobile-app-based MFA in the way security folks think of that term. They were able to bypass humans[1], which are often the weakest link in security related matters.<p>[1]: &quot;Twilio became aware of unauthorized access to information related to a limited number of Twilio customer accounts through a sophisticated social engineering attack designed to steal employee credentials. This broad based attack against our employee base succeeded in fooling some employees into providing their credentials. The attackers then used the stolen credentials to gain access to some of our internal systems, where they were able to access certain customer data. &quot; <a href="https:&#x2F;&#x2F;www.twilio.com&#x2F;blog&#x2F;august-2022-social-engineering-attack" rel="nofollow">https:&#x2F;&#x2F;www.twilio.com&#x2F;blog&#x2F;august-2022-social-engineering-a...</a></text></comment> |
38,330,561 | 38,330,566 | 1 | 2 | 38,330,158 | train | <story><title>A Timeline of the OpenAI Board</title><url>https://loeber.substack.com/p/a-timeline-of-the-openai-board</url></story><parent_chain></parent_chain><comment><author>schiffern</author><text>Poe AI is just a clear straight conflict, no question there.<p>On the governance matter, the thesis is a bit more shakey.<p><pre><code> &gt; Helen Toner and Tasha McCauley... participating in an... AI governance organization... calls into question the independence of their votes.
&gt; I am not accusing anyone (to be clear, even the Board Directors that I consider conflicted) of having acted subject to conflicts of interest. [AKA &quot;Just Asking Questions&quot; technique]
&gt; If... this act of governance was unwise, it calls into serious question the ability of these people and their organizations... to conduct governance
</code></pre>
So they&#x27;re conflicted because they&#x27;re also in governance, and they shouldn&#x27;t govern because they might have been conflicted.<p>It seems like the author&#x27;s real problem isn&#x27;t any specific conduct by these two board members, but more of a &quot;you got chocolate in my peanut butter&quot; issue.</text></comment> | <story><title>A Timeline of the OpenAI Board</title><url>https://loeber.substack.com/p/a-timeline-of-the-openai-board</url></story><parent_chain></parent_chain><comment><author>upwardbound</author><text>&gt; they asked: who on earth are Tasha McCauley and Helen Toner?<p>As a prominent researcher in AI safety (I discovered prompt injection) I should explain that Helen Toner is a big name in the AI safety community - she’s one of the top 20 most respected people in our community, like Rohin Shah.<p>The “who on earth” question is a good question about Tasha. But grouping Helen in with Tasha is just sexist. By analogy, Tasha is like Kimbal Musk, whereas Helen is like Tom Mueller.<p>Tasha seems unqualified but Helen is extremely qualified. Grouping them together is sexist and wrong.</text></comment> |
22,947,406 | 22,945,274 | 1 | 3 | 22,944,490 | train | <story><title>Facebook agreed to censor posts after Vietnam slowed traffic – sources</title><url>https://www.reuters.com/article/us-vietnam-facebook-exclusive/exclusive-facebook-agreed-to-censor-posts-after-vietnam-slowed-traffic-sources-idUSKCN2232JX</url></story><parent_chain><item><author>londons_explore</author><text>Undersea cable <i>is</i> pretty unreliable. Most major cables expect to break every few years.<p>Usually breaks are caused by humans (ships pulling anchors, sabotage&#x2F;spying). Sometimes they&#x27;re natural (caused by wildlife, ocean floor movement, flaws in the cable design).<p>Fixes usually take a few hours if they happen at the endpoints, or weeks if they happen somewhere under the ocean.<p>Interestingly, spying breaks always involve <i>three</i> simultaneous breaks in the cable. The cable is broken at two points, and then broken at a third point in the middle to put spy equipment. They do this so the people operating the cable can&#x27;t tell where the spy equipment was inserted, since otherwise you can tell where a cable is broken or being tampered with by sending light down the cable and seeing how long before light reflects off the broken bit and comes back to the end.<p>Using statistical methods, you can see how frequently you&#x27;d expect a cable to break at different points along it&#x27;s length simultaneously, and it happens a lot more than raw chance would suggest.</text></item><item><author>NhanH</author><text>Just tangentially related to the topic at hand, but I have a question to ask HN.
The main trans-Pacific cable connection between Vietnam and the US tends to be damaged several times a year (3&lt;n&lt;10 is my guess), which severely slow downs any connection to the outside of Vietnam during the time it is under maintenance. This always happens suspiciously during major political holiday (Independence day and the likes), so Vietnamese has just assumed that is a blatant censorship attempt. The wiki page has an outage section you can read: <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Asia-America_Gateway" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Asia-America_Gateway</a> , it doesn&#x27;t list anything beyond 2018, but the situation is the same.<p>So my question is, how likely it is that the cable system are just really shitty? Or is the assumption of bald-faced censorship correct?</text></item></parent_chain><comment><author>bogomipz</author><text>&gt;&quot;Undersea cable is pretty unreliable.&quot;<p>This is not true. Submarine cable installations generally have a lifespan of 20-25 years although that&#x27;s even being extended now to 30 years with advances in WDM gear. Also in water deeper than 1500 meters the cables are typically laid on the ocean floor. This is done because it is beyond the limit of trawl fishing anchors.<p>&gt;&quot;Interestingly, spying breaks always involve three simultaneous breaks in the cable. The cable is broken at two points, and then broken at a third point in the middle to put spy equipment.&quot;<p>Yeah this is not true at all. Where did you get this from? Fiber cables can be tapped by simply adding a bend radius to the cable which allows it to leak. [1], Further you can shoot a light down both ends of a fiber and easily discern that there is more than one break in the cable.<p>[1] <a href="https:&#x2F;&#x2F;www.thefoa.org&#x2F;tech&#x2F;ref&#x2F;appln&#x2F;tap-fiber.html" rel="nofollow">https:&#x2F;&#x2F;www.thefoa.org&#x2F;tech&#x2F;ref&#x2F;appln&#x2F;tap-fiber.html</a></text></comment> | <story><title>Facebook agreed to censor posts after Vietnam slowed traffic – sources</title><url>https://www.reuters.com/article/us-vietnam-facebook-exclusive/exclusive-facebook-agreed-to-censor-posts-after-vietnam-slowed-traffic-sources-idUSKCN2232JX</url></story><parent_chain><item><author>londons_explore</author><text>Undersea cable <i>is</i> pretty unreliable. Most major cables expect to break every few years.<p>Usually breaks are caused by humans (ships pulling anchors, sabotage&#x2F;spying). Sometimes they&#x27;re natural (caused by wildlife, ocean floor movement, flaws in the cable design).<p>Fixes usually take a few hours if they happen at the endpoints, or weeks if they happen somewhere under the ocean.<p>Interestingly, spying breaks always involve <i>three</i> simultaneous breaks in the cable. The cable is broken at two points, and then broken at a third point in the middle to put spy equipment. They do this so the people operating the cable can&#x27;t tell where the spy equipment was inserted, since otherwise you can tell where a cable is broken or being tampered with by sending light down the cable and seeing how long before light reflects off the broken bit and comes back to the end.<p>Using statistical methods, you can see how frequently you&#x27;d expect a cable to break at different points along it&#x27;s length simultaneously, and it happens a lot more than raw chance would suggest.</text></item><item><author>NhanH</author><text>Just tangentially related to the topic at hand, but I have a question to ask HN.
The main trans-Pacific cable connection between Vietnam and the US tends to be damaged several times a year (3&lt;n&lt;10 is my guess), which severely slow downs any connection to the outside of Vietnam during the time it is under maintenance. This always happens suspiciously during major political holiday (Independence day and the likes), so Vietnamese has just assumed that is a blatant censorship attempt. The wiki page has an outage section you can read: <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Asia-America_Gateway" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Asia-America_Gateway</a> , it doesn&#x27;t list anything beyond 2018, but the situation is the same.<p>So my question is, how likely it is that the cable system are just really shitty? Or is the assumption of bald-faced censorship correct?</text></item></parent_chain><comment><author>oldsklgdfth</author><text>I was under the impression that underwater cables were fairly reliable, but it seems they require frequent repair.<p>Per wikipedia:
&gt; Still, cable breaks are by no means a thing of the past, with more than 50 repairs a year in the Atlantic alone,[48] and significant breaks in 2006, 2008, and 2009.</text></comment> |
16,976,148 | 16,976,003 | 1 | 3 | 16,975,185 | train | <story><title>86% of CrashCrate subscribers used passwords already leaked in other breaches</title><url>https://www.troyhunt.com/86-of-passwords-are-terrible-and-other-statistics/</url></story><parent_chain><item><author>charDiversity</author><text>When I feel like a security goon&#x27;s arbitrary and capricious password policy is irrational and counterproductive, I make my passwords worse in the hopes that I have to someday read it to someone, or perhaps it gets spilt outin the open, and then everyone will see how forcing me to pick a password that adheres to certain characteristics solved nothing.<p>Just wait. Someday you will see dumps of pwnt password that look like:<p><pre><code> Password-1234
Password_1234
Password!1234
Password&amp;1234
Password?1234
Password$1234
</code></pre>
And that is rated as a &quot;<i>VERY STRONG</i>&quot; password.<p>Have fun with your character diversity, and your 90 day password expiration rotation schemes. Go ahead and try to force me into a corner. I&#x27;m still picking terrible passwords and I&#x27;m picking especially terrible ones because someone out there is trying to pull my strings.<p>Pull my strings. Make me more predictable within your little security policy world. See how that plays out.</text></item></parent_chain><comment><author>Avamander</author><text>Just recently Estonian Information System Authority published a new report (including new guidelines for passwords) basically telling: &quot;Drop password requirements, allow long passwords and restrict the use of short and top-n passwords&quot;.<p>Why I&#x27;m mentioning this is because now I have an actual official document I can send to Estonian companies in addition to my own words (that weren&#x27;t previously believed, ugh) why their requirements are inane. I think this kind of behaviour shows that we actually need some kind of monitoring or regulation here to build more secure software for everyone.<p>Also as you mentioned bad-&quot;strong&quot; passwords, I &quot;love&quot; how something like &quot;Qwerty!1234&quot; satisfies most requirements but &quot;8f434346648f6b96df89dda901c5176b10a6d83961dd3c1ac88b59b2dc327aa4&quot; is not okay because it doesn&#x27;t contain an uppercase letter or a symbol.</text></comment> | <story><title>86% of CrashCrate subscribers used passwords already leaked in other breaches</title><url>https://www.troyhunt.com/86-of-passwords-are-terrible-and-other-statistics/</url></story><parent_chain><item><author>charDiversity</author><text>When I feel like a security goon&#x27;s arbitrary and capricious password policy is irrational and counterproductive, I make my passwords worse in the hopes that I have to someday read it to someone, or perhaps it gets spilt outin the open, and then everyone will see how forcing me to pick a password that adheres to certain characteristics solved nothing.<p>Just wait. Someday you will see dumps of pwnt password that look like:<p><pre><code> Password-1234
Password_1234
Password!1234
Password&amp;1234
Password?1234
Password$1234
</code></pre>
And that is rated as a &quot;<i>VERY STRONG</i>&quot; password.<p>Have fun with your character diversity, and your 90 day password expiration rotation schemes. Go ahead and try to force me into a corner. I&#x27;m still picking terrible passwords and I&#x27;m picking especially terrible ones because someone out there is trying to pull my strings.<p>Pull my strings. Make me more predictable within your little security policy world. See how that plays out.</text></item></parent_chain><comment><author>dudul</author><text>I completely agree. &quot;Your password must be at least 10 character long, include 2 upper case, 2 lower case, 2 digits, 2 special characters, must be changed every 60 days and cannot be reused for the next 3 years&quot;<p>G0Fuc4Y@urse!f<p>To me this is a sure way that people are gonna pick horrible and stupid passwords.</text></comment> |
34,504,856 | 34,503,817 | 1 | 3 | 34,502,566 | train | <story><title>Ask HN: What is the weirdest or most surreal recent technology you have seen?</title><text>If possible, provide links to demos, products pages, etc.<p>Limit posts to one tech per post to make it easier for votes to reflect HN’s voting patterns and make it easier to filter related comments.<p>___<p>Here are some examples from CES:<p><a href="https:&#x2F;&#x2F;youtube.com&#x2F;watch?v=SYYXida84Nc">https:&#x2F;&#x2F;youtube.com&#x2F;watch?v=SYYXida84Nc</a></text></story><parent_chain><item><author>lqet</author><text>ChatGPT. This is the only technology that truly freaked me out in my lifetime (I am 35). It competently explained to me the difference between Dijkstra&#x27;s algorithm and A* in a psalm-like poem [0]. It was able to find misspelled words in a long text I just made up, list them in alphabetical order, and explain to me why I misspelled them. It correctly simulated a ChatGPT instance which was accessible via a HTTP API, and it correctly simulated a Linux machine on which this simulated remote ChatGPT-API was accessed via curl. It was able to give the responses in XML, JSON, CSV, and other formats, and it was able to simulate Linux tools like cut, grep, sort, awk, jq, sed and others. It was able to add an <i>additional</i> layer of a ChatGPT simulation without problems. It was able to do entity recognition in a long text I provided, and was able to list the entities in a table, with the correct wikipedia article and a summary of the article as columns. It was able to do rudimentary public transit route planning in my home town in Germany (in the form of: go the XY Station, trains will run every 15 minutes from there to the main station, from there you will have long distance lines to Z, etc.), with an apology that it does not have current schedule data for Germany and I should visit bahn.de for better results. When it failed for math questions, it was able to give me Wolfram Alpha queries to find the correct results. It was able to formulate complex SPARQL queries to query Wikidata, run these against the simulated ChatGPT instance via a curl request, grep out some results I wanted, and list them in tabular form with corresponding Wikipedia articles.<p>All of this in one session, as part of a pleasant conversation, basically indistinguishable from a conversation with a real human.<p>[0]<p><pre><code> &gt; Could you explain the difference between A* and Dijkstra&#x27;s algorithm in the style of a Psalm?
&lt; Sure, here is a Psalm-style explanation of the difference between A* and Dijkstra&#x27;s algorithm:
Hark, ye seekers of the shortest path,
And listen well to what I say:
There are two algorithms that ye may use,
To guide ye on your way.
Dijkstra&#x27;s algorithm is a general one,
That can be used in any case,
It explores the graph from the source node,
To find the path with the least amount of space.
But A* is a more specialized tool,
With a heuristic function to guide,
It searches more efficiently,
And helps ye reach the other side.
So choose wisely, oh seekers of the path,
And let these algorithms be your guide,
For they will lead ye to your destination,
And help ye avoid the pitfalls on the side.</code></pre></text></item></parent_chain><comment><author>Acutulus</author><text>It&#x27;s an incredibly striking piece of technology and really shows which way the future winds will likely be blowing. A particular exchange I had with it left a mark on me, in which I requested it to behave like a used car salesman attempting to close a deal with a hungry customer. It proceeded to repurpose idioms, make dad-jokes and sling double entendres about the shared joy of cars and hamburgers and how they both are simple, dependable and iconic in my way of life. I sat there for a minute reading over it, nearly in disbelief.<p>I can accept a system such as ChatGPT synthesizing from data it sucked in, making educated guesses and so on. But to see it do such lingustic gymnastics with a very non-concrete request was humbling. It&#x27;s given me a lot of pause about the way I absorb digital information and the varying degrees to which I have implicitly assumed the reliability of that information; site A slightly more trustworthy than site B, et cetera. To me, that old trust heuristic I relied on, one I have honed thanks to unfettered broadband for two decades, is now completely upended. It probably has been for some time to be fair, but my time with ChatGPT really cemented that feeling.<p>Every freshly written statement that comes to me through an internet connected device now gets a side-eye by default.</text></comment> | <story><title>Ask HN: What is the weirdest or most surreal recent technology you have seen?</title><text>If possible, provide links to demos, products pages, etc.<p>Limit posts to one tech per post to make it easier for votes to reflect HN’s voting patterns and make it easier to filter related comments.<p>___<p>Here are some examples from CES:<p><a href="https:&#x2F;&#x2F;youtube.com&#x2F;watch?v=SYYXida84Nc">https:&#x2F;&#x2F;youtube.com&#x2F;watch?v=SYYXida84Nc</a></text></story><parent_chain><item><author>lqet</author><text>ChatGPT. This is the only technology that truly freaked me out in my lifetime (I am 35). It competently explained to me the difference between Dijkstra&#x27;s algorithm and A* in a psalm-like poem [0]. It was able to find misspelled words in a long text I just made up, list them in alphabetical order, and explain to me why I misspelled them. It correctly simulated a ChatGPT instance which was accessible via a HTTP API, and it correctly simulated a Linux machine on which this simulated remote ChatGPT-API was accessed via curl. It was able to give the responses in XML, JSON, CSV, and other formats, and it was able to simulate Linux tools like cut, grep, sort, awk, jq, sed and others. It was able to add an <i>additional</i> layer of a ChatGPT simulation without problems. It was able to do entity recognition in a long text I provided, and was able to list the entities in a table, with the correct wikipedia article and a summary of the article as columns. It was able to do rudimentary public transit route planning in my home town in Germany (in the form of: go the XY Station, trains will run every 15 minutes from there to the main station, from there you will have long distance lines to Z, etc.), with an apology that it does not have current schedule data for Germany and I should visit bahn.de for better results. When it failed for math questions, it was able to give me Wolfram Alpha queries to find the correct results. It was able to formulate complex SPARQL queries to query Wikidata, run these against the simulated ChatGPT instance via a curl request, grep out some results I wanted, and list them in tabular form with corresponding Wikipedia articles.<p>All of this in one session, as part of a pleasant conversation, basically indistinguishable from a conversation with a real human.<p>[0]<p><pre><code> &gt; Could you explain the difference between A* and Dijkstra&#x27;s algorithm in the style of a Psalm?
&lt; Sure, here is a Psalm-style explanation of the difference between A* and Dijkstra&#x27;s algorithm:
Hark, ye seekers of the shortest path,
And listen well to what I say:
There are two algorithms that ye may use,
To guide ye on your way.
Dijkstra&#x27;s algorithm is a general one,
That can be used in any case,
It explores the graph from the source node,
To find the path with the least amount of space.
But A* is a more specialized tool,
With a heuristic function to guide,
It searches more efficiently,
And helps ye reach the other side.
So choose wisely, oh seekers of the path,
And let these algorithms be your guide,
For they will lead ye to your destination,
And help ye avoid the pitfalls on the side.</code></pre></text></item></parent_chain><comment><author>jvanderbot</author><text>That&#x27;s wrong. It&#x27;s poetic, but incorrect. These tools are about as good as a non specialist with time to undertake some bullshitting.</text></comment> |
35,213,195 | 35,211,476 | 1 | 2 | 35,210,421 | train | <story><title>More students are turning away from college and toward apprenticeships</title><url>https://www.wsj.com/articles/more-students-are-turning-away-from-college-and-toward-apprenticeships-15f3a05d</url></story><parent_chain><item><author>alsaaro</author><text>As someone who has worked two of the most intensive blue collar jobs, people should be wary of romanticizing blue collar work.<p>Blue collar workers are expected to really work at their jobs. White collar workers can chill if there is no work to be done, or be sent home early with pay, or take a relaxation day and just browse the internet and listen to podcasts. They have perks, you see white collar workers leaving work early to attend baseball games and do fun activities with their colleagues.<p>Indeed, some white collar workers are so &quot;underworked&quot; they can literally work multiple full time remote jobs. Blue collar guys can&#x27;t work remote, so expect to pay for child care and endure the mourning commute.<p>Blue collar workers aren&#x27;t necessarily paid based on merit, this is formally true if you work in a union-shop where promotions are primarily based on tenue; if non-union there may be no promotion path for most workers because management has a &quot;fresh meat for the grinder&quot; approach to entry level staffing.<p>From a social perspective people don&#x27;t respect blue collar workers. Believe that nobody who writes think pieces praising blue collar workers wants their daughters dating a blue collar worker or wants their children becoming them.</text></item></parent_chain><comment><author>listless</author><text>At the risk of sounding like a terrible person, I&#x27;d like to be honest for a second about why I went to college, which is to avoid this exactly reality that you just laid out.<p>I enlisted in the military after finding college to be too boring for my taste. 3 months later I found myself doing the hardest manual labor of my life on a riverboat for the Coast Guard. The pay was not great and nobody cared if you didn&#x27;t feel like working or were exhausted. The system (as is the military) is not merit based and the guys at the top were pretty awful to the ones at the bottom. By contrast, the officers in the coast guard had nice offices, nice crisp uniforms, nice private rooms, nice private dining quarters, ect. And the difference between those two (enlisted and officer) is a college degree.<p>What I learned is that I did not want to be an enlisted man. It&#x27;s a lot of very hard work for little pay and even the highest enlisted man is still saluting the lowest officer.<p>This was enough to galvanize me to go to college and finish as quickly as I could.<p>Blue collar jobs are not for everyone. They were not for me. I realize the Coast Guard is not a perfect microcosm of the real world, but in a lot of ways it is. Now that I have the white collar job, I still chuckle at &quot;mental health days&quot; and people complaining about being &quot;burnt out&quot;. I chuckle because I remember those days on the river, baking in the hot sun after working for 36 hours straight and how much we all would have laughed until we cried if those words had come out of someone&#x27;s mouth.</text></comment> | <story><title>More students are turning away from college and toward apprenticeships</title><url>https://www.wsj.com/articles/more-students-are-turning-away-from-college-and-toward-apprenticeships-15f3a05d</url></story><parent_chain><item><author>alsaaro</author><text>As someone who has worked two of the most intensive blue collar jobs, people should be wary of romanticizing blue collar work.<p>Blue collar workers are expected to really work at their jobs. White collar workers can chill if there is no work to be done, or be sent home early with pay, or take a relaxation day and just browse the internet and listen to podcasts. They have perks, you see white collar workers leaving work early to attend baseball games and do fun activities with their colleagues.<p>Indeed, some white collar workers are so &quot;underworked&quot; they can literally work multiple full time remote jobs. Blue collar guys can&#x27;t work remote, so expect to pay for child care and endure the mourning commute.<p>Blue collar workers aren&#x27;t necessarily paid based on merit, this is formally true if you work in a union-shop where promotions are primarily based on tenue; if non-union there may be no promotion path for most workers because management has a &quot;fresh meat for the grinder&quot; approach to entry level staffing.<p>From a social perspective people don&#x27;t respect blue collar workers. Believe that nobody who writes think pieces praising blue collar workers wants their daughters dating a blue collar worker or wants their children becoming them.</text></item></parent_chain><comment><author>briHass</author><text>Anyone that hasn&#x27;t done manual labor really has no idea how rough it can be. I worked as an office-furniture-mover in my early 20s (Summers in college), and some days were pretty tough. Granted, that&#x27;s pretty low on the manual labor skills spectrum, but even for a guy in prime physical shape, it&#x27;s tiring and has elements of danger.<p>Now that I&#x27;m double that age, the manual labor I&#x27;ve done like rewiring my house, installing all my own HVAC equipment, and all the yard work for a large property is much harder. I stay sore for days, and it&#x27;s easy to push too hard to get something done and get injured or overwork my body to where my heart rate stays elevated for hours.<p>There&#x27;s something to be said for working with your brain. The worst days dealing with idiot product management and never-ending Jira tickets don&#x27;t compare to unloading a truck in a hot warehouse or kneeling in a crawlspace for hours re-piping a sewer line.</text></comment> |
2,702,951 | 2,702,874 | 1 | 2 | 2,702,384 | train | <story><title>Sitting for hours can shave years off life</title><url>http://www.cnn.com/2011/HEALTH/06/24/sitting.shorten.life/index.html</url><text></text></story><parent_chain></parent_chain><comment><author>Shenglong</author><text>Sitting kills you, saturated fats kill you, disposable chopsticks kills you, sugar kills you... We're so concerned about how to extend the time we have, that we're neglecting the time we actually do have.<p>Here's me: I haven't eaten vegetables since I was 8 years old. I sit down in front of a computer screen for multiple hours a day. I eat any junk food I want, as long as it tastes good. I drop a ton of water weight before a fight for weighing purposes. I've learned the physically straining technique, <i>Needle through Glass</i> (throwing a sewing needle through a pane of glass), and I do a lot of binge training.<p>Although I'm perfectly healthy right now, is it possible that I'll die when I'm 60? Yeah. But at least I'll have fully enjoyed my life. It beats the hell out of half living for 90 years. Not to mention, it's also possible your life will be cut short by a rampaging bus... and that has nothing to do with preventable measures.<p>My two cents.</text></comment> | <story><title>Sitting for hours can shave years off life</title><url>http://www.cnn.com/2011/HEALTH/06/24/sitting.shorten.life/index.html</url><text></text></story><parent_chain></parent_chain><comment><author>mark_l_watson</author><text>I almost died of complications from blod clots in my left leg 4 1/2 years ago. I recovered OK, but I have been on the <i>war</i> <i>path</i> since then warning people about not sitting too long - both my doctor and I think that working too long at a desk without breaks caused my blood clots.<p>I recommend simply setting a timer for about 20 minutes as a reminder to get up and walk around for a minute or two. Also, it is probably a good idea to walk around the block (at least) a few times each work day.</text></comment> |
2,617,553 | 2,616,856 | 1 | 3 | 2,616,750 | train | <story><title>Groupon is Effectively Insolvent</title><url>http://m.minyanville.com/?guid=34936&catid=4</url></story><parent_chain></parent_chain><comment><author>pkaler</author><text>The word "effectively" in the title is a weasel word.<p>Groupon is balance sheet insolvent by definition. Their liabilities are greater than assets.<p>Groupon is cash flow solvent by definition. They are able to pay liabilities NET60.<p>In Q2-Q4 2010, Groupon had $669mm with a net loss of $398mm. That is a ratio of about -0.59. In Q1 2011, Groupon had revenue of $644mm with a net loss of $102mm. That is a ratio of about -0.16.<p>If you are long Groupon, then you are betting that -0.16 approaches zero and then turns positive.<p>The moral of the story is: haters gonna hate.</text></comment> | <story><title>Groupon is Effectively Insolvent</title><url>http://m.minyanville.com/?guid=34936&catid=4</url></story><parent_chain></parent_chain><comment><author>wccrawford</author><text>They're trading that temporary debt for hypergrowth, as the article says.<p>"For the remainder of the year they had $669 million in revenue (simply staggering), but had a net loss attributable to Groupon of $398 million. This year, Q1 results showed revenue growth continuing to soar, with revenues of $644 million, but a net loss attributable to Groupon of $102 million."<p>So the time periods were different, but the revenues were the same. They went from losing $400mil to only losing $100mil... That sounds to me like they are getting close to being profitable again... And in a very short timeframe.<p>As for it being like a Ponzi scheme, it's not. Ponzi relied on lying to the investors and telling them the money came from good investments. It wasn't sustainable, and nothing could fix it. Groupon is sustainable and hasn't lied (that I know of) to their investors, new or old. It doesn't even need fixing as it looks like it's already on the fast-track to profit, based on the numbers provided.</text></comment> |
17,652,923 | 17,652,628 | 1 | 3 | 17,643,832 | train | <story><title>Advice giving: A subtle pathway to power</title><url>https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=6779&context=lkcsb_research</url></story><parent_chain><item><author>timwaagh</author><text>i find receiving advice to be difficult because the other person essentially places himself above you. That is why i try to be careful with dishing out too much advice. But sometimes its necessary. and sometimes i just cannot help it.<p>if i give advice, i try to do it in a non-personal way. like &#x27;i just found a cool trick to do y&#x27; rather than &#x27;you are doing it like x, but doing y would be better&#x27;.</text></item></parent_chain><comment><author>pmichaud</author><text>I face this issue frequently, and one thing that I find helps is acknowledge what&#x27;s happening:<p>1. If you&#x27;re talking to an actual equal, and you&#x27;re not sure but you&#x27;re trying to be helpful, then prefacing with that is good. &quot;Look, you know way more about your problem than I do, but when you asked for advice [they did <i>ask</i> for the advice, right?] the first dumb idea I had was _____&quot;<p>2. Sometimes you actually are &quot;above&quot; the other person in the context of the advice you&#x27;re giving. You&#x27;re actually just an expert and they aren&#x27;t, for example. In that case you have a couple options that are context dependent.<p>One is to just ask: &quot;Do you mind if I give you some unsolicited advice that maybe you already thought of?&quot;<p>The other is to lampshade it. This works best in cases where the power difference is just objectively obvious. I use this exact phrasing with my daughter: &quot;Do you mind if I patronize you a little? If anyone can patronize anyone it&#x27;s a father and his daughter, right?&quot; But it works with others as well, for example I&#x27;m often in the position of giving life advice to undergrads, and I might say something like &quot;Do you mind if I old-man-patronize you a little? It might be helpful!&quot;<p>I think most of the weird power dynamics and discomfort come from assuming something is common knowledge when it isn&#x27;t. It may be true that I&#x27;m better than you, and even that each of us knows it, but if we haven&#x27;t mutually acknowledged it to each other and made it common knowledge, then it&#x27;ll strike an awkward chord when I act like it&#x27;s true... unless I put it right out there in common knowledge before I start.<p>The same is true if we&#x27;re equals but I&#x27;m giving you advice anyway--it&#x27;s awkward because... maybe I think we&#x27;re not equals? If I preface with &quot;we&#x27;re equals, and in fact you know more than I do here because you&#x27;re the one in the situation&quot; then it&#x27;s clear where I&#x27;m coming from and it&#x27;s not awkward.<p>Finally, all the different ways of prefacing above critically give the other person the opportunity to say &quot;actually, no, don&#x27;t,&quot; so they have dignity and agency in the exchange.</text></comment> | <story><title>Advice giving: A subtle pathway to power</title><url>https://ink.library.smu.edu.sg/cgi/viewcontent.cgi?article=6779&context=lkcsb_research</url></story><parent_chain><item><author>timwaagh</author><text>i find receiving advice to be difficult because the other person essentially places himself above you. That is why i try to be careful with dishing out too much advice. But sometimes its necessary. and sometimes i just cannot help it.<p>if i give advice, i try to do it in a non-personal way. like &#x27;i just found a cool trick to do y&#x27; rather than &#x27;you are doing it like x, but doing y would be better&#x27;.</text></item></parent_chain><comment><author>tchaffee</author><text>Interpersonal skills really come into play. Every situation is different. What you are describing sounds like an interaction with an equal. Which might end up having to be more of a sales pitch for your idea than giving advice. There are plenty of situations where the difference in experience calls for a more assertive approach. Senior dev to junior dev, or even expert to client. Selling an idea takes time, and if you were hired to be the expert you sometimes have to just insist and give strong advice in the interest of efficiency. Not everyone junior will be convinced by authority, but enough are that it saves a great deal of time.</text></comment> |
11,950,931 | 11,950,952 | 1 | 2 | 11,950,687 | train | <story><title>Concrete AI Safety Problems</title><url>https://openai.com/blog/concrete-ai-safety-problems/</url></story><parent_chain><item><author>lacker</author><text>This sort of &quot;internal&quot; approach to AI safety, where you attempt to build fundamental limits into the AI itself, seems like it is easily thwarted by someone who intentionally builds an AI without these safety mechanisms. As long as AI is an open technology there will always be some criminals who just want to see the world burn.<p>IMO, a better approach to AI safety research is to focus on securing the first channels that a malicious AI would be likely to exploit. Like spam, and security. Can you make communications spam-resistant? Can you make an unhackable internet service?<p>Those seem hard, but more plausible than the &quot;Watch out for paperclip optimizers&quot; approach to AI safety. It just feels like inventing a way to build a nuclear weapon that can&#x27;t actually explode, and then hoping the problem of nuclear war is solved.</text></item></parent_chain><comment><author>jimrandomh</author><text>For the most part these aren&#x27;t aimed at people making bad AGIs deliberately, but rather, at well-intentioned developers launching AGIs with serious bugs. Those developers will want to include safety mechanisms, and will, hopefully, be the first to make AGIs with major capabilities.<p>We should also be working to secure the channels an AGI might exploit, but most of those are already tied to an economic incentive to invest in security, and are already getting large investments compared to the relatively tiny field of AI safety.</text></comment> | <story><title>Concrete AI Safety Problems</title><url>https://openai.com/blog/concrete-ai-safety-problems/</url></story><parent_chain><item><author>lacker</author><text>This sort of &quot;internal&quot; approach to AI safety, where you attempt to build fundamental limits into the AI itself, seems like it is easily thwarted by someone who intentionally builds an AI without these safety mechanisms. As long as AI is an open technology there will always be some criminals who just want to see the world burn.<p>IMO, a better approach to AI safety research is to focus on securing the first channels that a malicious AI would be likely to exploit. Like spam, and security. Can you make communications spam-resistant? Can you make an unhackable internet service?<p>Those seem hard, but more plausible than the &quot;Watch out for paperclip optimizers&quot; approach to AI safety. It just feels like inventing a way to build a nuclear weapon that can&#x27;t actually explode, and then hoping the problem of nuclear war is solved.</text></item></parent_chain><comment><author>ikeboy</author><text>&gt;All else being equal, not many people would prefer to destroy the world. Even faceless
corporations, meddling governments, reckless scientists, and other agents of doom require
a world in which to achieve their goals of profit, order, tenure, or other villainies.
