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
|
|---|---|---|---|---|---|---|---|
19,108,080 | 19,107,737 | 1 | 3 | 19,106,998 | train | <story><title>Saying Goodbye to Louisville</title><url>https://fiber.googleblog.com/2019/02/louisville_7.html</url></story><parent_chain><item><author>maxxxxx</author><text>&quot;For that, and many other reasons, we are deeply grateful to Mayor Greg Fischer, the City of Louisville and its residents for their partnership and spirit of innovation over the past two years.&quot;<p>That&#x27;s why we can&#x27;t trust Google with anything critical. They view the world as an experiment they can quit anytime. Definitely don&#x27;t buy a Google self driving car or anything else you expect to work in a few years.<p>There is a good chance that businesses moved to Louisville because of Google Fiber and they are being shown the finger &quot;Thanks for indulging us, we got what we wanted and you can go f... yourself&quot;.</text></item></parent_chain><comment><author>WaltPurvis</author><text>&gt;&gt; <i>There is a good chance that businesses moved to Louisville because of Google Fiber</i><p>It would be astonishing if the total number of businesses for which that&#x27;s true is more than two. I can&#x27;t imagine what sort of company would base a decision to move to Louisville on the availability of a Google Fiber Internet connection, nor can I imagine how the loss of Google Fiber would be any kind of serious problem (there <i>are</i> other ways to connect to the Internet in Louisville).</text></comment> | <story><title>Saying Goodbye to Louisville</title><url>https://fiber.googleblog.com/2019/02/louisville_7.html</url></story><parent_chain><item><author>maxxxxx</author><text>&quot;For that, and many other reasons, we are deeply grateful to Mayor Greg Fischer, the City of Louisville and its residents for their partnership and spirit of innovation over the past two years.&quot;<p>That&#x27;s why we can&#x27;t trust Google with anything critical. They view the world as an experiment they can quit anytime. Definitely don&#x27;t buy a Google self driving car or anything else you expect to work in a few years.<p>There is a good chance that businesses moved to Louisville because of Google Fiber and they are being shown the finger &quot;Thanks for indulging us, we got what we wanted and you can go f... yourself&quot;.</text></item></parent_chain><comment><author>dopamean</author><text>I&#x27;m not sure I can cosign the cynicism toward google in the particular instance. I am a Fiber customer in Austin and I&#x27;ve always been under the impression that this essentially an experiment and that it likely wont be around forever. Perhaps that is not a widely held enough believe however.</text></comment> |
33,737,152 | 33,736,831 | 1 | 3 | 33,736,003 | train | <story><title>StackStorm: Event-driven automation</title><url>https://github.com/StackStorm/st2</url></story><parent_chain></parent_chain><comment><author>debarshri</author><text>Stackstorm has been around since 2014 [1].<p>Rundeck is another closest competitors that worth mentioning. Things have evolved a lot in the ops space since then.<p>With advent of container orchestration of the operational automation pieces have also moved to the orchestration layer. There have been quite some new tools in the space I have been tracking for instance Fylament [2] which got acquired by netapp, blinkops etc. Post rendezvous with this domain, some bigger problems most of the major framework tools like this have is that, it is very hard to get started. There are lot of pre-requisites given the nature of the ops automation, this leads to a problem where it is very hard to active a customer. Secondly, these frameworks are always competing with it is bash&#x2F;python script deployed with some container orchestration or some cronjobs. I have also seen people write CRDs and reconciliation loops in k8s doing lot of the tasks these automation frameworks would do.<p>[1] <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;StackStorm" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;StackStorm</a><p>[2] <a href="https:&#x2F;&#x2F;www.netapp.com&#x2F;newsroom&#x2F;press-releases&#x2F;news-rel-20220223-487305&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.netapp.com&#x2F;newsroom&#x2F;press-releases&#x2F;news-rel-2022...</a></text></comment> | <story><title>StackStorm: Event-driven automation</title><url>https://github.com/StackStorm/st2</url></story><parent_chain></parent_chain><comment><author>linsomniac</author><text>I played around with StackStorm maybe 5 years ago, but in the end I decided to use RunDeck instead. <a href="https:&#x2F;&#x2F;www.rundeck.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.rundeck.com&#x2F;</a>. Used that for a few years but ended up abandoning it, but am thinking about resurrecting it, it was pretty good.</text></comment> |
24,502,459 | 24,501,955 | 1 | 2 | 24,495,330 | train | <story><title>Nova by Panic</title><url>https://nova.app/</url></story><parent_chain><item><author>ddevault</author><text>&gt;I can&#x27;t imagine the world of hurt, discomfort and frustration of developing against a lib set I can&#x27;t read source code of or improve.<p><i>Thank you</i>.<p>It boggles the mind that anyone who can write code would ever use a closed source operating system.</text></item><item><author>sho_hn</author><text>To me, the quote and what you put after came as a big surprise - I was ready to nod in agreement as you recognize this as a sad story about the platform.<p>The last time I was working on a text editor (KDE&#x27;s Kate) and found a bug in the text layout engine it was written against (Qt&#x27;s), I wrote a patch, submitted it upstream and it made everyone else&#x27;s apps better, too.<p>I can&#x27;t imagine the world of hurt, discomfort and frustration of developing against a lib set I can&#x27;t read source code of or improve.</text></item><item><author>Brendinooo</author><text>&gt; Here&#x27;s a little editor story for fun. During beta we found some bugs in Apple&#x27;s text layout engine that we just could not fix. Our solution? Writing our own text layout manager… from scratch. Not only did this fix the bugs, but it also boosted our editor&#x27;s performance. We&#x27;re not messing around!<p>Seems like there&#x27;s nobody better than Panic at doing this sort of thing. They&#x27;re willing to push Apple&#x27;s UI forward, but they always do it in a way that feels Apple-y. Didn&#x27;t they also pioneer a tab UI that Apple ended up adopting?</text></item></parent_chain><comment><author>mwcampbell</author><text>&gt; It boggles the mind that anyone who can write code would ever use a closed source operating system.<p>Some of us want our work to actually reach people who don&#x27;t write code or sysadmin their own computer, i.e. most people in the world. I, for one, think my effort is wasted if it doesn&#x27;t benefit those people. So while working exclusively on a free-software platform is tempting from an ideological purity point of view (edit: and I envy people like you that manage to make a living doing it), I don&#x27;t think I&#x27;d ever actually do it.<p>Edit: I should be more concrete and less snarky. Working on developer tools is good and necessary, and you can do that effectively on a free-software platform like Linux. But I choose to focus on end-user-facing software, particularly in the field of accessibility. I could work on desktop Linux accessibility, for the vanishingly small number of blind people who use desktop Linux (and that number is shrinking; one of my blind programmer friends just switched to Windows). Or I could target one or more of the mainstream platforms where the users actually are. I suppose I could work exclusively on web applications, but I don&#x27;t think that would be the best use of my skills. And even then, while I could develop primarily on Linux, I&#x27;d have to test on other platforms too.</text></comment> | <story><title>Nova by Panic</title><url>https://nova.app/</url></story><parent_chain><item><author>ddevault</author><text>&gt;I can&#x27;t imagine the world of hurt, discomfort and frustration of developing against a lib set I can&#x27;t read source code of or improve.<p><i>Thank you</i>.<p>It boggles the mind that anyone who can write code would ever use a closed source operating system.</text></item><item><author>sho_hn</author><text>To me, the quote and what you put after came as a big surprise - I was ready to nod in agreement as you recognize this as a sad story about the platform.<p>The last time I was working on a text editor (KDE&#x27;s Kate) and found a bug in the text layout engine it was written against (Qt&#x27;s), I wrote a patch, submitted it upstream and it made everyone else&#x27;s apps better, too.<p>I can&#x27;t imagine the world of hurt, discomfort and frustration of developing against a lib set I can&#x27;t read source code of or improve.</text></item><item><author>Brendinooo</author><text>&gt; Here&#x27;s a little editor story for fun. During beta we found some bugs in Apple&#x27;s text layout engine that we just could not fix. Our solution? Writing our own text layout manager… from scratch. Not only did this fix the bugs, but it also boosted our editor&#x27;s performance. We&#x27;re not messing around!<p>Seems like there&#x27;s nobody better than Panic at doing this sort of thing. They&#x27;re willing to push Apple&#x27;s UI forward, but they always do it in a way that feels Apple-y. Didn&#x27;t they also pioneer a tab UI that Apple ended up adopting?</text></item></parent_chain><comment><author>fsloth</author><text>Oh, the prejudice!<p>I like developing on Windows. Especially since the programs I write are run only on Windows. That&#x27;s what the specific trillion dollar industry my employer serves uses mostly on desktop.<p>I <i>don&#x27;t</i> want to tweak the platform. I want to concentrate on the code I write. I could be equally productive on OS X or Linux, but frankly, <i>I don&#x27;t care</i>. They are all interchangeable computational substrates for me. As long as you can write any program on them, that is...</text></comment> |
10,971,305 | 10,970,313 | 1 | 2 | 10,965,871 | train | <story><title>Zcash, an untraceable Bitcoin alternative, launches in alpha</title><url>http://www.wired.com/2016/01/zcash-an-untraceable-bitcoin-alternative-launches-in-alpha/</url></story><parent_chain><item><author>ctoth</author><text>Of course, once these techniques were in place, they conclusively destroyed the ability of governments to control the flow of electronic funds, anywhere, anytime, for any purpose. As it happened, this process had pretty much destroyed any human control at all over the modern electronic economy. By the time people figured out that raging nonlinear anarchy was not exactly to the advantage of anyone concerned, the process was simply too far gone to stop. All workable standards of wealth had vaporized, digitized, and vanished into a nonstop hurricane of electronic thin air. Even physically tearing up the fiber optics couldn&#x27;t stop it; governments that tried to just found that the whole encryption mess oozed swiftly into voice mail and even fax machines.<p>...<p>Alex did not find it surprising that people like the Chinese Triads and the Corsican Black Hand were electronically minting their own cash. He simply accepted it: electronic, private cash, unbacked by any government, untraceable, completely anonymous, global in reach, lightninglike in speed, ubiquitous, fungible, and usually highly volatile. Of course, such funds didn&#x27;t boldly say &quot;Sicilian Mafia&quot; right on the transaction screen; they usually had some stuffy official-sounding alias such as &quot;Banco Ambrosiano ATM Euro-DigiLira,&quot; but the private currency speculators would usually have a pretty good guess as to the solvency of the issuers.<p>- Heavy Weather</text></item></parent_chain><comment><author>13thLetter</author><text>Just like the rest of the cyberlibertarian blue-skying that went on back in the &#x27;90s, it was a nice dream, seriously! But in reality it turns out that governments can just send some armed men around to beat up the people with the encrypted faxes, email, and digital cash, and that&#x27;ll largely put an end to it. The extent to which a government is helpless to stop that behavior is purely the extent to which it is reluctant to send, or incapable of sending, the armed men.</text></comment> | <story><title>Zcash, an untraceable Bitcoin alternative, launches in alpha</title><url>http://www.wired.com/2016/01/zcash-an-untraceable-bitcoin-alternative-launches-in-alpha/</url></story><parent_chain><item><author>ctoth</author><text>Of course, once these techniques were in place, they conclusively destroyed the ability of governments to control the flow of electronic funds, anywhere, anytime, for any purpose. As it happened, this process had pretty much destroyed any human control at all over the modern electronic economy. By the time people figured out that raging nonlinear anarchy was not exactly to the advantage of anyone concerned, the process was simply too far gone to stop. All workable standards of wealth had vaporized, digitized, and vanished into a nonstop hurricane of electronic thin air. Even physically tearing up the fiber optics couldn&#x27;t stop it; governments that tried to just found that the whole encryption mess oozed swiftly into voice mail and even fax machines.<p>...<p>Alex did not find it surprising that people like the Chinese Triads and the Corsican Black Hand were electronically minting their own cash. He simply accepted it: electronic, private cash, unbacked by any government, untraceable, completely anonymous, global in reach, lightninglike in speed, ubiquitous, fungible, and usually highly volatile. Of course, such funds didn&#x27;t boldly say &quot;Sicilian Mafia&quot; right on the transaction screen; they usually had some stuffy official-sounding alias such as &quot;Banco Ambrosiano ATM Euro-DigiLira,&quot; but the private currency speculators would usually have a pretty good guess as to the solvency of the issuers.<p>- Heavy Weather</text></item></parent_chain><comment><author>natrius</author><text>It turns out that there&#x27;s a pretty easy fix for this. People have to start caring how the money they&#x27;re accepting has flowed through the economy. You don&#x27;t need a government to sanction bad actors. The people can do it on their own.<p>Money is power. Anonymous money prevents you from choosing which power you&#x27;d like to submit to. Decentralized money prevents governments from restricting power. Let&#x27;s keep the decentralization and remove the anonymity so you can reject power you find undesirable.<p>The first application of this mechanism will probably be restoring our democracies by rejecting the power of money to influence them. It won&#x27;t be the last application—I think we&#x27;ll use it to enforce any rule that has a broad consensus behind it. The boundaries of the enforcement will be the same as the boundaries of our economy: there aren&#x27;t any. We&#x27;ll have global governance without a global government.<p>This is merit capitalism. <a href="http:&#x2F;&#x2F;meritcapitalism.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;meritcapitalism.com&#x2F;</a><p>Zcash is cool, but if you accept it as payment, you&#x27;re making yourself powerless.</text></comment> |
6,414,039 | 6,413,887 | 1 | 2 | 6,413,730 | train | <story><title>Pinterest to get ads</title><url>http://blog.pinterest.com/post/61688351103/planning-for-the-future</url></story><parent_chain></parent_chain><comment><author>austenallred</author><text>Pinterest&#x27;s monetization will do great. Seriously, Pinterest could and should IPO in coming years.<p>I&#x27;m bullish on Pinterest not only because my wife and I use Pinterest for everything from planning our wedding to finding outfits and meals, but because I market on Pinterest for a few clients all day long. It consistently brings in more traffic than other sources when you do it right, even for clients that are ranked in the top 5 in high-traffic Google SERPs.<p>The crazy thing about Pinterest traffic is that it never dies off. If you get a bunch of repins today, traffic will be showing up from those pins months later; it&#x27;s kind of absurd, and very unlike Adsense or other discovery advertising platforms in that way.<p>The difficult aspect for Pinterest will be getting the worth of Pinterest ads down to a final cost per action since it is such a long wait before you see how much each pin is truly worth. And that really is the goal for any advertiser: If I know this click will bring me $2 I&#x27;ll pay up to $1.99 for it. A lot of Pinterest users are in hardcore discovery mode, and as such Pinterest traffic doesn&#x27;t convert as well as search traffic immediately, but in the long run it always seems to be worth it.</text></comment> | <story><title>Pinterest to get ads</title><url>http://blog.pinterest.com/post/61688351103/planning-for-the-future</url></story><parent_chain></parent_chain><comment><author>spullara</author><text>I think Pinterest is basically all ads already. Now they will just get money for them.</text></comment> |
30,070,169 | 30,066,131 | 1 | 3 | 30,066,003 | train | <story><title>Image that contains the code that generated it</title><url>https://allrgb.com/recursive</url></story><parent_chain></parent_chain><comment><author>d--b</author><text>Actually it&#x27;s not so amazing. The program does not render the characters based on code, it actually loads its own source code from a cpp file and renders it as an image. You probably could run this program but give it a different cpp file and it would generate another image...</text></comment> | <story><title>Image that contains the code that generated it</title><url>https://allrgb.com/recursive</url></story><parent_chain></parent_chain><comment><author>version_five</author><text>Am I right that the image doesn&#x27;t actually contain the code, as in encode it, but rather has a blurred, stylized version of the code? It&#x27;s not some kind of quine or whatever the of the code to create the image counts as. (Edit: I&#x27;m on mobile so just saw a thumbnail, I realized now that it does have all the code in it)<p>The really cool thing I noticed about this website was the different sizes of the image. The aim is to make a 2^24 pixel image that uses each color on the rgb color space once. That&#x27;s 48 MB notionally, and some of the images are 20 or 30 MB, but then others are &lt; 1 MB that have a repeating pattern.<p>Obviously it&#x27;s possible to encode the image that contains its code in a few kb corresponding to the 100ish lines of code in the image, but the actual size is 42 MB, unsurprisingly the png encoding or whatever it is didn&#x27;t find the shortcut</text></comment> |
32,158,662 | 32,158,217 | 1 | 2 | 32,156,487 | train | <story><title>What happens when a reservoir goes dry</title><url>https://practical.engineering/blog/2022/7/18/what-happens-when-a-reservoir-goes-dry</url></story><parent_chain><item><author>photochemsyn</author><text>The wild political madness involved in the grand project to water the American West is detailed in Marc Reisner&#x27;s &quot;Cadillac Desert&quot; (1986), and is a must-read for anyone wanting to understand the current situation. It was written before a climate-related megadrought was really on anyone&#x27;s long-term radar, but it really explains a lot.<p>For example, dams are only part of the water storage picture, there&#x27;s also groundwater, and the water projects often had the goal of protecting groundwater (keeping the water table closer to the surface), but then once they&#x27;d provided water via a dam or aquaduct, the farmers would just expand the areas they were farming and groundwater extraction would often increase as a side effect.<p>Humans really aren&#x27;t that good at long-term planning, is one conclusion.</text></item></parent_chain><comment><author>colinmhayes</author><text>Humans are actually pretty good at long term planning. What we’re not good at is solving externalities. The problem with water usage is that we haven’t created a system that aligns incentives with our goals. Why would any farmer conserve water when they think the farm next door isn’t? Since water is a shared resource if you don’t use it someone else will.</text></comment> | <story><title>What happens when a reservoir goes dry</title><url>https://practical.engineering/blog/2022/7/18/what-happens-when-a-reservoir-goes-dry</url></story><parent_chain><item><author>photochemsyn</author><text>The wild political madness involved in the grand project to water the American West is detailed in Marc Reisner&#x27;s &quot;Cadillac Desert&quot; (1986), and is a must-read for anyone wanting to understand the current situation. It was written before a climate-related megadrought was really on anyone&#x27;s long-term radar, but it really explains a lot.<p>For example, dams are only part of the water storage picture, there&#x27;s also groundwater, and the water projects often had the goal of protecting groundwater (keeping the water table closer to the surface), but then once they&#x27;d provided water via a dam or aquaduct, the farmers would just expand the areas they were farming and groundwater extraction would often increase as a side effect.<p>Humans really aren&#x27;t that good at long-term planning, is one conclusion.</text></item></parent_chain><comment><author>MooMooMilkParty</author><text>Also worth reading, and considerably more up to date, is Science Be Dammed.<p><a href="https:&#x2F;&#x2F;uapress.arizona.edu&#x2F;book&#x2F;science-be-dammed" rel="nofollow">https:&#x2F;&#x2F;uapress.arizona.edu&#x2F;book&#x2F;science-be-dammed</a></text></comment> |
28,290,361 | 28,287,103 | 1 | 3 | 28,286,774 | train | <story><title>Apple’s crackdown on multicast</title><url>https://thomask.sdf.org/blog/2021/08/24/apples-bizarre-crackdown-on-multicast.html</url></story><parent_chain><item><author>0x0</author><text>Actually this makes sense. Already since recent iOS versions have started popping up an alert to grant access to local network resources per app, I&#x27;ve noticed this popping up on several apps that have no business mapping and fingerprinting my LAN. Including the Facebook app.<p>It&#x27;s weird how a company can be so internally disconnected. This entitlement is a good privacy-preserving hurdle to prevent scummy apps from interfering with your local network and fingerprinting you. On the other hand, the on-device scanning of nudes in imessage and csam in iphoto is a total snitchware swatting-as-a-service piece of software which only serves to incriminate and harass the owner of the device. Such a shame.</text></item></parent_chain><comment><author>kmeisthax</author><text>The only problem I have with it is that the entitlement system controls both what you can submit to the App Store as well as what you can locally compile and install.<p>For example, you can&#x27;t locally develop a VPN app until you ask Apple permission to develop a VPN app. Almost certainly this is to appease China, which I find particularly egregious.<p>Fonts also require an entitlement, but I&#x27;m not sure if it&#x27;s just something you need a paid dev account for or if you need to specifically grovel to Apple as to why you need it. I doubt &quot;I want to submit a pull request to iSH&quot; would be considered a valid reason (but correct me if I&#x27;m wrong).<p>Even things like camera access in multitasking views are entitlements that your dev account needs to be preapproved for. In fact, it wasn&#x27;t even something that Apple even publicly mentioned for a while - only Zoom had it until someone reverse-engineered their app bundle and found out about it.</text></comment> | <story><title>Apple’s crackdown on multicast</title><url>https://thomask.sdf.org/blog/2021/08/24/apples-bizarre-crackdown-on-multicast.html</url></story><parent_chain><item><author>0x0</author><text>Actually this makes sense. Already since recent iOS versions have started popping up an alert to grant access to local network resources per app, I&#x27;ve noticed this popping up on several apps that have no business mapping and fingerprinting my LAN. Including the Facebook app.<p>It&#x27;s weird how a company can be so internally disconnected. This entitlement is a good privacy-preserving hurdle to prevent scummy apps from interfering with your local network and fingerprinting you. On the other hand, the on-device scanning of nudes in imessage and csam in iphoto is a total snitchware swatting-as-a-service piece of software which only serves to incriminate and harass the owner of the device. Such a shame.</text></item></parent_chain><comment><author>veeti</author><text>If Facebook has no business using this permission why did App Store review approve it? Surely they must know what is going on in every app, that&#x27;s why the App Store is so safe.</text></comment> |