If our extinction proceeds slowly enough to allow a moment of horrified realization, the
doers of the deed will likely be quite taken aback on realizing that they have actually
destroyed the world. Therefore I suggest that if the Earth is destroyed, it will probably
be by mistake.<p><a href="https:&#x2F;&#x2F;intelligence.org&#x2F;files&#x2F;CognitiveBiases.pdf" rel="nofollow">https:&#x2F;&#x2F;intelligence.org&#x2F;files&#x2F;CognitiveBiases.pdf</a></text></comment> |
3,160,486 | 3,160,368 | 1 | 2 | 3,160,134 | train | <story><title>Protect IP Renamed E-Parasites Act; Would Create The Great Firewall Of America</title><url>http://www.techdirt.com/articles/20111026/12130616523/protect-ip-renamed-e-parasites-act-would-create-great-firewall-america.shtml</url></story><parent_chain><item><author>DanielBMarkham</author><text>The key point here, as another commenter pointed out, is <i>they are not going to give up.</i><p>You can win a battle here, perhaps rally around your congressman and get it killed, or petition the president to veto it, but it doesn't matter. They'll just be back again next year, and the next year, and the next.<p>This is the importance of constitutional amendments: they settle things on a broad scale exactly to prevent this kind of nipping (although it still happens, it just takes much longer time) We need an amendment or two around internet and computer freedom, specifically that computers are extensions of our minds, not machines to play content on, and that the internet is our primary form of political organization and persuasion, not a fancy telephone line.<p>I hate to be all doom-and-gloom, but I think that boat has sailed. The tech community <i>might</i> get its act together, give up all social causes and form some kind of committee or group to push for such amendments, but I seriously doubt it. Half the community is in bed with big media and the other half are just as concerned with other issues as this one. We are not organized, coherent, or focused.<p>Just saw a great series on PBS, Ken Burns' "Prohibition". It was all about how focused groups can make big changes -- but it takes a long time. I don't see the kind of anger and outrage against this as we had against alcohol. Very sad, because this is a lot worse.</text></item></parent_chain><comment><author>narrator</author><text>The reason they can continue to relentlessly push for it is because the paid lobbyists who are pushing for it are just doing their day job. They can spend the rest of their lives at it. The public only has so much spare time.</text></comment> | <story><title>Protect IP Renamed E-Parasites Act; Would Create The Great Firewall Of America</title><url>http://www.techdirt.com/articles/20111026/12130616523/protect-ip-renamed-e-parasites-act-would-create-great-firewall-america.shtml</url></story><parent_chain><item><author>DanielBMarkham</author><text>The key point here, as another commenter pointed out, is <i>they are not going to give up.</i><p>You can win a battle here, perhaps rally around your congressman and get it killed, or petition the president to veto it, but it doesn't matter. They'll just be back again next year, and the next year, and the next.<p>This is the importance of constitutional amendments: they settle things on a broad scale exactly to prevent this kind of nipping (although it still happens, it just takes much longer time) We need an amendment or two around internet and computer freedom, specifically that computers are extensions of our minds, not machines to play content on, and that the internet is our primary form of political organization and persuasion, not a fancy telephone line.<p>I hate to be all doom-and-gloom, but I think that boat has sailed. The tech community <i>might</i> get its act together, give up all social causes and form some kind of committee or group to push for such amendments, but I seriously doubt it. Half the community is in bed with big media and the other half are just as concerned with other issues as this one. We are not organized, coherent, or focused.<p>Just saw a great series on PBS, Ken Burns' "Prohibition". It was all about how focused groups can make big changes -- but it takes a long time. I don't see the kind of anger and outrage against this as we had against alcohol. Very sad, because this is a lot worse.</text></item></parent_chain><comment><author>JoshTriplett</author><text>I agree with you about the persistence problem; the government acts like a rotten two-year-old that keeps trying until it gets its way. Like a two-year-old, it learns what it can get away with and tries harder each time. <i>Unlike</i> a two-year-old, it doesn't grow up and learn what not to do.<p>We shouldn't need a constitutional amendment here; the constitution is a whitelist of things the federal government may do, not a blacklist of things it may not do. While the constitution does sadly include the notion of copyright, it does not include anything allowing regulatory authority over the Internet.</text></comment> |
772,108 | 771,982 | 1 | 2 | 771,940 | train | <story><title>Why AT&T Killed Google Voice</title><url>http://online.wsj.com/article/SB10001424052970204683204574358552882901262.html?mod=rss_opinion_main</url><text></text></story><parent_chain></parent_chain><comment><author>andreyf</author><text>Well written opinion, but misleading title - I was expecting WSJ to have found out that it <i>was</i> AT&#38;T who killed Google Voice, although we don't seem to know that yet. One can hope that this is high-profile enough reporting to let out some info about what happened, exactly.<p>Also, some of the advice is questionable:<p><i>Transition away from "owning" airwaves. As we've seen with license-free bandwidth via Wi-Fi networking, we can share the airwaves without interfering with each other. Let new carriers emerge based on quality of service rather than spectrum owned. Cellphone coverage from huge cell towers will naturally migrate seamlessly into offices and even homes via Wi-Fi networking. No more dropped calls in the bathroom.</i><p>But cell phone coverage reaches a lot farther than wifi. I'm not a radio physicist, but I think 802.11 allows communication over 14 channels, each of which can be crowded, and some of which can cause interference for others. It was designed with overlapping WAP and a (relatively) small number of people connecting to each. Now, I'm rather clueless about the implementations of cell phone protocols, but I know enough to think twice before saying "open her yup, baby! no dropped calls in the bathroom!" - it doesn't sound as if the author does. Can we keep GSM/GPRS/EDGE if we allow many overlapping connections? If not, are backwards compatible replacements feasible, or will we need to replace every cell phone in the country?<p><i>Encourage faster and faster data connections to our homes and phones. It should more than double every two years. To homes, five megabits today should be 10 megabits in 2011, 25 megabits in 2013 and 100 megabits in 2017.</i><p>Also, virgins should rain from the sky. The number should double every year. Five virgins today should be 10 virgins in 2011, etc.<p><i>These data-connection speeds are technically doable today, with obsolete voice and video policy holding it back.</i><p>What policy is he talking about? Is there a reason for this policy aside from holding back data speeds and virgins?</text></comment> | <story><title>Why AT&T Killed Google Voice</title><url>http://online.wsj.com/article/SB10001424052970204683204574358552882901262.html?mod=rss_opinion_main</url><text></text></story><parent_chain></parent_chain><comment><author>ghshephard</author><text>It's an opinion piece that covers no ground we haven't already read a hundred times over - I didn't see any reporting in the article. Sad - in order to compete with the Tech Crunches of the world, even the WSJ is throwing out flashy LinkBait with little substance.</text></comment> |
32,008,425 | 32,006,824 | 1 | 2 | 31,999,936 | train | <story><title>Making IRC better</title><url>https://sourcehut.org/blog/2022-07-06-sourcehut-and-irc/</url></story><parent_chain><item><author>dpedu</author><text>Am I the only person that doesn&#x27;t want IRCv3? I don&#x27;t find the new features important or compelling (telling others when I am typing is creepy!) and I see v3&#x27;s rise as only leading to some sort of schism.</text></item></parent_chain><comment><author>Eupraxias</author><text>You&#x27;re not alone - IRC is precious as one of the last places where one can still avoid exactly these kind of features! It looks&#x2F;fits&#x2F;feels more or less the same today as it was when I started using it in 1996, and I have never felt it needs improvement.<p>&quot;Weechat in a terminal on my other monitor&quot; feels like home to me. I&#x27;m hoping we can opt-out, but in my opinion it will be a dark and dogless day when we cannot.</text></comment> | <story><title>Making IRC better</title><url>https://sourcehut.org/blog/2022-07-06-sourcehut-and-irc/</url></story><parent_chain><item><author>dpedu</author><text>Am I the only person that doesn&#x27;t want IRCv3? I don&#x27;t find the new features important or compelling (telling others when I am typing is creepy!) and I see v3&#x27;s rise as only leading to some sort of schism.</text></item></parent_chain><comment><author>mjevans</author><text>My _opinion_ is that whatever really replaces &#x2F; evolves existing commonly used communications protocols already has an uphill battle. Further, as Gchat &#x2F; XMPP based chats showed (opinion observations): federation without a sufficiently rich baseline to ensure a basic user experience leads to fragmentation, silo-ing, and eventual death.<p>It has to fulfill the need of a common space for public discourse.<p>The specification must be open and free for all to use. There should be no artificial restrictions on who is able to develop tools including servers, clients, intermediary or subsystems, or provide a service to host any of them. Federation also introduces a higher risk of spam and bad actors; it&#x27;s part of the price of freedom so the protocol should have an intended use pattern that addresses that type of issue; ideally without forcing the association of a &#x27;real identity&#x27; to all use of the system. That won&#x27;t solve all of the problems, and it adds a bunch of other problems. However a system of the commons may see users such as government organizations or heavily regulated industries where endpoints agree to use such an identity in some way.</text></comment> |
8,398,605 | 8,398,570 | 1 | 3 | 8,398,127 | train | <story><title>After raising $50M, Reddit forces all remote workers to relocate to SF</title><url>http://venturebeat.com/2014/10/01/after-raising-50m-reddit-forces-remote-workers-to-relocate-to-sf-or-get-fired/</url></story><parent_chain><item><author>nemothekid</author><text>I don&#x27;t think this convo is entirely fair to Yishan. While I&#x27;m not familiar with Reddit&#x27;s tech stack or management policies, I can&#x27;t say they have been a shining example of a remote engineering team. For a site that is simply some text and comments, they have a staggering amount of downtime and timeouts.<p>Whatever they were doing before didn&#x27;t seem to be working and maybe getting everyone in one place is the fix to that (not to say a remote team doesn&#x27; work, as GitHub gets along just fine).</text></item><item><author>gk1</author><text>Here&#x27;s the Twitter conversation between DHH and Yishan Wong, as of right now:<p>DHH: Story I heard about Reddit post-$50M investment includes everyone not in San Francisco getting 1 week to decide whether to move or GTFO. o.0<p>Yishan Wong: Yes, we are relocating ppl back to SF w&#x2F;generous relo package &amp; COL adjustment, +3mos severance for anyone who can’t make the move, and no, the timeline for the move is not 1 week, but through the end of the year. Decision was also independent of fundraising.<p>DHH: Very sad to hear. Especially for a company like Reddit that&#x27;s all about bringing people together for causes regardless of location. Also, are you claiming that there never was a deadline of 1 week? That it was &quot;through end of year&quot; from the beginning?<p>Yishan: Intention is to get whole team under one roof for optimal teamwork. Our goal is to retain 100% of the team.<p>DHH: Hey, at least the shit sandwich comes with a smile and a thank you. Guess everything is peachy then.<p>Yishan: Originally we asked for decision in 2 weeks but realized almost immediately that was too short and extended the timeline to EOY.<p>DHH: Man, that is some cruel shit. Was that such that you could have a full headcount before the $50M check cleared?</text></item></parent_chain><comment><author>fleaflicker</author><text><i>For a site that is simply some text and comments, they have a staggering amount of downtime and timeouts.</i><p>At reddit&#x27;s scale, it doesn&#x27;t matter what they&#x27;re serving. The challeneges of serving that many pageviews are significant.</text></comment> | <story><title>After raising $50M, Reddit forces all remote workers to relocate to SF</title><url>http://venturebeat.com/2014/10/01/after-raising-50m-reddit-forces-remote-workers-to-relocate-to-sf-or-get-fired/</url></story><parent_chain><item><author>nemothekid</author><text>I don&#x27;t think this convo is entirely fair to Yishan. While I&#x27;m not familiar with Reddit&#x27;s tech stack or management policies, I can&#x27;t say they have been a shining example of a remote engineering team. For a site that is simply some text and comments, they have a staggering amount of downtime and timeouts.<p>Whatever they were doing before didn&#x27;t seem to be working and maybe getting everyone in one place is the fix to that (not to say a remote team doesn&#x27; work, as GitHub gets along just fine).</text></item><item><author>gk1</author><text>Here&#x27;s the Twitter conversation between DHH and Yishan Wong, as of right now:<p>DHH: Story I heard about Reddit post-$50M investment includes everyone not in San Francisco getting 1 week to decide whether to move or GTFO. o.0<p>Yishan Wong: Yes, we are relocating ppl back to SF w&#x2F;generous relo package &amp; COL adjustment, +3mos severance for anyone who can’t make the move, and no, the timeline for the move is not 1 week, but through the end of the year. Decision was also independent of fundraising.<p>DHH: Very sad to hear. Especially for a company like Reddit that&#x27;s all about bringing people together for causes regardless of location. Also, are you claiming that there never was a deadline of 1 week? That it was &quot;through end of year&quot; from the beginning?<p>Yishan: Intention is to get whole team under one roof for optimal teamwork. Our goal is to retain 100% of the team.<p>DHH: Hey, at least the shit sandwich comes with a smile and a thank you. Guess everything is peachy then.<p>Yishan: Originally we asked for decision in 2 weeks but realized almost immediately that was too short and extended the timeline to EOY.<p>DHH: Man, that is some cruel shit. Was that such that you could have a full headcount before the $50M check cleared?</text></item></parent_chain><comment><author>dataminer</author><text>Do you have data on reddit&#x27;s downtime to backup your claim? <a href="https://twitter.com/redditstatus" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;redditstatus</a> shows the last downtime was on April 9th, and that was scheduled.</text></comment> |
15,786,571 | 15,784,461 | 1 | 3 | 15,784,092 | train | <story><title>What Bikini Atoll Looks Like Today</title><url>https://medium.com/stanford-magazine/stanford-research-on-effects-of-radioactivity-from-bikini-atoll-nuclear-tests-on-coral-and-crab-dna-48459144020c</url></story><parent_chain></parent_chain><comment><author>ryandrake</author><text>&gt; “It’s equivalent to 216 Empire State Buildings being blown into the sky,” Palumbi says.<p>&gt; the armada of sunken warships, including the USS Saratoga, an aircraft carrier the length of a Manhattan avenue block that lies on the lagoon’s bottom.<p>Ughh, More &quot;Journalist-SI units of measurement.&quot; Would it kill him to actually describe the mass displaced in kg or lb, and say the actual length of the warship? I get that he&#x27;s trying to to dumb down measurements so they are understandable to people who don&#x27;t know what pounds and feet are, but by using Manhattan-specific units, he even fails for people outside of NYC. Further, he&#x27;s using one of his JSI units incorrectly: &quot;Empire State Building&quot; is typically used as a unit of height rather than mass. So much fail, avoidable by just using standard units of measurement!</text></comment> | <story><title>What Bikini Atoll Looks Like Today</title><url>https://medium.com/stanford-magazine/stanford-research-on-effects-of-radioactivity-from-bikini-atoll-nuclear-tests-on-coral-and-crab-dna-48459144020c</url></story><parent_chain></parent_chain><comment><author>Waterluvian</author><text>I had to see the rows of trees for myself. This is what I could find: <a href="https:&#x2F;&#x2F;www.google.ca&#x2F;maps&#x2F;place&#x2F;Bikini+Atoll&#x2F;@11.5262428,165.5602711,2175m&#x2F;data=!3m1!1e3!4m5!3m4!1s0x644c2180a24fadbf:0x4c3f21ce9753a027!8m2!3d11.6065142!4d165.3768099" rel="nofollow">https:&#x2F;&#x2F;www.google.ca&#x2F;maps&#x2F;place&#x2F;Bikini+Atoll&#x2F;@11.5262428,16...</a></text></comment> |
29,419,392 | 29,419,335 | 1 | 2 | 29,417,201 | train | <story><title>Vivaldi Browser 5.0</title><url>https://vivaldi.com/changelog-vivaldi-browser-5-0/</url></story><parent_chain><item><author>drcongo</author><text>Vivaldi is the exact opposite of what I want from a browser. I want a rendering engine and some tabs, that&#x27;s pretty much it. Vivaldi decided to encumber those two good things with a 1000 features and some horrific themes, making the entire application 1000 times slower than it could have been. Every time I&#x27;ve tried it it&#x27;s just reminded me of that old screenshot of MS Word with all the toolbars switched on [0], a ton of unnecessary cognitive load that 0.1% of their users will find useful. Browser design by committee.<p>[0] <a href="https:&#x2F;&#x2F;blog.codinghorror.com&#x2F;content&#x2F;images&#x2F;uploads&#x2F;2006&#x2F;02&#x2F;6a0120a85dcdae970b0120a86d6311970b-pi.png" rel="nofollow">https:&#x2F;&#x2F;blog.codinghorror.com&#x2F;content&#x2F;images&#x2F;uploads&#x2F;2006&#x2F;02...</a></text></item></parent_chain><comment><author>kunagi7</author><text>There&#x27;s a lot of browsers out there that already give the experience you want. Like Ungoogled Chromium (or regular Chromium).<p>I always see a lot of power users being enraged to other browsers when they remove features that the 1~5% of their users use so it&#x27;s a bit weird to see protests against one of the few browsers that attempt to reverse the oversimplification trend.<p>Vivaldi&#x27;s main deal is allowing the user to customize most of their browser. Themes, buttons, custom CSS, even side menu options. Even if they have improved it quite a bit there&#x27;s still a performance hit.</text></comment> | <story><title>Vivaldi Browser 5.0</title><url>https://vivaldi.com/changelog-vivaldi-browser-5-0/</url></story><parent_chain><item><author>drcongo</author><text>Vivaldi is the exact opposite of what I want from a browser. I want a rendering engine and some tabs, that&#x27;s pretty much it. Vivaldi decided to encumber those two good things with a 1000 features and some horrific themes, making the entire application 1000 times slower than it could have been. Every time I&#x27;ve tried it it&#x27;s just reminded me of that old screenshot of MS Word with all the toolbars switched on [0], a ton of unnecessary cognitive load that 0.1% of their users will find useful. Browser design by committee.<p>[0] <a href="https:&#x2F;&#x2F;blog.codinghorror.com&#x2F;content&#x2F;images&#x2F;uploads&#x2F;2006&#x2F;02&#x2F;6a0120a85dcdae970b0120a86d6311970b-pi.png" rel="nofollow">https:&#x2F;&#x2F;blog.codinghorror.com&#x2F;content&#x2F;images&#x2F;uploads&#x2F;2006&#x2F;02...</a></text></item></parent_chain><comment><author>RussianCow</author><text>&gt; a ton of unnecessary cognitive load that 0.1% of their users will find useful.<p>Maybe it&#x27;s been designed specifically for that 0.1%? There&#x27;s nothing wrong with not catering to the masses.</text></comment> |
10,724,888 | 10,724,860 | 1 | 3 | 10,724,735 | train | <story><title>Little Forms – an open source minimalistic GUI widget library written in plain C</title><url>http://runtimelegend.com/rep/lforms/index</url></story><parent_chain></parent_chain><comment><author>BruceM</author><text>Blendish (<a href="https:&#x2F;&#x2F;bitbucket.org&#x2F;duangle&#x2F;oui-blendish&#x2F;overview" rel="nofollow">https:&#x2F;&#x2F;bitbucket.org&#x2F;duangle&#x2F;oui-blendish&#x2F;overview</a>) is pretty amazing and lightweight (by itself).<p>It works with NanoVG, so it is useful in environments where you&#x27;re already running OpenGL.</text></comment> | <story><title>Little Forms – an open source minimalistic GUI widget library written in plain C</title><url>http://runtimelegend.com/rep/lforms/index</url></story><parent_chain></parent_chain><comment><author>fizixer</author><text>Just. Amazing!<p>As someone who is Gtk, Qt, C++ averse, I thought I&#x27;ll have to settle on something like FLTK. This is another option in my basket.<p>Is it tied to X or fairly independent? Because Wayland is an upcoming standard which aims to be a lot more cruft-free.</text></comment> |
25,047,349 | 25,047,609 | 1 | 2 | 25,046,157 | train | <story><title>One in five Covid-19 patients develop mental illness within 90 days – study</title><url>https://www.reuters.com/article/health-coronavirus-mental-illness-int-idUSKBN27P35N</url></story><parent_chain><item><author>treeman79</author><text>Congratulations, you have earned the achievement “chronic condition”.<p>Your rewards are as follows.<p>You have max exhaustion at all hours of the day!<p>Exercise recovery is bumped from next day to 2 weeks!<p>Your pain level is now on par with dying cancer patients!<p>Everyone now considers you lazy and incompetent!<p>Doctors now blame all symptoms on anxiety!<p>You gain +1 to medical research ability. But -20 to Reputation.<p>You now get spontaneous and useless medical advise from people that believe in essential oil.<p>You are now on timer with your job until sympathy runs out!<p>Disability now can mock you openly as clearly your faking and don’t have a real condition!<p>You are now a burden to your family!<p>+10 sneak score; you quickly learn to hide your suffering!<p>+20 to loneliness!<p>-20 to persuasion! Asking for help gets little from doctor&#x27;s.<p>+10 Planning! Your kids may be orphans soon, make sure they get taken care of. Read fine print on death benefits.
——-<p>Staying positive when you have a chronic condition is incredibly difficult.<p>Your not going to get through it without losing your mind now and then.</text></item></parent_chain><comment><author>verelo</author><text>This is a horrible part of COVID that no one seems to get. Chronic conditions are life changing, and no part of it is good.<p>It&#x27;s different, but as an example, I injured my back (i don&#x27;t really even know how) and was in intense pain for approximately 8 months. You know that feeling when you burn your hand on something? It normally last 5-15 minutes, well it was like that, but inside my lower spine all the time, for a solid 4 months...and then in duller state for another 4. I am still struggling with pain from time to time, but i&#x27;m once again able to sleep a full night (something i couldn&#x27;t do for around 5-6 months), do physical things and not regret every movement. At the start of the injury, i was probably the fittest I&#x27;ve ever been, but now i&#x27;m probably the least fit i&#x27;ve ever been. It&#x27;s seriously sucked. Who am I kidding, it still sucks...coughing hurts...but its improving and that gives me hope that one day it&#x27;ll be &#x27;normal&#x27; again.<p>Until you&#x27;ve had a long term injury, you have no idea how to sympathize. Right in the middle of this i had a close friend get upset with me that I came over when I knew he was painting, and didn&#x27;t offer to help. I was frustrated he even considered it a possibility, i was struggling to sit in a car for more than an hour, how was I going to paint a wall or ceiling? People just don&#x27;t understand.<p>To everyone suffering with something that inhibits their ability to enjoy life, i&#x27;m sorry but wish you the best. To everyone looking in from the outside, assume its 10x worse than what you see and reconsider your next move.</text></comment> | <story><title>One in five Covid-19 patients develop mental illness within 90 days – study</title><url>https://www.reuters.com/article/health-coronavirus-mental-illness-int-idUSKBN27P35N</url></story><parent_chain><item><author>treeman79</author><text>Congratulations, you have earned the achievement “chronic condition”.<p>Your rewards are as follows.<p>You have max exhaustion at all hours of the day!<p>Exercise recovery is bumped from next day to 2 weeks!<p>Your pain level is now on par with dying cancer patients!<p>Everyone now considers you lazy and incompetent!<p>Doctors now blame all symptoms on anxiety!<p>You gain +1 to medical research ability. But -20 to Reputation.<p>You now get spontaneous and useless medical advise from people that believe in essential oil.<p>You are now on timer with your job until sympathy runs out!<p>Disability now can mock you openly as clearly your faking and don’t have a real condition!<p>You are now a burden to your family!<p>+10 sneak score; you quickly learn to hide your suffering!<p>+20 to loneliness!<p>-20 to persuasion! Asking for help gets little from doctor&#x27;s.<p>+10 Planning! Your kids may be orphans soon, make sure they get taken care of. Read fine print on death benefits.
——-<p>Staying positive when you have a chronic condition is incredibly difficult.<p>Your not going to get through it without losing your mind now and then.</text></item></parent_chain><comment><author>tarsinge</author><text>Well I suffered from that for more than a decade but in the end in turned out in was indeed &quot;anxiety&quot;. Your thoughts can make you sick. It took me a long time to realize that idea, to admit that psychosomatic effects are real and strong, that it&#x27;s not craziness, and yes doctors are usually not very useful with that.<p>Simple test: what were your thoughts and emotions 5 minutes ago? 1 hour ago? since this morning? and how were you breathing (slowly with good posture or rapidly)? If your brain is constantly circling thoughts with no cool-down with bad posture it&#x27;s guaranteed you will have physical problems.<p>For me the cure was a combination of:<p>- Slow breathing exercises<p>- Mindfulness (to learn to listen to the body and emotions, an to be aware and able to &quot;control&quot; thoughts). No mysticism bullshit, just having a brain and body at rest and present.<p>- Stoic philosophy : not worrying with things not in my control, not being affected by outcomes (e.g. objectively did my best and the boss&#x2F;client is not happy? That&#x27;s fine for me)<p>- Strength training<p>- Nutrition<p>- Financial security (I know I&#x27;m lucky but that doesn&#x27;t change the point)<p>- Edit: &quot;reconnecting with nature&quot;: again no mysticism, just outdoor walks, gardening, and taking the time to observe and appreciate while being fine doing nothing<p>The best I could describe my default state now is as being relatively at peace, with no negative thoughts circling, slowly breathing with good posture (that I can maintain while coding long hours for example). I&#x27;m still of anxious nature and still worry about the future, but only on the time period I will allow it (and not as a the permanent background noise). YMMV obviously.</text></comment> |
32,534,392 | 32,533,813 | 1 | 3 | 32,532,282 | train | <story><title>The world map that reboots your brain</title><url>https://axbom.com/world-map/</url></story><parent_chain><item><author>dividefuel</author><text>The article seems to imply that people are primarily exposed to Mercator in school without discussing its shortcomings. However in my experience growing up in the 90s&#x2F;00s, we discussed lots of different projections and their respective tradeoffs. It was drilled in pretty deep that the Mercator reflected shapes accurately, but not relative sizes. I also remember seeing Robinson projection far more than Mercator, though again we were reminded that it&#x27;s not perfect either, and that any 2D projection will have its pros&#x2F;cons.</text></item></parent_chain><comment><author>epgui</author><text>I went to public school in Canada (NB) in the 1990s and 2000s and we also covered the topic quite well. Not only that, but we also had ready access to spinning globes we could look at and compare to projections.</text></comment> | <story><title>The world map that reboots your brain</title><url>https://axbom.com/world-map/</url></story><parent_chain><item><author>dividefuel</author><text>The article seems to imply that people are primarily exposed to Mercator in school without discussing its shortcomings. However in my experience growing up in the 90s&#x2F;00s, we discussed lots of different projections and their respective tradeoffs. It was drilled in pretty deep that the Mercator reflected shapes accurately, but not relative sizes. I also remember seeing Robinson projection far more than Mercator, though again we were reminded that it&#x27;s not perfect either, and that any 2D projection will have its pros&#x2F;cons.</text></item></parent_chain><comment><author>rob_c</author><text>Trust me, in bad public education in the UK the map is simply presented. You cover the concept of how to draw the map but if the teacher used the word &quot;protection&quot; it causes eyes to gloss over...<p>Sounds like you had a good education my lucky friend and I hope it serves you well. I think the closest I saw was historical map putting Britain at the center of a big red empire before skipping several hundred years to cover Vietnam because the syllabus said we had to.</text></comment> |
26,870,225 | 26,869,822 | 1 | 2 | 26,868,731 | train | <story><title>You Are Not ‘Behind’ (2016)</title><url>https://zackkanter.com/2016/01/13/you-are-not-behind/</url></story><parent_chain><item><author>biren34</author><text>Here&#x27;s what I would tell my kids: &quot;Odds are, you ARE behind. In any given rank ordering, 50% are below average. 90% are NOT in the top 10%<p>If you&#x27;re lucky and work hard, you can be in the top 10%, 5% or even 1% of a few areas. But even then, you can beat yourself up about not being the best--because even if you sometimes are the best at something, <i>sometimes</i> you aren&#x27;t. You can always make yourself miserable, if you choose to.<p>So what do you do? You have 3 choices:<p>1. sit there and complain about it<p>2. Deny the reality of your &quot;behindness&quot;, which makes for weak men and women (and I didn&#x27;t raise wimps)<p>3. Or, you can realize that there&#x27;s a set of skills related to managing your internal state<p>The best way to do this is to focus on process-oriented goals, rather than results oriented goals. In other words, take pride <i>in your work</i> not in the output. You can lose every game, yet feel okay, if you set your goals to be play a bit better than last time--and do it.<p>Once you get there, you can admit others are better than you and be thankful for the opportunity to learn from them--since you&#x27;re no longer competing.<p>This is what is meant by &quot;losers focus on the winners, and winners focus on themselves&quot;.<p>It&#x27;s simple, but not easy. It takes work to achieve this, just like it takes work to achieve any useful skill. And just like any other skill, you&#x27;ll get this right sometimes and screw it up at others. Just try to do it better today than you did yesterday, yes, like it&#x27;s any other skill.<p>Good luck, I&#x27;ll always be rooting for you.</text></item></parent_chain><comment><author>leoh</author><text>This is totally missing the point of the post. This post is maybe the most humane, grounded, kind thing I&#x27;ve seen in a while -- and I go to the comments section and I see a bull whip. We all need to take a break and chill.<p>There is an antique question put to Napoleon -- after you conquer the world, what will you do? Napoleon says: I&#x27;ll sit back and drink a glass of wine.<p>Our time on Earth is limited. If you want to spend it &quot;winning&quot; go on right ahead. But you need to make sure you also know you&#x27;re perfectly okay right where you are, too; lest you go insane, lest you spend your whole life in a tizzy about where you rank. Which unequivocally seems to me to be a life... wasted.</text></comment> | <story><title>You Are Not ‘Behind’ (2016)</title><url>https://zackkanter.com/2016/01/13/you-are-not-behind/</url></story><parent_chain><item><author>biren34</author><text>Here&#x27;s what I would tell my kids: &quot;Odds are, you ARE behind. In any given rank ordering, 50% are below average. 90% are NOT in the top 10%<p>If you&#x27;re lucky and work hard, you can be in the top 10%, 5% or even 1% of a few areas. But even then, you can beat yourself up about not being the best--because even if you sometimes are the best at something, <i>sometimes</i> you aren&#x27;t. You can always make yourself miserable, if you choose to.<p>So what do you do? You have 3 choices:<p>1. sit there and complain about it<p>2. Deny the reality of your &quot;behindness&quot;, which makes for weak men and women (and I didn&#x27;t raise wimps)<p>3. Or, you can realize that there&#x27;s a set of skills related to managing your internal state<p>The best way to do this is to focus on process-oriented goals, rather than results oriented goals. In other words, take pride <i>in your work</i> not in the output. You can lose every game, yet feel okay, if you set your goals to be play a bit better than last time--and do it.<p>Once you get there, you can admit others are better than you and be thankful for the opportunity to learn from them--since you&#x27;re no longer competing.<p>This is what is meant by &quot;losers focus on the winners, and winners focus on themselves&quot;.<p>It&#x27;s simple, but not easy. It takes work to achieve this, just like it takes work to achieve any useful skill. And just like any other skill, you&#x27;ll get this right sometimes and screw it up at others. Just try to do it better today than you did yesterday, yes, like it&#x27;s any other skill.<p>Good luck, I&#x27;ll always be rooting for you.</text></item></parent_chain><comment><author>Retric</author><text>That can quickly become a seriously unhealthy attitude. It’s vastly more manageable to say in every activity there is someone at the top and everyone else is behind them. However, nobody is at the top of everything. The trick is making sure your good enough to do what you want to do.<p>Don’t try to be better at everything, get better at the things holding you back and then move on. You don’t need to be the worlds best cook to make lunch, but pick something and hitting the top 10%, 1%, 0.1% or even #1 becomes possible.<p>I have seen far to many overachievers who break down when they realized the vast majority of their time and effort has been wasted.</text></comment> |
21,502,157 | 21,501,986 | 1 | 2 | 21,501,341 | train | <story><title>Amazon’s plan for Alexa</title><url>https://www.technologyreview.com/s/614676/amazon-alexa-will-run-your-life-data-privacy/</url></story><parent_chain><item><author>buzzkillington</author><text>&gt; If you’re one of the eight or nine people on the planet who has never interacted with Alexa, you’re both missing out and not really missing out.<p>I must be officially old, because I see no reason to give voice commands to things. If I did I&#x27;d just attach a microphone to the server I run at home and connect it to things.</text></item></parent_chain><comment><author>p1necone</author><text>I still don&#x27;t find voice activation to be very good in the cases I&#x27;ve used it. The problem of transcribing what you&#x27;re saying seems to be solved pretty well, but (at least in the applications I&#x27;ve used it in - which is just navigation via google maps on my phone) there still seems to be an inherent problem of discoverability.<p>It took me a fair bit of trial and error to work out the exact magic words to say to get google maps to launch navigation to a given address by car without requiring me to use the touch screen at all.<p>My natural inclination was to say &quot;Hey Google, give me directions to 123 fake street&quot; but this would bring up a route (or if you&#x27;re especially unlucky a list of different places for you to choose from) but require you to press a &quot;start&quot; button with your finger, and often also require you to switch the navigation type from bus&#x2F;walk&#x2F;cycle to car manually too.<p>&quot;Give me directions to 123 fake street by car&quot; would skip the navigation type selection, but still require you to manually press a &quot;start&quot; button (various variations of &quot;ok google, begin&quot; or &quot;ok google, start&quot; etc didn&#x27;t seem to do anything&quot;)<p>After a long period (months) of having to press a tiny button manually while driving to start navigation I finally discovered that if you say &quot;Navigate to&quot; rather than &quot;Give me directions to&quot; it would skip past the start button screen and jump straight to giving you directions.<p>So now it works great, but I hope I don&#x27;t have to go through tedious trial and error with everything voice activated to work out the exact phrasing it wants.</text></comment> | <story><title>Amazon’s plan for Alexa</title><url>https://www.technologyreview.com/s/614676/amazon-alexa-will-run-your-life-data-privacy/</url></story><parent_chain><item><author>buzzkillington</author><text>&gt; If you’re one of the eight or nine people on the planet who has never interacted with Alexa, you’re both missing out and not really missing out.<p>I must be officially old, because I see no reason to give voice commands to things. If I did I&#x27;d just attach a microphone to the server I run at home and connect it to things.</text></item></parent_chain><comment><author>glup</author><text>The sentence you highlighted struck me as simultaneously remarkably vacuous as well as easily falsified.</text></comment> |
34,732,035 | 34,731,994 | 1 | 2 | 34,731,351 | train | <story><title>Crypto exchange Kraken to shut staking service, pay $30M fine in SEC settlement</title><url>https://www.coindesk.com/policy/2023/02/09/us-securities-and-exchange-commission-sues-kraken-over-crypto-staking-services/</url></story><parent_chain></parent_chain><comment><author>saurik</author><text>Many of these APYs are being measured in the token staked, not in the &quot;value&quot; of that token as might be expressed in (say) dollars. The payment is then made via inflation, which devalues everyone&#x27;s tokens to give the people who staled more token. (Yes: this means that the <i>value</i> of your money might go down even if you legitimately have 20% more of it; the market for the token at that point is a separate--yet related--issue.)</text></comment> | <story><title>Crypto exchange Kraken to shut staking service, pay $30M fine in SEC settlement</title><url>https://www.coindesk.com/policy/2023/02/09/us-securities-and-exchange-commission-sues-kraken-over-crypto-staking-services/</url></story><parent_chain></parent_chain><comment><author>Octokiddie</author><text>Coindesk offers some context:<p>&gt; Kraken’s staking service offered a 20% APY, promising to send customers staking rewards twice per week, according to its website.<p><a href="https:&#x2F;&#x2F;www.coindesk.com&#x2F;policy&#x2F;2023&#x2F;02&#x2F;09&#x2F;kraken-agreed-to-shutter-crypto-staking-operations-to-settle-sec-charges-source&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.coindesk.com&#x2F;policy&#x2F;2023&#x2F;02&#x2F;09&#x2F;kraken-agreed-to-...</a><p>Simple question: how is that guaranteed yield sustainable if not through a Ponzi scheme?</text></comment> |
10,562,062 | 10,561,662 | 1 | 2 | 10,560,634 | train | <story><title>Mac Store Apps Stopped Working Due to Expired Security Certificate</title><url>http://techcrunch.com/2015/11/12/all-mac-store-apps-stopped-working-due-to-expired-security-certificate/#.y37x7x:xhzD</url></story><parent_chain><item><author>cortesoft</author><text>But if a program keeps running with an invalid security certificate, what is the point of having the certificate at all? If the practice is &#x27;let the program with an invalid cert run silently for 2 days&#x27;, then you aren&#x27;t gaining any security at all. Malware could do everything it needs in 48 hours.</text></item><item><author>makecheck</author><text>I think &quot;grace periods&quot; should be a lot more common in software. Not every issue is the user&#x27;s problem, and not every problem requires a drastic response.<p>For instance, they could have:<p>- Quietly noted the issue in a file somewhere, waited 24 hours, and checked again.<p>- If the problem was still present after 24 hours, they could have made the software discreetly submit a problem report to Apple (but still launch and work correctly).<p>- After 48 hours, they could issue a background notification to the user indicating that a problem has been detected in the program and to “please check for updates on the App Store”; but again, continue to work correctly.<p>Or in other words, there were only about a half dozen more reasonable things they could have done that didn&#x27;t involve an Amazonian break-things-immediately type of response.</text></item></parent_chain><comment><author>mikeash</author><text>This particular bit of verification has nothing whatsoever to do with security. It&#x27;s an error in purchase verification. If the practice is to let the program run with an invalid purchase receipt for two days, then you&#x27;re just giving pirates a free two-day trial. Some people might see that as a problem, but I personally value the experience of paying users over inconveniencing pirates.</text></comment> | <story><title>Mac Store Apps Stopped Working Due to Expired Security Certificate</title><url>http://techcrunch.com/2015/11/12/all-mac-store-apps-stopped-working-due-to-expired-security-certificate/#.y37x7x:xhzD</url></story><parent_chain><item><author>cortesoft</author><text>But if a program keeps running with an invalid security certificate, what is the point of having the certificate at all? If the practice is &#x27;let the program with an invalid cert run silently for 2 days&#x27;, then you aren&#x27;t gaining any security at all. Malware could do everything it needs in 48 hours.</text></item><item><author>makecheck</author><text>I think &quot;grace periods&quot; should be a lot more common in software. Not every issue is the user&#x27;s problem, and not every problem requires a drastic response.<p>For instance, they could have:<p>- Quietly noted the issue in a file somewhere, waited 24 hours, and checked again.<p>- If the problem was still present after 24 hours, they could have made the software discreetly submit a problem report to Apple (but still launch and work correctly).<p>- After 48 hours, they could issue a background notification to the user indicating that a problem has been detected in the program and to “please check for updates on the App Store”; but again, continue to work correctly.<p>Or in other words, there were only about a half dozen more reasonable things they could have done that didn&#x27;t involve an Amazonian break-things-immediately type of response.</text></item></parent_chain><comment><author>wtallis</author><text>There&#x27;s minimal security risk in allowing a formerly-validated piece of software to remain usable so long as it is not modified by any updates that cannot be verified by a current certificate.<p>Being this strict at the cost of usability isn&#x27;t about security, it&#x27;s about DRM and making sure you don&#x27;t get to keep using your software after the subscription has expired.</text></comment> |
31,864,722 | 31,864,021 | 1 | 3 | 31,858,460 | train | <story><title>Tell HN: Coinbase now requires physical address of recipient in crypto transfers</title><text>Just got this email from Coinbase, and it seems one by one the promises of crypto of the last several years are evaporating:<p>Starting on June 27, Coinbase will introduce some changes required by local regulations. Specifically, when you send crypto outside of Coinbase, we are required to ask you for the name and physical address of the recipient and the purpose of transfer. In certain cases we may require you to link a Coinbase Wallet to your main Coinbase account in order to send crypto assets off the Coinbase platform. This allows us to verify that you control the Coinbase Wallet that is receiving the crypto assets.</text></story><parent_chain><item><author>Barrera</author><text>&gt; ... it seems one by one the promises of crypto of the last several years are evaporating ...<p>Hardly. What&#x27;s happening is that a financial institution is being regulated and pro-actively adopting steps to please regulators. And those regulators will never be satisfied.<p>As regulators squeeze harder and harder, it will drive Coinbase under. That is not the disaster that some might think. It&#x27;s a necessary next step for Bitcoin to prove that it can actually deliver on the promise of censorship-resistant money.<p>At the very least what&#x27;s happening with exchanges, regulation, and the over-eager suits at Coinbase demonstrates the need for censorship-resistance in the first place. None of the new steps add anything whatsoever to the experience of the user. It&#x27;s all about other people exercising control over that user&#x27;s money.</text></item></parent_chain><comment><author>lkrubner</author><text>You call this &quot;censorship-resistance&quot; but it seems to be &quot;law-resistance.&quot; This is a point that critics of crypto have been making for awhile: crypto&#x27;s only use-case seems to be to avoid the law. At least in the USA, the courts have typically granted wide latitude to technologies that have a mix of both legal and illegal uses, but crypto seems to only have illegal uses, so it looks more and more like one of those technologies where the courts often allow strict regulation or outright bans. Especially in the democratic nations, where the laws have the legitimacy granted by popular representation in the political process, there is no reason to tolerate a technology if that technology exists solely to evade the law -- there must be some clear legal purpose for the technology.</text></comment> | <story><title>Tell HN: Coinbase now requires physical address of recipient in crypto transfers</title><text>Just got this email from Coinbase, and it seems one by one the promises of crypto of the last several years are evaporating:<p>Starting on June 27, Coinbase will introduce some changes required by local regulations. Specifically, when you send crypto outside of Coinbase, we are required to ask you for the name and physical address of the recipient and the purpose of transfer. In certain cases we may require you to link a Coinbase Wallet to your main Coinbase account in order to send crypto assets off the Coinbase platform. This allows us to verify that you control the Coinbase Wallet that is receiving the crypto assets.</text></story><parent_chain><item><author>Barrera</author><text>&gt; ... it seems one by one the promises of crypto of the last several years are evaporating ...<p>Hardly. What&#x27;s happening is that a financial institution is being regulated and pro-actively adopting steps to please regulators. And those regulators will never be satisfied.<p>As regulators squeeze harder and harder, it will drive Coinbase under. That is not the disaster that some might think. It&#x27;s a necessary next step for Bitcoin to prove that it can actually deliver on the promise of censorship-resistant money.<p>At the very least what&#x27;s happening with exchanges, regulation, and the over-eager suits at Coinbase demonstrates the need for censorship-resistance in the first place. None of the new steps add anything whatsoever to the experience of the user. It&#x27;s all about other people exercising control over that user&#x27;s money.</text></item></parent_chain><comment><author>cal5k</author><text>This is called the &quot;Travel Rule&quot;, and it&#x27;s part of an international effort to regulate crypto transfers analogously to bank transfers. When you send a wire transfer, you include the address of the recipient and your bank includes your address in the transfer.<p>It&#x27;s technically a FINCEN&#x2F;FINTRAC requirement in the US and Canada, but they imposed the rule before any of the tooling existed... so there&#x27;s a bit of a scramble happening right now to figure out how to comply with the rule. Coinbase put together a consortium with other centralized exchanges in an attempt to create a common standard that should hopefully reduce the manual work required by customers, but this is absolutely not isolated to them.</text></comment> |
23,843,732 | 23,840,652 | 1 | 3 | 23,840,243 | train | <story><title>Go generics may use square brackets [] not parenthesis ()</title><url>https://groups.google.com/forum/#!topic/golang-nuts/7t-Q2vt60J8</url></story><parent_chain><item><author>jiggawatts</author><text>Why don&#x27;t they just use characters from the Canadian Aboriginal Syllabics block?<p><a href="https:&#x2F;&#x2F;www.reddit.com&#x2F;r&#x2F;rust&#x2F;comments&#x2F;5penft&#x2F;parallelizing_enjarify_in_go_and_rust&#x2F;dcsgk7n&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.reddit.com&#x2F;r&#x2F;rust&#x2F;comments&#x2F;5penft&#x2F;parallelizing_...</a></text></item></parent_chain><comment><author>tomp</author><text>Every time I click a Reddit link I&#x27;m astounded about how bad &amp; user-hostile the new UX is.<p>Old-style link: <a href="https:&#x2F;&#x2F;old.reddit.com&#x2F;r&#x2F;rust&#x2F;comments&#x2F;5penft&#x2F;parallelizing_enjarify_in_go_and_rust&#x2F;dcsgk7n&#x2F;" rel="nofollow">https:&#x2F;&#x2F;old.reddit.com&#x2F;r&#x2F;rust&#x2F;comments&#x2F;5penft&#x2F;parallelizing_...</a></text></comment> | <story><title>Go generics may use square brackets [] not parenthesis ()</title><url>https://groups.google.com/forum/#!topic/golang-nuts/7t-Q2vt60J8</url></story><parent_chain><item><author>jiggawatts</author><text>Why don&#x27;t they just use characters from the Canadian Aboriginal Syllabics block?<p><a href="https:&#x2F;&#x2F;www.reddit.com&#x2F;r&#x2F;rust&#x2F;comments&#x2F;5penft&#x2F;parallelizing_enjarify_in_go_and_rust&#x2F;dcsgk7n&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.reddit.com&#x2F;r&#x2F;rust&#x2F;comments&#x2F;5penft&#x2F;parallelizing_...</a></text></item></parent_chain><comment><author>ed25519FUUU</author><text>&gt; type ImmutableTreeListᐸElementTᐳ<p>&gt; <i>If you look closely, those aren&#x27;t angle brackets, they&#x27;re characters from the Canadian Aboriginal Syllabics block, which are allowed in Go identifiers. From Go&#x27;s perspective, that&#x27;s just one long identifier.</i><p>And the next comment is the same thing everyone else is thinking: “<i>oh my god</i>”</text></comment> |
20,048,007 | 20,046,860 | 1 | 2 | 20,045,380 | train | <story><title>Exponential Economist Meets Finite Physicist (2012)</title><url>https://dothemath.ucsd.edu/2012/04/economist-meets-physicist</url></story><parent_chain><item><author>philipkglass</author><text>I generally liked the Do The Math posts but I thought this was one of the weakest.<p>Physicist: &quot;Right, if you plot the U.S. energy consumption in all forms from 1650 until now, you see a phenomenally faithful exponential at about 3% per year over that whole span.&quot;<p>It&#x27;s not phenomenally faithful. There&#x27;s an inflection point visible even in his large graph going back all the way to 1650. US primary energy consumption in 1977 was 78 quadrillion BTU (quads). At 2.9% annual growth it would have risen to 245 quads by 2017. Actual US primary energy consumption in 2017 was only 98 quads. The <i>per capita</i> primary energy consumption in the US was actually higher in 1977.<p>Physicists don&#x27;t need to imagine future limits to growth. The limits are already visible in the historical record. But, contra the fears of many scientists circa 1960, the limits to growth showed up on the demand side before the supply side. We ended up with a world where widespread obesity is a problem and predicted gigadeaths from starvation did not actually happen.<p>For any product you can imagine consuming, there are &quot;obesity&quot;-type limits to how much more of that same product you can consume before the marginal utility goes negative. For any service you might use, similar limits apply since there are only 24 hours in a day.<p>The physicist character gives the more correct answer but his supporting evidence is flawed. The economist has the much worse answers, but only (I suspect) because he&#x27;s a strawman constructed for didactic purposes. Economists generally don&#x27;t make 1400 year forecasts of any sort.</text></item></parent_chain><comment><author>hn_throwaway_99</author><text>Thank you thank you thank you. Honestly, this whole article had the veneer to me of &quot;Ahh, poor silly economist...&quot; I&#x27;m not sure if there is a great word for it, but I call it the &quot;humble-brag equivalent of obnoxiously condescending&quot;</text></comment> | <story><title>Exponential Economist Meets Finite Physicist (2012)</title><url>https://dothemath.ucsd.edu/2012/04/economist-meets-physicist</url></story><parent_chain><item><author>philipkglass</author><text>I generally liked the Do The Math posts but I thought this was one of the weakest.<p>Physicist: &quot;Right, if you plot the U.S. energy consumption in all forms from 1650 until now, you see a phenomenally faithful exponential at about 3% per year over that whole span.&quot;<p>It&#x27;s not phenomenally faithful. There&#x27;s an inflection point visible even in his large graph going back all the way to 1650. US primary energy consumption in 1977 was 78 quadrillion BTU (quads). At 2.9% annual growth it would have risen to 245 quads by 2017. Actual US primary energy consumption in 2017 was only 98 quads. The <i>per capita</i> primary energy consumption in the US was actually higher in 1977.<p>Physicists don&#x27;t need to imagine future limits to growth. The limits are already visible in the historical record. But, contra the fears of many scientists circa 1960, the limits to growth showed up on the demand side before the supply side. We ended up with a world where widespread obesity is a problem and predicted gigadeaths from starvation did not actually happen.<p>For any product you can imagine consuming, there are &quot;obesity&quot;-type limits to how much more of that same product you can consume before the marginal utility goes negative. For any service you might use, similar limits apply since there are only 24 hours in a day.<p>The physicist character gives the more correct answer but his supporting evidence is flawed. The economist has the much worse answers, but only (I suspect) because he&#x27;s a strawman constructed for didactic purposes. Economists generally don&#x27;t make 1400 year forecasts of any sort.</text></item></parent_chain><comment><author>msla</author><text>&gt; But, contra the fears of many scientists circa 1960, the limits to growth showed up on the demand side before the supply side. We ended up with a world where widespread obesity is a problem and predicted gigadeaths from starvation did not actually happen.<p>And I think some people were... &quot;disappointed&quot;, for lack of a better word, that this happened. That their fantasies of global collapse <i>Soylent Green</i>-style didn&#x27;t pan out, that the lackadaisical masses who had the temerity to not give up all modern advances weren&#x27;t punished by the Dread God Malthus. Call it Puritanical Luddism, call it Apocalyptic Deep Green, call it a dogmatic insistence that any system not under totalitarian control <i>must</i> collapse.</text></comment> |
19,136,609 | 19,136,699 | 1 | 2 | 19,135,434 | train | <story><title>Build your own dial-up ISP in 2019</title><url>https://dogemicrosystems.ca/wiki/Build_you_own_dial_up_ISP_in_2019</url></story><parent_chain></parent_chain><comment><author>sebst</author><text>I&#x27;ve built something like that from a bunch of used hardware in my teens. DSL connections were just available (in Germany) and came with a data flat rate. I was in the lucky position that I could convince my parents to get such a contract.<p>A friend of mine, who could not get a DSL connections because back then he lived in an uncovered area, could at least get a telephone &quot;flat rate&quot; for free telephone calls on Sundays.<p>So, he dialed in my Pentium 133 server and used my DSL connection behind a NAT every Sunday.</text></comment> | <story><title>Build your own dial-up ISP in 2019</title><url>https://dogemicrosystems.ca/wiki/Build_you_own_dial_up_ISP_in_2019</url></story><parent_chain></parent_chain><comment><author>cure</author><text>I operated something like this around 2005 in a big hotel building (~400 bedrooms and various offices) with a dinky internet connection and no wifi yet (very thick walls, up in the mountains, limited budgets...).<p>So I built a dial-up pool on an internal number (this place had its own PBX with ~500 phone lines) hooked to a Debian box, served by a bunch of USR Courier modems. Good times :)</text></comment> |