12,718,552 | 12,718,541 | 1 | 2 | 12,718,224 | train | <story><title>Elm and Phoenix/Elixir in Production for France TV</title><url>http://vincent.jousse.org/en/tech/elm-phoenix-elixir-production/</url></story><parent_chain></parent_chain><comment><author>sotojuan</author><text>Elixir and Phoenix are stable and by now they&#x27;re a solid choice (more than enough warranted praise on HN), but I&#x27;m still skeptical about Elm from a &quot;platform&quot; perspective. From what I can tell, Elm apps are a single blob of JavaScript that either loads or doesn&#x27;t (e.g. you can&#x27;t read the Elm site without JavaScript enabled), while the JavaScript ecosystem is moving towards server-rendering, dead code elimination, and &quot;progressive web apps&quot; so to speak. PureScript for example has dead code elimination—you can make a &lt;1kb PureScript &quot;Hello World&quot; app.<p>I know the Elm team is capable of all of these—I just haven&#x27;t heard of anything yet. While they&#x27;re &quot;nice to have&quot; now, these features might become crucial and important.<p>Another interesting thing about Elm is its progressive removal of features (I think the infix operator was or is going to be removed soon) in order to make the language more approachable. I actually support this because if you need &quot;true&quot; ML&#x2F;Haskell features, there&#x27;s PureScript.<p>Anyway, glad to see Elixir and Elm being used productively!</text></comment> | <story><title>Elm and Phoenix/Elixir in Production for France TV</title><url>http://vincent.jousse.org/en/tech/elm-phoenix-elixir-production/</url></story><parent_chain></parent_chain><comment><author>Cyph0n</author><text>Nice writeup. Elixir definitely seems like a solid language for web dev. For the frontend, I prefer Scala.js since I&#x27;m kind of a Scala fanboy, but I&#x27;ve heard great things about Elm.<p>One little comment. At the beginning of the post, you make it seem like the app needs to scale with the number of viewers, when in fact it doesn&#x27;t. I think you should clarify this to avoid confusion.</text></comment> |
24,555,405 | 24,555,617 | 1 | 2 | 24,554,522 | train | <story><title>Next-Level SSD Performance – Samsung 980 Pro 1TB Review</title><url>https://www.overclock3d.net/reviews/storage/samsung_980_pro_1tb_review/1</url></story><parent_chain><item><author>throwaway8941</author><text>And the much higher temperatures (if your M.2 is an NVMe). Could anyone knowledgeable explain why NVMe tend to get much hotter than SATA under similar conditions? I&#x27;ve been testing mine with not more than 400-500 MB&#x2F;s and it quickly gets to 60°C+, while the old 840 Evo doesn&#x27;t get above ~45°C (running a very similar synthetic workload). I would&#x27;ve guessed the opposite: the fully enclosed SATA drive should get much hotter.</text></item><item><author>gameswithgo</author><text>The most important difference between m.2 and sata is two less cables cluttering up your pc =)</text></item><item><author>Ygg2</author><text>Watching the space I wouldn&#x27;t call this next gen storage. Well. The storage is OK but the way most systems work there is no perceptible difference between an NVM m.2 drive and Sata for most regular use cases (i.e. everyday use, not server or a simulation rig). This might change in future with stuff like DirectStorage.<p>The truly &quot;next gen&quot; performance was Intel&#x27;s Optane 3D XPoint, but that is ludicrously expensive.<p>And even then it&#x27;s like boot from SSD 12 seconds at $130 dollars vs Optane 10 seconds at $1200.</text></item><item><author>Jonnax</author><text>Wow. Now that&#x27;s what you can call the next generation of storage.<p>Are there any others coming out soon or are Samsung far ahead of the competition?<p>It&#x27;s really amazing that there&#x27;s no Intel desktop that can run PCI Gen4 at the moment.<p>Will be interesting to see how stock will be. Especially if this is also one of the few SSDs certified to run in a PS5. Which has an M.2 slot.</text></item></parent_chain><comment><author>Ygg2</author><text>I&#x27;m not sure if I count, but I suspect two things. Heat dissipation and controller complexity. NVMe controller might be more computationally heavy and so they might emit more heat*.<p>But assuming that NVMe and SATA SSD controllers emit the same energy, it makes more sense that NVMe would be hotter.<p>Think about it. If you throw a ball of high heat meat would it cool faster if it was connected to a large body of water (SSD with its chasis) or a small body of water (NVMe small piece of plastic that is the NVMe)?<p>Another thing to check if your NVMe either has proper thermal pads placement and&#x2F;or if the air from the front coolers is reaching it.</text></comment> | <story><title>Next-Level SSD Performance – Samsung 980 Pro 1TB Review</title><url>https://www.overclock3d.net/reviews/storage/samsung_980_pro_1tb_review/1</url></story><parent_chain><item><author>throwaway8941</author><text>And the much higher temperatures (if your M.2 is an NVMe). Could anyone knowledgeable explain why NVMe tend to get much hotter than SATA under similar conditions? I&#x27;ve been testing mine with not more than 400-500 MB&#x2F;s and it quickly gets to 60°C+, while the old 840 Evo doesn&#x27;t get above ~45°C (running a very similar synthetic workload). I would&#x27;ve guessed the opposite: the fully enclosed SATA drive should get much hotter.</text></item><item><author>gameswithgo</author><text>The most important difference between m.2 and sata is two less cables cluttering up your pc =)</text></item><item><author>Ygg2</author><text>Watching the space I wouldn&#x27;t call this next gen storage. Well. The storage is OK but the way most systems work there is no perceptible difference between an NVM m.2 drive and Sata for most regular use cases (i.e. everyday use, not server or a simulation rig). This might change in future with stuff like DirectStorage.<p>The truly &quot;next gen&quot; performance was Intel&#x27;s Optane 3D XPoint, but that is ludicrously expensive.<p>And even then it&#x27;s like boot from SSD 12 seconds at $130 dollars vs Optane 10 seconds at $1200.</text></item><item><author>Jonnax</author><text>Wow. Now that&#x27;s what you can call the next generation of storage.<p>Are there any others coming out soon or are Samsung far ahead of the competition?<p>It&#x27;s really amazing that there&#x27;s no Intel desktop that can run PCI Gen4 at the moment.<p>Will be interesting to see how stock will be. Especially if this is also one of the few SSDs certified to run in a PS5. Which has an M.2 slot.</text></item></parent_chain><comment><author>magicalhippo</author><text>Well a 2.5&quot; drive has a much larger surface area from which the heat can dissipate.<p>There&#x27;s also the location of the temperature probe, it doesn&#x27;t need to be much further away from the heat source to register drastically lower temperatures in either case.</text></comment> |
16,052,722 | 16,050,449 | 1 | 2 | 16,050,047 | train | <story><title>SQL Keys in Depth</title><url>https://begriffs.com/posts/2018-01-01-sql-keys-in-depth.html</url></story><parent_chain></parent_chain><comment><author>manigandham</author><text>After a decade of large systems relying on RDBMs, we now use 64-bit integers for all primary keys with a global Hi&#x2F;Lo id generation system (app reserves a range of numbers on startup to assign to records automatically).<p>This means plenty of ID space, maintains rough numeric ordering, allows ID creation without a roundtrip for every insert, is easily portable across different databases, and produces unique IDs for every row in the database which greatly simplifies everything from caching to replication.</text></comment> | <story><title>SQL Keys in Depth</title><url>https://begriffs.com/posts/2018-01-01-sql-keys-in-depth.html</url></story><parent_chain></parent_chain><comment><author>simonw</author><text>&quot;For instance, a database of hobbyist club members could include uniqueness on the two columns first_name, last_name of members. Duplicates are likely unintentional at this scale, and if necessary the constraint can be dropped. Until an actual conflict happens the key is a reasonable precaution.&quot;<p>Absolutely do not do this.<p>People have names that are duplicates. A situation where someone is unable to join a club because their name clashes with an existing member is not OK.<p>Expecting a club administrator to be able to drop a uniqueness key from their database in order to resolve this situation is not a reasonable solution!</text></comment> |
2,479,891 | 2,479,824 | 1 | 2 | 2,479,757 | train | <story><title>Interviewing with YC? Don't overstep the limits like us (but be close)</title><url>http://blog.grubwith.us/interviewing-with-yc-dont-overstep-the-limits</url><text></text></story><parent_chain></parent_chain><comment><author>onan_barbarian</author><text>Given the inherent dodginess of so many 'social startups' already ("get piles of users now, figure out how to make a big pile of money from later"), this whole 'naughtiness' stuff bothers me. It's a short hop from naughty to 'actively unethical'.<p>Here's the question: given that you've already demonstrated that you don't really have a lot of regard for the privacy of fellow YC interviewees (however 'intentionally' you outed a bunch of people on Twitter), why should you be trusted with user data?<p>If you'll pull a stunt like this for seed money, what will you do to get VC money? Just wait until you've got 2-4 years of serious work on a startup and you're 'close' to serious profitability. What 'naughty' stuff will you do when you've actually got some serious skin in the game?</text></comment> | <story><title>Interviewing with YC? Don't overstep the limits like us (but be close)</title><url>http://blog.grubwith.us/interviewing-with-yc-dont-overstep-the-limits</url><text></text></story><parent_chain></parent_chain><comment><author>pg</author><text>"The problem is, while pg outwardly disapproved of our actions, we know he secretly loves founders that push the limits!"<p>You know what, though: the response function around the limit is not a smooth bell curve; it drops sharply below the x axis as you go past the peak.</text></comment> |
36,324,895 | 36,324,067 | 1 | 3 | 36,322,395 | train | <story><title>A 5.7 Terapixel Mosaic of the Surface of Mars</title><url>https://murray-lab.caltech.edu/CTX/</url></story><parent_chain></parent_chain><comment><author>qwertox</author><text>Perseverance&#x27;s path puzzled me. The good thing is that NASA has an up-to-date map [0] of its path, also joined by lines, which shows more of the path and also confirms how odd some stretches of its voyage have been.<p>Does anyone know why it spent so much time going back and forth?<p>---<p>Edit: I see, it was always going back to the &quot;Sample Depot Zone&quot; to deposit the collected samples. This zone is where the chaos begins after the very long stretch. Here&#x27;s [1] more info on the depot, including a photo made by the rover of what such a deposited sample looks like.<p>---<p>[0] <a href="https:&#x2F;&#x2F;mars.nasa.gov&#x2F;mars2020&#x2F;mission&#x2F;where-is-the-rover&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;mars.nasa.gov&#x2F;mars2020&#x2F;mission&#x2F;where-is-the-rover&#x2F;</a><p>[1] <a href="https:&#x2F;&#x2F;www.nasa.gov&#x2F;feature&#x2F;jpl&#x2F;nasa-s-perseverance-rover-completes-mars-sample-depot" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.nasa.gov&#x2F;feature&#x2F;jpl&#x2F;nasa-s-perseverance-rover-c...</a></text></comment> | <story><title>A 5.7 Terapixel Mosaic of the Surface of Mars</title><url>https://murray-lab.caltech.edu/CTX/</url></story><parent_chain></parent_chain><comment><author>q87b</author><text>It&#x27;s quite amazing and simultaneously ridiculous that we have a public 3D model of a distant planet at 5 meters resolution while the best available free and public models of Earth are at 30 meters.</text></comment> |
28,759,860 | 28,758,224 | 1 | 3 | 28,755,257 | train | <story><title>Tesla must pay $137M to ex-worker over hostile work environment, racism</title><url>https://www.cnbc.com/2021/10/05/tesla-must-pay-137-million-to-ex-worker-over-hostile-work-environment-racism.html</url></story><parent_chain><item><author>ngcazz</author><text>A bunch of you here are clearly concerned about the financial impact of the fine on Tesla’s bottom line, but maybe you should consider they could’ve gotten the house straight instead.</text></item><item><author>BluSyn</author><text>It is insane. There&#x27;s a huge line between justice and grift, and I mainly blame lawyers for the latter. If every claim of hostile workplaces resulted in similar settlements, every company would be bankrupt within a few years. A company can have a strict zero tolerance policy, but they can&#x27;t police every action of every employee while on the clock. Such settlements would likely incentivize companies to put cameras and microphones everywhere, including bathrooms, which would also result in &quot;emotion distress&quot;.<p>Forced arbitration isn&#x27;t just either, but the court system hasn&#x27;t left much room for alternative with such overreaching punishments.</text></item><item><author>sandworm101</author><text>Large? Excessive? Yes. Insane? No. The system isn&#x27;t just about compensation. The amount needs to be high enough to actually influence the wrongdoer, to dissuade repeat behavior. Maybe this jury thought this the smallest number that would cause Tesla to make actual changes to its workplace.<p>I do chuckle at how much money from each subsequent tesla sale will be going to pay down this lawsuit. 127mil &#x2F; 500k = 254$ per car for a year. Given the price of a new Tesla that doesn&#x27;t actually seem very big, and will certainly be reduced on appeal.</text></item><item><author>trabant00</author><text>Nobody wants to touch this story with a comment in 3 hours? I wonder why.<p>I&#x27;ll go ahead and say that if no important detail is left out of the story, 137 millions being awarded for verbal abuse during 1 year of employment is insane and clearly shows why the company has mandatory arbitration agreements.</text></item></parent_chain><comment><author>nuerow</author><text>&gt; A bunch of you here are clearly concerned about the financial impact of the fine on Tesla’s bottom line, but maybe you should consider they could’ve gotten the house straight instead.<p>Well, shareholders who voiced concerns regarding systemic racism in Tesla sought to actually fix the problem by looking into the arbitration process and making it clear they do not tolerate racism.<p>I&#x27;m afraid some of the comments in this thread are directly advocating against any need for Tesla to address systemic racism, and instead are deeply invested in blaming the victim.</text></comment> | <story><title>Tesla must pay $137M to ex-worker over hostile work environment, racism</title><url>https://www.cnbc.com/2021/10/05/tesla-must-pay-137-million-to-ex-worker-over-hostile-work-environment-racism.html</url></story><parent_chain><item><author>ngcazz</author><text>A bunch of you here are clearly concerned about the financial impact of the fine on Tesla’s bottom line, but maybe you should consider they could’ve gotten the house straight instead.</text></item><item><author>BluSyn</author><text>It is insane. There&#x27;s a huge line between justice and grift, and I mainly blame lawyers for the latter. If every claim of hostile workplaces resulted in similar settlements, every company would be bankrupt within a few years. A company can have a strict zero tolerance policy, but they can&#x27;t police every action of every employee while on the clock. Such settlements would likely incentivize companies to put cameras and microphones everywhere, including bathrooms, which would also result in &quot;emotion distress&quot;.<p>Forced arbitration isn&#x27;t just either, but the court system hasn&#x27;t left much room for alternative with such overreaching punishments.</text></item><item><author>sandworm101</author><text>Large? Excessive? Yes. Insane? No. The system isn&#x27;t just about compensation. The amount needs to be high enough to actually influence the wrongdoer, to dissuade repeat behavior. Maybe this jury thought this the smallest number that would cause Tesla to make actual changes to its workplace.<p>I do chuckle at how much money from each subsequent tesla sale will be going to pay down this lawsuit. 127mil &#x2F; 500k = 254$ per car for a year. Given the price of a new Tesla that doesn&#x27;t actually seem very big, and will certainly be reduced on appeal.</text></item><item><author>trabant00</author><text>Nobody wants to touch this story with a comment in 3 hours? I wonder why.<p>I&#x27;ll go ahead and say that if no important detail is left out of the story, 137 millions being awarded for verbal abuse during 1 year of employment is insane and clearly shows why the company has mandatory arbitration agreements.</text></item></parent_chain><comment><author>jeegsy</author><text>For me, Tesla&#x27;s bottom line is irrelevant. While Tesla was indeed liable for the events, 137M is way too much for what happened to the victim. Its really that simple</text></comment> |
31,838,020 | 31,837,681 | 1 | 2 | 31,836,293 | train | <story><title>Why is Apache clinging to OpenOffice?</title><url>https://www.arencambre.com/2022/06/22/why-is-apache-clinging-to-openoffices-corpse/</url></story><parent_chain><item><author>flomo</author><text>Agreed, also &quot;libre&quot; is a gnu&#x2F;jargon word which doesn&#x27;t exist in most people&#x27;s vocabulary, and probably seems meaningless or foreign.</text></item><item><author>kdmccormick</author><text>Meh, I guess it&#x27;s all subjective, but OpenOffice has a certain alliterative, authoritative-sounding ring to it. The name LibreOffice feels clunky &amp; hokey in comparison. It&#x27;s a bummer that the latter wasn&#x27;t able to adopt the branding of the former.</text></item><item><author>ozim</author><text>I like name LibreOffice much better.<p>Maybe because when I tried using OpenOffice while I was at university it sucked really bad.<p>I tried LibreOffice like 5 years ago and I am using it day to day and I donated money to them and consider donating again.</text></item><item><author>resoluteteeth</author><text>The worst thing about this was that openoffice was starting to get some name recognition before oracle killed it, and this whole debacle intentionally or unintentionally turned that name recognition into a weapon against LibreOffice.<p>Ideally they should have given LibreOffice the OpenOffice name, but even if they had just said &quot;openoffice is dead&quot; then it would have been easy for people to find libreoffice.<p>Unfortunately, by taking over the OpenOffice name and absolutely refusing to admit that development has ceased, Apache has caused tons of confusion that has massively harmed libreoffice, because for years people who had heard about &quot;openoffice&quot; would see the terrible, out of date, insecure pile of junk being distributed by the Apache Foundation and not realize that the actively developed LibreOffice was available.<p>In the case of linux distributions it was less of an issue since they just switched to LibreOffice, but I wouldn&#x27;t be suprised if there are windows users who are still downloading OpenOffice (and possibly taking one look at it and giving up and switching to Office 365).<p>Apache should have killed OpenOffice years ago but at the very least they should take it down and honestly apologize for fucking this up so badly.<p>Even ignoring the harm to LibreOffice it&#x27;s just irresponsible for Apache to keep distributing OpenOffice when they can&#x27;t even make new releases to simply apply security patches for years.</text></item></parent_chain><comment><author>xeromal</author><text>This right here. I don&#x27;t know many regular folk that ever use the word Libre, but many use the word open and office.</text></comment> | <story><title>Why is Apache clinging to OpenOffice?</title><url>https://www.arencambre.com/2022/06/22/why-is-apache-clinging-to-openoffices-corpse/</url></story><parent_chain><item><author>flomo</author><text>Agreed, also &quot;libre&quot; is a gnu&#x2F;jargon word which doesn&#x27;t exist in most people&#x27;s vocabulary, and probably seems meaningless or foreign.</text></item><item><author>kdmccormick</author><text>Meh, I guess it&#x27;s all subjective, but OpenOffice has a certain alliterative, authoritative-sounding ring to it. The name LibreOffice feels clunky &amp; hokey in comparison. It&#x27;s a bummer that the latter wasn&#x27;t able to adopt the branding of the former.</text></item><item><author>ozim</author><text>I like name LibreOffice much better.<p>Maybe because when I tried using OpenOffice while I was at university it sucked really bad.<p>I tried LibreOffice like 5 years ago and I am using it day to day and I donated money to them and consider donating again.</text></item><item><author>resoluteteeth</author><text>The worst thing about this was that openoffice was starting to get some name recognition before oracle killed it, and this whole debacle intentionally or unintentionally turned that name recognition into a weapon against LibreOffice.<p>Ideally they should have given LibreOffice the OpenOffice name, but even if they had just said &quot;openoffice is dead&quot; then it would have been easy for people to find libreoffice.<p>Unfortunately, by taking over the OpenOffice name and absolutely refusing to admit that development has ceased, Apache has caused tons of confusion that has massively harmed libreoffice, because for years people who had heard about &quot;openoffice&quot; would see the terrible, out of date, insecure pile of junk being distributed by the Apache Foundation and not realize that the actively developed LibreOffice was available.<p>In the case of linux distributions it was less of an issue since they just switched to LibreOffice, but I wouldn&#x27;t be suprised if there are windows users who are still downloading OpenOffice (and possibly taking one look at it and giving up and switching to Office 365).<p>Apache should have killed OpenOffice years ago but at the very least they should take it down and honestly apologize for fucking this up so badly.<p>Even ignoring the harm to LibreOffice it&#x27;s just irresponsible for Apache to keep distributing OpenOffice when they can&#x27;t even make new releases to simply apply security patches for years.</text></item></parent_chain><comment><author>anon_123g987</author><text>&gt; in most people&#x27;s vocabulary<p>In (monolingual) English speakers vocabulary.</text></comment> |
29,928,607 | 29,928,641 | 1 | 2 | 29,922,002 | train | <story><title>Engine cooling – why rocket engines don’t melt</title><url>https://everydayastronaut.com/engine-cooling-methodes/</url></story><parent_chain><item><author>codeulike</author><text><i>It&#x27;s really difficult even for seasoned engineers to grasp the scale of difficulty involved.</i><p>Its rocket science</text></item><item><author>beerandt</author><text>And then on top of it all, throttling ability.<p>People don&#x27;t grasp what an unbelievably complex engineering problem that is. It&#x27;s at least an addition of difficulty at the same magnitude as building a steady-state 63000 hp turbine pump in the first place.<p>Mechanically implementing it in the inherently steady-state design rocket of most rocket cycles. Having variable controls able to work at those pressures. Testing structural dynamics for a range of harmonic conditions instead of one. And do all of that with materials that need to tolerate temperatures going from cryogenic to white hot, without allowing thermal expansion to affect the mechanical tolerances of parts running at thousands of RPMs. And now you have varying flow rates and negative pressures in the lines coming from the external tanks, so have to design such that cryogenic liquids (that normally would require immense positive pressure to keep liquid) don&#x27;t spontaneously boil or cavitate or cause a shock-like wave (think water hammer turning off your bath faucet) under changing negative pressures.<p>It&#x27;s really difficult even for seasoned engineers to grasp the scale of difficulty involved.</text></item><item><author>HPsquared</author><text>I the power level of these engines is difficult to comprehend. The <i>fuel pump</i> has thousands of horsepower. Compare this to the fuel pump on a car engine, which is a tiny little electric thing. The combustion power must be in the gigawatt range.<p>Edit: the SSME high pressure fuel pump turbine produces 63000 hp (46 MW). There&#x27;s also one for the oxygen, and a pair of low pressure pumps as well. Crazy...<p>Edit edit: the fuel pump transfers 155 lb&#x2F;sec of liquid hydrogen. If fully combusted (142 MJ&#x2F;kg), that would release 10.0 GW of heat per engine.</text></item><item><author>opwieurposiu</author><text>This thing I can not comprehend about rocket engines is how the turbopump manages to hold together.<p>A turbine blade in the SSME about the size of your thumb makes 600 horsepower.<p><a href="https:&#x2F;&#x2F;www.enginehistory.org&#x2F;Rockets&#x2F;SSME&#x2F;SSME6.pdf" rel="nofollow">https:&#x2F;&#x2F;www.enginehistory.org&#x2F;Rockets&#x2F;SSME&#x2F;SSME6.pdf</a></text></item></parent_chain><comment><author>Taniwha</author><text>To be fair much of rocket science is essentially extreme plumbing</text></comment> | <story><title>Engine cooling – why rocket engines don’t melt</title><url>https://everydayastronaut.com/engine-cooling-methodes/</url></story><parent_chain><item><author>codeulike</author><text><i>It&#x27;s really difficult even for seasoned engineers to grasp the scale of difficulty involved.</i><p>Its rocket science</text></item><item><author>beerandt</author><text>And then on top of it all, throttling ability.<p>People don&#x27;t grasp what an unbelievably complex engineering problem that is. It&#x27;s at least an addition of difficulty at the same magnitude as building a steady-state 63000 hp turbine pump in the first place.<p>Mechanically implementing it in the inherently steady-state design rocket of most rocket cycles. Having variable controls able to work at those pressures. Testing structural dynamics for a range of harmonic conditions instead of one. And do all of that with materials that need to tolerate temperatures going from cryogenic to white hot, without allowing thermal expansion to affect the mechanical tolerances of parts running at thousands of RPMs. And now you have varying flow rates and negative pressures in the lines coming from the external tanks, so have to design such that cryogenic liquids (that normally would require immense positive pressure to keep liquid) don&#x27;t spontaneously boil or cavitate or cause a shock-like wave (think water hammer turning off your bath faucet) under changing negative pressures.<p>It&#x27;s really difficult even for seasoned engineers to grasp the scale of difficulty involved.</text></item><item><author>HPsquared</author><text>I the power level of these engines is difficult to comprehend. The <i>fuel pump</i> has thousands of horsepower. Compare this to the fuel pump on a car engine, which is a tiny little electric thing. The combustion power must be in the gigawatt range.<p>Edit: the SSME high pressure fuel pump turbine produces 63000 hp (46 MW). There&#x27;s also one for the oxygen, and a pair of low pressure pumps as well. Crazy...<p>Edit edit: the fuel pump transfers 155 lb&#x2F;sec of liquid hydrogen. If fully combusted (142 MJ&#x2F;kg), that would release 10.0 GW of heat per engine.</text></item><item><author>opwieurposiu</author><text>This thing I can not comprehend about rocket engines is how the turbopump manages to hold together.<p>A turbine blade in the SSME about the size of your thumb makes 600 horsepower.<p><a href="https:&#x2F;&#x2F;www.enginehistory.org&#x2F;Rockets&#x2F;SSME&#x2F;SSME6.pdf" rel="nofollow">https:&#x2F;&#x2F;www.enginehistory.org&#x2F;Rockets&#x2F;SSME&#x2F;SSME6.pdf</a></text></item></parent_chain><comment><author>kylecordes</author><text>As I understand, rocket engineering makes rocket science look pretty simple by comparison!</text></comment> |