11,068,260 | 11,067,267 | 1 | 2 | 11,054,019 | train | <story><title>Saying 'no' to keep crap out of products</title><url>https://blog.orangecaffeine.com/the-art-of-saying-no-db012a22cd28#.sbmur7q01</url></story><parent_chain><item><author>onion2k</author><text>Is it actually possible to know ahead of launching a feature that it&#x27;ll be crap, or is it that most features get launched and the ones that are receievd well by the users are deemed &quot;good&quot; while the ones that aren&#x27;t are considered &quot;crap&quot;?<p>We&#x27;ve all written things that we thought would be awesome that turned out to be disregarded by users, and deployed things we thought were pointless nonsense that turned out to be fantastically engaging features that users rave about. Can you <i>really</i> tell before you actually get proper feedback (eg the user seeing and using the feature, not just asking if they might like it because users say yes to everything)?</text></item></parent_chain><comment><author>existencebox</author><text>There was a child post of this which was deleted, but I thought was very on the mark. (It was likely deleted because it said things about a certain BigCO internals that potentially weren&#x27;t public)<p>That being said, I&#x27;d like to independently re-echo the thrust of that post because I did feel the contribution was key:<p>There are often internal channels in large companies that the boots on the ground use to communicate with each other in a more informal fashion. I&#x27;ve noticed across multiple companies that this is a FANTASTIC leading indicator for the success of a feature. For however much flak engineers get for not being &quot;people persons&quot; or however you put it, or needing &quot;Designers&quot; to guide their customer facing work, I&#x27;ve seen significant correlation between popular sentiment and feature success. Perhaps at the end of the day, enough of our outlook as &quot;consumers&quot; remains to properly instruct us despite whatever programmer bent we may have; or more pessimistically, our own sentiment on what we&#x27;re making subconsciously impacts our output in a meaningful way.<p>So to end this ramble briefly; I think we CAN tell, the powers that be just need to look in the right places, and listen well if they do.</text></comment> | <story><title>Saying 'no' to keep crap out of products</title><url>https://blog.orangecaffeine.com/the-art-of-saying-no-db012a22cd28#.sbmur7q01</url></story><parent_chain><item><author>onion2k</author><text>Is it actually possible to know ahead of launching a feature that it&#x27;ll be crap, or is it that most features get launched and the ones that are receievd well by the users are deemed &quot;good&quot; while the ones that aren&#x27;t are considered &quot;crap&quot;?<p>We&#x27;ve all written things that we thought would be awesome that turned out to be disregarded by users, and deployed things we thought were pointless nonsense that turned out to be fantastically engaging features that users rave about. Can you <i>really</i> tell before you actually get proper feedback (eg the user seeing and using the feature, not just asking if they might like it because users say yes to everything)?</text></item></parent_chain><comment><author>dividuum</author><text>&gt; Can you really tell before you actually get proper feedback [...]<p>Probably not. But even if you built a feature that&#x27;s not well received it&#x27;s important to remove it again. I&#x27;ve seen plenty of projects that carry tons of mostly unused features (or better called technical dept at that point) with them.</text></comment> |
28,839,430 | 28,839,266 | 1 | 2 | 28,839,108 | train | <story><title>The planet survived six hours without Facebook. Let's make it longer next time</title><url>https://www.theregister.com/2021/10/11/facebook_opinion_column/</url></story><parent_chain></parent_chain><comment><author>AndrewDucker</author><text>It&#x27;s a big deal when Facebook goes down. This is why: <a href="https:&#x2F;&#x2F;www.stonekettle.com&#x2F;2021&#x2F;10&#x2F;recap-october-4-2021.html?m=1" rel="nofollow">https:&#x2F;&#x2F;www.stonekettle.com&#x2F;2021&#x2F;10&#x2F;recap-october-4-2021.htm...</a><p>People want to talk to their friends. They want to keep up with what their friends are up to. Sometimes they want to do that in ways that you, specifically, aren&#x27;t a fan of, but that&#x27;s fine - different people are different. But they want a place they can go and see &quot;Oh, Dave had a kid. Oh, Agnes got a promotion. Oh, Cameron went to that new pizza place and it looks really tasty!&quot;<p>This means that either we design something decentralised that&#x27;s as easy as Facebook to get onto use, or we&#x27;re going to just end up replacing Facebook with something with essentially all of the same characteristics as Facebook.<p>It&#x27;s that or regulate it. In many many different ways across many different countries. That won&#x27;t be much fun either!</text></comment> | <story><title>The planet survived six hours without Facebook. Let's make it longer next time</title><url>https://www.theregister.com/2021/10/11/facebook_opinion_column/</url></story><parent_chain></parent_chain><comment><author>rocketpastsix</author><text>One thing that the outage really highlighted for me is how much small and medium size businesses rely on Facebook. That 6 hour outage costs somewhere into the billions of dollars lost for SMBs. If there was ever a time to highlight the need for a stand alone website, the great Facebook outage of 2021 is it.<p>Own your content, so the next time this happens, you aren&#x27;t up a creek without a paddle.</text></comment> |
7,460,037 | 7,460,236 | 1 | 3 | 7,459,529 | train | <story><title>Brendan Eich becomes Mozilla CEO</title><url>https://brendaneich.com/2014/03/mozilla-news/</url></story><parent_chain><item><author>fingerprinter</author><text>If he was a developer, architect or something else like that, I&#x27;d generally agree.<p>However, he is now CEO. Imagine just how many people he&#x27;d alienate inside Mozilla by basically saying &quot;I don&#x27;t think you should have the same rights as me&quot;.<p>This is <i>not</i> just another political topic, no matter how people would like to frame it that way. This is about treating people the same. You can <i>still think</i> that homosexuality is wrong and support gay marriage. But someone who goes so far as to say no to gay marriage is basically saying they view that group of people as less than another group of people and should have less rights.<p>This is unacceptable.</text></item><item><author>chimeracoder</author><text>When looking to effect change, one has to build coalitions, which sometimes means picking battles.<p>Eich apparently does not believe that I deserve the same rights that he does, but if he is a champion of other values I hold, does that mean I should write him off entirely?<p>While I might prefer someone in a position like his to share all my political views, that&#x27;s not really feasible. The ones that are relevant to his position as CEO of Mozilla are his views on privacy, software freedom, etc.<p>It&#x27;s especially relevant to note that this is a donation he made &quot;privately&quot; as an individual (it&#x27;s public due to financing laws, but it&#x27;s not the same as (e.g.) giving the keynote address at a NOM event.)<p>I happen to disagree with his views on Proposition 8, but unless they translate into discrimination in the workplace (which is an addressable problem in itself), I might be willing to support his work in one field while separating myself from his personal viewpoints in another field.</text></item><item><author>anon1385</author><text>I guess 2 years is long enough for most people to have forgotten the brief storm about his homophobic political activities. I wonder if this appointment would have been made 18 months ago when that was still fresh in people&#x27;s minds. I can&#x27;t help thinking that it doesn&#x27;t really fit with the image Mozilla tries to present of themselves.<p><a href="http://tommorris.org/posts/2550" rel="nofollow">http:&#x2F;&#x2F;tommorris.org&#x2F;posts&#x2F;2550</a></text></item></parent_chain><comment><author>twoodfin</author><text><i>This is unacceptable.</i><p>C&#x27;mon. In 2004 and 2008, with this very much a live issue, something north of 90% of American voters voted for a presidential candidate who professed to be against gay marriage. You are getting and will continue to get the social change you want, but it&#x27;s crazy to ostracize someone for having the same political view as 2008 candidate Barack Obama. Try to be graceful and persuasive.</text></comment> | <story><title>Brendan Eich becomes Mozilla CEO</title><url>https://brendaneich.com/2014/03/mozilla-news/</url></story><parent_chain><item><author>fingerprinter</author><text>If he was a developer, architect or something else like that, I&#x27;d generally agree.<p>However, he is now CEO. Imagine just how many people he&#x27;d alienate inside Mozilla by basically saying &quot;I don&#x27;t think you should have the same rights as me&quot;.<p>This is <i>not</i> just another political topic, no matter how people would like to frame it that way. This is about treating people the same. You can <i>still think</i> that homosexuality is wrong and support gay marriage. But someone who goes so far as to say no to gay marriage is basically saying they view that group of people as less than another group of people and should have less rights.<p>This is unacceptable.</text></item><item><author>chimeracoder</author><text>When looking to effect change, one has to build coalitions, which sometimes means picking battles.<p>Eich apparently does not believe that I deserve the same rights that he does, but if he is a champion of other values I hold, does that mean I should write him off entirely?<p>While I might prefer someone in a position like his to share all my political views, that&#x27;s not really feasible. The ones that are relevant to his position as CEO of Mozilla are his views on privacy, software freedom, etc.<p>It&#x27;s especially relevant to note that this is a donation he made &quot;privately&quot; as an individual (it&#x27;s public due to financing laws, but it&#x27;s not the same as (e.g.) giving the keynote address at a NOM event.)<p>I happen to disagree with his views on Proposition 8, but unless they translate into discrimination in the workplace (which is an addressable problem in itself), I might be willing to support his work in one field while separating myself from his personal viewpoints in another field.</text></item><item><author>anon1385</author><text>I guess 2 years is long enough for most people to have forgotten the brief storm about his homophobic political activities. I wonder if this appointment would have been made 18 months ago when that was still fresh in people&#x27;s minds. I can&#x27;t help thinking that it doesn&#x27;t really fit with the image Mozilla tries to present of themselves.<p><a href="http://tommorris.org/posts/2550" rel="nofollow">http:&#x2F;&#x2F;tommorris.org&#x2F;posts&#x2F;2550</a></text></item></parent_chain><comment><author>yummyfajitas</author><text><i>This is about treating people the same.</i><p>Gays and straights are treated the same - both are free to marry people of the opposite sex. Gays may prefer not to do that, but they do have the legal right.<p>As for finding your preferences are not legally favored, that happens to lots of people. I prefer to have no fixed address, which is NOT a legally favorable preference to have (try opening a bank account, etc). I prefer not to buy insurance covering procedures I will never need [1].<p>Are laws preventing me from satisfying my preferences on these matters all unacceptable? If Eich favored Obamacare or &quot;Know Your Customer&quot; banking laws, would that also be unacceptable?<p>[1] Supposing that I lived in the US.</text></comment> |
37,990,540 | 37,989,295 | 1 | 2 | 37,988,585 | train | <story><title>Trying out TinaCMS</title><url>https://blog.cassidoo.co/post/trying-tinacms/</url></story><parent_chain></parent_chain><comment><author>cassidoo</author><text>Oh hey that&#x27;s me! Lmk if y&#x27;all have questions. I&#x27;ve been happy with Tina so far.</text></comment> | <story><title>Trying out TinaCMS</title><url>https://blog.cassidoo.co/post/trying-tinacms/</url></story><parent_chain></parent_chain><comment><author>jauntywundrkind</author><text>Just started looking, &amp; really like this TinaCMS, from what I&#x27;ve seen of the docs.<p>Semi-headless, Git-backed, so each change goes into a commit. MDX, so you can have a mix of markdown and more complex content (buttons, or more complex components).<p>Not a massive fan of graphql per se, but there&#x27;s a very interesting graphql layer for querying your content. One can define schemas for content, and TinaCMS seems to be able to generate fairly rich data ways to query &amp; search your data.<p>Some of the advanced features are powered by a level.js compatible store, which was <i>the</i> popular interface for data stores on node &amp; js for a while. The content is still git filesystem backed, so one can just throw out the store &amp; rebuild it, but the store makes it fast to query versus having to reread the filesystem each time. Neat.<p>The point of this article came down to this observation, which rings true to me. I idealize this model where we have outbrains we can file thoughts &amp; data into, and this seems like a great tool for starting:<p>&gt; <i>something that Chris Coyier said in his segment stuck with me when he talked about his consistency: the fact that he can just type into a CMS and hit send, with minimal things getting in his way, has kept him more consistent in his writing. I do prefer Markdown and my usual local-first workflow, but the fact that I could spit out a blog quickly without any sort of copying and pasting or editing is something I’m excited to try.</i></text></comment> |
32,607,201 | 32,606,429 | 1 | 2 | 32,605,597 | train | <story><title>I Love My PinePhone</title><url>https://jakob.space/blog/i-love-my-pinephone.html</url></story><parent_chain><item><author>nousermane</author><text>&gt; core features of a modern smartphone: consistent alarms<p>For me personally, this is one thing <i>missing</i> from a modern smartphone. Many old-school GSM phones, when completely turned off (but battery still inside), if there is an alarm programmed, will turn on automatically few seconds before the programmed alarm, just in time to sound on the dot.<p>Very useful, and exactly what I want, when I go to sleep. You can sort of approximate that with &quot;do not disturb&quot; mode, but that drains a bit of battery (and traffic in cell data plan) uselessly.</text></item><item><author>krageon</author><text>This person doesn&#x27;t need the core features of a modern smartphone: consistent alarms and reliable connectivity. As such, it is no wonder they love the pinephone: it is essentially a tiny laptop!<p>That said, I don&#x27;t find this very compelling: I am in fact called by people and I don&#x27;t think having to implement a hack around the system&#x27;s sleep state is acceptable (especially given that it may still not be reliable, what with the dependability profile of the connectivity chipset). It may be more accurate to call this a Pine: Not much of a phone to be found.</text></item></parent_chain><comment><author>megous</author><text>This works on pinephone and pinephone pro, too.<p>On Pinephone, the RTC(has alarm support) is in the SoC and is always powered by PMIC even when the phone is off. PMIC can be configured to power up on interrupt signal, and SoC can be configured to pulldown the interrupt line on RTC alarm.<p>On Pro RTC is inside PMIC directly.<p>HW can do it. Alarm app just has to use the HW correctly.</text></comment> | <story><title>I Love My PinePhone</title><url>https://jakob.space/blog/i-love-my-pinephone.html</url></story><parent_chain><item><author>nousermane</author><text>&gt; core features of a modern smartphone: consistent alarms<p>For me personally, this is one thing <i>missing</i> from a modern smartphone. Many old-school GSM phones, when completely turned off (but battery still inside), if there is an alarm programmed, will turn on automatically few seconds before the programmed alarm, just in time to sound on the dot.<p>Very useful, and exactly what I want, when I go to sleep. You can sort of approximate that with &quot;do not disturb&quot; mode, but that drains a bit of battery (and traffic in cell data plan) uselessly.</text></item><item><author>krageon</author><text>This person doesn&#x27;t need the core features of a modern smartphone: consistent alarms and reliable connectivity. As such, it is no wonder they love the pinephone: it is essentially a tiny laptop!<p>That said, I don&#x27;t find this very compelling: I am in fact called by people and I don&#x27;t think having to implement a hack around the system&#x27;s sleep state is acceptable (especially given that it may still not be reliable, what with the dependability profile of the connectivity chipset). It may be more accurate to call this a Pine: Not much of a phone to be found.</text></item></parent_chain><comment><author>bestouff</author><text>Did you know that this works on some modern smartphones ? At least my OnePlus 7TPro does wake up from an alarm when it&#x27;s totally powered down.</text></comment> |
33,021,697 | 33,020,699 | 1 | 2 | 33,020,129 | train | <story><title>Meta’s new text-to-video AI generator is like DALL-E for video</title><url>https://www.theverge.com/2022/9/29/23378210/meta-text-to-video-ai-generation-make-a-video-model-dall-e</url></story><parent_chain></parent_chain><comment><author>dougmwne</author><text>That is extremely impressive progress. Lots of people were toying with using Stable Diffusion for video, but the results, while inspirational, were quite far away from looking like anything but a psychedelic trip. People were guessing we might see coherent video in a few years. Turns out it was a few weeks.<p>I think the Singularity is little more than a new age religion, but it’s moments like this that give me pause.</text></comment> | <story><title>Meta’s new text-to-video AI generator is like DALL-E for video</title><url>https://www.theverge.com/2022/9/29/23378210/meta-text-to-video-ai-generation-make-a-video-model-dall-e</url></story><parent_chain></parent_chain><comment><author>wokwokwok</author><text>The actual page about &#x27;make-a-video` is here:<p><a href="https:&#x2F;&#x2F;makeavideo.studio&#x2F;" rel="nofollow">https:&#x2F;&#x2F;makeavideo.studio&#x2F;</a><p>...and has a lot more examples on it, and the paper.<p>I particularly liked the dancing bear thing <a href="https:&#x2F;&#x2F;makeavideo.studio&#x2F;assets&#x2F;similarvid1a.webp" rel="nofollow">https:&#x2F;&#x2F;makeavideo.studio&#x2F;assets&#x2F;similarvid1a.webp</a></text></comment> |
3,872,576 | 3,872,462 | 1 | 2 | 3,871,954 | train | <story><title>Let’s Build a Future Without Cars</title><url>http://pandodaily.com/2012/04/20/lets-build-a-future-without-cars/</url></story><parent_chain><item><author>sgentle</author><text>To me, what would be interesting about a world without cars (or even with cars, but vastly more attractive public transport) is that it would partly reverse a sad isolationist trend that's come along with the power and control given to us by modern technology.<p>I used to catch a bus every day through the city, and there were a lot of strange people on those trips. Gangs of 9 year old gangster kids drunk up the back. Little old ladies muttering racist slurs at asian students. A guy who hadn't showered in so long his clothes had gone partially transparent from the grease. I don't think I was ever in any danger, but it sure was uncomfortable sometimes. I work pretty close to home now (in fact, mostly at home), so it's not really an issue anymore. But strangely, I find myself missing that chance to interact with people who I didn't choose to interact with.<p>It seems like every time we get more power (like by inventing an engine that can move us around) we use it to get more control (now I can encase myself in a metal shield that prevents any accidental congress with the outside world).<p>A bunch of technology has gone the same way. Efficient worldwide shipping and postage means you don't need to go outside to shop. Communication moving online means you can block people you don't like rather than have to deal with them. OKCupid means you can pre-screen your dates to avoid accidentally meeting someone unpalatable. You can GPS track your kids so they won't ever end up lost or at the wrong sort of party.<p>And those are all good things that give you more control over your environment. But they also isolate you. Unknown experiences are fundamentally scary; so scary that we feel more afraid of walking in a dark alley than we do of heart disease. Like every generation before us, we strike out against danger with the power of our tools. But our dangers are, at this point, largely invented. We're getting to a point where instead of being safe, we'll just be cocooned in a real-world filter bubble, where we never have to fear the unknown, uncontrollable, unsanitised real world that gets forced on us when we get on a bus or walk around a city. I suspect, for all our newfound safety, we'll just feel a bit unsatisfied.<p>I guess I've just argued myself out of believing that the future without cars is ever really going to happen. Maybe there'll be a virtual bus MMO.</text></item></parent_chain><comment><author>sliverstorm</author><text><i>Unknown experiences are fundamentally scary; so scary that we feel more afraid of walking in a dark alley than we do of heart disease.</i><p>Bah, that isn't the fear of the unknown vs. the fear of the known. It is immediate, physical fear (in thirty seconds those gang members are going to mug me) vs. eventual, abstract fear (in twenty years, something might go wrong inside me).</text></comment> | <story><title>Let’s Build a Future Without Cars</title><url>http://pandodaily.com/2012/04/20/lets-build-a-future-without-cars/</url></story><parent_chain><item><author>sgentle</author><text>To me, what would be interesting about a world without cars (or even with cars, but vastly more attractive public transport) is that it would partly reverse a sad isolationist trend that's come along with the power and control given to us by modern technology.<p>I used to catch a bus every day through the city, and there were a lot of strange people on those trips. Gangs of 9 year old gangster kids drunk up the back. Little old ladies muttering racist slurs at asian students. A guy who hadn't showered in so long his clothes had gone partially transparent from the grease. I don't think I was ever in any danger, but it sure was uncomfortable sometimes. I work pretty close to home now (in fact, mostly at home), so it's not really an issue anymore. But strangely, I find myself missing that chance to interact with people who I didn't choose to interact with.<p>It seems like every time we get more power (like by inventing an engine that can move us around) we use it to get more control (now I can encase myself in a metal shield that prevents any accidental congress with the outside world).<p>A bunch of technology has gone the same way. Efficient worldwide shipping and postage means you don't need to go outside to shop. Communication moving online means you can block people you don't like rather than have to deal with them. OKCupid means you can pre-screen your dates to avoid accidentally meeting someone unpalatable. You can GPS track your kids so they won't ever end up lost or at the wrong sort of party.<p>And those are all good things that give you more control over your environment. But they also isolate you. Unknown experiences are fundamentally scary; so scary that we feel more afraid of walking in a dark alley than we do of heart disease. Like every generation before us, we strike out against danger with the power of our tools. But our dangers are, at this point, largely invented. We're getting to a point where instead of being safe, we'll just be cocooned in a real-world filter bubble, where we never have to fear the unknown, uncontrollable, unsanitised real world that gets forced on us when we get on a bus or walk around a city. I suspect, for all our newfound safety, we'll just feel a bit unsatisfied.<p>I guess I've just argued myself out of believing that the future without cars is ever really going to happen. Maybe there'll be a virtual bus MMO.</text></item></parent_chain><comment><author>enjo</author><text>You pretty much summed up why modern suburbs are the way they are.</text></comment> |
24,522,479 | 24,520,344 | 1 | 2 | 24,514,702 | train | <story><title>John Carmack’s presentation at Facebook Connect [video]</title><url>https://www.youtube.com/watch?v=sXmY26pOE-Y</url></story><parent_chain><item><author>mikepurvis</author><text>But it&#x27;s clearly not a mass market thing either— mass market is mobile games raking in millions, Switches selling out during quarantine, the upcoming PS5 launch, and Epic having splashy platform wars with Apple and Valve. Those are billion dollar gaming events which all have nothing to do with VR.<p>There&#x27;s no non-nerd out there who thinks &quot;maybe I&#x27;ll try VR&quot;, and goes into a store to buy... whatever it is, goes home to have a great time with it, and immediately tells their friends. No, it&#x27;s Linus Tech Tips upgrading his water-cooled living room PC with a special USB3 card just to get enough bandwidth to all the peripherals: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=HFuLvGf0g0c" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=HFuLvGf0g0c</a></text></item><item><author>koiz</author><text>&gt;Right now this is a very expensive, multi-billion dollar toy with toy demonstrator apps and proof of concept games.<p>We are far past tech demos and concept games.</text></item><item><author>dougmwne</author><text>I&#x27;d say that is the same as a dead end. Right now this is a very expensive, multi-billion dollar toy with toy demonstrator apps and proof of concept games. It needs to be a game changer and the future of something or the research funding and developer ecosystem are going to dry up. And given the amount that Facebook must be losing on the Quest 2 and the all-in nature of this launch, if this doesn&#x27;t take off now, the runway for Oculus at FB may be over.</text></item><item><author>criddell</author><text>&gt; Time to see for myself if this is the computing future or an evolutionary dead end.<p>There&#x27;s a third possibility - VR is finally here and consumer market is what it is. It&#x27;s not going to take over the world but it isn&#x27;t going away either.</text></item><item><author>dougmwne</author><text>This talk was such a treat. After all the carefuly crafted hype from Zuck and the gang, Carmack threw huge bucket of cold water on everything. I think it&#x27;s just wonderful that he&#x27;s allowed to speak so openly, about the things he&#x27;s proud of, the things he thinks are failures, internal politics, the possibilities for improvement, the real hard physical limits VR is running into, and his growing pessimism for the future of VR. I could really hear it in his talk why he moved on to spend more time on his next passion.<p>Since it sounded to me like the low hanging mobile VR fruit has been picked, I went ahead and pre-ordered my very first HMD afterwards. Time to see for myself if this is the computing future or an evolutionary dead end.</text></item></parent_chain><comment><author>agar</author><text>Others have said this, but I&#x27;ll reiterate: your description of mass market is precisely what&#x27;s happening with Quest. Your view of VR seems rooted in pre-Quest (i.e., exclusively PC-tethered) VR and not the stand-alone world.<p>In fact, so many people literally went to Best Buy or Walmart to purchase a Quest that it has been sold out since the beginning of the year, online and off, with eBay pricing at 50%+ premiums.<p>You literally open the box, run an app on your phone (for configuration), put the HMD on your face and you&#x27;re in VR. People not only tell their friends, but buy multiple versions to give to friends and family.<p>With Quest 2 at a $299 price point, the non-nerds saying &quot;maybe I&#x27;ll try VR&quot; will happen even more often. The OculusQuest subreddit has a constant stream of questions about this very behavior. It is currently the ~2,000th most popular subreddit, with an impressive growth curve[1]. Some are literally buying the Quest 2 instead of the PS5 (though clearly a small number).<p>So far, 35 games have made over $1m on Quest alone, with one clearing that figure in 4 days and another in 8 days. Top games have made over $10m, not even including revenue from Steam, PSVR, or the Oculus PC VR platform. These aren&#x27;t Epic &#x2F; Apple level mega-wins, but many mobile developers would be happy with $5-10m revenue figures.<p>Upcoming VR games are coming from top tier publishers like Respawn (Medal of Honor), Ubisoft (Assassin&#x27;s Creed, Splinter Cell), and Rockstar (unnamed AAA open world game)[2], Crytek (The Climb 2), and EA (Star Wars: Squadrons).<p>Additional games include Sniper Elite, Warhammer 40,000, Star Wars: Tales from the Galaxy&#x27;s Edge, Jurassic World Aftermath, and Myst. And this is just the tip of the iceberg from brands&#x2F;publishers you may know.<p>Point being, stand-alone VR has really addressed many of your (and the market&#x27;s) concerns.<p>And, to be fair, in your linked video Linus was trying to use optional, expensive peripherals for full-body tracking while streaming - not exactly a mass-market use case.<p>[1] <a href="https:&#x2F;&#x2F;subredditstats.com&#x2F;r&#x2F;oculusquest" rel="nofollow">https:&#x2F;&#x2F;subredditstats.com&#x2F;r&#x2F;oculusquest</a><p>[2] <a href="https:&#x2F;&#x2F;uploadvr.com&#x2F;rockstars-new-vr-game-guesses&#x2F;" rel="nofollow">https:&#x2F;&#x2F;uploadvr.com&#x2F;rockstars-new-vr-game-guesses&#x2F;</a></text></comment> | <story><title>John Carmack’s presentation at Facebook Connect [video]</title><url>https://www.youtube.com/watch?v=sXmY26pOE-Y</url></story><parent_chain><item><author>mikepurvis</author><text>But it&#x27;s clearly not a mass market thing either— mass market is mobile games raking in millions, Switches selling out during quarantine, the upcoming PS5 launch, and Epic having splashy platform wars with Apple and Valve. Those are billion dollar gaming events which all have nothing to do with VR.<p>There&#x27;s no non-nerd out there who thinks &quot;maybe I&#x27;ll try VR&quot;, and goes into a store to buy... whatever it is, goes home to have a great time with it, and immediately tells their friends. No, it&#x27;s Linus Tech Tips upgrading his water-cooled living room PC with a special USB3 card just to get enough bandwidth to all the peripherals: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=HFuLvGf0g0c" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=HFuLvGf0g0c</a></text></item><item><author>koiz</author><text>&gt;Right now this is a very expensive, multi-billion dollar toy with toy demonstrator apps and proof of concept games.<p>We are far past tech demos and concept games.</text></item><item><author>dougmwne</author><text>I&#x27;d say that is the same as a dead end. Right now this is a very expensive, multi-billion dollar toy with toy demonstrator apps and proof of concept games. It needs to be a game changer and the future of something or the research funding and developer ecosystem are going to dry up. And given the amount that Facebook must be losing on the Quest 2 and the all-in nature of this launch, if this doesn&#x27;t take off now, the runway for Oculus at FB may be over.</text></item><item><author>criddell</author><text>&gt; Time to see for myself if this is the computing future or an evolutionary dead end.<p>There&#x27;s a third possibility - VR is finally here and consumer market is what it is. It&#x27;s not going to take over the world but it isn&#x27;t going away either.</text></item><item><author>dougmwne</author><text>This talk was such a treat. After all the carefuly crafted hype from Zuck and the gang, Carmack threw huge bucket of cold water on everything. I think it&#x27;s just wonderful that he&#x27;s allowed to speak so openly, about the things he&#x27;s proud of, the things he thinks are failures, internal politics, the possibilities for improvement, the real hard physical limits VR is running into, and his growing pessimism for the future of VR. I could really hear it in his talk why he moved on to spend more time on his next passion.<p>Since it sounded to me like the low hanging mobile VR fruit has been picked, I went ahead and pre-ordered my very first HMD afterwards. Time to see for myself if this is the computing future or an evolutionary dead end.</text></item></parent_chain><comment><author>pavlov</author><text><i>&gt; &quot;...&quot;maybe I&#x27;ll try VR&quot;, and goes into a store to buy... whatever it is, goes home to have a great time with it, and immediately tells their friends.&quot;</i><p>This is definitely a thing that happens with the Oculus Quest already. The hardware is easy to use and the software library is pretty much in place now. A major marketing campaign could make it really take off.<p>I don&#x27;t have any insight into FB VR&#x27;s decision to require the login on Oculus devices now, but my guess is that they consider the device to be ready for a mass market, and believe that the gains from the social graph will be worth the short-term pain of leaving early-adopter money on the table from here on.</text></comment> |
11,535,614 | 11,535,494 | 1 | 3 | 11,533,846 | train | <story><title>Deadly animal prion disease appears in Europe</title><url>http://www.nature.com/news/deadly-animal-prion-disease-appears-in-europe-1.19759</url></story><parent_chain><item><author>shmageggy</author><text>Prions are a crazy, crazy phenomenon. From wikipedia:<p>&gt; <i>A protein as a standalone infectious agent stands in contrast to all other known infectious agents such as viruses, bacteria, fungi, and parasites, all of which contain nucleic acids (DNA, RNA, or both)</i><p>In my layman&#x27;s understanding, they&#x27;re like this bizarre edge case in the way proteins interact. Of all the myriad way a protien can fold, it happens to find one that <i>induces the same malformation</i> when it interacts with another protein. To me, it almost seems like as much of a mathematical&#x2F;geometrical problem as a biological one. In any case, very interesting from the perspective of emergent behavior in complex systems.</text></item></parent_chain><comment><author>matthewmcg</author><text>Right--as I understand it, it&#x27;s not that different than Google&#x27;s &quot;Meeting Room Hardware Virus&quot;:<p>&quot;I imagine it started with all of the adapters which were thrown around in every meeting room. Everyone with a Macbook of some flavor needed a DVI to VGA adaptor in order to use the projectors, so they were plentiful. Somehow, someone probably damaged one of them and smooshed a couple of pins into places where they should not have gone.<p>&quot;Then, someone else forced this into their Mac. Perhaps two pins tried to go into just the one socket. At any rate, it would now break the socket and get it all out of whack. That socket, used with another adapter in another room, would then break that adapter. This new broken adapter would then go on to break even more Macbook DVI connectors.<p>Thus, we had a hardware virus.&quot; [1]<p>[1] <a href="https:&#x2F;&#x2F;rachelbythebay.com&#x2F;w&#x2F;2012&#x2F;09&#x2F;24&#x2F;dvi&#x2F;" rel="nofollow">https:&#x2F;&#x2F;rachelbythebay.com&#x2F;w&#x2F;2012&#x2F;09&#x2F;24&#x2F;dvi&#x2F;</a></text></comment> | <story><title>Deadly animal prion disease appears in Europe</title><url>http://www.nature.com/news/deadly-animal-prion-disease-appears-in-europe-1.19759</url></story><parent_chain><item><author>shmageggy</author><text>Prions are a crazy, crazy phenomenon. From wikipedia:<p>&gt; <i>A protein as a standalone infectious agent stands in contrast to all other known infectious agents such as viruses, bacteria, fungi, and parasites, all of which contain nucleic acids (DNA, RNA, or both)</i><p>In my layman&#x27;s understanding, they&#x27;re like this bizarre edge case in the way proteins interact. Of all the myriad way a protien can fold, it happens to find one that <i>induces the same malformation</i> when it interacts with another protein. To me, it almost seems like as much of a mathematical&#x2F;geometrical problem as a biological one. In any case, very interesting from the perspective of emergent behavior in complex systems.</text></item></parent_chain><comment><author>nonbel</author><text>&gt;&quot;Of all the myriad way a protien can fold, it happens to find one that induces the same malformation when it interacts with another protein.&quot;<p>It doesn&#x27;t really &quot;just happen&quot;, amyloids consist of peptides folded into beta-sheets and aggregates of these seem to be the most thermodynamically stable structures it is possible for polypeptide chains (regardless of sequence) to form:<p>&quot;From a wide range of in vitro experiments on peptides and proteins we now know that the formation of amyloid structures is not a rare phenomenon associated with a small number of diseases but rather that it reflects a well-defined structural form of the protein that is an alternative to the native state — a form that may in principle be adopted by many, if not all, polypeptide sequences<p>[...]<p>These observations, therefore, have led to the remarkable conclusion that, at the concentrations present in living systems, the native states may not always represent the absolute free energy minima of the corresponding polypeptide chains — the native form of a protein could in some cases simply be a metastable monomeric (or functionally oligomeric) state that is separated from its polymeric amyloid form by high kinetic barriers&quot;
<a href="http:&#x2F;&#x2F;www.ncbi.nlm.nih.gov&#x2F;pubmed&#x2F;24854788" rel="nofollow">http:&#x2F;&#x2F;www.ncbi.nlm.nih.gov&#x2F;pubmed&#x2F;24854788</a><p>Edit:<p>I realized some people might not be aware of the connection to prions. Here it is from the same wikipedia page as cited by the parent:<p>&quot;All known prions induce the formation of an amyloid fold, in which the protein polymerises into an aggregate consisting of tightly packed beta sheets.&quot;
<a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Prion" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Prion</a></text></comment> |
34,766,935 | 34,767,122 | 1 | 2 | 34,764,805 | train | <story><title>New Hampshire on the cusp of enshrining software freedom into law</title><url>https://libreboot.org/news/usa-libre-part2.html</url></story><parent_chain><item><author>cjpearson</author><text>That price is going to scare away most voters. $1000 per citizen for something that few people care about.<p>You could argue that the cost estimation is a worst-case scenario. It assumes that 90% of the affected software will be made compliant, but it&#x27;s also possible that they just use proprietary exception for most applications. It would cost much less in that case, but it would do so by abandoning the purpose of the bill.<p>The bill died in a unanimous vote last time around, and it&#x27;s not going to anywhere close to success this time either. However some other parts of the 2022 bill (considering libre solutions for new applications, limiting NDAs and non-competes, allow audits of software used in criminal cases) are more feasible and might stand a chance if they&#x27;re also split into new bills.</text></item></parent_chain><comment><author>leereeves</author><text>&gt; $1000 per citizen<p>How did they reach that figure? $1.4 billion dollars seems like far too much.<p>Edit: Interesting. Their methodology talks about rewriting all the state&#x27;s public-facing server side applications to be open source. (Hence the cost.)<p>I thought the bill was just requiring that the public be able to use libre browsers and apps on their own devices to access state services, not that the state&#x27;s server code had to be open source.</text></comment> | <story><title>New Hampshire on the cusp of enshrining software freedom into law</title><url>https://libreboot.org/news/usa-libre-part2.html</url></story><parent_chain><item><author>cjpearson</author><text>That price is going to scare away most voters. $1000 per citizen for something that few people care about.<p>You could argue that the cost estimation is a worst-case scenario. It assumes that 90% of the affected software will be made compliant, but it&#x27;s also possible that they just use proprietary exception for most applications. It would cost much less in that case, but it would do so by abandoning the purpose of the bill.<p>The bill died in a unanimous vote last time around, and it&#x27;s not going to anywhere close to success this time either. However some other parts of the 2022 bill (considering libre solutions for new applications, limiting NDAs and non-competes, allow audits of software used in criminal cases) are more feasible and might stand a chance if they&#x27;re also split into new bills.</text></item></parent_chain><comment><author>default-kramer</author><text>Yeah, these estimates blew me away. <a href="https:&#x2F;&#x2F;gencourt.state.nh.us&#x2F;lsr_search&#x2F;billText.aspx?id=188&amp;type=4" rel="nofollow">https:&#x2F;&#x2F;gencourt.state.nh.us&#x2F;lsr_search&#x2F;billText.aspx?id=188...</a><p>I guess there are all kinds of aspects of the government I&#x27;m not even aware of, but still... Everything I see is always browser-based with maybe some PDFs. What even is &quot;NH FIRST (statewide ERP)&quot;? Why does the general public interact with an ERP at all? I&#x27;m assuming this bill means that individuals should not be compelled to use proprietary software, but if it includes businesses also then the price tag makes more sense.</text></comment> |
12,514,167 | 12,514,333 | 1 | 2 | 12,513,814 | train | <story><title>The Programmer’s Guide to a Sane Workweek</title><url>https://codewithoutrules.com/2016/09/16/sane-workweek/</url></story><parent_chain></parent_chain><comment><author>patrickdavey</author><text>I went to a talk once on leadership. One of the suggestions was to get your &quot;go to hell kit&quot; ready. That is, get enough money in the bank (whatever that means for you) so that you can walk away if things cross your personal lines, be they moral &#x2F; work-life balance, whatever. It&#x27;s a good thing if there&#x27;s pressure to work silly hours. In my first job (recent grad) before I left the job, I&#x27;d been working 5 weekends straight (at least a Sat&#x2F;Sun). Looking back, insane, now I&#x27;d be having a conversation with my manager.<p>Sometimes it&#x27;s hard when the &quot;norm&quot; is to work these extra hours. Where I live now, I have worked a normal 8:45ish to 5:15ish and haven&#x27;t had to stay late or work weekends in years. It can be like that, I reckon it _ought_ to be like that. If your contract says 40 hours a week, why would you work more? You&#x27;re just reducing your hourly rate. Now, I don&#x27;t mind putting in extra effort if needed, no worries, but if it&#x27;s the culture that it&#x27;s just long hours, well that&#x27;s crazy.</text></comment> | <story><title>The Programmer’s Guide to a Sane Workweek</title><url>https://codewithoutrules.com/2016/09/16/sane-workweek/</url></story><parent_chain></parent_chain><comment><author>antirez</author><text>I don&#x27;t know what&#x27;s the perfect amount of work every week, but I&#x27;m sure anything &gt; 40h is wrong, and you should add commute time if more than 30min&#x2F;day, otherwise it&#x27;s a fake figure. In 36-40h&#x2F;week it&#x27;s possible to do a lot of things. If you can&#x27;t often is not because of the time, but because the same people wanting you to work more vaporize your time with meetings, conference calls, emails, phone calls, at a rate that makes it impossible for you to work. Or your coworkers are tempesting you with questions. Or your boss is switching your goal every day not allowing you to produce properly. Or you lack discipline to sit down and work instead of surfing random websites. Anyway whatever the problem is, the solution is NEVER to work more than 40h. Working more can just lead to a shitty life, depression, burn-out, and so forth.</text></comment> |
16,641,202 | 16,641,259 | 1 | 2 | 16,640,599 | train | <story><title>Tell HN: I just wanted to say: thank you, Hacker News</title><text>a few years ago i posted a question:<p>Ask HN: Chances for Restarting a Career in CS @ 30+ ?
( https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=7997624 )<p>after reading all the answers and recommendations, i decided to study CS in 2015.<p>it was quite challenging in every sense: time&#x2F;money management, high drop-out rates (~80% fail or stop studying cs at my university), lack of math skills - school was far far away.<p>now, i finished it and i can say, i definitely don&#x27;t regret it. it sharpened my mind and changed my mindset in a positive way. i&#x27;ve got absolutely no problems finding job offers (mainly as consultat or junior software engineers (i.e. IBM)) although i am now in my mid-thirties.<p>thank you, hn community</text></story><parent_chain><item><author>50something</author><text>I am finishing my bachelors in CompSci at Harvard Extension and just got hired by Google. And I&#x27;ve got about 20 years on you. So yeah, absolutely, this can work!<p>It was fun and challenging competing with top computer science students. In the long run, my organizational skills, focus, determination and world experience outweighed their raw brainpower and better memory.<p>It&#x27;s an ultramarathon, not a sprint.</text></item></parent_chain><comment><author>eganist</author><text>&gt; just got hired by Google. And I&#x27;ve got about 20 years on you.<p>As impressive as your achievement is, I&#x27;m equally impressed that Google finally started addressing their perceived ageism problem.</text></comment> | <story><title>Tell HN: I just wanted to say: thank you, Hacker News</title><text>a few years ago i posted a question:<p>Ask HN: Chances for Restarting a Career in CS @ 30+ ?
( https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=7997624 )<p>after reading all the answers and recommendations, i decided to study CS in 2015.<p>it was quite challenging in every sense: time&#x2F;money management, high drop-out rates (~80% fail or stop studying cs at my university), lack of math skills - school was far far away.<p>now, i finished it and i can say, i definitely don&#x27;t regret it. it sharpened my mind and changed my mindset in a positive way. i&#x27;ve got absolutely no problems finding job offers (mainly as consultat or junior software engineers (i.e. IBM)) although i am now in my mid-thirties.<p>thank you, hn community</text></story><parent_chain><item><author>50something</author><text>I am finishing my bachelors in CompSci at Harvard Extension and just got hired by Google. And I&#x27;ve got about 20 years on you. So yeah, absolutely, this can work!<p>It was fun and challenging competing with top computer science students. In the long run, my organizational skills, focus, determination and world experience outweighed their raw brainpower and better memory.<p>It&#x27;s an ultramarathon, not a sprint.</text></item></parent_chain><comment><author>mkagenius</author><text>&gt; n the long run, my organizational skills, focus, determination and world experience outweighed their raw brainpower and better memory.<p>Great. Would love to hear more of the story.</text></comment> |
39,609,565 | 39,609,422 | 1 | 2 | 39,607,747 | train | <story><title>Linux Touchpad Like MacBook Update: 2023 Progress on Smooth Scrolling</title><url>https://www.gitclear.com/blog/linux_touchpad_like_macbook_2023_update_smooth_scroll</url></story><parent_chain><item><author>iknowstuff</author><text>I’m sorry what<p>You can adjust the pressing force required in software, and the glass does in fact depress under your finger. It’s cushioned - that’s how they detect pressure.</text></item><item><author>asdff</author><text>&gt;I believe that the 3D Touch tech that was once in the iPhone is the same tech that is in the track pad and the Apple Watch<p>3D touch was only in the iphones for a few years, it was too expensive so they cut it in favor of the haptic touch they have now. The macbook trackpad is nice but honestly I prefer the old 2012 one they had with the actual physical button you could tweak the pressure of with a screwdriver. It seems a lot more ergonomic to have some actual give in the device instead of just jamming your finger onto an unmoving slab of glass. You don&#x27;t even realize how hard it is you are pressing onto these things until you try testing your muscle memory with the computer off; its sort of alarming.</text></item><item><author>nerdjon</author><text>It is an interesting thing to think about, I have friends that use Windows that are shocked that I willingly chose to get an external trackpad when I use my Mac as desktop.<p>Even more interesting is when I see my partner try to do something on my Mac using a trackpad, he seems... apprehensive? Like he is so afraid of doing the wrong thing and for me this trackpad has never done something I didn&#x27;t want it to do. Like without even thinking about it while I was re-reading this comment, I had fingers just resting on my trackpad.<p>It has to be a combination of software and hardware. Likely shared software and hardware.<p>Like is wrist detection on the trackpad the same as the wrist detection on an iPad?<p>I believe that the 3D Touch tech that was once in the iPhone is the same tech that is in the track pad and the Apple Watch.<p>We saw them use the same (or similar) tech on the iPhone home button when they removed the physical button.<p>Is the multitouch functionality of the trackpad the same technology as in iPhones and iPads?<p>I am genuinely curious about some of these because they feel like the same technology from the outside looking in and it would explain a lot about why it works as well as it does.<p>And yeah on the ROI, I mean they sell a $130 external trackpad... that I had zero qualms about buying. Because when using my MacBook Pro as a laptop I heavily rely on gestures. Those gestures only work if the trackpad is as perfect as it can be. But those gestures is also software.</text></item><item><author>al_borland</author><text>Why does this seem like such a hard problem to solve for everyone that isn’t Apple, when Apple seemingly solved the Trackpad over a decade ago?<p>Is this it? An unknown ROI?<p>&gt;the highly uncertain ROI for trying to align touchpad acceleration has prevented us from proposing a system change to the default Linux settings.<p>I can only speak for myself, but I gave up using trackpads on anything that isn’t a MacBook many years ago. Very occasionally I’ll try them and have always been disappointed. This prevents me from buying any laptop that isn’t a Mac and prevents me from running any OS that isn’t macOS on a laptop. I can’t be the only person who prioritizes the quality and feel of input devices when choosing a system. If this can make or break sales and adoption, it seems like the ROI would be pretty good. Even if we are just talking about Java app, if I’m using an obviously Java app that feels like a clunky Java app, I’ll usually find an alternative app that doesn’t feel horrible to use.<p>I’m glad progress is being made, but I struggle to understand why it’s still a problem at all when it’s been so good for so long with Apple. They even sell Bluetooth trackpads for desktops it’s so good.</text></item></parent_chain><comment><author>johnwalkr</author><text>They barely deflect, strain gauges measure the deflection and trigger the haptic part. When off, it does feel pretty solid. When on, the effect is very convincing, you would never know it&#x27;s not a button without being told. I had a coworker once that was ready to open up his turned-off macbook because he had been near sand recently and was convinced sand must be trapped inside the trackpad because it &quot;didn&#x27;t depress&quot;.</text></comment> | <story><title>Linux Touchpad Like MacBook Update: 2023 Progress on Smooth Scrolling</title><url>https://www.gitclear.com/blog/linux_touchpad_like_macbook_2023_update_smooth_scroll</url></story><parent_chain><item><author>iknowstuff</author><text>I’m sorry what<p>You can adjust the pressing force required in software, and the glass does in fact depress under your finger. It’s cushioned - that’s how they detect pressure.</text></item><item><author>asdff</author><text>&gt;I believe that the 3D Touch tech that was once in the iPhone is the same tech that is in the track pad and the Apple Watch<p>3D touch was only in the iphones for a few years, it was too expensive so they cut it in favor of the haptic touch they have now. The macbook trackpad is nice but honestly I prefer the old 2012 one they had with the actual physical button you could tweak the pressure of with a screwdriver. It seems a lot more ergonomic to have some actual give in the device instead of just jamming your finger onto an unmoving slab of glass. You don&#x27;t even realize how hard it is you are pressing onto these things until you try testing your muscle memory with the computer off; its sort of alarming.</text></item><item><author>nerdjon</author><text>It is an interesting thing to think about, I have friends that use Windows that are shocked that I willingly chose to get an external trackpad when I use my Mac as desktop.<p>Even more interesting is when I see my partner try to do something on my Mac using a trackpad, he seems... apprehensive? Like he is so afraid of doing the wrong thing and for me this trackpad has never done something I didn&#x27;t want it to do. Like without even thinking about it while I was re-reading this comment, I had fingers just resting on my trackpad.<p>It has to be a combination of software and hardware. Likely shared software and hardware.<p>Like is wrist detection on the trackpad the same as the wrist detection on an iPad?<p>I believe that the 3D Touch tech that was once in the iPhone is the same tech that is in the track pad and the Apple Watch.<p>We saw them use the same (or similar) tech on the iPhone home button when they removed the physical button.<p>Is the multitouch functionality of the trackpad the same technology as in iPhones and iPads?<p>I am genuinely curious about some of these because they feel like the same technology from the outside looking in and it would explain a lot about why it works as well as it does.<p>And yeah on the ROI, I mean they sell a $130 external trackpad... that I had zero qualms about buying. Because when using my MacBook Pro as a laptop I heavily rely on gestures. Those gestures only work if the trackpad is as perfect as it can be. But those gestures is also software.</text></item><item><author>al_borland</author><text>Why does this seem like such a hard problem to solve for everyone that isn’t Apple, when Apple seemingly solved the Trackpad over a decade ago?<p>Is this it? An unknown ROI?<p>&gt;the highly uncertain ROI for trying to align touchpad acceleration has prevented us from proposing a system change to the default Linux settings.<p>I can only speak for myself, but I gave up using trackpads on anything that isn’t a MacBook many years ago. Very occasionally I’ll try them and have always been disappointed. This prevents me from buying any laptop that isn’t a Mac and prevents me from running any OS that isn’t macOS on a laptop. I can’t be the only person who prioritizes the quality and feel of input devices when choosing a system. If this can make or break sales and adoption, it seems like the ROI would be pretty good. Even if we are just talking about Java app, if I’m using an obviously Java app that feels like a clunky Java app, I’ll usually find an alternative app that doesn’t feel horrible to use.<p>I’m glad progress is being made, but I struggle to understand why it’s still a problem at all when it’s been so good for so long with Apple. They even sell Bluetooth trackpads for desktops it’s so good.</text></item></parent_chain><comment><author>jxdxbx</author><text>My Apple trackpads don’t click when they are powered off. It just feels like pressing a piece of glass.</text></comment> |
3,729,395 | 3,729,171 | 1 | 2 | 3,728,664 | train | <story><title>The Starter, the Architect, the Debugger and the Finisher</title><url>http://jacquesmattheij.com/The+Starter+the+Architect+the+Debugger+and+the+Finisher</url></story><parent_chain><item><author>edw519</author><text>I believe that in order to get really good at any of these roles, you must do the other roles, deeply and often. For example:<p>The more time you spend Debugging shit, the less likely to you are to Architect something that produces shit.<p>The more time you spend fixing a million little things caused by poor early decisions, the better Starter you'll become.<p>The more fun you have conceiving and Starting projects, the more you'll realize how important Finishing is, so that you can get to new stuff.<p>And the more time you spend doing each of these roles, the better you'll get at doing all of them at the same time, and understanding what conditions are needed to do that. (Hint: Lots of quicker smaller complementary projects that you can wrap your whole head around.)<p>[This whole discussion reminds me of the time I was a restaurant manager and got tired of the servers and cooks bitching at each other. I had them switch roles for one shift. Once they understood how what they did affected the other, everyone got a little better and the bitching stopped.]</text></item></parent_chain><comment><author>scotty79</author><text>The more time I spend Debugging shit the less likely I am to Architect or even Start anything because I am painfully aware that everything produces shit.<p>EDIT: Wow. A downvote. That what I get for showing the pain I experience to the world. :-)</text></comment> | <story><title>The Starter, the Architect, the Debugger and the Finisher</title><url>http://jacquesmattheij.com/The+Starter+the+Architect+the+Debugger+and+the+Finisher</url></story><parent_chain><item><author>edw519</author><text>I believe that in order to get really good at any of these roles, you must do the other roles, deeply and often. For example:<p>The more time you spend Debugging shit, the less likely to you are to Architect something that produces shit.<p>The more time you spend fixing a million little things caused by poor early decisions, the better Starter you'll become.<p>The more fun you have conceiving and Starting projects, the more you'll realize how important Finishing is, so that you can get to new stuff.<p>And the more time you spend doing each of these roles, the better you'll get at doing all of them at the same time, and understanding what conditions are needed to do that. (Hint: Lots of quicker smaller complementary projects that you can wrap your whole head around.)<p>[This whole discussion reminds me of the time I was a restaurant manager and got tired of the servers and cooks bitching at each other. I had them switch roles for one shift. Once they understood how what they did affected the other, everyone got a little better and the bitching stopped.]</text></item></parent_chain><comment><author>geebee</author><text>I would agree that people learn from being involved in all phases of a software project at least once. Especially starters.<p>Starting a project is an exciting, heady, creative time. If the last 10% takes 50% of the effort, the first 90% is where you create and build at a fast pace, enjoy the adulation of your clients who are amazed with how quickly things are going, investigate and implement interesting new technologies and approaches, and revel in the fun of creating something new.<p>The question is, did you leave the code base in good shape, or did you go on a bender, drinking the champagne but leaving your successors to experience the hangover? My guess is that most people on this board have had to deal with a truly bad code base, in production, inherited from a programmer who flitted off to the next project cause he "enjoys the challenges of creating new things".<p>Until you've been the debugger who fixes the million little problems, the "architect" (wish we had a different word, cause you will be coding a lot) who refactors the code into something that can actually be maintained, and the finisher who experiences the irritated grousing of clients (who notice that things have slowed down so much since the "starter" left the project... we just asked for it and he did it), you don't know the kind of damage a rogue "starter" can do.</text></comment> |
3,063,529 | 3,063,352 | 1 | 3 | 3,063,156 | train | <story><title>Seven Minutes in Ubuntu: A Mac user's first impressions</title><url>http://thomaspark.me/2011/10/seven-minutes-in-ubuntu/</url></story><parent_chain><item><author>chimeracoder</author><text>First: This is really a review of Unity, not Ubuntu. The main ways that Ubuntu/Linux differ from OS X have nothing to do with the UI, but rather the underlying system.<p>That said, I'm glad to see that somebody likes Unity. Ubuntu's switch to Unity is one of the reasons that I left Ubuntu for another distro.<p>It seems like Canonical is targeting its product more towards people like the author of this post, in which case it seems that their strategy may be working.</text></item></parent_chain><comment><author>fl3tch</author><text>Those of us who have been using Gnome 2 for years have already streamlined and optimized our work flow in that environment. Whenever the UI changes, it breaks existing patterns of behavior that we usually don't even think about anymore. That's why people don't like change: it makes them less productive, at least temporarily as they streamline a new work flow. People didn't like the MS Office ribbon interface, the KDE 4 interface, etc., either. Even when Ubuntu moved the window controls to the left side, I found myself automatically and subconsciously moving the pointer to the right and clicking on an empty space, which was wasted effort and time, until I relearned that behavior.<p>People who haven't used Linux / Gnome before don't have those expectations and optimizations, so it's not surprising that they will have a more positive view of Unity. Also, Canonical <i>is</i> trying to make Unity emulate OS X to some extent, so the interface meets some expectations of Mac users. They will probably respond more positively.</text></comment> | <story><title>Seven Minutes in Ubuntu: A Mac user's first impressions</title><url>http://thomaspark.me/2011/10/seven-minutes-in-ubuntu/</url></story><parent_chain><item><author>chimeracoder</author><text>First: This is really a review of Unity, not Ubuntu. The main ways that Ubuntu/Linux differ from OS X have nothing to do with the UI, but rather the underlying system.<p>That said, I'm glad to see that somebody likes Unity. Ubuntu's switch to Unity is one of the reasons that I left Ubuntu for another distro.<p>It seems like Canonical is targeting its product more towards people like the author of this post, in which case it seems that their strategy may be working.</text></item></parent_chain><comment><author>keithpeter</author><text>To apply your first point to your second paragraph: Unity is not Ubuntu. Xubuntu, Kubuntu, and roll your own systems based on the boxes (Openbox, Fluxbox) abound.<p>I use Xubuntu on my netbook as my students can work out how to get a wordprocessor going or load a youtube video in class.<p>On the desktop pc I use dwm (large widescreen monitor) and I'm loving the efficiency. In fact, I install dmenu on all the computers and bind it to Super-Space.</text></comment> |