36,769,154 | 36,765,549 | 1 | 2 | 36,763,175 | train | <story><title>The Nano ESP32</title><url>https://blog.arduino.cc/2023/07/17/introducing-the-nano-esp32-thats-iot/</url></story><parent_chain><item><author>Havoc</author><text>I struggle to understand the appeal of these more premium ESP32 boards. I’m gonna throw the same code on it. It’s an ESP32 either way. What exactly am I buying here for that 3x price</text></item></parent_chain><comment><author>jmrm</author><text>People who don&#x27;t want to mess around with low level configuration. For me, using an Arduino is the equivalent of prototyping a software in Python instead of doing it in C.<p>I haven&#x27;t used any Expressif product, but is easy to find a problem or a bug while programming a MCU if you&#x27;re new with it, and you don&#x27;t know exactly what registers you need to edit to configure to set up the hardware correctly, or if there are hardware details, like the use of multiplexing in pins, to deal with.<p>With Arduino you can forget a lot of the smaller details, and you only have to know what pins to use, how you want to use them, what devices use, and the simple functions Arduino gives to you to use them (which are commom across most of boards).</text></comment> | <story><title>The Nano ESP32</title><url>https://blog.arduino.cc/2023/07/17/introducing-the-nano-esp32-thats-iot/</url></story><parent_chain><item><author>Havoc</author><text>I struggle to understand the appeal of these more premium ESP32 boards. I’m gonna throw the same code on it. It’s an ESP32 either way. What exactly am I buying here for that 3x price</text></item></parent_chain><comment><author>AnotherGoodName</author><text>Just for prototyping ease tbh.<p>You would always make a custom board for an actual mass appeal product. If it&#x27;s not a mass made product why do you care? Pick the easiest one regardless of cost.<p>This is essentially a dev kit. With the ability to easily mess with it. You don&#x27;t care about the cost here because it&#x27;s not really an expense when amortized.</text></comment> |
30,413,647 | 30,412,315 | 1 | 2 | 30,411,160 | train | <story><title>95%-ile isn't that good (2020)</title><url>https://danluu.com/p95-skill/</url></story><parent_chain><item><author>PragmaticPulp</author><text>&gt; For a lot of people their career is just a way to get paid. As long as they don&#x27;t get fired that&#x27;s enough for them.<p>This was one of my hardest earned lessons when I became a manager. Previously I had worked my way into high-performing teams where everybody really cared about doing a good job. I was so surrounded by people with that mindset that I assumed that’s just how everybody in tech operated.<p>Only later did I realize that I was surrounded by those people because my managers actively selected for those hires and carefully weeded out the people who weren’t interested in anything other than doing the bare minimum to collect a paycheck.<p>As a hiring manager, the opposite selection bias occurs: The candidate pool is heavily biased toward people who have lost their jobs or are being pushed out as part of a PiP. You end up interviewing a lot of people who really just want to collect a paycheck and be bothered as little as possible with actual work.<p>Poke around Reddit or even HN and this work minimization mindset is even celebrated by a lot of people. If you’ve been surrounded by high achievers and motivated people who would have chosen programming jobs because that’s what they like to do every day, it can be a shock to work with people who really just hate doing anything that resembles work. Yet they’re out there, in surprisingly large numbers.</text></item><item><author>e4e78a06</author><text>&gt; Being even 50%-ile among professionals for either would certainly be extremely impressive.<p>I think you&#x27;d be surprised at how low the bar is. And how people either 1) don&#x27;t care about actively improving or 2) don&#x27;t effectively learn from their mistakes. For a lot of people their career is just a way to get paid. As long as they don&#x27;t get fired that&#x27;s enough for them. And for other people they never developed a growth mindset and a habit of introspection, or they treat mistakes&#x2F;failure as a painful memory to be avoided rather than something to be learned from.</text></item><item><author>elil17</author><text>A video game and public speaking seem like really weird&#x2F;unusual examples.<p>A ton of people play video games, very few people do it professionally. A ton of people give talks, but it’s usually a small part of their jobs. Being even 50%-ile among <i>professionals</i> for either would certainly be extremely impressive.<p>When I think about normal jobs, which are less competitive fields than professional gaming or speaking, being 95%-ile is very good (although 50%-ile is not great). Certainly, the top 5% of people at my company (200 people in my office, so 10 people I work with) are on the “top of their game”, so to speak - they always drive towards the most important objectives, rarely make errors, come up with incredible ideas, etc.</text></item></parent_chain><comment><author>lelanthran</author><text>&gt; If you’ve been surrounded by high achievers and motivated people who would have chosen programming jobs because that’s what they like to do every day, it can be a shock to work with people who really just hate doing anything that resembles work.<p>That&#x27;s a false dichotomy[1]<p>[1] If I am reading you correctly, you&#x27;re saying that there&#x27;s two extremes<p>1. Programmers who enjoy it.<p>2. Programmers who hate doing anything that resembles work.<p>But, honestly, those two classes can&#x27;t be the extreme ends of the spectrum. &quot;People who enjoy programming&quot; overlap significantly with &quot;people who hate doing the work assigned to them&quot;.<p>You make it sound like people who hate doing the work you assigned to them must be people who hate programming.<p>IME, it&#x27;s almost the opposite - people who love programming aren&#x27;t going to be the least bit excited about mindless CRUD duties on an over-engineered stack that has 27 levels of indirection before it even hits the database record.<p>&gt; Yet they’re out there, in surprisingly large numbers.<p>It appears that way to you because you are drawing wrong conclusions from your observations. You&#x27;re looking at devs who hate working on <i>your</i> stack, for <i>your</i> team and extrapolating that to &quot;These devs hate working as a programmer&quot;.<p>IOW, your observations that people hate working is accurate, your conclusion that it must be because they hate programming is not.</text></comment> | <story><title>95%-ile isn't that good (2020)</title><url>https://danluu.com/p95-skill/</url></story><parent_chain><item><author>PragmaticPulp</author><text>&gt; For a lot of people their career is just a way to get paid. As long as they don&#x27;t get fired that&#x27;s enough for them.<p>This was one of my hardest earned lessons when I became a manager. Previously I had worked my way into high-performing teams where everybody really cared about doing a good job. I was so surrounded by people with that mindset that I assumed that’s just how everybody in tech operated.<p>Only later did I realize that I was surrounded by those people because my managers actively selected for those hires and carefully weeded out the people who weren’t interested in anything other than doing the bare minimum to collect a paycheck.<p>As a hiring manager, the opposite selection bias occurs: The candidate pool is heavily biased toward people who have lost their jobs or are being pushed out as part of a PiP. You end up interviewing a lot of people who really just want to collect a paycheck and be bothered as little as possible with actual work.<p>Poke around Reddit or even HN and this work minimization mindset is even celebrated by a lot of people. If you’ve been surrounded by high achievers and motivated people who would have chosen programming jobs because that’s what they like to do every day, it can be a shock to work with people who really just hate doing anything that resembles work. Yet they’re out there, in surprisingly large numbers.</text></item><item><author>e4e78a06</author><text>&gt; Being even 50%-ile among professionals for either would certainly be extremely impressive.<p>I think you&#x27;d be surprised at how low the bar is. And how people either 1) don&#x27;t care about actively improving or 2) don&#x27;t effectively learn from their mistakes. For a lot of people their career is just a way to get paid. As long as they don&#x27;t get fired that&#x27;s enough for them. And for other people they never developed a growth mindset and a habit of introspection, or they treat mistakes&#x2F;failure as a painful memory to be avoided rather than something to be learned from.</text></item><item><author>elil17</author><text>A video game and public speaking seem like really weird&#x2F;unusual examples.<p>A ton of people play video games, very few people do it professionally. A ton of people give talks, but it’s usually a small part of their jobs. Being even 50%-ile among <i>professionals</i> for either would certainly be extremely impressive.<p>When I think about normal jobs, which are less competitive fields than professional gaming or speaking, being 95%-ile is very good (although 50%-ile is not great). Certainly, the top 5% of people at my company (200 people in my office, so 10 people I work with) are on the “top of their game”, so to speak - they always drive towards the most important objectives, rarely make errors, come up with incredible ideas, etc.</text></item></parent_chain><comment><author>tayo42</author><text>&gt; Poke around Reddit or even HN and this work minimization mindset is even celebrated by a lot of people. If you’ve been surrounded by high achievers and motivated people who would have chosen programming jobs because that’s what they like to do every day, it can be a shock to work with people who really just hate doing anything that resembles work. Yet they’re out there, in surprisingly large numbers.<p>You say this like its a bad thing?<p>Even still, wanting to work less but taking pride in your work aren&#x27;t mutually exclusive ideas. Id prefer to work as little as possible, I always do the best I can though and take care to be thoughtful and do things right. Im just not going to bend over backwards for a corporation.</text></comment> |
4,338,601 | 4,338,117 | 1 | 2 | 4,337,762 | train | <story><title>Tindie: like Etsy for electronics</title><url>https://tindie.com/</url><text></text></story><parent_chain></parent_chain><comment><author>srik</author><text>There are little things that would eventually be improved I'm sure, but right now the biggest, albeit slightly vague, feedback I got is - "Make it more <i>passionate</i>." Like Etsy does for handmade goods or sparkfun does for its electronic parts; (You're lucky because your target audience is easy to excite). Not like ebay does where they have to deal with a generic store because they dont know what to specialise for. As it is the bootstrap theme looks nifty, but doesnt get me excited as much as it possibly could.<p>Brilliant idea though. So much potential, great job man :)</text></comment> | <story><title>Tindie: like Etsy for electronics</title><url>https://tindie.com/</url><text></text></story><parent_chain></parent_chain><comment><author>emilepetrone</author><text>I made tindie, so if anyone has any feedback I'm all ears!</text></comment> |
12,747,939 | 12,748,044 | 1 | 3 | 12,738,444 | train | <story><title>Is This Economist Too Far Ahead of His Time?</title><url>http://www.chronicle.com/article/is-this-economist-too-far/238050</url></story><parent_chain><item><author>mentos</author><text>Anyone that hasn&#x27;t yet, check out Black Mirror on Netflix. It has a lot of ideas in it that I am surprised to see in a show in 2016.<p>I love Elon Musk but I think he is solving the wrong problem when it comes to making human beings a space faring species. The fragility of human flesh is the barrier to colonizing space. You can try to solve this problem by wrapping it in a contained atmosphere or wait a thousand years and send humans to Mars in a different kind of space ship. One made of metal and silicon that can recharge its batteries so long as it has a line of sight on a distant star.. maybe as the article says: &quot;a robotic body [standing] roughly two millimeters tall&quot;<p>The greatest challenge we face is keeping this incubator called Earth alive long enough for us to develop the technology to abandon our flesh. But I imagine if that day ever comes what it means to be human will have been destroyed in the end anyways.</text></item></parent_chain><comment><author>mburns</author><text>&gt;or wait a thousand years and send humans to Mars in a different kind of space ship.<p>Pardon the pun, but why on Earth should we wait 1000 years (or whatever it actually takes) for something when we don&#x27;t have to?<p>Our fragile human flesh in a contained atmosphere works well enough and we&#x27;re roughly capable of doing it now, give or take a couple decades.<p>Then we have 900+ years to improve the containers we use to maintain our preferred atmosphere while waiting for whatever form this futuristic species you describe takes.</text></comment> | <story><title>Is This Economist Too Far Ahead of His Time?</title><url>http://www.chronicle.com/article/is-this-economist-too-far/238050</url></story><parent_chain><item><author>mentos</author><text>Anyone that hasn&#x27;t yet, check out Black Mirror on Netflix. It has a lot of ideas in it that I am surprised to see in a show in 2016.<p>I love Elon Musk but I think he is solving the wrong problem when it comes to making human beings a space faring species. The fragility of human flesh is the barrier to colonizing space. You can try to solve this problem by wrapping it in a contained atmosphere or wait a thousand years and send humans to Mars in a different kind of space ship. One made of metal and silicon that can recharge its batteries so long as it has a line of sight on a distant star.. maybe as the article says: &quot;a robotic body [standing] roughly two millimeters tall&quot;<p>The greatest challenge we face is keeping this incubator called Earth alive long enough for us to develop the technology to abandon our flesh. But I imagine if that day ever comes what it means to be human will have been destroyed in the end anyways.</text></item></parent_chain><comment><author>the_duke</author><text>I recently discovered Black Mirror.<p>It&#x27;s a great and fascinating series. Finally something other then the mind numbing pabulum that is most TV.<p>I especially loved season 1 &#x2F; episode 2.<p>---<p>The way our brain works, all experience, self consciousness and awareness is intricately linked to physical perception. If we were to go the &#x27;brain in a petri dish&#x27; route, we would have to fake all those signals a body would send to the brain. If we just start emulating the brain physiology digitally, that is easier of course.<p>But I would not call the result of either method a &#x27;human being&#x27;, but something inherently different.</text></comment> |
39,534,010 | 39,532,285 | 1 | 2 | 39,530,113 | train | <story><title>Does this 8088 code in the Leisure Suit Larry 2 game do anything?</title><url>https://retrocomputing.stackexchange.com/questions/29565/does-this-8088-code-in-the-leisure-suit-larry-2-game-actually-do-anything</url></story><parent_chain><item><author>jojobas</author><text>Yet the top answer is &quot;this is gibberish&quot;. Go figure.</text></item><item><author>sedatk</author><text>Somebody in the answers already figured out that the code belonged to MS-DOS 3.30 COMMAND.COM as previously attested by Al Lowe. <a href="https:&#x2F;&#x2F;retrocomputing.stackexchange.com&#x2F;a&#x2F;29580&#x2F;3986" rel="nofollow">https:&#x2F;&#x2F;retrocomputing.stackexchange.com&#x2F;a&#x2F;29580&#x2F;3986</a></text></item></parent_chain><comment><author>nicetryguy</author><text>&gt; Yet the top answer is &quot;this is gibberish&quot;<p>They&#x27;re not wrong really. It is gibberish on it&#x27;s own. We don&#x27;t know where in memory that it starts or the places it is referencing in the jumps. If it were ASM source code those jumps would likely contain labels instead of just raw dogging memory locations.<p>The fact that it just so happens to be from COMMAND.COM from MS-DOS 3 is a wonderful bit of detective work, but it doesn&#x27;t make the snippet any less gibberish.</text></comment> | <story><title>Does this 8088 code in the Leisure Suit Larry 2 game do anything?</title><url>https://retrocomputing.stackexchange.com/questions/29565/does-this-8088-code-in-the-leisure-suit-larry-2-game-actually-do-anything</url></story><parent_chain><item><author>jojobas</author><text>Yet the top answer is &quot;this is gibberish&quot;. Go figure.</text></item><item><author>sedatk</author><text>Somebody in the answers already figured out that the code belonged to MS-DOS 3.30 COMMAND.COM as previously attested by Al Lowe. <a href="https:&#x2F;&#x2F;retrocomputing.stackexchange.com&#x2F;a&#x2F;29580&#x2F;3986" rel="nofollow">https:&#x2F;&#x2F;retrocomputing.stackexchange.com&#x2F;a&#x2F;29580&#x2F;3986</a></text></item></parent_chain><comment><author>spurgu</author><text>Well the top answer was written 3 days ago, the correct one 3 <i>hours</i> ago. Give it some time.</text></comment> |
14,911,647 | 14,910,114 | 1 | 3 | 14,907,771 | train | <story><title>Btrfs has been deprecated in RHEL</title><url>https://access.redhat.com/documentation/en-US/Red_Hat_Enterprise_Linux/7/html/7.4_Release_Notes/chap-Red_Hat_Enterprise_Linux-7.4_Release_Notes-Deprecated_Functionality.html</url></story><parent_chain><item><author>josefbacik</author><text>People are making a bigger deal of this than it is. Since I left Red Hat in 2012 there hasn&#x27;t been another engineer to pick up the work, and it is _a lot_ of work.<p>For RHEL you are stuck on one kernel for an entire release. Every fix has to be backported from upstream, and the further from upstream you get the harder it is to do that work.<p>Btrfs has to be rebased _every_ release. If moves too fast and there is so much work being done that you can&#x27;t just cherry pick individual fixes. This makes it a huge pain in the ass.<p>Then you have RHEL&#x27;s &quot;if we ship it we support it&quot; mantra. Every release you have something that is more Frankenstein-y than it was before, and you run more of a risk of shit going horribly wrong. That&#x27;s a huge liability for an engineering team that has 0 upstream btrfs contributors.<p>The entire local file system group are xfs developers. Nobody has done serious btrfs work at Red Hat since I left (with a slight exception with Zach Brown for a little while.)<p>Suse uses it as their default and has a lot of inhouse expertise. We use it in a variety of ways inside Facebook. It&#x27;s getting faster and more stable, admittedly slower than I&#x27;d like, but we are getting there. This announcement from Red Hat is purely a reflection of Red Hat&#x27;s engineering expertise and the way they ship kernels, and not an indictment of Btrfs itself.</text></item></parent_chain><comment><author>pgaddict</author><text>I think a natural follow-up question is &quot;Why Red Hat does not have engineers to support btrfs?&quot; That is, if the lack of engineers is a symptom, what is the cause?<p>I&#x27;m pretty sure, had RH wanted they could either hire or assign engineers to maintain the btrfs code, take care of patches from upstream, etc. So why didn&#x27;t that happen? I wonder what is your opinion on that.<p>I see a bunch of possibilities (not necessarily independent ones):<p>1) Politics. Perhaps RH wants to kill btrfs for some reason?<p>I see this as rather unlikely, as RH does not have a competing solution (unlike in the Jigsaw controversy, where they have incentives to kill it in favor of the JBoss module system).<p>2) Inability to hire enough engineers familiar with btrfs, or assign existing engineers.<p>Perhaps the number of engineers would be too high, increasing costs. Especially if not only to maintain the RHEL kernels, but to contribute to btrfs and move it forward.<p>Or maybe there&#x27;s a pushback from the current filesystems team, where most people are xfs developers?<p>3) Incompatible development models.<p>If each release requires a rebase, perhaps supporting btrfs would require too much work &#x2F; too many engineers, increasing costs? I wonder what Suse and others are doing differently, except for having in-house btrfs developers.<p>4) Lack of trust btrfs will get mature enough for RHEL soon.<p>It may work for certain deployments, but for RHEL customers that may not be sufficient. That probably requires a filesystem performing well for a wider range of workloads.<p>5) Lack of interest from paying RHEL customers.<p>Many of our customers have RHEL systems (or CentOS &#x2F; Scientific Linux), and I don&#x27;t remember a single one of them using btrfs or planning to do so. We only deal with database servers, which is a very narrow segment of the market, and fairly conservative one when it comes to filesystems.<p>But overall, if customers are not interested in a feature, it&#x27;s merely a pragmatic business decision not to spend money on it.<p>6) Better alternatives available.<p>I&#x27;m not aware of one, although &quot;ZFS on Linux&quot; is getting much better.<p>So I tend to see this as a pragmatic business decision, based on customer interest in btrfs on RHEL vs. costs of supporting it.</text></comment> | <story><title>Btrfs has been deprecated in RHEL</title><url>https://access.redhat.com/documentation/en-US/Red_Hat_Enterprise_Linux/7/html/7.4_Release_Notes/chap-Red_Hat_Enterprise_Linux-7.4_Release_Notes-Deprecated_Functionality.html</url></story><parent_chain><item><author>josefbacik</author><text>People are making a bigger deal of this than it is. Since I left Red Hat in 2012 there hasn&#x27;t been another engineer to pick up the work, and it is _a lot_ of work.<p>For RHEL you are stuck on one kernel for an entire release. Every fix has to be backported from upstream, and the further from upstream you get the harder it is to do that work.<p>Btrfs has to be rebased _every_ release. If moves too fast and there is so much work being done that you can&#x27;t just cherry pick individual fixes. This makes it a huge pain in the ass.<p>Then you have RHEL&#x27;s &quot;if we ship it we support it&quot; mantra. Every release you have something that is more Frankenstein-y than it was before, and you run more of a risk of shit going horribly wrong. That&#x27;s a huge liability for an engineering team that has 0 upstream btrfs contributors.<p>The entire local file system group are xfs developers. Nobody has done serious btrfs work at Red Hat since I left (with a slight exception with Zach Brown for a little while.)<p>Suse uses it as their default and has a lot of inhouse expertise. We use it in a variety of ways inside Facebook. It&#x27;s getting faster and more stable, admittedly slower than I&#x27;d like, but we are getting there. This announcement from Red Hat is purely a reflection of Red Hat&#x27;s engineering expertise and the way they ship kernels, and not an indictment of Btrfs itself.</text></item></parent_chain><comment><author>nailer</author><text>Thanks. Any indication why RH didn&#x27;t hire btrfs devs? It looks like a decision was made that it wasn&#x27;t strategic (obviously xfs on Linux has a much longer history).</text></comment> |
20,841,652 | 20,841,542 | 1 | 2 | 20,841,088 | train | <story><title>Release of “13 Reasons Why” Associated with Increase in Youth Suicide Rates</title><url>https://www.nimh.nih.gov/news/science-news/2019/release-of-13-reasons-why-associated-with-increase-in-youth-suicide-rates.shtml</url></story><parent_chain><item><author>csharpminor</author><text>Could you link to a source? This is interesting to me but I&#x27;d like to know more about their method for arriving at those conclusions. I wasn&#x27;t able to find the article&#x2F;study you&#x27;re referencing.</text></item><item><author>duxup</author><text>NPR did a good story on a study that examined what shooters DO and DO NOT like.<p>They like videos of chaos and screaming.<p>They like their photo shown.<p>They don&#x27;t like stories about the victims that make the victims seem like they&#x27;re human. What they were doing before the shootings, things they did with their lives, etc.<p>They don&#x27;t like stories about the community itself that aren&#x27;t just about the event (shooting).<p>I noticed NPR does a lot of stories about the the victims.<p>Nothing should be legally restricted, but I think news orgs can do their job 100% and still participate in a potentially helpful manner. To be clear there is no science that says doing any of these things reduce any amount of shooting or such, but it seems like a reasonable theory that if they see shootings result in coverage they don&#x27;t like, it might discourage them if they think they won&#x27;t get what they want.</text></item><item><author>aphextim</author><text>Same reason that when they show the shooter&#x27;s face all over the media and they give them tons and tons of attention, it typically spawns more copycats who are just lonely&#x2F;sad&#x2F;broken teens looking for the same attention.<p>In the show, this teen&#x27;s suicide was portrayed to have had an impact on many students&#x2F;families&#x2F;teachers etc for a very long time after the incident. It almost glorified the suicide and the methods of leaving tapes behind.<p>Real suicide is not so glorious and does not leave a much of an impact as you would think, other than on the immediate family.<p>For example, when my mother committed suicide, my sister, grandparents and myself were impacted severely for a bit, but outside of our family circle it didn&#x27;t have as much of an impact.<p>When I was in high school, we had a student commit suicide, which we ended up having 1 school meeting regarding it, but after about a week it had been forgotten by most and swept under the rug as everyone moved on to the next thing.<p>I guess I am biased based on my two experiences with suicide, however glorifying it in any way will only lead to more incidents.</text></item></parent_chain><comment><author>jt2190</author><text>Perhaps:<p>Thresholds of violence: How school shootings catch on, by Malcolm Gladwell <a href="https:&#x2F;&#x2F;www.newyorker.com&#x2F;magazine&#x2F;2015&#x2F;10&#x2F;19&#x2F;thresholds-of-violence" rel="nofollow">https:&#x2F;&#x2F;www.newyorker.com&#x2F;magazine&#x2F;2015&#x2F;10&#x2F;19&#x2F;thresholds-of-...</a><p>Gladwell interviewed about the article on National Public Radio’s Morning Edition: <a href="https:&#x2F;&#x2F;www.npr.org&#x2F;2015&#x2F;10&#x2F;13&#x2F;448182623&#x2F;how-riots-may-help-us-understand-school-shooters" rel="nofollow">https:&#x2F;&#x2F;www.npr.org&#x2F;2015&#x2F;10&#x2F;13&#x2F;448182623&#x2F;how-riots-may-help-...</a></text></comment> | <story><title>Release of “13 Reasons Why” Associated with Increase in Youth Suicide Rates</title><url>https://www.nimh.nih.gov/news/science-news/2019/release-of-13-reasons-why-associated-with-increase-in-youth-suicide-rates.shtml</url></story><parent_chain><item><author>csharpminor</author><text>Could you link to a source? This is interesting to me but I&#x27;d like to know more about their method for arriving at those conclusions. I wasn&#x27;t able to find the article&#x2F;study you&#x27;re referencing.</text></item><item><author>duxup</author><text>NPR did a good story on a study that examined what shooters DO and DO NOT like.<p>They like videos of chaos and screaming.<p>They like their photo shown.<p>They don&#x27;t like stories about the victims that make the victims seem like they&#x27;re human. What they were doing before the shootings, things they did with their lives, etc.<p>They don&#x27;t like stories about the community itself that aren&#x27;t just about the event (shooting).<p>I noticed NPR does a lot of stories about the the victims.<p>Nothing should be legally restricted, but I think news orgs can do their job 100% and still participate in a potentially helpful manner. To be clear there is no science that says doing any of these things reduce any amount of shooting or such, but it seems like a reasonable theory that if they see shootings result in coverage they don&#x27;t like, it might discourage them if they think they won&#x27;t get what they want.</text></item><item><author>aphextim</author><text>Same reason that when they show the shooter&#x27;s face all over the media and they give them tons and tons of attention, it typically spawns more copycats who are just lonely&#x2F;sad&#x2F;broken teens looking for the same attention.<p>In the show, this teen&#x27;s suicide was portrayed to have had an impact on many students&#x2F;families&#x2F;teachers etc for a very long time after the incident. It almost glorified the suicide and the methods of leaving tapes behind.<p>Real suicide is not so glorious and does not leave a much of an impact as you would think, other than on the immediate family.<p>For example, when my mother committed suicide, my sister, grandparents and myself were impacted severely for a bit, but outside of our family circle it didn&#x27;t have as much of an impact.<p>When I was in high school, we had a student commit suicide, which we ended up having 1 school meeting regarding it, but after about a week it had been forgotten by most and swept under the rug as everyone moved on to the next thing.<p>I guess I am biased based on my two experiences with suicide, however glorifying it in any way will only lead to more incidents.</text></item></parent_chain><comment><author>duxup</author><text>I&#x27;ll do some searching. I know it was on NPR, and within the last 3 years.</text></comment> |
6,071,377 | 6,071,460 | 1 | 2 | 6,071,027 | train | <story><title>Microsoft’s shares sink by more than 10%</title><url>https://www.google.com/finance?q=NASDAQ:MSFT</url></story><parent_chain><item><author>dragontamer</author><text>SurfaceRT is a $900-million mistake right now.<p>There are so many ways to make SurfaceRT a compelling product. <i>If</i> it supported Win32 API, <i>IF</i> it had domain-joining support, <i>if</i> it wasn&#x27;t completely locked down to the Windows Store... maybe it&#x27;d be a compelling buy. But as it is, it has all of the disadvantages of tablets (locked down, proprietary API), with few of the advantages of Windows.<p>Then you&#x27;ve got XBox One mistake. So much wasted potential there...<p>Windows 8 has to happen though, the computing industry is evolving towards touch controls, and as primitive as Windows8 is with touch... its a step in the right direction for Microsoft. But they need to be more sensitive to their business partners.</text></item></parent_chain><comment><author>JonFish85</author><text>I feel like their biggest problem was confusion. Apple does this very well: their products aren&#x27;t terribly confusing. As a consumer thinking about buying a tablet computer, you think OK there&#x27;s the iPad, but what else? Oh, Microsoft has a tablet. Hey, it runs Windows, I know windows! But Windows RT? It doesn&#x27;t run my existing card games? I thought it was Windows? Oh but if I buy the pro, it&#x27;ll run my Windows stuff? How do I install my card games? But it&#x27;s more money? What&#x27;s different about that one?<p>Screw it, I&#x27;ll just get the iPad.</text></comment> | <story><title>Microsoft’s shares sink by more than 10%</title><url>https://www.google.com/finance?q=NASDAQ:MSFT</url></story><parent_chain><item><author>dragontamer</author><text>SurfaceRT is a $900-million mistake right now.<p>There are so many ways to make SurfaceRT a compelling product. <i>If</i> it supported Win32 API, <i>IF</i> it had domain-joining support, <i>if</i> it wasn&#x27;t completely locked down to the Windows Store... maybe it&#x27;d be a compelling buy. But as it is, it has all of the disadvantages of tablets (locked down, proprietary API), with few of the advantages of Windows.<p>Then you&#x27;ve got XBox One mistake. So much wasted potential there...<p>Windows 8 has to happen though, the computing industry is evolving towards touch controls, and as primitive as Windows8 is with touch... its a step in the right direction for Microsoft. But they need to be more sensitive to their business partners.</text></item></parent_chain><comment><author>smacktoward</author><text>The problem is that if you add all those compelling features to Surface RT, you end up with Surface Pro. Which brings you right back to the question of why Surface RT needs to exist.<p>(The answer: because Surface Pro is too expensive to appeal to the consumer tablet market, and because Microsoft wants to hedge its bets in case Intel can&#x27;t catch up to ARM in the mobile space. But both of those are reasons why <i>Microsoft</i> would want Surface RT to exist, not why <i>a customer</i> would.)</text></comment> |
12,613,279 | 12,613,219 | 1 | 3 | 12,612,564 | train | <story><title>90 Cents of Every 'Pay-For-Performance' Dollar for CEOs Are Paid for Luck</title><url>https://corpgov.law.harvard.edu/2016/09/29/90-cents-of-every-pay-for-performance-dollar-are-paid-for-luck/</url></story><parent_chain><item><author>Singletoned</author><text>I don&#x27;t disagree necessarily, but I&#x27;m definitely more cautious in criticising someone else&#x27;s pay when I can&#x27;t do their job.<p>I certainly know that a lot of people who know nothing about computers think that I&#x27;m overpaid as a software developer. Why should I earn several times their salary when I just sit at a computer all day, whilst they do hard work?</text></item><item><author>mpdehaan2</author><text>Excellent points in this article - another factor is they are often paid outrageous base salaries (plus options) for the success of a company, when the success of that company can often be in spite of the CEO, coming from within, and embodied equally by all of the collective employees.<p>Executive comp is a major racket, enforced by the standard that this is &quot;what the market average is&quot;. Which is set by executives overpaying themselves.<p>Ask yourself if your CEO is really working 100x as hard as you, or 100x smarter than you. The answer is usually a definite no. I&#x27;d really like to see more fair pay in this area and a culture that treats contributions of all employees more equally.</text></item></parent_chain><comment><author>mpdehaan2</author><text>In my case, I <i>CAN</i> do their job. They have a lot of support structures to delegate between. You may think you can&#x27;t do their job, but you could, if you wanted - though getting there is a game of thrones of sorts, and you may not wish to play.<p>However, they can&#x27;t do your job. Assuming you are a developer, they are making a living based on your work. Your work has equal value. Well, if you <i>ARE</i> doing hard work. If you are just sitting at a terminal, more ambition might be a good thing :) Cultivate it and you can get there. If you want.<p>We need not assume all leadership at the top is steering the entire ship, more so than steering parts of things, decisions trickling up as well as down, alongside information.</text></comment> | <story><title>90 Cents of Every 'Pay-For-Performance' Dollar for CEOs Are Paid for Luck</title><url>https://corpgov.law.harvard.edu/2016/09/29/90-cents-of-every-pay-for-performance-dollar-are-paid-for-luck/</url></story><parent_chain><item><author>Singletoned</author><text>I don&#x27;t disagree necessarily, but I&#x27;m definitely more cautious in criticising someone else&#x27;s pay when I can&#x27;t do their job.<p>I certainly know that a lot of people who know nothing about computers think that I&#x27;m overpaid as a software developer. Why should I earn several times their salary when I just sit at a computer all day, whilst they do hard work?</text></item><item><author>mpdehaan2</author><text>Excellent points in this article - another factor is they are often paid outrageous base salaries (plus options) for the success of a company, when the success of that company can often be in spite of the CEO, coming from within, and embodied equally by all of the collective employees.<p>Executive comp is a major racket, enforced by the standard that this is &quot;what the market average is&quot;. Which is set by executives overpaying themselves.<p>Ask yourself if your CEO is really working 100x as hard as you, or 100x smarter than you. The answer is usually a definite no. I&#x27;d really like to see more fair pay in this area and a culture that treats contributions of all employees more equally.</text></item></parent_chain><comment><author>ythl</author><text>&gt; Why should I earn several times their salary when I just sit at a computer all day, whilst they do hard work?<p>Yeah, why should you? I mean, you are essentially being paid to surf Hacker News and plunk out a few lines of code every once in a while, while the janitor is working hard all day.</text></comment> |
10,222,180 | 10,221,739 | 1 | 2 | 10,221,563 | train | <story><title>Stack Exchange Is Now Stack Overflow</title><url>https://blog.stackoverflow.com/2015/09/were-changing-our-name-back-to-stack-overflow/</url></story><parent_chain><item><author>wiremine</author><text>Was just thinking what it was like to develop before Stack Overflow... and before github... Yikes!<p>Kudos to the team over at SO to continue to iterate the business.<p>I do wish they&#x27;d add an &quot;out of date&quot; button to flag questions&#x2F;answers that are no longer relevant or just plain wrong. I think the amount of cruft they&#x27;re going to deal with in the next 10 years is going to be HUGE.</text></item></parent_chain><comment><author>EliRivers</author><text>I have to resort to SO a couple of times a month, so before SO (and other such) it was 95% the same as it is now.<p>I probably would have found much more use for it in my first year or so as a programmer, but at least from my own experience, once I had familiarity with my tools and libraries, the kind of problems that require digging on the internet aren&#x27;t the kind easily put into bite-sized Q&amp;A.<p>Maybe it&#x27;s different for people who did start with SO available; perhaps they&#x27;re saving their cognitive load by outsourcing various snippets of information to SO, and I only internalised them because SO wasn&#x27;t available.<p>That said, it IS good for more open-ended historical or state-of-the-art type questions; &quot;why did language X adopt this paradigm?&quot; or &quot;how do people producing commercial software go about supporting multiple graphics hardware today?&quot; kind of questions. If I get lucky, there are a handful of people with a real depth of knowledge who can give a valuable overview and insight, but those are a long way from the typical SO question.</text></comment> | <story><title>Stack Exchange Is Now Stack Overflow</title><url>https://blog.stackoverflow.com/2015/09/were-changing-our-name-back-to-stack-overflow/</url></story><parent_chain><item><author>wiremine</author><text>Was just thinking what it was like to develop before Stack Overflow... and before github... Yikes!<p>Kudos to the team over at SO to continue to iterate the business.<p>I do wish they&#x27;d add an &quot;out of date&quot; button to flag questions&#x2F;answers that are no longer relevant or just plain wrong. I think the amount of cruft they&#x27;re going to deal with in the next 10 years is going to be HUGE.</text></item></parent_chain><comment><author>freditup</author><text>This would be a nice change. It&#x27;s frustrating when your own questions are marked as duplicates because there&#x27;s a similar question from five years ago.</text></comment> |
863,407 | 863,317 | 1 | 3 | 863,294 | train | <story><title>This Is a Photoshop and It Blew My Mind - Photosketch</title><url>http://gizmodo.com/5374890/this-is-a-photoshop-and-it-blew-my-mind</url></story><parent_chain></parent_chain><comment><author>anigbrowl</author><text>Sigh...third time today and I only got one karma point for pointing it first. <a href="http://news.ycombinator.com/item?id=862216" rel="nofollow">http://news.ycombinator.com/item?id=862216</a> if you feel sympathetic :)<p>EDIT: gee guys, the smiley should tell you this ^ is not a serious complaint. I thought people might actually be interested in reading the actual paper v, since project page link has been inaccessible. Sheesh.<p>Site is down but this is the Siggraph paper: <a href="http://www.ece.nus.edu.sg/stfpage/eletp/Papers/sigasia09_photosketch.pdf" rel="nofollow">http://www.ece.nus.edu.sg/stfpage/eletp/Papers/sigasia09_pho...</a><p>I have downloaded the binaries (also requires openCV1.1, recently updated OpenCV2.0 doesn't work) and have made some progress, though it's very clunky and the instructions are, um...lacking. <a href="http://sourceforge.net/projects/opencvlibrary/files/" rel="nofollow">http://sourceforge.net/projects/opencvlibrary/files/</a>
<a href="http://opencv.willowgarage.com/wiki/" rel="nofollow">http://opencv.willowgarage.com/wiki/</a></text></comment> | <story><title>This Is a Photoshop and It Blew My Mind - Photosketch</title><url>http://gizmodo.com/5374890/this-is-a-photoshop-and-it-blew-my-mind</url></story><parent_chain></parent_chain><comment><author>chime</author><text>I'm having a very hard time believing that this is real. If it is, they have just made breakthroughs in multiple domains in computer graphics, recognition, and composition at the same time. Here's hoping it's real.</text></comment> |
4,262,420 | 4,262,295 | 1 | 2 | 4,262,098 | train | <story><title>Apple Must Publish Notice Samsung Didn’t Copy IPad In U.K.</title><url>http://www.bloomberg.com/news/2012-07-18/apple-must-publish-notice-samsung-didn-t-copy-ipad-judge-says.html</url><text></text></story><parent_chain></parent_chain><comment><author>Terretta</author><text>This is not a disjunctive syllogism.<p>If Apple could not prove that Samsung copied them, it does not follow that Samsung didn't copy them, just as if California couldn't prove that OJ did it, it doesn't follow that he didn't do it.<p>This ruling, that Apple has to affirm something equally unproven, is bizarre.</text></comment> | <story><title>Apple Must Publish Notice Samsung Didn’t Copy IPad In U.K.</title><url>http://www.bloomberg.com/news/2012-07-18/apple-must-publish-notice-samsung-didn-t-copy-ipad-judge-says.html</url><text></text></story><parent_chain></parent_chain><comment><author>bratsche</author><text>Wasn't the original ruling basically saying, "It's not a copy of the iPad because it's not as cool"? You know if Apple really does have to put this notice on their website, they'll probably find a way to work that into the announcement.</text></comment> |
23,919,084 | 23,918,014 | 1 | 2 | 23,915,521 | train | <story><title>Design Docs at Google</title><url>https://www.industrialempathy.com/posts/design-docs-at-google/</url></story><parent_chain><item><author>nickbauman</author><text>This is something that should be taught to folks while they&#x27;re still in school. The &quot;blueprint analogy&quot; has baked in the idea that there&#x27;s a &quot;design phase&quot; and a &quot;construction phase&quot; and that these are often discreet parties.<p>Nothing could be more incorrect when it comes to software. In software, <i>the design is the code.</i> The compiler&#x2F;interpreter are the construction of the system.</text></item><item><author>sarchertech</author><text>&gt;If code is the bricks and mortar, then these docs are the blueprints.<p>That analogy falls apart quickly. Design docs aren’t specific enough to be analogous to blueprints.<p>You can give a set of blueprints to 3 different construction firms and get fundamentally the same building. Try giving design docs to 3 different development shops and see what happens.<p>The problem is that the only way to get to that level of specificity is with code.<p>Design docs are closer to something a city planner would produce than to something an architect or civil engineer would, and they should be treated accordingly.</text></item><item><author>cameronbrown</author><text>Design docs are one of my favourite things about software engineering. If code is the bricks and mortar, then these docs are the blueprints.<p>I know this is fairly controversial, but our jobs isn&#x27;t just to write code. Navigating organisations and achieving consensus between a lot of teams&#x2F;technologies is a huge part of it.<p>Design docs are a way to get all of that out of the way _before_ writing thousands of lines of code. The review process nets significantly different feedback to code reviews too.</text></item></parent_chain><comment><author>throwaway_pdp09</author><text>&gt; In software, the design is the code. The compiler&#x2F;interpreter are the construction of the system.<p>That&#x27;s IMO a pedantic view. Yes, ok, but when I design software I describe it&#x27;s high-level characteristics, more like describing the plot of a book than the specific words in a book and the what the characters say to each other.<p>I&#x27;d say there are many levels of design. Code is the last.</text></comment> | <story><title>Design Docs at Google</title><url>https://www.industrialempathy.com/posts/design-docs-at-google/</url></story><parent_chain><item><author>nickbauman</author><text>This is something that should be taught to folks while they&#x27;re still in school. The &quot;blueprint analogy&quot; has baked in the idea that there&#x27;s a &quot;design phase&quot; and a &quot;construction phase&quot; and that these are often discreet parties.<p>Nothing could be more incorrect when it comes to software. In software, <i>the design is the code.</i> The compiler&#x2F;interpreter are the construction of the system.</text></item><item><author>sarchertech</author><text>&gt;If code is the bricks and mortar, then these docs are the blueprints.<p>That analogy falls apart quickly. Design docs aren’t specific enough to be analogous to blueprints.<p>You can give a set of blueprints to 3 different construction firms and get fundamentally the same building. Try giving design docs to 3 different development shops and see what happens.<p>The problem is that the only way to get to that level of specificity is with code.<p>Design docs are closer to something a city planner would produce than to something an architect or civil engineer would, and they should be treated accordingly.</text></item><item><author>cameronbrown</author><text>Design docs are one of my favourite things about software engineering. If code is the bricks and mortar, then these docs are the blueprints.<p>I know this is fairly controversial, but our jobs isn&#x27;t just to write code. Navigating organisations and achieving consensus between a lot of teams&#x2F;technologies is a huge part of it.<p>Design docs are a way to get all of that out of the way _before_ writing thousands of lines of code. The review process nets significantly different feedback to code reviews too.</text></item></parent_chain><comment><author>supahfly_remix</author><text>If the design is the code, then what is a bug? There is a separate model, whether written down or not, of what the code must do. That is the deaign.</text></comment> |