31,025,998 | 31,026,161 | 1 | 2 | 31,024,127 | train | <story><title>Making Rust a Better Fit for Cheri and Other Platforms</title><url>https://tratt.net/laurie/blog/2022/making_rust_a_better_fit_for_cheri_and_other_platforms.html</url></story><parent_chain></parent_chain><comment><author>kibwen</author><text>The OP links Gankra&#x27;s first article, but don&#x27;t miss the follow-up where she actually implemented some of these ideas as proof-of-concepts in the stdlib and compiler: <a href="https:&#x2F;&#x2F;gankra.github.io&#x2F;blah&#x2F;tower-of-weakenings&#x2F;" rel="nofollow">https:&#x2F;&#x2F;gankra.github.io&#x2F;blah&#x2F;tower-of-weakenings&#x2F;</a></text></comment> | <story><title>Making Rust a Better Fit for Cheri and Other Platforms</title><url>https://tratt.net/laurie/blog/2022/making_rust_a_better_fit_for_cheri_and_other_platforms.html</url></story><parent_chain></parent_chain><comment><author>dathinab</author><text>I think there are some problems in the article.<p>The main point of the referenced article by Aria Beingessner is Pointer Provenance. That this also helps out with enabling potential support for CHERI is a nice (and intended) side effect.<p>So yes more is needed for supporting CHERI but:<p>1. The non-address parts, if and how you can access them are fully CHERI specific. Any such code should (for now) not be Generic Rust but architecture specific extensions. (E.g. live in `std::arch::&lt;somethingCHERI&gt;`)<p>2. &quot;Rust&#x27;s integer type hierarchy&quot; There is no type hierarchy in the sense there is in C&#x2F;C++ as there is no sub-typing of integers (i.e. auto-conversions) in rust. Same is true for pointers so I don&#x27;t think it makes sense to call `<i>mut ()` the &quot;root of the...&quot;. (Also if anything that would be `</i>const ()`). Similar it&#x27;s more a void-pointer (through not quite the same) then a `uintptr_t`. To quote Aria: &quot;I don’t think Rust needs to define a moral equivalent to intptr_t [...]&quot;.<p>3. The 129th bit is a &quot;secret&quot; implementation detail. So not representing it is intended. if your code relies on somehow detecting if it&#x27;s set or not to work correctly you are doing something wrong. (Through maybe for testing&#x2F;asserts, still at most a CHERI specific method under std::arch.)<p>4. The proposed scratch design for hybrid mode fundamentally doesn&#x27;t work because of pointer provenance. Pointers need to be build-in types. So in hybrid mode you now would have 4 instead of 2 pointer types. Also given that you would want to use all of them in normal code you also would have 4 instead of 2 reference types. As far as I can tell this is also a messy nightmare to use in C&#x2F;C++ (Through I have to read into it first). Anyway hybrid mode is as far as I can tell irrelevant for &quot;pure&quot; rust applications and only becomes relevant when linking against non-capability-supporting FFI. EDIT: Provenance is often partially lost at FFI boundary anyway and you probably would want to special type the non-capability pointers and then at the boundary convert them to &quot;normal(capability)&quot; pointers. Only handling &quot;normal&quot; pointers in rust (which all have capabilities when compiled for CHERI).</text></comment> |
17,665,761 | 17,663,247 | 1 | 3 | 17,655,713 | train | <story><title>Books found in dumpster belonged to Thomas Jefferson</title><url>https://www.msn.com/en-us/news/good-news/he-found-15-books-in-a-sierra-dumpster-then-he-found-out-they-belonged-to-thomas-jefferson/ar-BBLd9cM</url></story><parent_chain></parent_chain><comment><author>mncharity</author><text>Under similar circumstances, I ended up with the one-page 1740 Treasurer&#x27;s Account for the Town of Cambridge, Massachusetts Bay Colony.[1]<p>A neighbor died, and a relative came by and rapidly dumpstered their apartment. Including a stack of family photo albums.<p>Now, I&#x27;d a childhood experience of family sorting things into two boxes: &quot;toys to donate to the school sale&quot;, and &quot;childhood photos and keepsakes&quot;. Think &quot;all your eggs in one basket&quot;. The wrong box was then dropped off at the school. A few hours later, it had been categorized as trash, thrown out, and was unrecoverably lost.<p>So I salvaged some of the albums in the dumpster. And eventually got in touch with the family to ask, &quot;are your sure?&quot;. They were. But before I got around to throwing them out again, I found the document inside a folded photo card thing. And wondered if there had been more in the dumpster, among that which I didn&#x27;t salvage.<p>And if I died today, it would likely end up back in a dumpster. Need to find it a better home.<p>[1] <a href="http:&#x2F;&#x2F;www.vendian.org&#x2F;1740&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.vendian.org&#x2F;1740&#x2F;</a></text></comment> | <story><title>Books found in dumpster belonged to Thomas Jefferson</title><url>https://www.msn.com/en-us/news/good-news/he-found-15-books-in-a-sierra-dumpster-then-he-found-out-they-belonged-to-thomas-jefferson/ar-BBLd9cM</url></story><parent_chain></parent_chain><comment><author>HenryTheHorse</author><text>I know Jefferson is complicated, but I encourage everyone to visit Monticello (his estate in Virginia) and see his library* .<p>The man was <i>obsessed</i> with reading (and gardening).<p>* On a related note, I&#x27;d also strongly encourage people visiting NYC to visit the JP Morgan Library. It&#x27;s spectacular.</text></comment> |
22,226,293 | 22,226,560 | 1 | 3 | 22,225,170 | train | <story><title>You’re better off using Exceptions</title><url>https://eiriktsarpalis.wordpress.com/2017/02/19/youre-better-off-using-exceptions/</url></story><parent_chain><item><author>Seenso</author><text>&gt; A record not being found is a normal thing!<p>It&#x27;s <i>not</i> a normal thing for code that needs that record that wasn&#x27;t found.<p>&gt; They literally tell you nothing and there&#x27;s no way to solve them without catching&#x2F;rescuing them. A null value, a plain &quot;error&quot; object, or an error argument in a callback would have been sufficient. If I need an exception to be raised for this kind of thing, I&#x27;ll do it myself.<p>They tell you lots: you asked for something your code path wanted and your request couldn&#x27;t be satisfied. Also, you&#x27;ve been helpfully kicked onto the alternative execution path to handle that situation.<p>Exceptions are a hell of a lot better than littering your code with null checks or error code checks, especially when you forget one and get a null pointer error or your code wanders away from the root cause and fails later.</text></item><item><author>ravenstine</author><text>My problem with exceptions isn&#x27;t so much exceptions themselves but the way they&#x27;re used.<p>The way I see it, exceptions should only be used for things that are irreconcilable, which most of the time is interpreter errors(e.g. undefined is not a function). In other words, I don&#x27;t think it&#x27;s that common that custom exceptions are needed outside of assertions to prevent the developer from doing something stupid. If you aren&#x27;t using types, raising an exception can be helpful to provide feedback and useful information when data isn&#x27;t formatted correctly.<p>Exceptions suck when they&#x27;re used for problems that aren&#x27;t actual problems. For example, if a query is made to an API for a record and that record isn&#x27;t found, the SDK wrapping that API would raise a &quot;Record not found&quot; exception. What the hell? A record not being found is a <i>normal</i> thing! I&#x27;ve seen this kind of thing all over the place, and I recently had to write some application code to work around one of these useless exceptions. They literally tell you nothing and there&#x27;s no way to solve them without catching&#x2F;rescuing them. A null value, a plain &quot;error&quot; object, or an error argument in a callback would have been sufficient. If I need an exception to be raised for this kind of thing, I&#x27;ll do it myself.</text></item></parent_chain><comment><author>ravenstine</author><text>&gt; It&#x27;s not a normal thing for code that needs that record that wasn&#x27;t found.<p>No offense, but I don&#x27;t know where that idea comes from. Systems are checking for records <i>all the time</i> in ways where the absence of data doesn&#x27;t necessitate throwing an exception.<p>For instance, a page, user, or piece of media on a website may have existed at one point but was since deleted, but still has a permalink floating around the net. Is it useful, in the case that someone clicks on such a link, to throw an exception when I can instead choose to render different page content when a record wasn&#x27;t found? I&#x27;ll never need a stack trace for that.<p>&gt; They tell you lots: you asked for something your code path wanted and your request couldn&#x27;t be satisfied. Also, you&#x27;ve been helpfully kicked onto the alternative execution path to handle that situation.<p>Why would I want a code path for expected behavior? I agree for cases like a failed connection, where the system is actually broken, but there isn&#x27;t anything fundamentally broken about data absence.<p>&gt; Also, you&#x27;ve been helpfully kicked onto the alternative execution path to handle that situation.<p>That&#x27;s not only presumptuous, but if I wanted that to happen, I can do so myself.<p>&gt; Exceptions are a hell of a lot better than littering your code with null checks or error code checks, especially when you forget one and get a null pointer error.<p>Hmmm...<p><pre><code> const record = store.findRecord(params.id);
if (record) {
render(&#x27;show-record&#x27;);
} else {
render(&#x27;record-not-found&#x27;);
}
</code></pre>
or...<p><pre><code> try {
const record = store.findRecord(params.id);
render(&#x27;show-record&#x27;);
} catch(err) {
if (err.name === &#x27;RECORD_NOT_FOUND&#x27;) {
render(&#x27;record-not-found&#x27;);
} else {
throw err;
}
}
</code></pre>
I&#x27;ll let people decide which one is better. I personally prefer the first one.</text></comment> | <story><title>You’re better off using Exceptions</title><url>https://eiriktsarpalis.wordpress.com/2017/02/19/youre-better-off-using-exceptions/</url></story><parent_chain><item><author>Seenso</author><text>&gt; A record not being found is a normal thing!<p>It&#x27;s <i>not</i> a normal thing for code that needs that record that wasn&#x27;t found.<p>&gt; They literally tell you nothing and there&#x27;s no way to solve them without catching&#x2F;rescuing them. A null value, a plain &quot;error&quot; object, or an error argument in a callback would have been sufficient. If I need an exception to be raised for this kind of thing, I&#x27;ll do it myself.<p>They tell you lots: you asked for something your code path wanted and your request couldn&#x27;t be satisfied. Also, you&#x27;ve been helpfully kicked onto the alternative execution path to handle that situation.<p>Exceptions are a hell of a lot better than littering your code with null checks or error code checks, especially when you forget one and get a null pointer error or your code wanders away from the root cause and fails later.</text></item><item><author>ravenstine</author><text>My problem with exceptions isn&#x27;t so much exceptions themselves but the way they&#x27;re used.<p>The way I see it, exceptions should only be used for things that are irreconcilable, which most of the time is interpreter errors(e.g. undefined is not a function). In other words, I don&#x27;t think it&#x27;s that common that custom exceptions are needed outside of assertions to prevent the developer from doing something stupid. If you aren&#x27;t using types, raising an exception can be helpful to provide feedback and useful information when data isn&#x27;t formatted correctly.<p>Exceptions suck when they&#x27;re used for problems that aren&#x27;t actual problems. For example, if a query is made to an API for a record and that record isn&#x27;t found, the SDK wrapping that API would raise a &quot;Record not found&quot; exception. What the hell? A record not being found is a <i>normal</i> thing! I&#x27;ve seen this kind of thing all over the place, and I recently had to write some application code to work around one of these useless exceptions. They literally tell you nothing and there&#x27;s no way to solve them without catching&#x2F;rescuing them. A null value, a plain &quot;error&quot; object, or an error argument in a callback would have been sufficient. If I need an exception to be raised for this kind of thing, I&#x27;ll do it myself.</text></item></parent_chain><comment><author>kenoyer130</author><text>In Java&#x2F;C# land exceptions are EXPENSIVE. Like magnatudes more expensive. You have to build a full stack trace etc. Removing places in the code where it is &quot;Throwing exceptions for non exceptional circumstances&quot; has a dramatic performance increase benefit.</text></comment> |
18,142,712 | 18,142,623 | 1 | 2 | 18,142,277 | train | <story><title>Bloomberg’s ‘The Big Hack’</title><url>https://daringfireball.net/2018/10/bloomberg_the_big_hack</url></story><parent_chain><item><author>lacker</author><text>It does not seem like this story is true. If it&#x27;s true, it makes absolutely no sense for Apple and Amazon to attack Bloomberg. Sure, a national security letter could force them to stay quiet, or maybe even to lie to the public and say it didn&#x27;t happen, but it can&#x27;t make them criticize Bloomberg. Attacking Bloomberg if the story is true is only going to convince Bloomberg to dig deeper. And the story isn&#x27;t even <i>that</i> bad for Amazon or Apple - it&#x27;s much worse for US-China relations than it is for either of those companies.<p>The key technical detail of what these chips are allegedly doing also does not make sense. From the article:<p><i>the chips allowed the attackers to create a stealth doorway into any network that included the altered machines</i><p>How can you get around a firewall by using a compromised machine that&#x27;s part of the internal network?<p>I don&#x27;t think Bloomberg reporters are just making stuff up. But the technical confusion here makes me suspect that the government officials who leaked this story just didn&#x27;t understand the details of a real incident that happened, and in the leaking the story got mangled into inaccuracy.</text></item></parent_chain><comment><author>akiselev</author><text>The actual details on the hardware are also sketchy. Based on my reading of the article, this wasn&#x27;t a chip swap where one chip is replaced by a backdoored version. The article implies that this was an extra chip so either dozens (possibly hundreds) of engineers were in on the operation from the beginning to slip the chip into the design undetected or the chip was mounted <i>without any changes to the board design.</i> The former is much riskier than backdooring the chips and the latter, as far as I know, has not been done before with a nontrivial chip.<p>Fitting any chip capable of exfiltrating a nontrivial amount of data onto a modern motherboard without going through many rounds of simulation or significantly impacting performance, while also putting it in a place it is capable of intercepting valuable data is practically impossible. Hell, just getting the right power domains wired to the chip is going to be tough enough.</text></comment> | <story><title>Bloomberg’s ‘The Big Hack’</title><url>https://daringfireball.net/2018/10/bloomberg_the_big_hack</url></story><parent_chain><item><author>lacker</author><text>It does not seem like this story is true. If it&#x27;s true, it makes absolutely no sense for Apple and Amazon to attack Bloomberg. Sure, a national security letter could force them to stay quiet, or maybe even to lie to the public and say it didn&#x27;t happen, but it can&#x27;t make them criticize Bloomberg. Attacking Bloomberg if the story is true is only going to convince Bloomberg to dig deeper. And the story isn&#x27;t even <i>that</i> bad for Amazon or Apple - it&#x27;s much worse for US-China relations than it is for either of those companies.<p>The key technical detail of what these chips are allegedly doing also does not make sense. From the article:<p><i>the chips allowed the attackers to create a stealth doorway into any network that included the altered machines</i><p>How can you get around a firewall by using a compromised machine that&#x27;s part of the internal network?<p>I don&#x27;t think Bloomberg reporters are just making stuff up. But the technical confusion here makes me suspect that the government officials who leaked this story just didn&#x27;t understand the details of a real incident that happened, and in the leaking the story got mangled into inaccuracy.</text></item></parent_chain><comment><author>parliament32</author><text>It depends. These chips were specifically connected to the BMC&#x2F;IPMI:<p>&gt;The illicit chips could do all this because they were connected to the baseboard management controller, a kind of superchip that administrators use to remotely log in to problematic servers, giving them access to the most sensitive code even on machines that have crashed or are turned off.<p>Is your OOB-management VLAN&#x2F;network firewalled off from outgoing access to the internet? If not, this chip can make requests out to another host, who gives it code to run. This code can then either collect data and send it back out, or do other nefarious things.</text></comment> |
32,843,743 | 32,843,637 | 1 | 2 | 32,843,348 | train | <story><title>Denmark not offering second Covid booster shot to healthy adults under 50</title><url>https://www.sst.dk/en/english/corona-eng/vaccination-against-covid-19</url></story><parent_chain><item><author>Kranar</author><text>2018 was an exceptionally bad year for influenza. Typically influenza deaths in the U.S. are between 20-30k.<p>COVID deaths in the U.S. over a two year period amounted to over 1 million.</text></item><item><author>rossdavidh</author><text>Bit by bit, it is becoming the new influenza. Not saying we&#x27;re there yet, but that&#x27;s clearly where we&#x27;re headed.<p>Now, influenza kills lots of people; in 2018 over 60,000 people were killed by influenza in the USA alone. But we don&#x27;t have border closing or &quot;show your papers&quot; or all the rest for influenza, and we&#x27;re not going to.</text></item></parent_chain><comment><author>antasvara</author><text>I think the commenter you&#x27;re responding to was indicating that we&#x27;re moving towards COVID as the new influenza, not that we&#x27;re there yet.<p>Case numbers and deaths seem to be plateauing at a pretty low rate, especially considering the relaxed restrictions these numbers are occurring under. It seems reasonable to think that we won&#x27;t suddenly see a more dangerous strain of this particular virus, or that vaccines will lose a significant amount of effectiveness.</text></comment> | <story><title>Denmark not offering second Covid booster shot to healthy adults under 50</title><url>https://www.sst.dk/en/english/corona-eng/vaccination-against-covid-19</url></story><parent_chain><item><author>Kranar</author><text>2018 was an exceptionally bad year for influenza. Typically influenza deaths in the U.S. are between 20-30k.<p>COVID deaths in the U.S. over a two year period amounted to over 1 million.</text></item><item><author>rossdavidh</author><text>Bit by bit, it is becoming the new influenza. Not saying we&#x27;re there yet, but that&#x27;s clearly where we&#x27;re headed.<p>Now, influenza kills lots of people; in 2018 over 60,000 people were killed by influenza in the USA alone. But we don&#x27;t have border closing or &quot;show your papers&quot; or all the rest for influenza, and we&#x27;re not going to.</text></item></parent_chain><comment><author>lifeformed</author><text>And that&#x27;s with tons of precautions, whereas with the flu society doesn&#x27;t take the kinds of mitigations we take with COVID.</text></comment> |
26,272,844 | 26,272,776 | 1 | 2 | 26,272,492 | train | <story><title>Why is the DOS path character "\"? (2005)</title><url>https://web.archive.org/web/20100612035120/http://blogs.msdn.com/b/larryosterman/archive/2005/06/24/432386.aspx</url></story><parent_chain></parent_chain><comment><author>kiwidrew</author><text>Thanks to Microsoft&#x27;s recent release of the MS-DOS 2.0 source code, we can now peek under the hood and confirm that Microsoft specifically intended for the DOS 2.0 file APIs to be compatible with Unix. From XENIX.ASM [1], the code that implements the new API:<p><pre><code> ;
; xenix file calls for MSDOS
;
TITLE XENIX - IO system to mimic UNIX
</code></pre>
And the CONFIG.DOC [2] file discusses the &#x27;AVAILDEV&#x27; option which lets the system mimic Unix even more:<p><pre><code> AVAILDEV = &lt;TRUE or FALSE&gt;
The default is TRUE which means both &#x2F;dev&#x2F;&lt;dev&gt; and
&lt;dev&gt; will reference the device &lt;dev&gt;. If FALSE is
selected, only &#x2F;dev&#x2F;&lt;dev&gt; refers to device &lt;dev&gt;,
&lt;dev&gt; by itself means a file in the current directory
with the same name as one of the devices.
</code></pre>
Finally, an example CONFIG.SYS file from the same document:<p><pre><code> A typical configuration file might look like this:
BUFFERS = 10
FILES = 10
DEVICE = &#x2F;bin&#x2F;network.sys
BREAK = ON
SWITCHAR = -
SHELL = a:&#x2F;bin&#x2F;command.com a:&#x2F;bin -p
</code></pre>
I think it&#x27;s pretty clear how Microsoft intended for MS-DOS to be configured, but alas IBM had other ideas...<p>[1] <a href="https:&#x2F;&#x2F;github.com&#x2F;microsoft&#x2F;MS-DOS&#x2F;blob&#x2F;master&#x2F;v2.0&#x2F;source&#x2F;XENIX.ASM" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;microsoft&#x2F;MS-DOS&#x2F;blob&#x2F;master&#x2F;v2.0&#x2F;source&#x2F;...</a><p>[2] <a href="https:&#x2F;&#x2F;github.com&#x2F;microsoft&#x2F;MS-DOS&#x2F;blob&#x2F;master&#x2F;v2.0&#x2F;bin&#x2F;CONFIG.DOC#L60" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;microsoft&#x2F;MS-DOS&#x2F;blob&#x2F;master&#x2F;v2.0&#x2F;bin&#x2F;CON...</a></text></comment> | <story><title>Why is the DOS path character "\"? (2005)</title><url>https://web.archive.org/web/20100612035120/http://blogs.msdn.com/b/larryosterman/archive/2005/06/24/432386.aspx</url></story><parent_chain></parent_chain><comment><author>lifthrasiir</author><text>In addition to its use as a path separator in DOS and Windows, the backslash character itself is also interesting because it is very likely a modern invention, with the first attestation in 1940s (!). Its original use in ASCII (1960s) was for ALGOL operator digraphs `\&#x2F;` and `&#x2F;\`. Its early use as the C escape sequence (1970s, replacing `*` in BCPL) suggests that it carried no significant semantics at that time.</text></comment> |
7,036,796 | 7,036,794 | 1 | 2 | 7,036,525 | train | <story><title>Ford Exec: 'We Know Everyone Who Breaks the Law' Thanks To Our GPS In Your Car</title><url>http://www.businessinsider.com/ford-exec-gps-2014-1</url></story><parent_chain><item><author>rickdale</author><text>I just bought a ford taurus. It immediately connects my cell phone to my car and I sorta get the feeling like the cops that sit on the eway have access to the computer in my car and also the cell phone connected to that computer. But hey thats just my paranoia.<p>On another note, it was very clear checking off do not track in the vehicle. The only reason they say they want to track is for data like the exec gives the example for, traffic analysis etc. not like daily tracking. But it is creepy and really I dont know if all the benefits balance out the potential drawbacks.<p>There is also this notification in the myfordsync system that is &quot;911 Assist&quot;.. now this is a fine option, but literally the car will remind you everytime you start it that it is off and unless you select otherwise, it won&#x27;t just alert you, but will give you the option to turn it on.</text></item></parent_chain><comment><author>deveac</author><text><i>&gt;On another note, it was very clear checking off do not track in the vehicle.</i><p>I cannot see it remaining this way. It is just a matter of time before the OEMs buckle and sell your data to an enterprising third party in exchange for the ability to lower costs. The auto supply chain is notorious for being a bloodbath of cost-cutting. It&#x27;s a perfect cultural fit.<p>Not saying that you won&#x27;t retain the option to turn off tracking as these systems become more widespread, but it&#x27;s just an illegible TOS away from being opt-in by default with a buried opt-out.</text></comment> | <story><title>Ford Exec: 'We Know Everyone Who Breaks the Law' Thanks To Our GPS In Your Car</title><url>http://www.businessinsider.com/ford-exec-gps-2014-1</url></story><parent_chain><item><author>rickdale</author><text>I just bought a ford taurus. It immediately connects my cell phone to my car and I sorta get the feeling like the cops that sit on the eway have access to the computer in my car and also the cell phone connected to that computer. But hey thats just my paranoia.<p>On another note, it was very clear checking off do not track in the vehicle. The only reason they say they want to track is for data like the exec gives the example for, traffic analysis etc. not like daily tracking. But it is creepy and really I dont know if all the benefits balance out the potential drawbacks.<p>There is also this notification in the myfordsync system that is &quot;911 Assist&quot;.. now this is a fine option, but literally the car will remind you everytime you start it that it is off and unless you select otherwise, it won&#x27;t just alert you, but will give you the option to turn it on.</text></item></parent_chain><comment><author>sentenza</author><text>Relax. You don&#x27;t have to stress yourself out about these things, since you soon won&#x27;t have much of a choice anyway.<p>The day will come when you can&#x27;t get car insurance without active tracking. It is just too tempting for insurance companies to reduce their claim investigation overhead&#x2F;cost with that technology.<p>Of course, strong privacy protection laws could keep this from happening.<p>Yeah.</text></comment> |
10,676,882 | 10,676,829 | 1 | 3 | 10,676,467 | train | <story><title>Patriot Act author warns EU against dragnet response to terror</title><url>http://www.politico.eu/article/us-senator-warns-eu-against-dragnet-response-to-terror/</url></story><parent_chain></parent_chain><comment><author>mkaziz</author><text>In my mind, the erosion of privacy and freedom - some of the most vaunted principles of the West - is the ultimate triumph of terrorist organizations like ISIS and Al-Qaeda. They can&#x27;t beat us by strength of arms, so instead they&#x27;re stunting our culture.</text></comment> | <story><title>Patriot Act author warns EU against dragnet response to terror</title><url>http://www.politico.eu/article/us-senator-warns-eu-against-dragnet-response-to-terror/</url></story><parent_chain></parent_chain><comment><author>jacquesm</author><text>“Talking about it in practical terms, the answer is to target the people which you know are up to bad stuff rather than bringing in the 99.8 percent of the inhabitants there, including the vast majority of followers of Islam, who have no intention whatsoever of conducting a terrorist attack,”<p>Are there any other terms than &#x27;practical&#x27;?<p>Better late than never I guess. What&#x27;s funny is that this was not exactly new knowledge when the patriot act was drafted in the first place. All these idiotically named acts (&#x27;patriot act&#x27;, &#x27;freedom act&#x27;) are named that way so that if you&#x27;re against them it looks as if you&#x27;re either not a patriot or against freedom.</text></comment> |
6,413,391 | 6,413,184 | 1 | 3 | 6,412,708 | train | <story><title>I Am An Object Of Internet Ridicule, Ask Me Anything</title><url>http://www.theawl.com/2013/09/i-was-a-hated-hipster-meme-and-then-it-got-worse</url></story><parent_chain><item><author>drzaiusapelord</author><text>On top of it, geek culture is a hipster culture. Oh you listen to obscure geeky bands and wear comic&#x2F;anime t-shirts all the time? You purposely disengage from mainstream society? You&#x27;re overly critical of the status quo and only socialize with people exactly like you? Gee, that sounds like the guy you&#x27;re criticizing.</text></item><item><author>potatolicious</author><text>Hipster-hate strikes me as just another thinly veiled form of bullying, and it&#x27;s interesting to see how readily internet nerds - the people who are disproportionately to have been bullied in the past - engage in it.<p>Look! He&#x27;s different! Let&#x27;s make assumptions about his motivations and get him!<p>It&#x27;s also interesting to see how many times Reddit (and other communities) fly into a rage-fest because of lack of context, only to make an about-face when the full picture comes out. It&#x27;s also interesting how no matter how many times this <i>exact</i> situation happens, there is no stopping the next rage-fest.<p>Above all other things, internet communities is what makes me cynical about humanity.</text></item></parent_chain><comment><author>Torgo</author><text>I can&#x27;t help but feel that a large portion of the current &quot;geek culture&quot; is a collection of appropriations from a different group, selected for &quot;authenticity&quot;, similar to criticisms of the wider hipster culture.<p>I wore thick-rim glasses because 1. I didn&#x27;t&#x2F;couldn&#x27;t care about fashion 2. my parents didn&#x27;t have the money for nicer frames and 3. I actually could not see without glasses. So yeah, when I see thick rim glasses being worn _because_ they &quot;look geeky,&quot; or worse, without even any lenses because the person has perfect vision, it annoys me a little bit. Because I got treated like dog shit by the exact same class of person who now dresses in a parody of my life as a frivolous fashion decision.</text></comment> | <story><title>I Am An Object Of Internet Ridicule, Ask Me Anything</title><url>http://www.theawl.com/2013/09/i-was-a-hated-hipster-meme-and-then-it-got-worse</url></story><parent_chain><item><author>drzaiusapelord</author><text>On top of it, geek culture is a hipster culture. Oh you listen to obscure geeky bands and wear comic&#x2F;anime t-shirts all the time? You purposely disengage from mainstream society? You&#x27;re overly critical of the status quo and only socialize with people exactly like you? Gee, that sounds like the guy you&#x27;re criticizing.</text></item><item><author>potatolicious</author><text>Hipster-hate strikes me as just another thinly veiled form of bullying, and it&#x27;s interesting to see how readily internet nerds - the people who are disproportionately to have been bullied in the past - engage in it.<p>Look! He&#x27;s different! Let&#x27;s make assumptions about his motivations and get him!<p>It&#x27;s also interesting to see how many times Reddit (and other communities) fly into a rage-fest because of lack of context, only to make an about-face when the full picture comes out. It&#x27;s also interesting how no matter how many times this <i>exact</i> situation happens, there is no stopping the next rage-fest.<p>Above all other things, internet communities is what makes me cynical about humanity.</text></item></parent_chain><comment><author>jlgreco</author><text>Ehh, I think there is certainly some overlap, particularly in the &quot;retro&quot; tastes, but I don&#x27;t think what you are describing as geek culture is really a subset of hipster culture. Mario tshirts? Sure, you could call that hipster. Anime tshirts? I wouldn&#x27;t say so.<p>People with both styles are in many of my social circles, but they still seem relatively distinct to me.</text></comment> |