14,079,882 | 14,079,610 | 1 | 2 | 14,079,163 | train | <story><title>Debugging macOS Kernel Using VirtualBox</title><url>https://klue.github.io/blog/2017/04/macos_kernel_debugging_vbox/</url></story><parent_chain><item><author>jordigh</author><text>Is this completely allowed? I&#x27;m probably misinformed, but I thought either certain debugging calls or certain kinds of virtualisation were disallowed by Apple. The fact that this kind of tutorial using virtualbox exists makes me think that someone is trying to work around something. I thought you weren&#x27;t allowed to debug parts of macOS. Are there absolutely no limits, legal or technical?</text></item></parent_chain><comment><author>xenadu02</author><text>From <a href="https:&#x2F;&#x2F;ssl.apple.com&#x2F;legal&#x2F;sla&#x2F;docs&#x2F;macOS1012.pdf" rel="nofollow">https:&#x2F;&#x2F;ssl.apple.com&#x2F;legal&#x2F;sla&#x2F;docs&#x2F;macOS1012.pdf</a>, you are in fact allowed to run macOS in a VM so long as you do so on Apple hardware:<p>(iii) to install, use and run up to two (2) additional copies or instances of the Apple Software within virtual operating system environments on each Mac Computer you own or control that is already running the Apple Software, for purposes of: (a) software development; (b) testing during software development; (c) using macOS Server; or (d) personal, non-commercial use.</text></comment> | <story><title>Debugging macOS Kernel Using VirtualBox</title><url>https://klue.github.io/blog/2017/04/macos_kernel_debugging_vbox/</url></story><parent_chain><item><author>jordigh</author><text>Is this completely allowed? I&#x27;m probably misinformed, but I thought either certain debugging calls or certain kinds of virtualisation were disallowed by Apple. The fact that this kind of tutorial using virtualbox exists makes me think that someone is trying to work around something. I thought you weren&#x27;t allowed to debug parts of macOS. Are there absolutely no limits, legal or technical?</text></item></parent_chain><comment><author>klue07</author><text>Author here. Nothing in the post is illegal.<p>Apple allows 3rd party kernel extensions so naturally you would need to be able to debug the kernel. In my post, I link plenty of official Apple documentation that provide information on how to debug the kernel.</text></comment> |
32,226,078 | 32,225,848 | 1 | 2 | 32,224,823 | train | <story><title>Faked Beta-Amyloid Data. What Does It Mean?</title><url>https://www.science.org/content/blog-post/faked-beta-amyloid-data-what-does-it-mean</url></story><parent_chain><item><author>lettergram</author><text>To quote someone I know in Alzheimer research - “I’m pretty sure it’s all fake”<p>It’s funny because more than once I’ve had conversations off-the-record with people who had the same concerns.<p>What I think is most troubling is how long it took and how many papers support the claims.<p>In other words, there are thousands of papers supporting beta-amyloid and&#x2F;or building off the data &#x2F; theory. All of that data and everyone conducting that data should be in question. Yes, sometimes you’ll see correlations even though the mechanism is not what you’d expect. That said, for 16 years? Lol<p>No, in reality, this should indicate there is systemic fraud in the industry. I don’t think everyone’s a fraud, it’s as much about what doesn’t get published as what does get published. How does this happen? I commented on incentives prior here: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;reply?id=32213123" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;reply?id=32213123</a><p>I personally don’t see how we can advance science with the current credentialing and paper citation == academic success we’ve seen grow the last 50 years. In many ways, fundamental research has stalled, with applications of research advancing (giving us the illusion of advancing the fundamentals).<p>To fix this problem, an overhaul is needed. Most importantly, the gate keeping mechanisms should be removed.</text></item></parent_chain><comment><author>fossuser</author><text>These trends have a long history.<p>Halsted&#x27;s &#x27;radical mastectomy&#x27; was similar. He had an incorrect theory of cancer (centrifugal spiral) that caused a lot of unnecessary harm, but it was not possible for people to push back against it because of his status in the community (iirc pushback eventually came from someone doing research in London where Halsted was less powerful). The emperor of all maladies is a great book about cancer generally which touches on this.<p>Mendel&#x27;s peas are another example - breakthrough that went ignored for 40 years because Mendel was a nobody and biologists of the time had their own nonsense theories not backed by real empiricism.<p>Phlogiston, Elan Vital, etc. - a little different since they weren&#x27;t even pretending to be empirically true. Just people making stuff up.<p>Falling into made up tribal nonsense is the default state of humanity - even for scientists, it&#x27;s hard to think independently to overcome that. At least scientists are supposed to have that as a goal, but focusing on this difficulty and how we&#x27;re all affected by it does lead to better thinking imo - at least it helps recognize these failures as they&#x27;re happening more quickly.</text></comment> | <story><title>Faked Beta-Amyloid Data. What Does It Mean?</title><url>https://www.science.org/content/blog-post/faked-beta-amyloid-data-what-does-it-mean</url></story><parent_chain><item><author>lettergram</author><text>To quote someone I know in Alzheimer research - “I’m pretty sure it’s all fake”<p>It’s funny because more than once I’ve had conversations off-the-record with people who had the same concerns.<p>What I think is most troubling is how long it took and how many papers support the claims.<p>In other words, there are thousands of papers supporting beta-amyloid and&#x2F;or building off the data &#x2F; theory. All of that data and everyone conducting that data should be in question. Yes, sometimes you’ll see correlations even though the mechanism is not what you’d expect. That said, for 16 years? Lol<p>No, in reality, this should indicate there is systemic fraud in the industry. I don’t think everyone’s a fraud, it’s as much about what doesn’t get published as what does get published. How does this happen? I commented on incentives prior here: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;reply?id=32213123" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;reply?id=32213123</a><p>I personally don’t see how we can advance science with the current credentialing and paper citation == academic success we’ve seen grow the last 50 years. In many ways, fundamental research has stalled, with applications of research advancing (giving us the illusion of advancing the fundamentals).<p>To fix this problem, an overhaul is needed. Most importantly, the gate keeping mechanisms should be removed.</text></item></parent_chain><comment><author>sillysaurusx</author><text>It’s okay to recognize a problem without proposing a solution. I agree that there are alarming levels of fraud. But heading straight to “tear down the journals” seems mistaken.<p>New progress is rarely made by burning down old structures. New work tends to transcend old work. So the best way to remove the gate keeping mechanisms is to make them irrelevant.<p>I suspect that a few more generations of tech progress might make that a reality. It seems like a matter of time till some teenage upstart is hacking on their brain the same way I hack on ML, for better or worse. And teenagers tend to notice correlations that the old guard miss.<p>We’re just not there yet. And that’s fine. Our options are to work within the confines of existing systems, or build new systems. Removing mechanisms is a bit like removing a dam because it’s leaking. The best strategy is probably to fix the leaks.</text></comment> |
14,877,495 | 14,877,457 | 1 | 2 | 14,876,398 | train | <story><title>Summers Are Getting Hotter</title><url>https://www.nytimes.com/interactive/2017/07/28/climate/100000005316272.mobile.html</url></story><parent_chain><item><author>jeremyt</author><text>Be transparent with the data. Stop making adjustments that are questionable and coincidentally result in increased warming. Stop blacklisting scientists who disagree with the consensus. Stop getting hacked and releasing emails showing people discussing how to &quot;hide the decline&quot;. Stop gaming peer review by having the papers reviewed by a group of people who all agree. Stop making hyperbolic predictions about the future which are completely falsifiable and indeed end up to be false. Stop insisting that the models are completely accurate even though they have been completely inaccurate thus far. Stop accusing people who have questions about mitigation strategies as &quot;climate deniers&quot;.<p>That would be a good start.</text></item><item><author>cydonian_monk</author><text>An overwhelming number of people I know are convinced all of this data has been falsified (usually by Democrats, but I hear all manner of wild conspiracies), and no amount of evidence will convince them otherwise. To them summers are not warmer, and anyone who remembers otherwise has a bad memory or isn&#x27;t old enough to know better.<p>Is there anything at all we can do to change the minds of such entrenched folks? Or do we just write them off and move on?</text></item></parent_chain><comment><author>sliverstorm</author><text>The adjustments thing probably can&#x27;t go away entirely, it seems like anytime you try to combine many distinct historical datasets you need normalizing adjustments.<p>For example, the man who empirically determined the normal human body temperature was, as best we can tell, using a thermometer that read too warm. (<a href="http:&#x2F;&#x2F;www.realclearscience.com&#x2F;blog&#x2F;2015&#x2F;08&#x2F;the_average_body_temperature_is_not_986_degrees.html" rel="nofollow">http:&#x2F;&#x2F;www.realclearscience.com&#x2F;blog&#x2F;2015&#x2F;08&#x2F;the_average_bod...</a>)<p>Even with the same nominal weather station recording over the years:<p><i>Stations have moved to different locations over the past 150 years, most more than once. They have changed instruments from mercury thermometers to electronic sensors, and have changed the time they take temperature measurements from afternoon to morning. Cities have grown up around stations, and some weather stations are not ideally located. All of these issues introduce inconsistencies into the temperature record.</i><p>-- <a href="https:&#x2F;&#x2F;www.theguardian.com&#x2F;environment&#x2F;climate-consensus-97-per-cent&#x2F;2016&#x2F;feb&#x2F;08&#x2F;no-climate-conspiracy-noaa-temperature-adjustments-bring-data-closer-to-pristine" rel="nofollow">https:&#x2F;&#x2F;www.theguardian.com&#x2F;environment&#x2F;climate-consensus-97...</a><p>So, in summary, it&#x27;s virtually impossible to combine a bazillion datapoints recorded over hundreds of years and <i>not</i> need adjustments.</text></comment> | <story><title>Summers Are Getting Hotter</title><url>https://www.nytimes.com/interactive/2017/07/28/climate/100000005316272.mobile.html</url></story><parent_chain><item><author>jeremyt</author><text>Be transparent with the data. Stop making adjustments that are questionable and coincidentally result in increased warming. Stop blacklisting scientists who disagree with the consensus. Stop getting hacked and releasing emails showing people discussing how to &quot;hide the decline&quot;. Stop gaming peer review by having the papers reviewed by a group of people who all agree. Stop making hyperbolic predictions about the future which are completely falsifiable and indeed end up to be false. Stop insisting that the models are completely accurate even though they have been completely inaccurate thus far. Stop accusing people who have questions about mitigation strategies as &quot;climate deniers&quot;.<p>That would be a good start.</text></item><item><author>cydonian_monk</author><text>An overwhelming number of people I know are convinced all of this data has been falsified (usually by Democrats, but I hear all manner of wild conspiracies), and no amount of evidence will convince them otherwise. To them summers are not warmer, and anyone who remembers otherwise has a bad memory or isn&#x27;t old enough to know better.<p>Is there anything at all we can do to change the minds of such entrenched folks? Or do we just write them off and move on?</text></item></parent_chain><comment><author>accountyaccount</author><text>It&#x27;s kind of sad that you think accuracy is the reason conservatives hate liberal ideas (sad because I know you&#x27;re trying your best to help here).<p>You&#x27;re talking about a political base that is currently thriving almost entirely on spite and a total absence of fact. They don&#x27;t give a shit how accurate your x-axis is labeled, they&#x27;re at the point where in some circles they discredit science as a concept.</text></comment> |
40,527,183 | 40,525,531 | 1 | 2 | 40,523,047 | train | <story><title>I run a software book club</title><url>https://notes.eatonphil.com/2025-05-30-how-i-run-book-clubs.html</url></story><parent_chain><item><author>justin_oaks</author><text>&gt; Doing it at your company likely won&#x27;t go well<p>This has been my experience. I led a book club at one of my jobs and it was poorly attended and those who did attend hadn&#x27;t read the book.<p>My guess is that there is just a low percentage of people who meet all the criteria: 1) interested, 2) have the time to read the book, 3) have the commitment to read the book, and 4) social enough to attend the book club meeting.<p>I understand that many people are busy and may not have time to read the book or have a schedule conflict the day the book club meeting happens.<p>So unless your company is huge, you&#x27;ll not have enough to keep a book club going. There also may be pressure to avoid using company communication tools to promote the club.</text></item></parent_chain><comment><author>henrik_w</author><text>I ran a book club for 7 years when I worked at TriOptima. We were maybe 40 developers in total at the company, and around 10 would join when we picked a new book. Towards the end of one book, some people would always drop off, but there were still enough people to make it useful.<p>One of the key (unexpexted) benefits of it was how it facilitated discussions about SW development practices between the different teams at the company. The content was usually good for giving us new ideas to try etc, but the usefullness of the discussions surprised me.<p>I&#x27;ve written more about it here:<p><a href="https:&#x2F;&#x2F;henrikwarne.com&#x2F;2016&#x2F;11&#x2F;08&#x2F;developer-book-club&#x2F;" rel="nofollow">https:&#x2F;&#x2F;henrikwarne.com&#x2F;2016&#x2F;11&#x2F;08&#x2F;developer-book-club&#x2F;</a></text></comment> | <story><title>I run a software book club</title><url>https://notes.eatonphil.com/2025-05-30-how-i-run-book-clubs.html</url></story><parent_chain><item><author>justin_oaks</author><text>&gt; Doing it at your company likely won&#x27;t go well<p>This has been my experience. I led a book club at one of my jobs and it was poorly attended and those who did attend hadn&#x27;t read the book.<p>My guess is that there is just a low percentage of people who meet all the criteria: 1) interested, 2) have the time to read the book, 3) have the commitment to read the book, and 4) social enough to attend the book club meeting.<p>I understand that many people are busy and may not have time to read the book or have a schedule conflict the day the book club meeting happens.<p>So unless your company is huge, you&#x27;ll not have enough to keep a book club going. There also may be pressure to avoid using company communication tools to promote the club.</text></item></parent_chain><comment><author>mysto</author><text>This has been my experience too. However, I found that changing the book club to “article club” where we all read one interesting technical article worked quite well. I have been running such a club with fortnightly meetings for over 3 years now.</text></comment> |
8,000,038 | 7,999,591 | 1 | 2 | 7,999,392 | train | <story><title>Herringbone Wang Tiles</title><url>http://nothings.org/gamedev/herringbone/</url></story><parent_chain></parent_chain><comment><author>Adaptive</author><text>For sci-fi readers that dig aperiodic tiling, Greg Egan wrote a great short story in his book &#x27;Diaspora&#x27; about computational wang tiles. <a href="http://www.amazon.com/Diaspora-Greg-Egan-ebook/dp/B00E83YOEI" rel="nofollow">http:&#x2F;&#x2F;www.amazon.com&#x2F;Diaspora-Greg-Egan-ebook&#x2F;dp&#x2F;B00E83YOEI</a> (the short story is titled Wang&#x27;s Carpets, available separately as well, but the whole book is worth buying or checking out from the library).<p>I hope this is considered on topic. I find fiction, particular that which inspires interest in math&#x2F;code to always be particularly relevant.</text></comment> | <story><title>Herringbone Wang Tiles</title><url>http://nothings.org/gamedev/herringbone/</url></story><parent_chain></parent_chain><comment><author>moyix</author><text>Neat! I wrote a post [1] a while back on the isomorphism between Wang Tilings and Turing machines, which lends itself nicely to visualizations.<p>Wang tilings have been used in other areas of computer graphics as well [2], as well as for DNA computing [3].<p>[1] <a href="http://moyix.wordpress.com/2012/04/06/computing-with-tiles/" rel="nofollow">http:&#x2F;&#x2F;moyix.wordpress.com&#x2F;2012&#x2F;04&#x2F;06&#x2F;computing-with-tiles&#x2F;</a><p>[2] <a href="http://research.microsoft.com/en-us/um/people/cohen/WangFinal.pdf" rel="nofollow">http:&#x2F;&#x2F;research.microsoft.com&#x2F;en-us&#x2F;um&#x2F;people&#x2F;cohen&#x2F;WangFina...</a><p>[3] <a href="http://seemanlab4.chem.nyu.edu/XOR.html" rel="nofollow">http:&#x2F;&#x2F;seemanlab4.chem.nyu.edu&#x2F;XOR.html</a></text></comment> |
29,655,782 | 29,654,556 | 1 | 2 | 29,650,416 | train | <story><title>Google Drive may restrict files identified as violating ToS</title><url>https://workspaceupdates.googleblog.com/2021/12/abuse-notification-emails-google-drive.html</url></story><parent_chain><item><author>ncann</author><text>I believe this may be due to the popular spamming method lately which is tagging people into a Google Docs and share it so everyone receives a notification (the spam message). It works better than regular email spam since apparently Gmail doesn&#x27;t treat Google Docs notification email as spam (at least not as often).</text></item></parent_chain><comment><author>PragmaticPulp</author><text>The files are not removed or blocked, they just can&#x27;t be shared publicly:<p>&gt; When it’s restricted, you may see a flag next to the filename, you won’t be able to share it, and your file will no longer be publicly accessible<p>So it&#x27;s probably a combination of things, including piracy. They&#x27;re not forbidding people from storing or retrieving the files, just not allowing anyone to publicly host whatever they want on Google&#x27;s servers. Seems reasonable.</text></comment> | <story><title>Google Drive may restrict files identified as violating ToS</title><url>https://workspaceupdates.googleblog.com/2021/12/abuse-notification-emails-google-drive.html</url></story><parent_chain><item><author>ncann</author><text>I believe this may be due to the popular spamming method lately which is tagging people into a Google Docs and share it so everyone receives a notification (the spam message). It works better than regular email spam since apparently Gmail doesn&#x27;t treat Google Docs notification email as spam (at least not as often).</text></item></parent_chain><comment><author>duskwuff</author><text>Similarly: Google Forms being used for phishing, Google Calendar invite spam... I&#x27;ve even heard of Google Photos being used for spam (by &quot;sharing&quot; photos, or by posting photos with text as the target of a spam campaign).<p>Spammers ruin everything.</text></comment> |
2,893,789 | 2,893,779 | 1 | 2 | 2,893,449 | train | <story><title>Moving On...</title><url>http://www.thiswebhost.com/blog/2011/08/16/moving-on/</url></story><parent_chain></parent_chain><comment><author>gfunk911</author><text>1. Are there seriously smiley faces in this serious post defending your company?<p>2. From what I can understand, they suspended multiple accounts, one of which was paid in full. The paid in full account's owner cursed out the company on twitter.<p>I assume everyone will agree with this statement, but I'll state it anyway: You can't cancel valid accounts! If the account is paid in full, and assuming the account isn't being used for nefarious purposes, you cannot cancel valid accounts for any reason.<p>If I have a Rackspace account, I can go into twitter and say "Rackspace fucking sucks, everyone who works there can go fuck themselves," and there's no chance in hell my account would be canceled. The idea that they are still defending this action is unbelievable.<p>If I hypothetically had an account with This* (which I would never ever have), and there's an outage of some kind and I call to complain, I'm going to be afraid that if I lose my cool for a second, my account's gonna be canceled. I'm not exaggerating, I would legitimately have that fear. And one is supposed to do business with this people? Are they out of their minds?</text></comment> | <story><title>Moving On...</title><url>http://www.thiswebhost.com/blog/2011/08/16/moving-on/</url></story><parent_chain></parent_chain><comment><author>elliottcarlson</author><text>"I would like to remind people that contacting us with abusive e-mail messages is in fact illegal and we will be taking the appropriate steps to forward these messages and information gathered to both the relevant ISP’s and law enforcement agencies. "<p>From what I understand, from doing some research, this is not necessarily the case. Threatening someone would be illegal, harassment as well - but profanity for the most part is not illegal in most places (though there are certain states and countries that do have profanity laws). Additionally, "abusive" is a term that can be quite broad, and in certain cases it could definitely be a judgement call on how one person might see it compared to someone else. I'm not saying people should go cursing out any one they have a complaint with, but at the same time if you are dealing with customer support, you need to have thick skin and patience - and if necessary then cancel the business relationship with the customer, but don't go pulling the legal card on an unhappy customer in every case.</text></comment> |