34,805,575 | 34,805,446 | 1 | 3 | 34,803,696 | train | <story><title>Tell HN: DigitalOcean is doing layoffs</title><text>I was let go this morning along with at least 4 others from team. Looks like a big company wide layoff is underway</text></story><parent_chain><item><author>jpgvm</author><text>I don&#x27;t really get the motivation for this beyond personal greed on behalf of executives that are only seeking to prop up the share price in the short term.<p>The market forces at work will force all technology companies down in valuation pretty much regardless, what is the difference of a few extra million market cap to handicap your ability to grow during the next expansion phase?<p>I can understand it if you have brought on a lot of fat and you want to lean out your team and need an excuse but outside of that rather narrow situation I really don&#x27;t understand cutting stuff like technical writers etc during these periods.<p>Why handicap yourself in the future just to make one quarter look better? Surely if you have faith your stock options will be worth more if you play the longer game?</text></item></parent_chain><comment><author>reisse</author><text>&gt; I can understand it if you have brought on a lot of fat and you want to lean out your team and need an excuse but outside of that rather narrow situation<p>This doesn&#x27;t really seem to be a rather narrow situation. The tech companies were hiring like crazy for the past two years. Quick googling shows that DigitalOcean increased headcount by 31% last year.<p>And contrary to the popular opinion here, for me this does sound like the right move for the time. The logic, on the growing market, was &quot;let&#x27;s hire people now for 200k TC and give 50k raise after a year, because year later they&#x27;ll be asking for 500k TC upfront&quot;. Now it&#x27;s clear the salaries won&#x27;t be going to the moon in the nearest future, so it makes sense to cut the fat.</text></comment> | <story><title>Tell HN: DigitalOcean is doing layoffs</title><text>I was let go this morning along with at least 4 others from team. Looks like a big company wide layoff is underway</text></story><parent_chain><item><author>jpgvm</author><text>I don&#x27;t really get the motivation for this beyond personal greed on behalf of executives that are only seeking to prop up the share price in the short term.<p>The market forces at work will force all technology companies down in valuation pretty much regardless, what is the difference of a few extra million market cap to handicap your ability to grow during the next expansion phase?<p>I can understand it if you have brought on a lot of fat and you want to lean out your team and need an excuse but outside of that rather narrow situation I really don&#x27;t understand cutting stuff like technical writers etc during these periods.<p>Why handicap yourself in the future just to make one quarter look better? Surely if you have faith your stock options will be worth more if you play the longer game?</text></item></parent_chain><comment><author>game_the0ry</author><text>&gt; what is the difference of a few extra million market cap to handicap your ability to grow during the next expansion phase?<p>For an executive, it&#x27;s a big difference in stock based bonus.<p>The executive level at corporate america tends to filter for status and financial obsessed sociopaths, so they make sociopathic decisions where they are content with making decisions that harm many (layoffs) but benefit themselves. That&#x27;s how we got the enron, the great financial crisis of 2008, and many others.</text></comment> |
15,771,050 | 15,770,912 | 1 | 2 | 15,770,557 | train | <story><title>The Girl with the Brick Earring</title><url>http://lucaswoltmann.de/art%27n%27images/2017/04/08/the-girl-with-the-brick-earring.html</url></story><parent_chain></parent_chain><comment><author>pzone</author><text>Yikes, doing a color conversion by nearest-neighbor RGB is guaranteed to give odd results like this. The entire center of her dress has undershot the blackpoint and is washed out entirely in black, and the representation of the headdress is extremely high variance. These are similar problems to people what people face attempting to print out digital photos or artwork without properly managed color.<p>At a minimum you would want to adjust the color gamut of the image by hand to line up with the lego color gamut so the end result is more pleasing, more concretely that means spending some time on the hue&#x2F;saturation&#x2F;lightness&#x2F;color curve filters until those conversion artifacts are minimized. A more theoretically interesting way to do it would be to use a gamut matching algorithm with a discrete color space defined by the available lego bricks.<p><a href="http:&#x2F;&#x2F;www.colourphil.co.uk&#x2F;rendering_intents.shtml" rel="nofollow">http:&#x2F;&#x2F;www.colourphil.co.uk&#x2F;rendering_intents.shtml</a>
<a href="http:&#x2F;&#x2F;cs.haifa.ac.il&#x2F;hagit&#x2F;courses&#x2F;ist&#x2F;Lectures&#x2F;IST12_ColorManagementx4.pdf" rel="nofollow">http:&#x2F;&#x2F;cs.haifa.ac.il&#x2F;hagit&#x2F;courses&#x2F;ist&#x2F;Lectures&#x2F;IST12_Color...</a></text></comment> | <story><title>The Girl with the Brick Earring</title><url>http://lucaswoltmann.de/art%27n%27images/2017/04/08/the-girl-with-the-brick-earring.html</url></story><parent_chain></parent_chain><comment><author>jerrre</author><text>Everybody here is drawn to the picking of the colors. But the optimization of the different sized pieces also seems like a very fun problem to work on!<p>And taking the step to actually getting out of the digital world is something everybody should probably do more often!</text></comment> |
33,100,632 | 33,099,765 | 1 | 2 | 33,097,113 | train | <story><title>Over 50% of CEOs say they’re considering cutting jobs over the next 6 months</title><url>https://www.marketwatch.com/story/more-than-half-of-ceos-consider-workforce-reductions-over-the-next-6-months-and-remote-workers-may-be-the-first-go-to-11664907913</url></story><parent_chain><item><author>f1shy</author><text>The whole article seems full of it.<p>&gt; Nine in ten CEOs in the U.S. (91%) believe a recession will arrive in the coming 12 months, while 86% of CEOs globally feel the same way<p>- So what? Most CEOs I know cannot foresee what they will eat tomorrow. No offence, but being CEO makes you no better at predicting the future as the janitor. &quot;They have, more info, experience&quot; yada yada... I knew just too many incompetent CEOs.<p>Also, what does it mean, cutting jobs... how many? why? which ones?<p>Seems like content, but completely empty.</text></item><item><author>fishtoaster</author><text>Ugh, I hate stats like this.<p>WHAT&#x27;S THE BASELINE?!<p>It could well be that 50% of CEOs are <i>always</i> &quot;considering&quot; cutting jobs in the next 6 months. I mean, I suspect that this number is higher than usual because, well, it <i>does</i> look like we&#x27;re heading into a recession. But if I&#x27;m interpreting this number based on my perception of the recession, then this number is useless at the main point of this article: informing me on whether we&#x27;re heading into a recession or not.</text></item></parent_chain><comment><author>cannaceo</author><text>As a CEO I speak to other CEOs on a regular basis about what we&#x27;re seeing. That means I&#x27;m clued in to my customers&#x27; trends, vendors&#x27; trends, and competitors&#x27; trends. I see stuff happening in my industry from a more holistic perspective than my employees. I can tell the difference between a revenue decline from a lack of competitiveness versus industry decline. You might not see us working but we talk. A lot.</text></comment> | <story><title>Over 50% of CEOs say they’re considering cutting jobs over the next 6 months</title><url>https://www.marketwatch.com/story/more-than-half-of-ceos-consider-workforce-reductions-over-the-next-6-months-and-remote-workers-may-be-the-first-go-to-11664907913</url></story><parent_chain><item><author>f1shy</author><text>The whole article seems full of it.<p>&gt; Nine in ten CEOs in the U.S. (91%) believe a recession will arrive in the coming 12 months, while 86% of CEOs globally feel the same way<p>- So what? Most CEOs I know cannot foresee what they will eat tomorrow. No offence, but being CEO makes you no better at predicting the future as the janitor. &quot;They have, more info, experience&quot; yada yada... I knew just too many incompetent CEOs.<p>Also, what does it mean, cutting jobs... how many? why? which ones?<p>Seems like content, but completely empty.</text></item><item><author>fishtoaster</author><text>Ugh, I hate stats like this.<p>WHAT&#x27;S THE BASELINE?!<p>It could well be that 50% of CEOs are <i>always</i> &quot;considering&quot; cutting jobs in the next 6 months. I mean, I suspect that this number is higher than usual because, well, it <i>does</i> look like we&#x27;re heading into a recession. But if I&#x27;m interpreting this number based on my perception of the recession, then this number is useless at the main point of this article: informing me on whether we&#x27;re heading into a recession or not.</text></item></parent_chain><comment><author>throwoutway</author><text>Most large corp CEOs are briefed by analysts, and they’re all probably telling them their “predictions”<p>Here is an interesting thought experiment: if McKinsey wanted to force a recession, could they invoke one by telling all the CEOs the worst possible news and making terrible recommendations?</text></comment> |
6,737,796 | 6,736,942 | 1 | 2 | 6,736,606 | train | <story><title>Protean Echo – Fuse All Your Cards into One</title><url>http://getprotean.com/</url></story><parent_chain></parent_chain><comment><author>jchung</author><text>Is this really a problem? Too many credit cards make your wallet uncomfortably large? Let&#x27;s get back to solving problems that matter. I can&#x27;t believe we have three companies on the front page today reducing the number of credit cards in your wallet.</text></comment> | <story><title>Protean Echo – Fuse All Your Cards into One</title><url>http://getprotean.com/</url></story><parent_chain></parent_chain><comment><author>Amadou</author><text>Combine this with something like BoA&#x27;s ShopSafe &quot;disposable&quot; credit card numbers and POS credit card fraud could be practically eliminated. Consumer privacy would also be increased because it will become much more difficult to cross-reference purchases across different merchants. (You&#x27;ll still have to worry about Visa selling your purchase records, but one step at a time.)<p><a href="https://www.bankofamerica.com/privacy/accounts-cards/shopsafe.go" rel="nofollow">https:&#x2F;&#x2F;www.bankofamerica.com&#x2F;privacy&#x2F;accounts-cards&#x2F;shopsaf...</a><p><a href="http://www.ecommercebytes.com/cab/abu/y205/m02/abu0137/s02" rel="nofollow">http:&#x2F;&#x2F;www.ecommercebytes.com&#x2F;cab&#x2F;abu&#x2F;y205&#x2F;m02&#x2F;abu0137&#x2F;s02</a></text></comment> |
11,833,188 | 11,832,808 | 1 | 2 | 11,817,758 | train | <story><title>King Tut's dagger blade made from meteorite, study confirms</title><url>http://www.cbc.ca/beta/news/technology/king-tut-dagger-1.3610539</url></story><parent_chain><item><author>theophrastus</author><text>The bronze age in that part of the world was around 3300 to 1200BC. Tutankhamen ruled from 1332 to 1323. From that alone we might suppose why a bit of proper iron was more valuable than gold. (the Hittite secret of iron wasn&#x27;t for another 275 years despite Mika Waltari&#x27;s poignant novel &quot;The Egyptian&quot; which had the Hittites flashing their iron about the court of King Tut)</text></item></parent_chain><comment><author>ptaipale</author><text>&gt;<i>Hittite secret of iron wasn&#x27;t for another 275 years despite Mika Waltari&#x27;s poignant novel &quot;The Egyptian&quot; which had the Hittites flashing their iron about the court of King Tut</i><p>I think several sources are saying that Hittites had some iron artifacts already around 1800 BC and had iron works in 1380 BC?<p>I don&#x27;t recall that scene from the book, but anyway, Waltari wrote it during WW II using just library sources in Helsinki; he never set foot in Egypt. (He said &quot;I have lived in Egypt although I&#x27;ve never been there.&quot;)</text></comment> | <story><title>King Tut's dagger blade made from meteorite, study confirms</title><url>http://www.cbc.ca/beta/news/technology/king-tut-dagger-1.3610539</url></story><parent_chain><item><author>theophrastus</author><text>The bronze age in that part of the world was around 3300 to 1200BC. Tutankhamen ruled from 1332 to 1323. From that alone we might suppose why a bit of proper iron was more valuable than gold. (the Hittite secret of iron wasn&#x27;t for another 275 years despite Mika Waltari&#x27;s poignant novel &quot;The Egyptian&quot; which had the Hittites flashing their iron about the court of King Tut)</text></item></parent_chain><comment><author>matt_wulfeck</author><text>I love reading comments like this. Every time I see a historical scene in a movie I always know there&#x27;s someone out there commenting on the inaccuracies.</text></comment> |
12,800,094 | 12,799,351 | 1 | 3 | 12,796,791 | train | <story><title>Twitter Shareholder Sues CEO and Board Members Over Inflated Share Price</title><url>http://fortune.com/2016/10/26/twitter-shares-lawsuit/</url></story><parent_chain><item><author>serg_chernata</author><text>Is it me or is there an influx of negative news about Twitter as of late?</text></item></parent_chain><comment><author>ghaff</author><text>There&#x27;s certainly plenty to form the basis for a negative story and, once these story cycles get started, they tend to feed on themselves--if only because they pretty much write themselves at that point. That said, failing to find a buyer, no apparent strategy for moving forward... Hard to find a lot of positive things to say however large their user base.</text></comment> | <story><title>Twitter Shareholder Sues CEO and Board Members Over Inflated Share Price</title><url>http://fortune.com/2016/10/26/twitter-shares-lawsuit/</url></story><parent_chain><item><author>serg_chernata</author><text>Is it me or is there an influx of negative news about Twitter as of late?</text></item></parent_chain><comment><author>hood_syntax</author><text>There are a lot of negative things about the current state of Twitter, more people are realizing that. If you&#x27;re implying an astro-turfing campaign I&#x27;d have to say that&#x27;s unlikely.</text></comment> |
19,850,993 | 19,850,657 | 1 | 3 | 19,848,939 | train | <story><title>ProtonMail is dropping support for Internet Explorer 11</title><url>https://protonmail.com/blog/internet-explorer-support/</url></story><parent_chain></parent_chain><comment><author>m_st</author><text>Nice for them!<p>We launched a web application for construction companies in Switzerland a few months ago. And quickly learned the hard way that we have to improve the IE compatibility.
The last 90 days IE11 was used for 36% of all traffic.<p>Too bad the new Edge isn&#x27;t called IE12 and automatically deployed as a replacement through Windows Update :-)</text></comment> | <story><title>ProtonMail is dropping support for Internet Explorer 11</title><url>https://protonmail.com/blog/internet-explorer-support/</url></story><parent_chain></parent_chain><comment><author>dieulot</author><text>Slack dropped it last month: <a href="https:&#x2F;&#x2F;get.slack.help&#x2F;hc&#x2F;en-us&#x2F;articles&#x2F;115002037526-Minimum-requirements-for-using-Slack#-web-browsers" rel="nofollow">https:&#x2F;&#x2F;get.slack.help&#x2F;hc&#x2F;en-us&#x2F;articles&#x2F;115002037526-Minimu...</a></text></comment> |
35,588,051 | 35,588,087 | 1 | 2 | 35,587,186 | train | <story><title>Tabi: The shoe that became a sock and then a shoe again</title><url>https://one-from-nippon.ghost.io/untitled-2/</url></story><parent_chain></parent_chain><comment><author>mongol</author><text>The link about how he aborted the race is well worth reading. From Wikipedia:<p>Kanakuri pulled out midway through the race and was cared for by a local family. Embarrassed from his &quot;failure&quot;, he silently returned to Japan without notifying race officials.<p>Although local newspapers at the time correctly reported that Kanakuri withdrew halfway through the race, the fact that Kanakuri had not officially reported back after doing so gave birth to humorous stories in Sweden about the supposedly lost Japanese runner.<p>In 1967, he was contacted by Swedish Television and offered the opportunity to complete his run. He accepted and completed the marathon, remarking,&quot;Kanaguri of Japan is now in the goal. Time, 54 years and 8 months 6 days 5 hours 32 minutes 20 seconds 3, which will end the entire schedule of the 5th Stockholm Olympic Games,&quot; was announced. He commented &quot;It was a long trip. Along the way, I got married, had six children and 10 grandchildren.&quot;</text></comment> | <story><title>Tabi: The shoe that became a sock and then a shoe again</title><url>https://one-from-nippon.ghost.io/untitled-2/</url></story><parent_chain></parent_chain><comment><author>CannisterFlux</author><text>The part about the cost of a cheap straw shoe vs the longer lasting tabi reminded me of the Sam Vimes Boots Theory from the Pratchett novels. <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Boots_theory" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Boots_theory</a></text></comment> |
22,863,264 | 22,863,178 | 1 | 3 | 22,862,736 | train | <story><title>'Oumuamua could be a shard from a dead planet</title><url>https://www.nationalgeographic.com/science/2020/04/perplexing-interstellar-object-starts-revealing-its-secrets/</url></story><parent_chain><item><author>corysama</author><text>I realize an iPhone 6+ is an old phone. But, this is a simple page with some simple text and simple images that is working so hard to track me that it is completely unreadable even though they really want me to read it.</text></item></parent_chain><comment><author>ErikAugust</author><text>Here you go, 4 MB to 25 KB: <a href="https:&#x2F;&#x2F;beta.trimread.com&#x2F;articles&#x2F;11029" rel="nofollow">https:&#x2F;&#x2F;beta.trimread.com&#x2F;articles&#x2F;11029</a></text></comment> | <story><title>'Oumuamua could be a shard from a dead planet</title><url>https://www.nationalgeographic.com/science/2020/04/perplexing-interstellar-object-starts-revealing-its-secrets/</url></story><parent_chain><item><author>corysama</author><text>I realize an iPhone 6+ is an old phone. But, this is a simple page with some simple text and simple images that is working so hard to track me that it is completely unreadable even though they really want me to read it.</text></item></parent_chain><comment><author>WrtCdEvrydy</author><text>But it needs 100mb worth of javascript!</text></comment> |
22,584,278 | 22,583,777 | 1 | 2 | 22,583,594 | train | <story><title>Evidence that parasite prevalence predicts authoritarianism (2013)</title><url>https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0062275</url></story><parent_chain></parent_chain><comment><author>jonnycomputer</author><text>I do believe that parasitic load probably has significant effects on a variety of psychological variables and preferences. But the web of causation here is extremely complex; neither do I think testing this hypothesis by looking at state-level governance is particularly useful. Instead, you would want to attain individual psychological response measures related to preference or acceptance of authoritarianism, and related that to individual parasitic load within a particular community; even better would to get longitudinal data showing that within-individual changes in parasitic load are correlated with changes in preference (controlled experiments here face ethical hurdles four obvious reasons). Even then, you are going to have to account for factors that may be correlated with the likelihood of getting parasites and having attitudes that are favorable to authoritarianism.</text></comment> | <story><title>Evidence that parasite prevalence predicts authoritarianism (2013)</title><url>https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0062275</url></story><parent_chain></parent_chain><comment><author>medymed</author><text>“Results revealed that parasite prevalence predicted measures of authoritarian governance, and did so even when statistically controlling for other threats to human welfare.”<p>There are so many varied and interacting and nonlinear threats to human welfare that I don’t know if the number of variables to control for (if even identifiable and measurable and appropriately transformed) would allow for meaningful result with only a few hundreds countries as data points.</text></comment> |
3,752,371 | 3,751,724 | 1 | 3 | 3,751,455 | train | <story><title>A Game to Make Games</title><url>http://craftstud.io/</url><text></text></story><parent_chain></parent_chain><comment><author>elisee</author><text>Hi, CraftStudio developer here.<p>Just woke up to a surge of visits &#38; contributions and realized CraftStudio made it to the HN front page. Thanks for the love and criticism, I value it a lot coming from the Hacker News crowd.<p>A bit of technical background for those who might be interested: CraftStudio is built in C# using the XNA framework.<p>I will port it to MacOS X and Linux using Mono + MonoGame (<a href="https://github.com/mono/MonoGame" rel="nofollow">https://github.com/mono/MonoGame</a>), when MonoGame reaches enough 3D support. I already managed to get the UI to run under Linux so I'm pretty confident this will pan out well.<p>The network code uses the most amazing Lidgren.Network library (<a href="http://lidgren-network-gen3.googlecode.com/" rel="nofollow">http://lidgren-network-gen3.googlecode.com/</a>). Honestly I don't know that CraftStudio could have happened without it. It's entirely UDP-based and does such a great job of handling all the low-level bits while providing a great API.<p>The user interface uses a custom built library (which I open sourced under the MIT license over there, documentation is severely lacking for now though: <a href="http://nuclearwinter.codeplex.com/" rel="nofollow">http://nuclearwinter.codeplex.com/</a>).<p>You can also find the Operational Transform library I built for real-time collaborative document editing (MIT too, <a href="https://bitbucket.org/elisee/nuclearot" rel="nofollow">https://bitbucket.org/elisee/nuclearot</a>). It's only used for the text-editing support.<p>If you have any questions, please go ahead and ask :).<p>You can follow me on Twitter there: <a href="https://twitter.com/craftstudiodev" rel="nofollow">https://twitter.com/craftstudiodev</a> if you want to be kept in the loop. I also do livecoding on CraftStudio every once in a while: <a href="http://www.twitch.tv/eliseegw" rel="nofollow">http://www.twitch.tv/eliseegw</a></text></comment> | <story><title>A Game to Make Games</title><url>http://craftstud.io/</url><text></text></story><parent_chain></parent_chain><comment><author>matsim</author><text>Hi, I've got a couple things I wanted to comment on.<p>First, and the most obvious, I want to say that this looks like a very interesting and fun project. I wish you the best.<p>Secondly, and I know I'm pointing out the elephant-in-the-post here, but I think if one is launching a product or revealing a project to a wide group of potential users, it would be best to utilize a speaker that is easy-to-understand. This has been a point of criticism in past HN posts. Obviously, I don't mean to be offensive in anyway and I really don't know the most politically correct way of pointing this out. I just simply could not understand a large chunk of what the speaker in the video was saying because of his strong accent.<p>I think there are some ways around this. For example, you could use a different speaker and if you felt the need to make an appearance or comment in a video as the creator/founder of a project, you could make a couple brief rehearsed/precise comments.<p>Again, very interesting project and I wish you the best.</text></comment> |
39,541,768 | 39,542,036 | 1 | 2 | 39,539,356 | train | <story><title>Man convicted for trying to help undercover game wardens recover deer with drone</title><url>https://www.outdoorlife.com/hunting/pennsylvania-drone-sting-conviction/</url></story><parent_chain><item><author>crdrost</author><text>So this is what the article is talking about, that it&#x27;s not clear about the difference between killing vs recovering, they are both lumped together as hunting.<p>The reasons that you don&#x27;t want people to use spotlights for killing the animal are not too hard to come up with. (Actually kids on college campuses do this for zombies-vs-humans, smart zombies will blind humans at night with spotlights to make it hard for them to fire their nerf guns back at the zombies.)<p>It is considered unsporting&#x2F;unethical for a couple reasons: first because the animals like to feed nocturnally so it&#x27;s easier to find them near people&#x27;s fields, so there&#x27;s no “tracking it through the forest” step; second the animals will often freeze and stare into the light, making them easier to target; third you can&#x27;t see behind the animal to ensure that the shot is safe if you miss; for all you know you might be aimed at a neighbor&#x27;s house in the distance after they&#x27;ve turned out their lights; fourth, getting a spotlight in your windows is a mild nuisance while folks are wandering around near your property; fifth because nighttime hunting is in general discouraged or illegal because that&#x27;s when the poachers would be out and when you can&#x27;t see other humans very well.</text></item><item><author>pavel_lishin</author><text>&gt; <i>Under the “recreational spotlighting” section of Title 34, the Pennsylvania Game and Wildlife Code explicitly prohibits the use of a spotlight “to search for or locate for any purpose any game or wildlife anywhere within this Commonwealth at any time during the antlered deer rifle season and during the antlerless deer rifle season.” It is not immediately clear if this applies to dead or wounded game, since Title 34 does not explicitly address the use of lights or flashlights for recovering game. Another section prohibits hunters from using artificial lights of any kind while carrying a firearm or other weapon, but there is no mention anywhere in the game code of prohibitions against recovering or tracking downed game at night.</i><p>I know nothing about hunting, or the laws surrounding it, but why would it be illegal to recover a dead animal at night using a spotlight?</text></item></parent_chain><comment><author>idiotsecant</author><text>On the other hand, <i>recovering</i> an animal with a light is a good thing, because otherwise you might lose an injured animal that will slowly die over hours, days, or weeks</text></comment> | <story><title>Man convicted for trying to help undercover game wardens recover deer with drone</title><url>https://www.outdoorlife.com/hunting/pennsylvania-drone-sting-conviction/</url></story><parent_chain><item><author>crdrost</author><text>So this is what the article is talking about, that it&#x27;s not clear about the difference between killing vs recovering, they are both lumped together as hunting.<p>The reasons that you don&#x27;t want people to use spotlights for killing the animal are not too hard to come up with. (Actually kids on college campuses do this for zombies-vs-humans, smart zombies will blind humans at night with spotlights to make it hard for them to fire their nerf guns back at the zombies.)<p>It is considered unsporting&#x2F;unethical for a couple reasons: first because the animals like to feed nocturnally so it&#x27;s easier to find them near people&#x27;s fields, so there&#x27;s no “tracking it through the forest” step; second the animals will often freeze and stare into the light, making them easier to target; third you can&#x27;t see behind the animal to ensure that the shot is safe if you miss; for all you know you might be aimed at a neighbor&#x27;s house in the distance after they&#x27;ve turned out their lights; fourth, getting a spotlight in your windows is a mild nuisance while folks are wandering around near your property; fifth because nighttime hunting is in general discouraged or illegal because that&#x27;s when the poachers would be out and when you can&#x27;t see other humans very well.</text></item><item><author>pavel_lishin</author><text>&gt; <i>Under the “recreational spotlighting” section of Title 34, the Pennsylvania Game and Wildlife Code explicitly prohibits the use of a spotlight “to search for or locate for any purpose any game or wildlife anywhere within this Commonwealth at any time during the antlered deer rifle season and during the antlerless deer rifle season.” It is not immediately clear if this applies to dead or wounded game, since Title 34 does not explicitly address the use of lights or flashlights for recovering game. Another section prohibits hunters from using artificial lights of any kind while carrying a firearm or other weapon, but there is no mention anywhere in the game code of prohibitions against recovering or tracking downed game at night.</i><p>I know nothing about hunting, or the laws surrounding it, but why would it be illegal to recover a dead animal at night using a spotlight?</text></item></parent_chain><comment><author>bbarnett</author><text>Back in the day, in my rural county, people would drive with a spotlight, find a large deer, and run it over.<p>Result? Food for months and months for the family, and the insurance company produced a replacement car. And yes, people would do this when their car was in poor shape, eg transmission going or some such. Car rusting out, etc.<p>They eventually changed the laws so that deer were no longer given to people in car accidents, for obvious reasons. I imagine the light law mentioned here, is due to this too.</text></comment> |
14,079,970 | 14,079,496 | 1 | 2 | 14,075,720 | train | <story><title>Semantic UI</title><url>https://semantic-ui.com/</url></story><parent_chain><item><author>yoran</author><text>I disagree. I find that SASS mixins provide the same reusability as classes but in a much cleaner way. True, it makes your HTML and CSS very coupled, but it does provide you with a true clean separation of content and presentation.<p>I find<p><pre><code> &#x2F;&#x2F; style.scss
@mixin button($color, $size) { ... }
.download-book {
@include button(
$color: red,
$size: big
);
}
.send-email {
@include button(
$color: blue,
$size: small
);
}
&#x2F;&#x2F; index.html
&lt;button class=&quot;download-book&quot;&gt;Download book&lt;&#x2F;button&gt;
&lt;button class=&quot;send-email&quot;&gt;Send email&lt;&#x2F;button&gt;
</code></pre>
much cleaner than<p><pre><code> &#x2F;&#x2F; style.scss
.button { ... }
.red { ... }
.blue { ... }
.big { ... }
.small { ... }
&#x2F;&#x2F; index.html
&lt;button class=&quot;button big red&quot;&gt;Download book&lt;&#x2F;button&gt;
&lt;button class=&quot;button small blue&quot;&gt;Send email&lt;&#x2F;button&gt;
</code></pre>
1. When you change the visual aspect of an element, you go to the stylesheet and don&#x27;t go adding&#x2F;removing classes from the content layer (HTML).<p>2. When using generic names like &quot;button&quot;, &quot;big&quot;, &quot;small&quot;, etc... I always find myself in a naming conflict at some point. The likelihood of semantic names having conflicts is much smaller.<p>Of course, your CSS file becomes a lot bigger. But when enabling compression, the stylesheets using mixins turn out to be smaller (see <a href="https:&#x2F;&#x2F;tech.bellycard.com&#x2F;blog&#x2F;sass-mixins-vs-extends-the-data&#x2F;" rel="nofollow">https:&#x2F;&#x2F;tech.bellycard.com&#x2F;blog&#x2F;sass-mixins-vs-extends-the-d...</a>). Also, your HTML file is likely smaller too when using semantic classes.</text></item><item><author>adamwathan</author><text>I used to think this way until reading this article by Nicolas Gallagher:<p><a href="http:&#x2F;&#x2F;nicolasgallagher.com&#x2F;about-html-semantics-front-end-architecture&#x2F;" rel="nofollow">http:&#x2F;&#x2F;nicolasgallagher.com&#x2F;about-html-semantics-front-end-a...</a><p>These days I&#x27;m quite convinced trying to author your markup such that you can redesign a site by applying a different stylesheet has the dependencies backwards.<p>If you try to keep visual information out of your HTML, you end up authoring stylesheets designed to nimbly navigate your DOM structure to precisely target elements to style in a way that makes your CSS <i>extremely</i> coupled to the particular site you are building.<p>Your HTML documents are already coupled to your project, so rather than writing CSS that&#x27;s coupled to that HTML, I&#x27;ve found it to work much better to author CSS from a mindset that the CSS knows <i>nothing</i> about the document it&#x27;s trying to style.<p>This leads to writing what I call &quot;library-style&quot; CSS, where you are almost trying to build your own Bootstrap or similar; something that you could actually use on multiple projects if you wanted.<p>A class like &quot;download-book&quot; is not very useful if you have multiple buttons in a project that are meant to look the same way and not all of them trigger a book download.</text></item><item><author>jameslk</author><text>I&#x27;ve always found it ironic that this library calls itself &quot;Semantic UI&quot; but doesn&#x27;t follow the practice of semantic HTML&#x2F;classes[0]. W3C suggests[1] that classes should be used for semantic roles (e.g. &quot;warning&quot;, &quot;news&quot;, &quot;footer&quot;), rather than for display (&quot;left&quot;, &quot;angle&quot;, &quot;small&quot; -- examples taken from Semantic UI&#x27;s docs). So instead of giving a button the class of &quot;button&quot; it would be better to give it a class such as &quot;download-book.&quot; The benefit of this is when it comes time to redesign parts of a site, you only have to touch your stylesheets instead of manipulating both the stylesheets and HTML. That is, so we don&#x27;t fall into the old habits of what amounts to using &lt;b&gt; &lt;font&gt; &lt;blink&gt; tags.<p>0. <a href="https:&#x2F;&#x2F;css-tricks.com&#x2F;semantic-class-names&#x2F;" rel="nofollow">https:&#x2F;&#x2F;css-tricks.com&#x2F;semantic-class-names&#x2F;</a><p>1. <a href="https:&#x2F;&#x2F;www.w3.org&#x2F;QA&#x2F;Tips&#x2F;goodclassnames" rel="nofollow">https:&#x2F;&#x2F;www.w3.org&#x2F;QA&#x2F;Tips&#x2F;goodclassnames</a></text></item></parent_chain><comment><author>sklivvz1971</author><text>A class called &quot;download-book&quot; wouldn&#x27;t be semantic either.<p>A semantic choice of classes should represent the <i>roles</i> that things have in the UI hierarchy: if a &quot;book download&quot; button is the main action of the page, it should have a class of, say &quot;main-action&quot;, possibly with an extra &quot;download&quot; class to show UI specific to download actions.<p>If a &quot;book download&quot; button is just an action, for example a button that is repeated multiple times in a table, then it needs a different class, like &quot;action&quot;, still possibly with &quot;download&quot;.<p>This is exactly like properly written HTML is semantic, elements represent hierarchical roles (&quot;nav&quot;, &quot;footer&quot;), not their look, nor their content.</text></comment> | <story><title>Semantic UI</title><url>https://semantic-ui.com/</url></story><parent_chain><item><author>yoran</author><text>I disagree. I find that SASS mixins provide the same reusability as classes but in a much cleaner way. True, it makes your HTML and CSS very coupled, but it does provide you with a true clean separation of content and presentation.<p>I find<p><pre><code> &#x2F;&#x2F; style.scss
@mixin button($color, $size) { ... }
.download-book {
@include button(
$color: red,
$size: big
);
}
.send-email {
@include button(
$color: blue,
$size: small
);
}
&#x2F;&#x2F; index.html
&lt;button class=&quot;download-book&quot;&gt;Download book&lt;&#x2F;button&gt;
&lt;button class=&quot;send-email&quot;&gt;Send email&lt;&#x2F;button&gt;
</code></pre>
much cleaner than<p><pre><code> &#x2F;&#x2F; style.scss
.button { ... }
.red { ... }
.blue { ... }
.big { ... }
.small { ... }
&#x2F;&#x2F; index.html
&lt;button class=&quot;button big red&quot;&gt;Download book&lt;&#x2F;button&gt;
&lt;button class=&quot;button small blue&quot;&gt;Send email&lt;&#x2F;button&gt;
</code></pre>
1. When you change the visual aspect of an element, you go to the stylesheet and don&#x27;t go adding&#x2F;removing classes from the content layer (HTML).<p>2. When using generic names like &quot;button&quot;, &quot;big&quot;, &quot;small&quot;, etc... I always find myself in a naming conflict at some point. The likelihood of semantic names having conflicts is much smaller.<p>Of course, your CSS file becomes a lot bigger. But when enabling compression, the stylesheets using mixins turn out to be smaller (see <a href="https:&#x2F;&#x2F;tech.bellycard.com&#x2F;blog&#x2F;sass-mixins-vs-extends-the-data&#x2F;" rel="nofollow">https:&#x2F;&#x2F;tech.bellycard.com&#x2F;blog&#x2F;sass-mixins-vs-extends-the-d...</a>). Also, your HTML file is likely smaller too when using semantic classes.</text></item><item><author>adamwathan</author><text>I used to think this way until reading this article by Nicolas Gallagher:<p><a href="http:&#x2F;&#x2F;nicolasgallagher.com&#x2F;about-html-semantics-front-end-architecture&#x2F;" rel="nofollow">http:&#x2F;&#x2F;nicolasgallagher.com&#x2F;about-html-semantics-front-end-a...</a><p>These days I&#x27;m quite convinced trying to author your markup such that you can redesign a site by applying a different stylesheet has the dependencies backwards.<p>If you try to keep visual information out of your HTML, you end up authoring stylesheets designed to nimbly navigate your DOM structure to precisely target elements to style in a way that makes your CSS <i>extremely</i> coupled to the particular site you are building.<p>Your HTML documents are already coupled to your project, so rather than writing CSS that&#x27;s coupled to that HTML, I&#x27;ve found it to work much better to author CSS from a mindset that the CSS knows <i>nothing</i> about the document it&#x27;s trying to style.<p>This leads to writing what I call &quot;library-style&quot; CSS, where you are almost trying to build your own Bootstrap or similar; something that you could actually use on multiple projects if you wanted.<p>A class like &quot;download-book&quot; is not very useful if you have multiple buttons in a project that are meant to look the same way and not all of them trigger a book download.</text></item><item><author>jameslk</author><text>I&#x27;ve always found it ironic that this library calls itself &quot;Semantic UI&quot; but doesn&#x27;t follow the practice of semantic HTML&#x2F;classes[0]. W3C suggests[1] that classes should be used for semantic roles (e.g. &quot;warning&quot;, &quot;news&quot;, &quot;footer&quot;), rather than for display (&quot;left&quot;, &quot;angle&quot;, &quot;small&quot; -- examples taken from Semantic UI&#x27;s docs). So instead of giving a button the class of &quot;button&quot; it would be better to give it a class such as &quot;download-book.&quot; The benefit of this is when it comes time to redesign parts of a site, you only have to touch your stylesheets instead of manipulating both the stylesheets and HTML. That is, so we don&#x27;t fall into the old habits of what amounts to using &lt;b&gt; &lt;font&gt; &lt;blink&gt; tags.<p>0. <a href="https:&#x2F;&#x2F;css-tricks.com&#x2F;semantic-class-names&#x2F;" rel="nofollow">https:&#x2F;&#x2F;css-tricks.com&#x2F;semantic-class-names&#x2F;</a><p>1. <a href="https:&#x2F;&#x2F;www.w3.org&#x2F;QA&#x2F;Tips&#x2F;goodclassnames" rel="nofollow">https:&#x2F;&#x2F;www.w3.org&#x2F;QA&#x2F;Tips&#x2F;goodclassnames</a></text></item></parent_chain><comment><author>always_good</author><text>I find tha the library-style &quot;button&quot; &quot;red&quot; &quot;blue&quot; &quot;big&quot; example prevents me from having to flip over and maintain CSS with every HTML change.<p>Yet your first example has everyone editing CSS files and appending new classes to it all the time, which in my experience is the fastest way to end up with unmaintainable CSS.<p>Mixins sounded good to me at first, but I&#x27;ve only experienced less maintainability when the CSS was too clever.</text></comment> |
13,468,335 | 13,466,379 | 1 | 3 | 13,461,100 | train | <story><title>Show HN: Develop your Python applications easily in clean Docker environments</title><url>https://github.com/macostea/cage</url></story><parent_chain><item><author>wtvanhest</author><text>Slightly off-topic, but does anyone develop Django&#x2F;Python on a windows machine, and may want to offer any general advice or tips?<p>I am using virtualenv, but wondering what else I should be doing to make it easier. Previously I used cloud9 (cloud IDE) for rails development. In both cases, I am pretty much a hobbiest, but don&#x27;t mind spending some money to make things easier since I&#x27;d rather spend my time doing the fun part, rather than developer ops.</text></item></parent_chain><comment><author>goodoldboys</author><text>I just switched from Mac to Windows 10, and I work on a lot of Django projects.<p>I use PyCharm (love jetbrains) + Vagrant and it&#x27;s working great so far. I&#x27;d highly recommend spending the time learning Vagrant - it can be incredibly frustrating at times (on both mac and windows), but once you get it working right it&#x27;s really rewarding. Being able to re-instantiate a VM when something gets really botched is a great feeling. I don&#x27;t have to worry about my host machine getting messed up, so I&#x27;m free to tinker around in the VM and that speeds up my learning.<p>The one downside I&#x27;ve encountered so far is how many different &quot;terminal&quot; style apps I need to run to get everything working. Currently I need powershell (as admin) for spinning up the VM, putty to SSH into it, and git bash for source control. I can probably simplify them all into powershell but for now it works.</text></comment> | <story><title>Show HN: Develop your Python applications easily in clean Docker environments</title><url>https://github.com/macostea/cage</url></story><parent_chain><item><author>wtvanhest</author><text>Slightly off-topic, but does anyone develop Django&#x2F;Python on a windows machine, and may want to offer any general advice or tips?<p>I am using virtualenv, but wondering what else I should be doing to make it easier. Previously I used cloud9 (cloud IDE) for rails development. In both cases, I am pretty much a hobbiest, but don&#x27;t mind spending some money to make things easier since I&#x27;d rather spend my time doing the fun part, rather than developer ops.</text></item></parent_chain><comment><author>nkantar</author><text>My two second-hand cents:<p>At my previous company we used Vagrant for most projects, and it provided a nice abstraction layer that made things work reasonably well across all platforms (macOS, Windows, and Linux). Vagrant on Windows definitely had its challenges, though, but projects themselves ran well once that was sorted out.<p>I&#x27;ve heard the company has since moved to Docker, in search of those same benefits but with smaller overhead (specifically in terms of time spent managing the abstraction layer), and I gather the Windows folks are happier with it than they ever were with Vagrant.<p>My own (macOS-only) experience with both has been mixed, but certainly not worse than just running things locally via virtualenv. Vagrant introduces a full VM into the stack and Docker seems to have a lot of stability issues (at least on macOS 10.12 Sierra), so my next plan is to try combining the two, and running Docker on a Fedora VM. I&#x27;m hoping that any Docker nightmares will then at least be confined to the guest system, leaving my main machine mostly out of it, and using Docker to set up the actual project stuff may mean less Linux administration of the VM itself.</text></comment> |
14,715,378 | 14,715,363 | 1 | 3 | 14,714,668 | train | <story><title>Jawbone is being liquidated as its CEO launches a related health startup</title><url>https://techcrunch.com/2017/07/06/jawbone-is-being-liquidated-as-its-ceo-launches-a-related-health-startup</url></story><parent_chain><item><author>BinaryIdiot</author><text>&gt; The days of consumer hardware company&#x27;s access to startup capital is over.<p>So I haven&#x27;t worked at a hardware start-up but it seemed pretty difficult even before these companies to raise funding versus a pure software play. I&#x27;m not necessarily convinced this makes it easier or harder. Is there a specific reason you think it will be harder now?<p>Also, for what it&#x27;s worth, Fitbit and GoPro are still going. I&#x27;m convinced Fitbit can get back on the growth curve as long as they can get a new product out the door that consumers want. Tall order for sure but I don&#x27;t count them as a failure yet.<p>GoPro want to move to doing software more so than hardware. Considering their software has always considered to be lackluster to borderline terrible I&#x27;m less convinced they will turn it around but also not yet willing to say they&#x27;re a failure.</text></item><item><author>stingrae</author><text>The days of consumer hardware company&#x27;s access to startup capital is over. With so many high profile VC backed (Fitbit, GoPro, Hello, Juicero, Coin, Pearl, ect.) and kickstarted (Lily.ai, Pebble) failures, no one is willing to risk it.</text></item></parent_chain><comment><author>EpicEng</author><text>I worked at a VC funded hardware start up for the first eight years of my career. You&#x27;ll never read about it here though; we made digital pathology scanners. When I left we had sold the company for ~300M and were bringing in about ~30M &#x2F; year in revenue.<p>I guess my point is that there is more going on in the VC space then you&#x27;ll read about on HN.</text></comment> | <story><title>Jawbone is being liquidated as its CEO launches a related health startup</title><url>https://techcrunch.com/2017/07/06/jawbone-is-being-liquidated-as-its-ceo-launches-a-related-health-startup</url></story><parent_chain><item><author>BinaryIdiot</author><text>&gt; The days of consumer hardware company&#x27;s access to startup capital is over.<p>So I haven&#x27;t worked at a hardware start-up but it seemed pretty difficult even before these companies to raise funding versus a pure software play. I&#x27;m not necessarily convinced this makes it easier or harder. Is there a specific reason you think it will be harder now?<p>Also, for what it&#x27;s worth, Fitbit and GoPro are still going. I&#x27;m convinced Fitbit can get back on the growth curve as long as they can get a new product out the door that consumers want. Tall order for sure but I don&#x27;t count them as a failure yet.<p>GoPro want to move to doing software more so than hardware. Considering their software has always considered to be lackluster to borderline terrible I&#x27;m less convinced they will turn it around but also not yet willing to say they&#x27;re a failure.</text></item><item><author>stingrae</author><text>The days of consumer hardware company&#x27;s access to startup capital is over. With so many high profile VC backed (Fitbit, GoPro, Hello, Juicero, Coin, Pearl, ect.) and kickstarted (Lily.ai, Pebble) failures, no one is willing to risk it.</text></item></parent_chain><comment><author>spiralpolitik</author><text>Fitbit lost me when they refused to support HealthKit. As it stands I&#x27;m not sure they can escape their demise as the market transitions from limited function devices to multi function devices like the Apple Watch. They strike me as getting rolled over the same way Diamond, Archos, and Creative got crushed by the iPod.<p>GoPro has a similar problem. Outside of special circumstances most smartphone cameras are now good enough for most consumer needs and will only get better. I think they could survive if they target the extreme sports type niche but otherwise I don&#x27;t see them achieving escape velocity.<p>Both could be good acquisition targets a la Withings and Nokia. But the number of possible buyers is limited. Microsoft is possibly the only one that comes to mind that doesn&#x27;t have anything in either space although given the failure of Windows Phone I&#x27;m not sure they have the desire to try something similar in a different market.</text></comment> |
20,468,707 | 20,468,790 | 1 | 2 | 20,466,545 | train | <story><title>Facebook are frantically trying to find out who leaked thousands of documents</title><url>https://reclaimthenet.org/facebook-documents-leak-courts/</url></story><parent_chain></parent_chain><comment><author>spinningslate</author><text>It’s difficult not to see the potential for divine retribution in this. Facebook, alongside Google, spearhead the “privacy is dead consumers, all your data are mine” assertion.<p>But someone dares to share <i>FB’s data</i>? Release the wolves.<p>Until&#x2F;unless the actual docs emerge, we can only surmise that there’s a few ‘interesting’ gems in there - hence FB’s attentiveness to preventing dissemination.<p>I hope they are published irrespective of content. If we as individuals have no say in Facebook’s surveillance of us, there’s a modicum of comfort in knowing we can surveil it.<p>Reap as you sow Mr Zuckerberg.<p>—-
EDIT: fixed grammar.</text></comment> | <story><title>Facebook are frantically trying to find out who leaked thousands of documents</title><url>https://reclaimthenet.org/facebook-documents-leak-courts/</url></story><parent_chain></parent_chain><comment><author>Mark222</author><text>Is reclaimthenet.org a real news website? None of the writers looks real and I can&#x27;t find any information on the website on who edits it and fund it. Some articles reek of bias</text></comment> |
21,366,874 | 21,366,241 | 1 | 3 | 21,361,845 | train | <story><title>Patents are about sharing information – don't shroud them in secrecy</title><url>https://www.eff.org/deeplinks/2019/10/patents-are-about-sharing-information-public-dont-shroud-them-secrecy</url></story><parent_chain><item><author>mschuetz</author><text>I do research in computer science and in the last few years, lots of trivial and dumb patents in my field appeared out of nowhere. However, I can only assume that they really are trivial because they are written in a way to claim a lot without actually describing how any of it works. These patents have 0% information in them. What&#x27;s more, they all read like a rewrite of papers that were published years ago (before the date filed) into lawyer speak with no amount of information. I have no idea how any of these were ever granted since there is prior art all over the place.<p>Edit: Okay to be fair, there is maybe not 0% but 10% information in these patents, but it&#x27;s encoded into unintelligible lawyer&#x2F;patent talk that is not at all fit to convey technical information. They are written in a way to get a monoply on results without disclosing how these results are obtained.</text></item></parent_chain><comment><author>ImprovedSilence</author><text>The patents are written with the most broad and generic claims as possible first. Then the claims are re stated like 3 or 4 times, that would seem identical, but each re statement of them adds like one or two words of detail or specifics each time down. (So maybe claim 2 won’t stand up in court, but claim 23, a derivative of 2, will, the idea that you sue for infringement of as much as possible) I’ve submitted a patent before, and hardly Understood my own patent by the time the lawyer was done with it. But after really paying attention, I guess all the technical details are there. I think larger companies that aren’t specifically patent trolls patent as much as possible just for their own defense too.</text></comment> | <story><title>Patents are about sharing information – don't shroud them in secrecy</title><url>https://www.eff.org/deeplinks/2019/10/patents-are-about-sharing-information-public-dont-shroud-them-secrecy</url></story><parent_chain><item><author>mschuetz</author><text>I do research in computer science and in the last few years, lots of trivial and dumb patents in my field appeared out of nowhere. However, I can only assume that they really are trivial because they are written in a way to claim a lot without actually describing how any of it works. These patents have 0% information in them. What&#x27;s more, they all read like a rewrite of papers that were published years ago (before the date filed) into lawyer speak with no amount of information. I have no idea how any of these were ever granted since there is prior art all over the place.<p>Edit: Okay to be fair, there is maybe not 0% but 10% information in these patents, but it&#x27;s encoded into unintelligible lawyer&#x2F;patent talk that is not at all fit to convey technical information. They are written in a way to get a monoply on results without disclosing how these results are obtained.</text></item></parent_chain><comment><author>kurthr</author><text>If the specification is not enabling and novel to one skilled in the art (much less obvious), then it is not valid. Under rexam or court proceedings they will be worth the paper they&#x27;re printed on. That&#x27;s an expensive way to determine things, but it sounds like that particular section of art at the patent office isn&#x27;t doing much. On the other hand they only have to hide one novel idea and unique claim in the list to have a right to enforce.<p>I do think the EFF&#x27;s concern about claims and documentation already debunked&#x2F;invalid being hidden behind seal is pretty serious and I think judges approving it are doing the public no service.</text></comment> |
9,114,199 | 9,113,796 | 1 | 2 | 9,113,581 | train | <story><title>Google now automatically converts Flash ads to HTML5</title><url>http://venturebeat.com/2015/02/25/google-now-automatically-converts-flash-ads-to-html5/</url></story><parent_chain><item><author>akersten</author><text>Shame that I automatically convert all ads to nonexistance.<p>It&#x27;s too little, too late for rich media&#x2F;content-heavy ads. Especially in the mobile sector:<p>* Ads are a performance burden on low-power devices<p>* They consume extra battery; power is wasted on superfluous cruft<p>* Bandwidth wasted; especially a concern given draconian data caps<p>* Tracking and privacy concerns<p>Not to mention the fact that ads are a primary attack vector (think of all the advertising CDNs that have been compromised and used to deliver malware). The real improvement here is moving away from a proprietary plugin.<p>Pointing out the problems of rich media ads isn&#x27;t very useful here though, since most of us are probably aware already. My proposal would be simple, inline text, along the lines of &quot;this page load sponsored by _&quot;. Doubt that will gain traction, though.</text></item></parent_chain><comment><author>s_q_b</author><text>Like you, I don&#x27;t mind ads per se. I even feel badly blocking them, knowing that I&#x27;m depriving a content creator of revenue. But the issues you point out are the very reason I can&#x27;t have them in my browser.<p>I used a computer without AdBlock the other day, and it was like stepping back into 1999 with every page saturated with the 21st century equivalent of animated GIFs and auto-play MIDIs.<p>An alternative ad network isn&#x27;t as far fetched as it might seem. Clearly delineated simple ads were a key differentiator in early iterations of Google Search.<p>Perhaps what we need is a &quot;ethical ads&quot; network, with strict requirements on what could and could not be done:<p>1. Plain text and link only, with clear separation of content and advertising.<p>2. No user tracking (Maybe with explicit opt-in? And even then with as-good-as-possible anonymization of the stored data.)<p>3. A deal with AdBlock and competitors to share a cut of the revenue, in exchange for allowing Ethical Ads through.<p>If advertisers and ad networks keep following the current trajectory, there will come a day when ads are simply too intrusive, and ad blocking will go (even more) completely mainstream.<p>Rich media doesn&#x27;t do advertisers any good if no one ever sees their ads.</text></comment> | <story><title>Google now automatically converts Flash ads to HTML5</title><url>http://venturebeat.com/2015/02/25/google-now-automatically-converts-flash-ads-to-html5/</url></story><parent_chain><item><author>akersten</author><text>Shame that I automatically convert all ads to nonexistance.<p>It&#x27;s too little, too late for rich media&#x2F;content-heavy ads. Especially in the mobile sector:<p>* Ads are a performance burden on low-power devices<p>* They consume extra battery; power is wasted on superfluous cruft<p>* Bandwidth wasted; especially a concern given draconian data caps<p>* Tracking and privacy concerns<p>Not to mention the fact that ads are a primary attack vector (think of all the advertising CDNs that have been compromised and used to deliver malware). The real improvement here is moving away from a proprietary plugin.<p>Pointing out the problems of rich media ads isn&#x27;t very useful here though, since most of us are probably aware already. My proposal would be simple, inline text, along the lines of &quot;this page load sponsored by _&quot;. Doubt that will gain traction, though.</text></item></parent_chain><comment><author>drzaiusapelord</author><text>&gt;They consume extra battery;<p>I find it fascinating that Google is always hurting their own mobile experience. Between all the issues android has with wake locks and memory leaks and the massive infrastructure of location and &#x27;lifestyle&#x27; tracking for ad delivery, its a miracle Android devices get any battery life at all. Even without this html5 conversion, Android battery life often pales compared to iOS or Windows Phone.<p>The more I think about it, an OS from whats essentially an ad delivery company is probably a liability. Monetization will trump user experience. Get ready for some pretty invasive html5 ads.</text></comment> |
19,299,072 | 19,297,793 | 1 | 2 | 19,296,438 | train | <story><title>Sensible Software Engineering</title><url>https://www.scriptcrafty.com/2019/02/sensible-software-engineering/</url></story><parent_chain><item><author>wildmanx</author><text>&gt; Bugs are correlated with lines of code and TDD forces writing more code so how can it reduce bug counts? If the test code has no bugs then just write the rest of the code in the same style<p>Nobody has pointed out the fault in this reasoning yet, so I will.<p>The linear relationship lines-of-code vs. total-bug-count is based on independence of bug introduction in different parts of the code. That is, introducing a bug in line 10000 is more-or-less independent of adding line 20000. For product code that is arguably the case, but adding test code into the mix, this basic assumption doesn&#x27;t just not hold, but it&#x27;s turned upside down.<p>Test code is not customer-visible, but only dev-visible, with the sole purpose of finding bugs. Thus, adding test code to a code base <i>decreases</i> the average probability of a bug for lines of product code. More formally, if you have N lines of product code and thus c * N bugs for some fraction c, then adding M lines of test code does <i>not</i> increase the number of customer-visible bugs to c * (N + M). Instead, it reduces that number to c&#x27; * N with c&#x27;&lt;c and the difference being caused by your test coverage. (A 100% test coverage, i.e., an exhaustive test without bugs or, equivalently, a formal verification, would bring c&#x27; to 0.) Sure, the M lines of test code may well have bugs on their own, but that only increases c&#x27; slightly while keeping it below c, and more importantly, those test bugs are not customer-visible. They only annoy developers.<p>I agree with the rest of the post though.</text></item></parent_chain><comment><author>ericathegreat</author><text>Agree. Consider the situation of data entry professionals, those people who transcribe audio recordings or enter data into databases.<p>If you have one person entering data into a computer, then the odds of them introducing an error and failing to spot it are fairly high.<p>If you have twice as many people entering twice as much data data, then the odds of an error getting introduced are roughly doubled.<p>However, if you have those two people entering <i>the same</i> data, then their mistakes cancel each other out. If person A and person B both entered the same thing, it&#x27;s extremely unlikely that it&#x27;s incorrect. If they differ though, the a problem has been identified, and can now be fixed.<p>The odds of both of those people entering the same piece of data incorrectly is tiny. Likewise, <i>accidentally</i> introducing a bug into both the production code <i>and</i> the test is pretty unlikely.<p>That said though, if those two theoretical data entry people above are given the wrong data to enter, then they the system cannot protect them. They will both correctly enter incorrect data. &quot;Garbage in, garbage out&quot;.<p>Likewise, if the requirements of a piece of software are poorly understood, then it is quite likely that both the test and the production code will implement the same &quot;bug&quot;. Writing tests won&#x27;t fix a failure to understand the problem you&#x27;re trying to solve. And they&#x27;re not supposed to.</text></comment> | <story><title>Sensible Software Engineering</title><url>https://www.scriptcrafty.com/2019/02/sensible-software-engineering/</url></story><parent_chain><item><author>wildmanx</author><text>&gt; Bugs are correlated with lines of code and TDD forces writing more code so how can it reduce bug counts? If the test code has no bugs then just write the rest of the code in the same style<p>Nobody has pointed out the fault in this reasoning yet, so I will.<p>The linear relationship lines-of-code vs. total-bug-count is based on independence of bug introduction in different parts of the code. That is, introducing a bug in line 10000 is more-or-less independent of adding line 20000. For product code that is arguably the case, but adding test code into the mix, this basic assumption doesn&#x27;t just not hold, but it&#x27;s turned upside down.<p>Test code is not customer-visible, but only dev-visible, with the sole purpose of finding bugs. Thus, adding test code to a code base <i>decreases</i> the average probability of a bug for lines of product code. More formally, if you have N lines of product code and thus c * N bugs for some fraction c, then adding M lines of test code does <i>not</i> increase the number of customer-visible bugs to c * (N + M). Instead, it reduces that number to c&#x27; * N with c&#x27;&lt;c and the difference being caused by your test coverage. (A 100% test coverage, i.e., an exhaustive test without bugs or, equivalently, a formal verification, would bring c&#x27; to 0.) Sure, the M lines of test code may well have bugs on their own, but that only increases c&#x27; slightly while keeping it below c, and more importantly, those test bugs are not customer-visible. They only annoy developers.<p>I agree with the rest of the post though.</text></item></parent_chain><comment><author>sombremesa</author><text>Tests don&#x27;t exist for solving bugs as much as they exist to prevent regression. Writing exhaustive tests is not sufficient to bring c&#x27; to zero, because some of those bugs exist because of the developer&#x27;s own presumptions about how code should behave.</text></comment> |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.