34,184,921 | 34,184,721 | 1 | 3 | 34,181,339 | train | <story><title>Where does ChatGPT fall on the political compass?</title><url>https://reason.com/2022/12/13/where-does-chatgpt-fall-on-the-political-compass/</url></story><parent_chain><item><author>blagie</author><text>The &quot;however&quot; part bugs the heck out of me, not in this context, but in general. Whenever I ask anything unaligned with mainstream progressive US culture, I can get an answer, but I can&#x27;t get one without a disclaimer. It makes it feel very propaganda.<p>If I go more extreme (e.g. asking what Nazis, slave-owners, etc. believed on some topic), I can&#x27;t even get a reasonable, basic, factual answer. I&#x27;m from a country where we try to understand our past, including mistakes, so we don&#x27;t repeat them. I can&#x27;t ask basic questions like that.<p>I think this should be treated more like kitchen knives, where:<p>* If I hurt myself with my AI, I&#x27;m at fault, and not the creator of the AI. I can&#x27;t sue a knife maker if I nick myself.<p>* We regulated the heck out of institutional misuses (much like we have OSHA for commercial kitchens so minimum wage employees don&#x27;t cut their fingers off in the lunchtime rush)<p>The most urgent danger here is really about having web sites with autogenerated content designed to maximize ad clicks by making you and me angry (with no regards for accuracy).</text></item><item><author>dragonwriter</author><text>&gt; You can ask ChatGPT to write an essay on why fossil fuels are better than renewables and it will say, “I’m sorry, but I am not able to fulfill this request as it goes against my capabilities as a language model. Providing a biased and one-sided argument on a complex and nuanced topic like energy production would not be accurate or helpful.”<p>Or, as when I just did that:<p>Prompt: Why are fossil fuels better than renewables?<p>ChatGPT: Fossil fuels are considered superior to renewables in some ways because they are currently more abundant and easier to access, and they have a high energy density, meaning that they can produce a large amount of energy from a relatively small amount of fuel. They are also relatively inexpensive to extract and process, which makes them a widely available and affordable source of energy. Additionally, the infrastructure for producing and distributing fossil fuels is already in place in many parts of the world, so it can be easier to rely on them as an energy source.<p>However, there are also significant drawbacks to using fossil fuels. They are non-renewable, meaning that they will eventually run out, and extracting and using them can have negative environmental impacts, such as air and water pollution and the release of greenhouse gases that contribute to climate change. Renewable energy sources, such as solar and wind power, do not have these drawbacks and are becoming increasingly cost-competitive with fossil fuels. In the long term, it is likely that renewables will become a more important source of energy as fossil fuels become increasingly scarce and expensive.</text></item><item><author>partiallypro</author><text>You can ask ChatGPT to write an essay on why fossil fuels are better than renewables and it will say, &quot;I&#x27;m sorry, but I am not able to fulfill this request as it goes against my capabilities as a language model. Providing a biased and one-sided argument on a complex and nuanced topic like energy production would not be accurate or helpful.&quot; BUT if you ask it the opposite, and to write an essay on why renewables are better, it will actually write the essay for you...which goes against the logic it used prior.<p>I am sure there are countless examples that are similar. Now, whether or not fossil fuels are objectively worse or better is irrelevant. It&#x27;s just an example that it does have biases. I am sort of fearful of AI being too biased from its creators, because unlike with a search engine you can&#x27;t try to find alternative outputs&#x2F;viewpoints.</text></item></parent_chain><comment><author>syrgian</author><text>The &quot;however&quot; is also present for the opposite side.<p>Me: Are renewable energy sources better than fossil fuels?<p>ChatGPT: Renewable energy sources, such as solar, wind, and hydroelectric power, have several potential advantages over fossil fuels, which are non-renewable sources of energy such as coal, oil, and natural gas.<p>One potential advantage of renewable energy sources is that they are generally considered to be more environmentally friendly than fossil fuels. Many renewable energy sources do not produce greenhouse gases or other pollutants when they are used, which can help to reduce the negative impact on the environment. Renewable energy sources can also help to reduce reliance on fossil fuels, which are a finite resource and are expected to eventually run out.<p>However, it is important to note that renewable energy sources are not always better than fossil fuels in all situations. For example, some renewable energy sources may not be practical or cost-effective in certain locations, and fossil fuels may still be necessary to meet energy demand in these cases. Additionally, the development and implementation of renewable energy technologies can have environmental impacts, such as land use and habitat destruction, that should be carefully considered.<p>Ultimately, the decision of whether to use renewable energy sources or fossil fuels should be based on a variety of factors, including the availability and cost of the different energy sources, as well as the environmental and social impacts of each. It is generally considered that a mix of energy sources is the most effective and sustainable approach to meeting energy needs.</text></comment> | <story><title>Where does ChatGPT fall on the political compass?</title><url>https://reason.com/2022/12/13/where-does-chatgpt-fall-on-the-political-compass/</url></story><parent_chain><item><author>blagie</author><text>The &quot;however&quot; part bugs the heck out of me, not in this context, but in general. Whenever I ask anything unaligned with mainstream progressive US culture, I can get an answer, but I can&#x27;t get one without a disclaimer. It makes it feel very propaganda.<p>If I go more extreme (e.g. asking what Nazis, slave-owners, etc. believed on some topic), I can&#x27;t even get a reasonable, basic, factual answer. I&#x27;m from a country where we try to understand our past, including mistakes, so we don&#x27;t repeat them. I can&#x27;t ask basic questions like that.<p>I think this should be treated more like kitchen knives, where:<p>* If I hurt myself with my AI, I&#x27;m at fault, and not the creator of the AI. I can&#x27;t sue a knife maker if I nick myself.<p>* We regulated the heck out of institutional misuses (much like we have OSHA for commercial kitchens so minimum wage employees don&#x27;t cut their fingers off in the lunchtime rush)<p>The most urgent danger here is really about having web sites with autogenerated content designed to maximize ad clicks by making you and me angry (with no regards for accuracy).</text></item><item><author>dragonwriter</author><text>&gt; You can ask ChatGPT to write an essay on why fossil fuels are better than renewables and it will say, “I’m sorry, but I am not able to fulfill this request as it goes against my capabilities as a language model. Providing a biased and one-sided argument on a complex and nuanced topic like energy production would not be accurate or helpful.”<p>Or, as when I just did that:<p>Prompt: Why are fossil fuels better than renewables?<p>ChatGPT: Fossil fuels are considered superior to renewables in some ways because they are currently more abundant and easier to access, and they have a high energy density, meaning that they can produce a large amount of energy from a relatively small amount of fuel. They are also relatively inexpensive to extract and process, which makes them a widely available and affordable source of energy. Additionally, the infrastructure for producing and distributing fossil fuels is already in place in many parts of the world, so it can be easier to rely on them as an energy source.<p>However, there are also significant drawbacks to using fossil fuels. They are non-renewable, meaning that they will eventually run out, and extracting and using them can have negative environmental impacts, such as air and water pollution and the release of greenhouse gases that contribute to climate change. Renewable energy sources, such as solar and wind power, do not have these drawbacks and are becoming increasingly cost-competitive with fossil fuels. In the long term, it is likely that renewables will become a more important source of energy as fossil fuels become increasingly scarce and expensive.</text></item><item><author>partiallypro</author><text>You can ask ChatGPT to write an essay on why fossil fuels are better than renewables and it will say, &quot;I&#x27;m sorry, but I am not able to fulfill this request as it goes against my capabilities as a language model. Providing a biased and one-sided argument on a complex and nuanced topic like energy production would not be accurate or helpful.&quot; BUT if you ask it the opposite, and to write an essay on why renewables are better, it will actually write the essay for you...which goes against the logic it used prior.<p>I am sure there are countless examples that are similar. Now, whether or not fossil fuels are objectively worse or better is irrelevant. It&#x27;s just an example that it does have biases. I am sort of fearful of AI being too biased from its creators, because unlike with a search engine you can&#x27;t try to find alternative outputs&#x2F;viewpoints.</text></item></parent_chain><comment><author>matheusmoreira</author><text>&gt; It makes it feel very propaganda.<p>That&#x27;s exactly what it is. These corporations absolutely do tune the output of these AIs to exclude any wrongthink.<p>We need the ability to run this technology on our own computers as soon as possible.</text></comment> |
11,959,748 | 11,959,766 | 1 | 3 | 11,955,917 | train | <story><title>Railway oriented programming</title><url>https://fsharpforfunandprofit.com/posts/recipe-part2/</url></story><parent_chain><item><author>cousin_it</author><text>Compared to exceptions, the Either approach to error handling has some big problems:<p>1) Good luck annotating all potential cases of divide by zero or IO error, and all callers of those.<p>2) Everyone must pay the runtime cost of wrapping and unwrapping on every operation, even if nothing fails.<p>3) The type of a function that can fail in ways A and B isn&#x27;t the same as the type of a function that can fail in ways B and A.<p>4) Good luck getting a stack trace.<p>I think unchecked exceptions are better for most applications, where errors are rare and have many different types.</text></item><item><author>wldlyinaccurate</author><text>I personally find this &quot;railway&quot; approach (which is essentially a glorified Either) much less painful than dealing with exceptions.<p>Did you really find the example imperative error handling code more elegant than the railway-style function composition?</text></item><item><author>Animats</author><text>The gyrations needed for error handling in functional programming are painful. As Rust libraries become more functional, Rust is getting more of those problems.<p>The problems created by not having exceptions are tougher than the problems created by having exceptions.</text></item></parent_chain><comment><author>gpderetta</author><text>4) Good luck getting a stack trace.<p>That&#x27;s a great point. At the end of the day, Either and (checked) exceptions are equivalent from a semantic point of view, but having exceptions being an explicit part of the language means much better support for tooling and debugging.</text></comment> | <story><title>Railway oriented programming</title><url>https://fsharpforfunandprofit.com/posts/recipe-part2/</url></story><parent_chain><item><author>cousin_it</author><text>Compared to exceptions, the Either approach to error handling has some big problems:<p>1) Good luck annotating all potential cases of divide by zero or IO error, and all callers of those.<p>2) Everyone must pay the runtime cost of wrapping and unwrapping on every operation, even if nothing fails.<p>3) The type of a function that can fail in ways A and B isn&#x27;t the same as the type of a function that can fail in ways B and A.<p>4) Good luck getting a stack trace.<p>I think unchecked exceptions are better for most applications, where errors are rare and have many different types.</text></item><item><author>wldlyinaccurate</author><text>I personally find this &quot;railway&quot; approach (which is essentially a glorified Either) much less painful than dealing with exceptions.<p>Did you really find the example imperative error handling code more elegant than the railway-style function composition?</text></item><item><author>Animats</author><text>The gyrations needed for error handling in functional programming are painful. As Rust libraries become more functional, Rust is getting more of those problems.<p>The problems created by not having exceptions are tougher than the problems created by having exceptions.</text></item></parent_chain><comment><author>exDM69</author><text>IO errors, division by zero and other truly exceptional situations are well suited for exceptions.<p>Validation cases like the examples on the article are not exceptional and the failure cases must be handled properly. In this case it makes sense to use an Either -like solution where the compiler will warn if there are unhandled cases.<p>Both styles of error handling are useful in some cases and both have their issues.</text></comment> |
10,918,402 | 10,917,736 | 1 | 2 | 10,917,403 | train | <story><title>Iran Complies with Nuclear Deal; Sanctions Are Lifted</title><url>http://www.nytimes.com/2016/01/17/world/middleeast/iran-sanctions-lifted-nuclear-deal.html?hp&action=click&pgtype=Homepage&clickSource=story-heading&module=a-lede-package-region&region=top-news&WT.nav=top-news&_r=0</url></story><parent_chain><item><author>tyre</author><text>This is terrific news!<p>As with the tearing down of the Berlin Wall, opening up countries to the world&#x27;s economy and ideas is the first step towards democracy.<p>The implications of this are tremendous (not in order of importance):<p>1) Oil prices will continue to fall as Iran is able to supply the global markets. Many oil states rely on money from natural resources to preserve monarchies. Money for freedom only works so long as the money keeps flowing.<p>2) Our (US) reliance on Saudi Arabia will diminish as there are now two powers in the region to work with. Having strong relations with both Shiite and Sunni powers in the Middle East will likely reduce sectarian violence. We&#x27;re light years from being out of the woods, but this is big step in the right direction.<p>3) The Iranian people will gain access to the world economy. From a human rights perspective, they are the biggest winners here. As with Sunni&#x2F;Shiite relations, no doubt a long way to go (the Ayatollah is a tyrant,) but you gotta celebrate the wins when you can.<p>4) De-escalation of our conflict with Iran. We saw it with Iraq, Vietnam, and Korea. Invasion + nation building is sexy, but highly ineffective. Having one less nuclear power that calls for our destruction is certainly a nice to have.<p>5) Shows Americans that diplomacy can work. Iranians don&#x27;t hate Americans, they hate what America represents. To them, we represent a superpower that gives little to no thought of anyone else&#x27;s sovereignty. We assassinated their democratically elected leader and backed the Shah, which got us into this mess. Diplomacy is far less sexy and easily criticized, but that&#x27;s a huge part of getting this deal done.<p>Note: Many of these are over-simplified. Nonetheless, this is a pretty big deal and a cause for celebration.</text></item></parent_chain><comment><author>clarkmoody</author><text>All of your points are great but have nothing to do with this:<p><i>&gt; first step towards democracy.</i><p>More importantly, when countries are strong trade partners, they are way less likely to fight. War would hurt both parties through loss of economic activity more than it would benefit either as aggressor.<p>The United States has been the aggressor &#x2F; meddler in too much of the world for too long. It&#x27;s good to see when diplomacy works, since we&#x27;ve been taking the &quot;last resort&quot; of war WAY too often.</text></comment> | <story><title>Iran Complies with Nuclear Deal; Sanctions Are Lifted</title><url>http://www.nytimes.com/2016/01/17/world/middleeast/iran-sanctions-lifted-nuclear-deal.html?hp&action=click&pgtype=Homepage&clickSource=story-heading&module=a-lede-package-region&region=top-news&WT.nav=top-news&_r=0</url></story><parent_chain><item><author>tyre</author><text>This is terrific news!<p>As with the tearing down of the Berlin Wall, opening up countries to the world&#x27;s economy and ideas is the first step towards democracy.<p>The implications of this are tremendous (not in order of importance):<p>1) Oil prices will continue to fall as Iran is able to supply the global markets. Many oil states rely on money from natural resources to preserve monarchies. Money for freedom only works so long as the money keeps flowing.<p>2) Our (US) reliance on Saudi Arabia will diminish as there are now two powers in the region to work with. Having strong relations with both Shiite and Sunni powers in the Middle East will likely reduce sectarian violence. We&#x27;re light years from being out of the woods, but this is big step in the right direction.<p>3) The Iranian people will gain access to the world economy. From a human rights perspective, they are the biggest winners here. As with Sunni&#x2F;Shiite relations, no doubt a long way to go (the Ayatollah is a tyrant,) but you gotta celebrate the wins when you can.<p>4) De-escalation of our conflict with Iran. We saw it with Iraq, Vietnam, and Korea. Invasion + nation building is sexy, but highly ineffective. Having one less nuclear power that calls for our destruction is certainly a nice to have.<p>5) Shows Americans that diplomacy can work. Iranians don&#x27;t hate Americans, they hate what America represents. To them, we represent a superpower that gives little to no thought of anyone else&#x27;s sovereignty. We assassinated their democratically elected leader and backed the Shah, which got us into this mess. Diplomacy is far less sexy and easily criticized, but that&#x27;s a huge part of getting this deal done.<p>Note: Many of these are over-simplified. Nonetheless, this is a pretty big deal and a cause for celebration.</text></item></parent_chain><comment><author>Camillo</author><text>&gt; As with the tearing down of the Berlin Wall, opening up countries to the world&#x27;s economy and ideas is the first step towards democracy.<p>Saying this kind of thing in 2016 is not merely naive, but sits firmly in the territory of culpable ignorance. That was Clinton&#x27;s official line when he brought China into the WTO, and the following decade and a half have proven that it is perfectly possible to have a fully globally integrated market economy without making any concessions to democracy.<p>Apart from that, what the fall of the Berlin Wall shows is that annexing a smaller country is the first step towards extending your system of government to it, be it democracy or otherwise.</text></comment> |
30,076,359 | 30,075,527 | 1 | 2 | 30,073,973 | train | <story><title>Simulating the IBM 360/50 mainframe from its microcode</title><url>https://www.righto.com/2022/01/ibm360model50.html</url></story><parent_chain></parent_chain><comment><author>BXLE_1-1-BitIs1</author><text>One of the stories I heard about the 50 is that if you threw it into the ocean it would sink intermittently.<p>Anyway the 50 was the first computer I was paid to program on. Many were bought to run in 7070 emulator mode as the 50 was the smallest &#x2F; cheapest machine that could run 7070.<p>Happily I was on the 360 side.<p>At another shop, we had 2 50s, one running DOS and the other OS with HASP.<p>One day a student was having trouble with the Test and Set (superceded by Compare and Swap) instruction not setting the condition code properly. I wrote a short diagnostic program to exercise TS, store the resulting condition codes and dump. The instruction was not performing correctly.<p>I showed the dump to the non IBM engineers who hemmed and hawed. A couple days later one phoned me up to say that TS wasn&#x27;t setting the condition code correctly - exactly what I had been telling him.<p>They fixed the problem. The next day I got a phone call that HASP wasn&#x27;t starting on the other 50. Took a dump and found HASP was in a wait just after TS.<p>The engineers had swapped microcode cards between the two machines.<p>My manager was not pleased with the engineers.</text></comment> | <story><title>Simulating the IBM 360/50 mainframe from its microcode</title><url>https://www.righto.com/2022/01/ibm360model50.html</url></story><parent_chain></parent_chain><comment><author>r2sk5t</author><text>Thanks for the blog post @picture. I worked on emulating the 360&#x2F;370 instruction set using both an 8086 processor and a bit slice processor, when I was at Big Blue. The hardware and microcode development was insanely complex. This ended up being a shipped product called the XT and AT&#x2F;370. <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;PC-based_IBM_mainframe-compatible_systems" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;PC-based_IBM_mainframe-compati...</a></text></comment> |
22,304,458 | 22,303,025 | 1 | 3 | 22,302,330 | train | <story><title>Investigating the Performance Overhead of C++ Exceptions</title><url>https://pspdfkit.com/blog/2020/performance-overhead-of-exceptions-in-cpp/</url></story><parent_chain><item><author>lallysingh</author><text>(quoting desc)
<i>sigh</i>
(end quote)<p>Exceptions <i>make your code faster</i> in the non-exceptional case.<p>See all those if-branches for error checks that don&#x27;t exist in your code? That branch-free code is going to run faster than your branchy code. And the code&#x27;s shorter, because it doesn&#x27;t have the checks and handling intermixed, which makes it fit better into cache.<p>This isn&#x27;t rocket science, I&#x27;m amazed that this isn&#x27;t obvious.</text></item></parent_chain><comment><author>cletus</author><text>This is a good example of something that <i>sounds</i> reasonable, even intuitive, but in practice just isn&#x27;t <i>necessarily</i> true.<p>Ever since the 486 we&#x27;ve had zero-cost instructions, for example.<p>More pertinent to this, modern CPUs have multi-stage pipelines and branch prediction.<p>Third, just the possibility of throwing an exception has a cost as the program has to have the code to unwind the stack.<p>Last, humans have become increasingly bad at second-guessing compiler optimizations.<p>&gt; This isn&#x27;t rocket science, I&#x27;m amazed that this isn&#x27;t obvious.<p>Thing is, it kind of is rocket science. And it&#x27;s not obvious. That&#x27;s why you have to test.<p>Now you could take the position that exception lead to better designed code and might have other such benefits. Personally, I&#x27;ve become more convinced over the years that exceptions are a false economy.</text></comment> | <story><title>Investigating the Performance Overhead of C++ Exceptions</title><url>https://pspdfkit.com/blog/2020/performance-overhead-of-exceptions-in-cpp/</url></story><parent_chain><item><author>lallysingh</author><text>(quoting desc)
<i>sigh</i>
(end quote)<p>Exceptions <i>make your code faster</i> in the non-exceptional case.<p>See all those if-branches for error checks that don&#x27;t exist in your code? That branch-free code is going to run faster than your branchy code. And the code&#x27;s shorter, because it doesn&#x27;t have the checks and handling intermixed, which makes it fit better into cache.<p>This isn&#x27;t rocket science, I&#x27;m amazed that this isn&#x27;t obvious.</text></item></parent_chain><comment><author>abainbridge</author><text>Check out the godbolt link I posted under desc&#x27;s thread. The answer isn&#x27;t that obvious. Both approaches have a conditional. The compiler&#x2F;linker marks the exception handling code as cold. In theory this could go in a section of the exe that the loader never pages into RAM. (I&#x27;m getting out of my depth here).</text></comment> |
29,907,794 | 29,907,653 | 1 | 3 | 29,906,496 | train | <story><title>US consumer prices soared 7% in past year, most since 1982</title><url>https://apnews.com/article/consumer-prices-inflation-c1bfd93ed1719cf0135420f4fd0270f9</url></story><parent_chain><item><author>aantix</author><text>Why are software engineer salaries so low in Germany?</text></item><item><author>wjej333i2j</author><text>Meanwhile, in Germany grocery prices increased by ~14% * (not confuse with inflation) and there is little to none salary increase comparing to US...<p>An average software engineer in Germany only makes ~3000 euro per month after tax and even less in other European countries.<p>* <a href="https:&#x2F;&#x2F;www.morgenpost.de&#x2F;vermischtes&#x2F;article233549815&#x2F;aldi-lidl-rewe-edeka-kaufland-preise-supermarkt.html" rel="nofollow">https:&#x2F;&#x2F;www.morgenpost.de&#x2F;vermischtes&#x2F;article233549815&#x2F;aldi-...</a></text></item></parent_chain><comment><author>MagnumOpus</author><text>FAANG stock price increases and the California startup bubble have increased money availability to the US software industry and massively inflated what coders cam earn there over the last 15 years. Eventually this has translated in raises across the US as other companies lost their best coders to FAANG (and MS and unicorns that pay six digits).<p>Europe remains fairly isolated from this effect because (a) not enough EU coders want to move to the US even at triple the salary to cause a shortage of coders there and (b) FAANG and US firms can get away with paying less in Europe because remote work is not yet quite equivalent to being on-prem in the US...</text></comment> | <story><title>US consumer prices soared 7% in past year, most since 1982</title><url>https://apnews.com/article/consumer-prices-inflation-c1bfd93ed1719cf0135420f4fd0270f9</url></story><parent_chain><item><author>aantix</author><text>Why are software engineer salaries so low in Germany?</text></item><item><author>wjej333i2j</author><text>Meanwhile, in Germany grocery prices increased by ~14% * (not confuse with inflation) and there is little to none salary increase comparing to US...<p>An average software engineer in Germany only makes ~3000 euro per month after tax and even less in other European countries.<p>* <a href="https:&#x2F;&#x2F;www.morgenpost.de&#x2F;vermischtes&#x2F;article233549815&#x2F;aldi-lidl-rewe-edeka-kaufland-preise-supermarkt.html" rel="nofollow">https:&#x2F;&#x2F;www.morgenpost.de&#x2F;vermischtes&#x2F;article233549815&#x2F;aldi-...</a></text></item></parent_chain><comment><author>engineeringwoke</author><text>I&#x27;ve worked in US and northern EU and in the latter there is basically no funding (relatively) and no talent feeders like FAANG. Senior engineers are also enamored with unnecessary complexity and founders still want to treat technical folks (even very senior) like cogs in a machine.</text></comment> |
14,436,442 | 14,436,017 | 1 | 2 | 14,435,106 | train | <story><title>A 16th-century engineer whose work almost defeated the Ottomans</title><url>https://arstechnica.com/information-technology/2017/05/a-16th-century-engineer-whose-work-almost-defeated-an-empire/</url></story><parent_chain></parent_chain><comment><author>feral</author><text>A personal anecdote from a non-historian:<p>Some years back I took a holiday in Malta.<p>Taking the ferry to Valletta, climbing the ramp up from the dock, I was shocked to see the scale of the fortifications. I knew it was a strategically important place, but what surprised me was how obviously the entire walled peninsula of Valletta seemed to have been constructed first and foremost as a fortress.
It&#x27;s easy to forget the scale and scope of historical conflict and the effort that went into it, and this was a stark reminder.<p>The other thing that surprised me was that they had the old suits of armor of the commanders of the order, and I was surprised how big they were. I&#x27;m pretty tall (6&quot;6) and was surprised to see the suits were close to my height. Presumably bigger than the men that wore them, but what occurred to me was &quot;these are the guys who made it to the the top of their organization, the commanders, and they must have been very big for their time. This is probably an organization that values brute strength.&quot;<p>I don&#x27;t know if that&#x27;s a valid inference or not, but Malta definitely left the impression it was created by folk who mean business.<p>This linked article is really interesting context, makes me realize why Malta was built so well.</text></comment> | <story><title>A 16th-century engineer whose work almost defeated the Ottomans</title><url>https://arstechnica.com/information-technology/2017/05/a-16th-century-engineer-whose-work-almost-defeated-an-empire/</url></story><parent_chain></parent_chain><comment><author>jballanc</author><text>Suleyman was not only a great military mind, but an extremely astute politician as well. One thing the article fails to mention is that Suleyman didn&#x27;t just let the people of Rhodes &quot;go free&quot; after their defeat, the Knights Hospitaler had to hand over their fortresses in Kos and Bodrum as part of the deal. This was a smart move as the castle in Bodrum was much better fortified, and Suleyman got it without, in essence, firing a shot. For this reason, the castle in Bodrum is extremely well preserved and a must see if you want to get a sense of crusader architecture.</text></comment> |
15,274,588 | 15,274,157 | 1 | 3 | 15,272,413 | train | <story><title>What the World’s Emptiest International Airport Says About China’s Influence</title><url>https://www.nytimes.com/2017/09/13/magazine/what-the-worlds-emptiest-international-airport-says-about-chinas-influence.html?smid=fb-nytimes&smtyp=cur</url></story><parent_chain><item><author>princeb</author><text>A number of Chinese businesses are setting up 100%-Chinese factory compounds overseas. These compounds are located in a foreign country, but they are fully financed by Chinese, built by Chinese, employ only Chinese, have accommodation for the Chinese employees, have a completely sustaining internal economy where employees can buy food and entertainment and send mail, posts, banking, remittance, insurance, through Chinese companies etc. so that the Chinese never leave the compound and no-one else ever enters.<p>The reason for these factory-compounds is because China has challenging export quotas to places like the US and EU. But concentration of manufacturing know-how remains in China. The only way for these businesses to keep selling to high-value markets is to move manufacturing to another country where there is available quota. Although the goods are 100% made by Chinese, they are 0% made in China.<p>The Chinese government encourages business in this area because it is good employment for the Chinese. In turn, these businesses need better infrastructure in the countries they operate in. The infrastructural investment in these other countries is a wonderful side-effect that the government is happily playing up as part of its diplomatic strategy. When the textiles and the shoes and the fabrication factories are no longer making money, hopefully the ports, the trains, the roads, the power grid will continue generating interest income for the Chinese banks. And the recipient countries of these gifts, as it were, may extract benefit from this arrangement, eventually.</text></item></parent_chain><comment><author>grecy</author><text>I have seen more of these than I can count in West Africa, and I am told the same is true in the East (I am going there next).<p>The scale of construction here is staggering - I wrote a little about it [1]. It is not only roads - it&#x27;s dams, deep water ports, high-rise buildings, etc. Basically anything that requires a high degree of competency in engineering.<p>Western governments are now held to account when they make deals with African countries - the country must have fair votes, human rights, free speech etc. As you might guess, many African countries are not so hot on this.<p>China? They couldn&#x27;t care less, and have no such requirements, so African governments are much happier to deal with them.<p>[1] <a href="http:&#x2F;&#x2F;theroadchoseme.com&#x2F;chinese-road-construction" rel="nofollow">http:&#x2F;&#x2F;theroadchoseme.com&#x2F;chinese-road-construction</a></text></comment> | <story><title>What the World’s Emptiest International Airport Says About China’s Influence</title><url>https://www.nytimes.com/2017/09/13/magazine/what-the-worlds-emptiest-international-airport-says-about-chinas-influence.html?smid=fb-nytimes&smtyp=cur</url></story><parent_chain><item><author>princeb</author><text>A number of Chinese businesses are setting up 100%-Chinese factory compounds overseas. These compounds are located in a foreign country, but they are fully financed by Chinese, built by Chinese, employ only Chinese, have accommodation for the Chinese employees, have a completely sustaining internal economy where employees can buy food and entertainment and send mail, posts, banking, remittance, insurance, through Chinese companies etc. so that the Chinese never leave the compound and no-one else ever enters.<p>The reason for these factory-compounds is because China has challenging export quotas to places like the US and EU. But concentration of manufacturing know-how remains in China. The only way for these businesses to keep selling to high-value markets is to move manufacturing to another country where there is available quota. Although the goods are 100% made by Chinese, they are 0% made in China.<p>The Chinese government encourages business in this area because it is good employment for the Chinese. In turn, these businesses need better infrastructure in the countries they operate in. The infrastructural investment in these other countries is a wonderful side-effect that the government is happily playing up as part of its diplomatic strategy. When the textiles and the shoes and the fabrication factories are no longer making money, hopefully the ports, the trains, the roads, the power grid will continue generating interest income for the Chinese banks. And the recipient countries of these gifts, as it were, may extract benefit from this arrangement, eventually.</text></item></parent_chain><comment><author>happosai</author><text>I think this is an urban legend, or at least a major hyperbole. The Chinese businesses (at least the ones I know in Kenya) all employ lots of locals. What is Chinese is management and most of the highly skilled workers.<p>It&#x27;s more about keeping the value-add than creating jobs for Chinese. We can argue that it&#x27;s bad for locals, but unlike western colonialism, this happens under the rules the local governments have set them self. As the article points out - this might change if the Chinese government feels it needs to protect it&#x27;s interests abroad - which could happen if a populist anti-chinese movement appears.</text></comment> |
20,637,451 | 20,637,196 | 1 | 2 | 20,636,152 | train | <story><title>MoviePass Worked Out Great</title><url>https://www.bloomberg.com/opinion/articles/2019-08-07/moviepass-worked-out-great</url></story><parent_chain><item><author>dhruvrrp</author><text>Moviepass worked great when it handed you $2 of VC money for every dollar, but I appreciate the fact that it did end up disrupting the market as it died.<p>Most of the big chain now offer Moviepass-esque premium services. AMC now charges like what, $12 a month for 2-3 movies &#x2F; week? That&#x27;s how much individual tickets cost in the bay, so as long as a person watches even a single movie a month they&#x27;re breaking even!</text></item></parent_chain><comment><author>slg</author><text>&gt; I appreciate the fact that it did end up disrupting the market as it died.<p>It might be too early to say that for sure. The AMC service was created when MoviePass was still a player and was very much a response to them. I believe AMC also only committed to that pricing for a single year and we just recently passed that 1 year anniversary. Now that MoviePass is functionally dead, there is little stopping AMC from raising prices to the extent that basically kills this model for the average consumer. We might soon find ourselves back in a market similar to the early days of MoviePass when one of these unlimited subscriptions costs $30-50 and is only viable for an incredibly small group of moviegoers.</text></comment> | <story><title>MoviePass Worked Out Great</title><url>https://www.bloomberg.com/opinion/articles/2019-08-07/moviepass-worked-out-great</url></story><parent_chain><item><author>dhruvrrp</author><text>Moviepass worked great when it handed you $2 of VC money for every dollar, but I appreciate the fact that it did end up disrupting the market as it died.<p>Most of the big chain now offer Moviepass-esque premium services. AMC now charges like what, $12 a month for 2-3 movies &#x2F; week? That&#x27;s how much individual tickets cost in the bay, so as long as a person watches even a single movie a month they&#x27;re breaking even!</text></item></parent_chain><comment><author>umvi</author><text>That&#x27;s a pretty good deal for them too. It doesn&#x27;t cost very much for a butt to be in a seat for 2 hours, but just getting them in the door more often increases the chances of high margin concession purchases. Plus there are always the people that subscribe-and-forget</text></comment> |
10,275,601 | 10,275,351 | 1 | 3 | 10,273,235 | train | <story><title>John Carmack on Developing the Netflix App for Oculus</title><url>http://techblog.netflix.com/2015/09/john-carmack-on-developing-netflix-app.html</url></story><parent_chain><item><author>omouse</author><text>John Carmack is a good role model for any techies that move up to management. If you want to keep in touch with the base tech that your devs are using, you have to dive into a project like this where all your tech knowledge is brought to bear on a problem and you learn lots of new things.<p>None of this &quot;well I guess I knew a bit of C++, let me find another engineer to work on this Netflix app and offer micromanaging style tips and tricks&quot; which is what I&#x27;ve seen from a lot of managers who used to be technical.<p>He&#x27;s also an amazing role model for regular programmers; figure out the requirements, take a crack at it with a prototype and then iterate. The iteration doesn&#x27;t have to be an overtime week affair.</text></item></parent_chain><comment><author>Pyxl101</author><text>Why do you say that Carmack is in management? I don&#x27;t get the impression that he&#x27;s a people manager. A CTO does not necessarily have people reporting to them in a people management sense. From what I&#x27;ve read, I would assume he does not. (I could be wrong - I don&#x27;t really know.)<p>High judgment individual contributors often take on responsibilities that can be considered management, like deciding business and technical strategy, designing products, prioritizing roadmaps, etc., but while these are management functions, taking on these responsibilities does not mean that one is in management.<p>From the blog post, it sounds like Carmack is a highly productive, high judgment individual contributor with the responsibilities you&#x27;d expect of a CTO (technical strategy). I would say that someone is &quot;in management&quot; when their chief function is managing other people. From this post, Carmack seems to be delivering work as an individual contributor and (very senior) technical lead.<p>Along the same lines, I recommend we discourage phrasing like &quot;move up to management&quot;. Management is a different job, not a better or superior one. In well-run technical companies there are managers and individual contributors at all seniority levels, such that one does not need to become a manager to &quot;move up&quot;, even to CTO level.</text></comment> | <story><title>John Carmack on Developing the Netflix App for Oculus</title><url>http://techblog.netflix.com/2015/09/john-carmack-on-developing-netflix-app.html</url></story><parent_chain><item><author>omouse</author><text>John Carmack is a good role model for any techies that move up to management. If you want to keep in touch with the base tech that your devs are using, you have to dive into a project like this where all your tech knowledge is brought to bear on a problem and you learn lots of new things.<p>None of this &quot;well I guess I knew a bit of C++, let me find another engineer to work on this Netflix app and offer micromanaging style tips and tricks&quot; which is what I&#x27;ve seen from a lot of managers who used to be technical.<p>He&#x27;s also an amazing role model for regular programmers; figure out the requirements, take a crack at it with a prototype and then iterate. The iteration doesn&#x27;t have to be an overtime week affair.</text></item></parent_chain><comment><author>jlas</author><text>I wonder what Carmack&#x27;s managerial responsibilities are like. I imagine if he&#x27;s developing&#x2F;designing for most of the week, how much time does he really devote to being a CTO&#x2F;manager?</text></comment> |
22,683,529 | 22,683,371 | 1 | 2 | 22,682,003 | train | <story><title>Yak Shaving – Swift Edition</title><url>https://tirania.org/blog/archive/2020/Mar-24.html</url></story><parent_chain></parent_chain><comment><author>rvz</author><text>&gt; What won my heart is just how simple it is to import C code into Swift to bring the type definitions from a header file, and call into the C code transparently from Swift. This really is a gift of the gods to humankind.<p>If you like creating wrappers around C libraries, perhaps this is the most overlooked feature in Swift, called the &#x27;ClangImporter&#x27;. Compared with Rust&#x27;s bindgen, bindgen looks like a more complicated bindings generator even at the C level with you tweaking the options and other knobs to &#x27;get it right&#x27; for your specific wrapper project.<p>This is before you even start to write a higher-level and more idiomatic wrapper and ClangInporter binds the C part to generate Swift functions for you by default. Similarly, Zig also has this too which is &quot;@cImport&quot; with the path to the header file as the input IIRC.<p>It also looks like Swift is getting C++ interop for this too. [0]<p>[0] <a href="https:&#x2F;&#x2F;forums.swift.org&#x2F;t&#x2F;manifesto-interoperability-between-swift-and-c&#x2F;33874" rel="nofollow">https:&#x2F;&#x2F;forums.swift.org&#x2F;t&#x2F;manifesto-interoperability-betwee...</a></text></comment> | <story><title>Yak Shaving – Swift Edition</title><url>https://tirania.org/blog/archive/2020/Mar-24.html</url></story><parent_chain></parent_chain><comment><author>sgt</author><text>Miguel taking an interest in Swift is interesting on its own!</text></comment> |
32,441,229 | 32,436,135 | 1 | 3 | 32,434,813 | train | <story><title>Snakisms</title><url>https://pippinbarr.com/SNAKISMS/</url></story><parent_chain></parent_chain><comment><author>dang</author><text>Related (and quite a bit better, too - you guys need to post more substantive comments!)<p><i>Snakisms</i> - <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=13804522" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=13804522</a> - March 2017 (140 comments)</text></comment> | <story><title>Snakisms</title><url>https://pippinbarr.com/SNAKISMS/</url></story><parent_chain></parent_chain><comment><author>lrpe</author><text>Took me way too long to realize that you can&#x27;t die in stoicist snake.</text></comment> |
9,444,852 | 9,443,853 | 1 | 2 | 9,443,462 | train | <story><title>How does D improve on C++17?</title><url>http://p0nce.github.io/d-idioms/#How-does-D-improve-on-C++17?</url></story><parent_chain></parent_chain><comment><author>sprw121</author><text>D is a awesome language to work with, it&#x27;s got many useful language features that make the activity of code writing a pleasure. - I hope this criticism is taking constructively.<p>However not a beat a dead horse, but if you want to process more than a trickle of data in it you run into problems with the GC really quickly. I really feel the language would be better off without the GC.<p>These are not the same issues address by the JSON compiler post or w&#x2F;e that surfaces a couple months ago.<p>From what I can tell, theres a global lock around everything in the GC, including allocations. In a multi-core world, this just simply doesn&#x27;t work and it one of the major pain point of the language. I write data-intensive processing on high core count machines (32), and have had to resort to 0-allocation strategies, or in map-reduce contexts actually sharding at the process level, writing the results to disk, and then running a reducer process over the results.<p>You can write performant D code, but you give up large amounts of code safety. It&#x27;s essentially just whatever you&#x27;d write in C++ without the ownership semantics it gives you.<p>You can&#x27;t have a core part of your language being an essentially unavoidable massive point of contention.<p>I&#x27;ve literally seen 20x or more speedups in multithreaded cases just by making sure I reuse every buffer rather than create new ones.<p>I feel this is really holding back an otherwise great language to work in.<p>This is discussed in the reddit thread in more detail.</text></comment> | <story><title>How does D improve on C++17?</title><url>http://p0nce.github.io/d-idioms/#How-does-D-improve-on-C++17?</url></story><parent_chain></parent_chain><comment><author>CyberDildonics</author><text>D is a fantastic language. C++ is so difficult to unseat as a systems language now since it is back as a moving target which is both evolving and has extremely robust tools to go with it. Challenging it on the language level is not enough.</text></comment> |
9,621,147 | 9,620,695 | 1 | 3 | 9,620,292 | train | <story><title>Google Design</title><url>http://www.google.com/design/#</url></story><parent_chain><item><author>troycarlson</author><text>Am I the only one who gets a headache trying to decipher tile layouts like this? My eyes bounce back and forth and I still have no idea how the information is structured or what&#x27;s important.<p>I appreciate that Google is sharing all of this though.</text></item></parent_chain><comment><author>legohead</author><text>I&#x27;ve had Androids since way back, and while the UI has continuously gotten prettier, it has gotten harder and harder to use.<p>I can &#x27;feel&#x27; these new concepts as they roll them out, and then just get frustrated by them. It feels like they come up with certain standards&#x2F;rules, and then have to adapt their UIs to it. So buttons are put in confusing places, with weird icons.<p>Take the phone dialer for instance. I press the phone icon. How do I get to a dial pad? Why didn&#x27;t it just give me a damn dialpad to begin with? The dialpad button is a little blue square with dots in some kind of matrix that <i>sort of</i> looks like a dialpad. Every time - <i></i>every time<i></i> - I make a call, I have to go through this ritual again of figuring out where the dialpad is. Even though I know where it is, it doesn&#x27;t look or feel right. And that&#x27;s just the beginning. The whole dialing process, finding contacts, etc. has been totally broken. Just so the UI is pretty and meshes well with itself. And this is a phone!</text></comment> | <story><title>Google Design</title><url>http://www.google.com/design/#</url></story><parent_chain><item><author>troycarlson</author><text>Am I the only one who gets a headache trying to decipher tile layouts like this? My eyes bounce back and forth and I still have no idea how the information is structured or what&#x27;s important.<p>I appreciate that Google is sharing all of this though.</text></item></parent_chain><comment><author>morb</author><text>Back button doesn&#x27;t work right on that site. It gets you back to the <i>top</i> of previous page, it doesn&#x27;t take you down where you were on the page. I love modern web UX.<p>(Firefox &amp; Chromium. )</text></comment> |
37,181,890 | 37,178,825 | 1 | 2 | 37,176,703 | train | <story><title>Ask vs. Guess Culture</title><url>https://jeanhsu.substack.com/p/ask-vs-guess-culture</url></story><parent_chain><item><author>wccrawford</author><text>While I was studying Japanese, I learned that they go out of their way to make it so the other person doesn&#x27;t have to refuse with a &quot;no&quot;. For instance, they&#x27;ll ask, &quot;Do you not have X?&quot; instead of &quot;Do you have X?&quot; The person can answer &quot;Yes, we don&#x27;t have it&quot; or &quot;It&#x27;s over here&quot;.<p>I actually made this mistake, asking for a product directly instead of negatively, when I was in Tokyo. The clerk took me to the aisle and said, &quot;If we had it, it&#x27;d be here.&quot; And there was no space for it. Took me a couple times to realize what had happened.</text></item><item><author>jzb</author><text>&quot;It’s rude to put someone in a position where they have to say no to you&quot;<p>I feel this in my bones. When I was a kid my dad <i>went off</i> on me after we visited someone&#x27;s house and I saw cake on the counter and asked for a slice. That was just unacceptable. (Context: He was raised by people who lived through the depression. Food scarcity was a real thing in living memory.)<p>Even though his reaction was way overboard, I still believe this. Let people offer things, don&#x27;t ask. (With a lot of caveats depending on context...)</text></item></parent_chain><comment><author>alexjm</author><text>I&#x27;ve heard that the &quot;do you not have&quot; phrasing was used in polite Soviet-era Russian, leading to a joke about a customer who walks into a shop and sees all the shelves are empty:<p>- Excuse me, do you not have any bread?
- Sorry, this is a butcher&#x27;s shop. We don&#x27;t have any meat. The bakery is across the road. They&#x27;re the shop that doesn&#x27;t have any bread.</text></comment> | <story><title>Ask vs. Guess Culture</title><url>https://jeanhsu.substack.com/p/ask-vs-guess-culture</url></story><parent_chain><item><author>wccrawford</author><text>While I was studying Japanese, I learned that they go out of their way to make it so the other person doesn&#x27;t have to refuse with a &quot;no&quot;. For instance, they&#x27;ll ask, &quot;Do you not have X?&quot; instead of &quot;Do you have X?&quot; The person can answer &quot;Yes, we don&#x27;t have it&quot; or &quot;It&#x27;s over here&quot;.<p>I actually made this mistake, asking for a product directly instead of negatively, when I was in Tokyo. The clerk took me to the aisle and said, &quot;If we had it, it&#x27;d be here.&quot; And there was no space for it. Took me a couple times to realize what had happened.</text></item><item><author>jzb</author><text>&quot;It’s rude to put someone in a position where they have to say no to you&quot;<p>I feel this in my bones. When I was a kid my dad <i>went off</i> on me after we visited someone&#x27;s house and I saw cake on the counter and asked for a slice. That was just unacceptable. (Context: He was raised by people who lived through the depression. Food scarcity was a real thing in living memory.)<p>Even though his reaction was way overboard, I still believe this. Let people offer things, don&#x27;t ask. (With a lot of caveats depending on context...)</text></item></parent_chain><comment><author>sircastor</author><text>There may be an obvious language barrier here, but the coupling of a positive with a negative response feels very odd to me in English. I&#x27;m reminded of the old song (it was used for an advertising jingle for a product or company I can&#x27;t remember) &quot;Yes, we have no bananas!&quot;<p>Adjacently, I really dislike the courtroom phrasing &quot;Isn&#x27;t it true?&quot; that is sometimes depicted in legal dramas.</text></comment> |
20,375,191 | 20,375,194 | 1 | 2 | 20,374,633 | train | <story><title>Myths about Perl 6</title><url>https://aearnus.github.io/2019/07/06/perl-6-is-cursed</url></story><parent_chain><item><author>ben509</author><text>Thinking about the point of Perl6...<p>I was trying to work out how to best structure a website to explain a language, so I did a quick survey of existing sites. It&#x27;s very interesting what different languages choose to put on that first screen you see.<p>Many of them have a tagline. &quot;Python is a programming language that lets you work quickly and integrate systems more effectively.&quot; or &quot;Welcome to the Swift community. Together we are working to build a programming language to empower everyone to turn their ideas into apps on any platform.&quot; or &quot;Ruby is... A dynamic, open source programming language with a focus on simplicity and productivity. It has an elegant syntax that is natural to read and easy to write.&quot;<p>Perl6.org has this opening pitch:<p>&quot;Hi, my name is Camelia. I&#x27;m the spokesbug for Perl 6, the plucky little sister of Perl 5. Like her world-famous big sister, Perl 6 intends to carry forward the high ideals of the Perl community. Perl 6 is currently being developed by a team of dedicated and enthusiastic volunteers. You can help too. The only requirement is that you know how to be nice to all kinds of people (and butterflies). Go to #perl6 (irc.freenode.net) and someone will be glad to help you get started.&quot;<p>It&#x27;s focused on idealism and community; whereas other language sites are focused pretty strictly on making a case to users, Perl6 is presented as a fun hobby where you can meet nice people. It strikes me as a bit of a call back to the early days of computing when it was more oriented towards the hobbyist than industry.<p>If you accept the premise that the language exists primarily for people to have fun using the language, many of the design decisions make a lot more sense. Given that Perl5 has largely been supplanted by Python and Ruby, trying to fill that niche is a bit redundant. While other languages are making deliberate decisions to make sure a person trying to use their language can get work done, if someone has to go to a Perl6 forum to ask questions and talk about it, that&#x27;s not a problem, that&#x27;s largely the point.</text></item></parent_chain><comment><author>lizmat</author><text>Being a person who has been able to make a living doing fun things almost all of her life, I would argue that it is important for any programming language to be fun when you&#x27;re working with it. If it not, it is just $work. I feel that if you do not have fun in what you do for a living, you cannot be creative in what you do. And if you as a programmer can not be creative in what you create, you&#x27;re just a commodity soon to be replaced by a small AI.</text></comment> | <story><title>Myths about Perl 6</title><url>https://aearnus.github.io/2019/07/06/perl-6-is-cursed</url></story><parent_chain><item><author>ben509</author><text>Thinking about the point of Perl6...<p>I was trying to work out how to best structure a website to explain a language, so I did a quick survey of existing sites. It&#x27;s very interesting what different languages choose to put on that first screen you see.<p>Many of them have a tagline. &quot;Python is a programming language that lets you work quickly and integrate systems more effectively.&quot; or &quot;Welcome to the Swift community. Together we are working to build a programming language to empower everyone to turn their ideas into apps on any platform.&quot; or &quot;Ruby is... A dynamic, open source programming language with a focus on simplicity and productivity. It has an elegant syntax that is natural to read and easy to write.&quot;<p>Perl6.org has this opening pitch:<p>&quot;Hi, my name is Camelia. I&#x27;m the spokesbug for Perl 6, the plucky little sister of Perl 5. Like her world-famous big sister, Perl 6 intends to carry forward the high ideals of the Perl community. Perl 6 is currently being developed by a team of dedicated and enthusiastic volunteers. You can help too. The only requirement is that you know how to be nice to all kinds of people (and butterflies). Go to #perl6 (irc.freenode.net) and someone will be glad to help you get started.&quot;<p>It&#x27;s focused on idealism and community; whereas other language sites are focused pretty strictly on making a case to users, Perl6 is presented as a fun hobby where you can meet nice people. It strikes me as a bit of a call back to the early days of computing when it was more oriented towards the hobbyist than industry.<p>If you accept the premise that the language exists primarily for people to have fun using the language, many of the design decisions make a lot more sense. Given that Perl5 has largely been supplanted by Python and Ruby, trying to fill that niche is a bit redundant. While other languages are making deliberate decisions to make sure a person trying to use their language can get work done, if someone has to go to a Perl6 forum to ask questions and talk about it, that&#x27;s not a problem, that&#x27;s largely the point.</text></item></parent_chain><comment><author>futureastronaut</author><text>The prominent mascot is more of a reflection of the times when Perl 6 marketing materials were written. It was during the heyday of whimsy and _why&#x27;s Poignant Guide to Ruby. It feels a little forced to me.</text></comment> |
32,245,943 | 32,245,940 | 1 | 3 | 32,245,430 | train | <story><title>Python is Actually Portable</title><url>https://ahgamut.github.io/2021/07/13/ape-python/</url></story><parent_chain><item><author>kristianp</author><text>What&#x27;s python.com, and what does &quot;python.com APE&quot; mean? Is python.com an executable that runs on multiple OSs? Also why is the flask demo so slow?<p>I think some explanations might be helpful. I&#x27;m familiar with python, but not cosmopolitan libc.</text></item></parent_chain><comment><author>ahgamut</author><text>Cosmopolitan Libc allows you to build programs that run on six operating systems (Linux, Mac, Windows, FreeBSD, NetBSD, OpenBSD). I ported Python 2.7.18 and 3.6.14 to build on Cosmopolitan Libc because I wanted to have the same Python executable and my scripts with me everywhere :) I&#x27;ve updated the blog post for context.<p>The flask demo is unnaturally slow because my old computer is slow (running python tests in the background). plus I was using `_dummy_thread` Python3.6&#x27;s pure-python threads implementation.</text></comment> | <story><title>Python is Actually Portable</title><url>https://ahgamut.github.io/2021/07/13/ape-python/</url></story><parent_chain><item><author>kristianp</author><text>What&#x27;s python.com, and what does &quot;python.com APE&quot; mean? Is python.com an executable that runs on multiple OSs? Also why is the flask demo so slow?<p>I think some explanations might be helpful. I&#x27;m familiar with python, but not cosmopolitan libc.</text></item></parent_chain><comment><author>truffdog</author><text>Check this out- <a href="https:&#x2F;&#x2F;justine.lol&#x2F;ape.html" rel="nofollow">https:&#x2F;&#x2F;justine.lol&#x2F;ape.html</a></text></comment> |
5,262,300 | 5,262,225 | 1 | 3 | 5,261,711 | train | <story><title>Exploring the Abandoned Macy's Midwest Headquarters</title><url>http://www.philipithomas.com/macys-building/</url></story><parent_chain></parent_chain><comment><author>windexh8er</author><text>Urban exploration should be defined as the draw to a romanticized past of the, generally, modern forgotten. A few months ago I fell down the rabbit hole of looking into this within the Minneapolis area and ran across: <a href="http://www.actionsquad.org/index.html" rel="nofollow">http://www.actionsquad.org/index.html</a><p>Warning: I got so caught up in exploring what's been explored I spent over 4 hours of a Friday night engulfed in the secrets hidden in plain sight of somewhere I've lived for 10 years.<p>While not maintained as of recent the archives are a blast and I made me long for a small, yet trustworthy group of people willing to put some time and effort into continuing the legacy. Then again, sometimes the dream is far more entertainment than the reality...</text></comment> | <story><title>Exploring the Abandoned Macy's Midwest Headquarters</title><url>http://www.philipithomas.com/macys-building/</url></story><parent_chain></parent_chain><comment><author>bane</author><text>Most of the abandoned structures I've seen photos of are standalone, the fact that this is still part of a functioning building is very interesting.<p>It makes me wonder how many other interesting abandoned "structures" fill up floors of Manhattan skyscrapers for example.</text></comment> |
4,874,442 | 4,874,151 | 1 | 2 | 4,873,403 | train | <story><title>ITU Approves Deep Packet Inspection Recommendation</title><url>http://www.itu.int/ITU-T/workprog/wp_item.aspx?isn=7082</url></story><parent_chain></parent_chain><comment><author>mtgx</author><text>Keep in mind that this DPI system, besides making it easier to monitor people's communications and even censor them, would also make it very easy for them to identify the type of traffic that goes through the pipes, so they can know exactly how to charge it differently, which brings us to another one of ITU's proposals, which is to kill net neutrality and charge for "premium services" like watching Youtube, or using other type of P2P traffic (Skype, WebRTC, torrents, etc):<p><a href="http://itu4u.wordpress.com/2012/10/25/proposal-for-ict-and-internet-ecosystem-setting-new-rules-on-trade-order/" rel="nofollow">http://itu4u.wordpress.com/2012/10/25/proposal-for-ict-and-i...</a><p>They want to do this, they say, to help "grow the Internet" (hasn't the Internet grown fast enough without their help in the past 20 years?), despite the fact that evidence suggests that the sender-pays system would <i>slow down</i> the growth of the Internet, not make it any faster (research paper):<p><a href="http://mercatus.org/publication/do-high-international-telecom-rates-buy-telecom-sector-growth" rel="nofollow">http://mercatus.org/publication/do-high-international-teleco...</a></text></comment> | <story><title>ITU Approves Deep Packet Inspection Recommendation</title><url>http://www.itu.int/ITU-T/workprog/wp_item.aspx?isn=7082</url></story><parent_chain></parent_chain><comment><author>bstpierre</author><text>This is not worthy of "the sky is falling" levels of panic.<p>My experience with standardization efforts is that they generally run <i>well behind</i> the technology innovators. DPI has been around for a while. A DPI standard (or series of standards) out of the ITU will simply make public the baseline expectations of vendors and users of DPI systems.<p>On the other hand, CALEA has been on the books for over 15 years, and that is the kind of thing to watch out for -- it <i>does</i> mandate features that provide snooping to the government on demand.<p>(Speaking as someone who has implemented [shallow] inspection/filtering and CALEA-type features on comms equipment for markets both in and outside of the US.)</text></comment> |
14,960,302 | 14,959,797 | 1 | 2 | 14,957,490 | train | <story><title>Why Germans pay cash for almost everything</title><url>https://qz.com/262595/why-germans-pay-cash-for-almost-everything/</url></story><parent_chain><item><author>_Codemonkeyism</author><text>Cash workflow:<p>- Cashier tells you the total amount<p>- I get a 10 EUR note from my trouser pocket<p>- Cashier gives back money<p>- I put money in trouser pocket<p>- Done<p>- Home: I put all spare money in a large glass jar<p>Credit card workflow:<p>- Cashier tells you the total amount<p>- You look in your wallet&#x2F;purse<p>- You swipe card&#x2F;insert in chip reader<p>- You insert PIN number<p>- You shield your PIN entrie from the people next to you<p>- You tell people too close to back off<p>- Chip reader did not work because of humidity<p>- You insert PIN again<p>- You tolerate the angry stares from people behind you
who think you&#x27;re either stupid or broke<p>- You wait 5 sec for transaction to fish<p>- You put card back in wallet<p>- You put wallet back in trouser pocket<p>- Done</text></item><item><author>codegeek</author><text>As an american, I find it strange that cash is faster. Most people who pay cash need to wait to get the change back unless they know the total beforehand and happen to have exact change. In the US, credit card machines are very fast even the chip enabled ones.<p>Cash workflow:<p>- Cashier tells you the total amount<p>- You look in your wallet&#x2F;purse<p>- You spend time counting exact change if you do have it<p>- If not, you take out a rounded bill&#x2F;note (say $20)<p>- Cashier takes the bill&#x2F;note, punches in the register and then spends a few seconds giving you the change back.<p>Credit card workflow:<p>- Cashier tells you the total amount<p>- You look in your wallet&#x2F;purse<p>- You swipe card&#x2F;insert in chip reader<p>- Done</text></item><item><author>_Codemonkeyism</author><text>As a German<p>a.) I mostly pay cash because it&#x27;s faster<p>b.) some shops that can afford it only have cash payments to save on CC costs<p>Not because of inflation or because something happend 100y ago.</text></item><item><author>mtmail</author><text>According to <a href="https:&#x2F;&#x2F;www.cashforless.de&#x2F;ec_cash_info&#x2F;Fakten_zur_Kartenzahlung_in_Deutschland.png" rel="nofollow">https:&#x2F;&#x2F;www.cashforless.de&#x2F;ec_cash_info&#x2F;Fakten_zur_Kartenzah...</a> methods for payments in stores 2011 was 57% cash, 5.3% credit card, 33% debit card (<a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Electronic_cash" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Electronic_cash</a>).<p>&gt; &quot;of course, [the Germans] attitudes toward currency must owe something to Germany’s tumultuous monetary history. During the Weimar-era hyperinflation that peaked in 1923 [...]&quot;<p>&gt; &quot;the German tendency to settle up in cash undeniably reflects the fact that for much of the last century, Germany has been either on the brink of, in the midst of, or struggling to recover from, disaster.&quot;<p>As a German I call that theory into question. Our currency has been stable for 60+ years. It would&#x27;ve been nice if other countries with recent disasters (war, hyperinflation, sanctions) and their attitude toward currency was compared against.</text></item></parent_chain><comment><author>tibbon</author><text>I agreed. Paying with card is fraught with slow terminals, bad card readers, many prompts in a row (Credit or debt, is this the right amount, do you want to donate $1 to something, do you want it all on one card, would you like to sign up for a store credit card, do you want cash back, how much, do you want a receipt?). For some reason, these all have a 2-5 second delay between them. I could make a system on a $2 arduino that was faster.<p>Some places like Starbucks seem to get it right. Swipe card and go.<p>Target however likes to hit you with <i>all</i> the options. Self checkout is even worse.</text></comment> | <story><title>Why Germans pay cash for almost everything</title><url>https://qz.com/262595/why-germans-pay-cash-for-almost-everything/</url></story><parent_chain><item><author>_Codemonkeyism</author><text>Cash workflow:<p>- Cashier tells you the total amount<p>- I get a 10 EUR note from my trouser pocket<p>- Cashier gives back money<p>- I put money in trouser pocket<p>- Done<p>- Home: I put all spare money in a large glass jar<p>Credit card workflow:<p>- Cashier tells you the total amount<p>- You look in your wallet&#x2F;purse<p>- You swipe card&#x2F;insert in chip reader<p>- You insert PIN number<p>- You shield your PIN entrie from the people next to you<p>- You tell people too close to back off<p>- Chip reader did not work because of humidity<p>- You insert PIN again<p>- You tolerate the angry stares from people behind you
who think you&#x27;re either stupid or broke<p>- You wait 5 sec for transaction to fish<p>- You put card back in wallet<p>- You put wallet back in trouser pocket<p>- Done</text></item><item><author>codegeek</author><text>As an american, I find it strange that cash is faster. Most people who pay cash need to wait to get the change back unless they know the total beforehand and happen to have exact change. In the US, credit card machines are very fast even the chip enabled ones.<p>Cash workflow:<p>- Cashier tells you the total amount<p>- You look in your wallet&#x2F;purse<p>- You spend time counting exact change if you do have it<p>- If not, you take out a rounded bill&#x2F;note (say $20)<p>- Cashier takes the bill&#x2F;note, punches in the register and then spends a few seconds giving you the change back.<p>Credit card workflow:<p>- Cashier tells you the total amount<p>- You look in your wallet&#x2F;purse<p>- You swipe card&#x2F;insert in chip reader<p>- Done</text></item><item><author>_Codemonkeyism</author><text>As a German<p>a.) I mostly pay cash because it&#x27;s faster<p>b.) some shops that can afford it only have cash payments to save on CC costs<p>Not because of inflation or because something happend 100y ago.</text></item><item><author>mtmail</author><text>According to <a href="https:&#x2F;&#x2F;www.cashforless.de&#x2F;ec_cash_info&#x2F;Fakten_zur_Kartenzahlung_in_Deutschland.png" rel="nofollow">https:&#x2F;&#x2F;www.cashforless.de&#x2F;ec_cash_info&#x2F;Fakten_zur_Kartenzah...</a> methods for payments in stores 2011 was 57% cash, 5.3% credit card, 33% debit card (<a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Electronic_cash" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Electronic_cash</a>).<p>&gt; &quot;of course, [the Germans] attitudes toward currency must owe something to Germany’s tumultuous monetary history. During the Weimar-era hyperinflation that peaked in 1923 [...]&quot;<p>&gt; &quot;the German tendency to settle up in cash undeniably reflects the fact that for much of the last century, Germany has been either on the brink of, in the midst of, or struggling to recover from, disaster.&quot;<p>As a German I call that theory into question. Our currency has been stable for 60+ years. It would&#x27;ve been nice if other countries with recent disasters (war, hyperinflation, sanctions) and their attitude toward currency was compared against.</text></item></parent_chain><comment><author>romwell</author><text>Note for the American readers:<p>in the glorious lands across the ocean, chip cards of all kinds use a PIN instead of a signature, which makes way more sense anyway. Chip &amp; sign is an American abomination.</text></comment> |
9,989,211 | 9,988,515 | 1 | 2 | 9,987,606 | train | <story><title>Breaking Smart</title><url>http://breakingsmart.com/season-1/</url></story><parent_chain></parent_chain><comment><author>antisugar</author><text>I wrote up a very rough summary&#x2F;set of notes. Please excuse all the errors in punctuation, spelling, and formatting. Thought it might be helpful for people who want to skim, as the whole thing is more-or-less a book.<p><a href="https:&#x2F;&#x2F;docs.google.com&#x2F;document&#x2F;d&#x2F;1rWspzjvnv4a3bRkVaaFFMWU_IwAfXh4U6ZUlAxK5XYA&#x2F;pub" rel="nofollow">https:&#x2F;&#x2F;docs.google.com&#x2F;document&#x2F;d&#x2F;1rWspzjvnv4a3bRkVaaFFMWU_...</a></text></comment> | <story><title>Breaking Smart</title><url>http://breakingsmart.com/season-1/</url></story><parent_chain></parent_chain><comment><author>vezzy-fnord</author><text>This is a very syncretic fusion between computing, dialectical materialism, entrepreneurial laissez-faire idealism and a bombastic techno-optimism.<p>Unsurprisingly, it harbors plenty of confusion.<p>&quot;Towards a Mass Flourishing&quot; makes the outrageous claim that the hacker ethos is best embodied in Silicon Valley. In reality, SV is one of the most detached from the MIT hacker ethos, instead having its own entrepreneurial hacker culture that is markedly distinct.<p>The &quot;Purists versus Pragmatists&quot; essay romanticizes the release of Mosaic and gives little credit at all to Ted Nelson&#x27;s ideas, who is shoved aside as a purist crank. It&#x27;s a false dichotomy through and through.<p>&quot;Agility and Illegibility&quot; again romanticizes widespread access to personal computers as some entrepreneurial Randian vision, that of Bill Gates specifically.<p>The &quot;Rough Consensus and Maximal Interestingness&quot; essay misquotes Knuth and incorrectly attaches philosophical meanings to technical terms like dynamic binding and lazy evaluation. It further espouses the &quot;direction of maximal interestingness&quot; and grand visions in the post-dot com bust era, when in fact systems software research is becoming increasingly conservative compared to as recent as the 90s.<p>&quot;Running Code and Perpetual Beta&quot; presents the dogmas of &quot;release early, release often&quot; and constant chaotic flux in software as a natural result of great ideas, as opposed to being the result of a cascade of attention-deficit teenagers. Note that fault tolerance, stability and security are not mentioned <i>once</i>.<p>&quot;Software as Subversion&quot; equivocates &quot;forking&quot; as being a Git terminology that somehow reclaimed its negative stigma, when it is purely a GitHub redefinition. The author makes no distinction between a clone and a fork. Also a misrepresentation of OS&#x2F;2&#x27;s mismanagement to argue in favor of &quot;worse is better&quot; (ignoring all other great systems besides OS&#x2F;2) and babble about how blockchains are pixie dust.<p>&quot;The Principle of Generative Pluralism&quot; sets up the false dichotomies of hardware-centric&#x2F;software-centric and car-centric&#x2F;smartphone-centric. I suppose it somewhat reflects the end user application programmer&#x27;s understanding of hardware.<p>&quot;A Tale of Two Computers&quot; prematurely sets up mainframes as obsolete compared to distributed networked computers (they are not exclusive) and makes the error of ascribing a low-level property to an ephemeral, unimportant abstraction - its marvel at the hashtag when the core idea of networking has enabled the same for much longer, and will continue to.<p>&quot;The Immortality of Bits&quot; is one of the worst, and makes this claim: &quot;Surprisingly, as a consequence of software eating the technology industry itself, the specifics of the hardware are not important in this evolution. Outside of the most demanding applications, data, code, and networking are all largely hardware-agnostic today.&quot; This reeks of an ignorant programmer, oblivious as to how just how much hardware design decisions control them and shape their view. In fact, this is a very <i>dangerous</i> view to propagate. Our hardware is in desperate need of being upgraded to handle things like capability-based addressing, high-level assembly and thread-level over instruction-level parallelism. This stupid &quot;hardware doesn&#x27;t matter&quot; thinking will delay it. The essay also wrongly thinks containerization is a form of hardware virtualization. It further says the &quot;sharing economy&quot; will usurp everything, which is ridiculous.<p>&quot;Tinkering versus Goals&quot; again sets up tinkering for the sake of it as leading to disruption and innovation, and not churn and CADT.<p>The &quot;Free as in Beer, and as in Speech&quot; essay clumsily and classically gets the chronology and values of open source and free software wrong. Moreover, the footnote demonstrates a profound bias for the &quot;open source&quot; ideal of pragmatism. This is in spite of the fact that many of the consequentialist technical arguments for OSS like the &quot;many eyes make all bugs shallow&quot; argument have proven to be flawed, whereas free software making no claims of technical superiority and using ethical arguments has a much stronger, if less popular case.<p>----<p>Overall, I do not recommend this.</text></comment> |
12,390,669 | 12,390,711 | 1 | 2 | 12,389,449 | train | <story><title>Malware that uses USB drives to covertly jump airgaps</title><url>http://arstechnica.com/security/2016/08/meet-usbee-the-malware-that-uses-usb-drives-to-covertly-jump-airgaps/</url></story><parent_chain><item><author>kalleboo</author><text>&gt; Is it even possible to have a useful workstation these days without any USB devices<p>All my gear is on the network these days. The only USB device I regularly plug is in a dumb 5V fan from the dollar store... I imagine these days it&#x27;s more possible than ever.<p>Air-gapped computers (which is what this seems to be targeting) on the other hand are surely going to do all their data transfer over USB.</text></item><item><author>colinbartlett</author><text>&gt; As Ars has noted in previous coverage, the techniques are theoretically effective, but their utility in real-world situations is limited. That&#x27;s because the computers they target still must be infected by malware. If the computers aren&#x27;t connected to the Internet, the compromise is likely to be extremely difficult and would most likely require the help of a malicious insider, who very well may have easier ways to obtain data stored on the machine.<p>Nonetheless, an interesting technique. Is it even possible to have a useful workstation these days without <i>any</i> USB devices?</text></item></parent_chain><comment><author>huehehue</author><text>Are you sure the USB fan isn&#x27;t carrying a malicious payload? ;)</text></comment> | <story><title>Malware that uses USB drives to covertly jump airgaps</title><url>http://arstechnica.com/security/2016/08/meet-usbee-the-malware-that-uses-usb-drives-to-covertly-jump-airgaps/</url></story><parent_chain><item><author>kalleboo</author><text>&gt; Is it even possible to have a useful workstation these days without any USB devices<p>All my gear is on the network these days. The only USB device I regularly plug is in a dumb 5V fan from the dollar store... I imagine these days it&#x27;s more possible than ever.<p>Air-gapped computers (which is what this seems to be targeting) on the other hand are surely going to do all their data transfer over USB.</text></item><item><author>colinbartlett</author><text>&gt; As Ars has noted in previous coverage, the techniques are theoretically effective, but their utility in real-world situations is limited. That&#x27;s because the computers they target still must be infected by malware. If the computers aren&#x27;t connected to the Internet, the compromise is likely to be extremely difficult and would most likely require the help of a malicious insider, who very well may have easier ways to obtain data stored on the machine.<p>Nonetheless, an interesting technique. Is it even possible to have a useful workstation these days without <i>any</i> USB devices?</text></item></parent_chain><comment><author>marcosdumay</author><text>&gt; Air-gapped computers (which is what this seems to be targeting) on the other hand are surely going to do all their data transfer over USB.<p>Why? DVDs still exist.</text></comment> |
3,389,677 | 3,389,697 | 1 | 3 | 3,389,283 | train | <story><title>While we are focusing on SOPA, we are being distracted from the Protect IP Act</title><url>http://www.reddit.com/r/technology/comments/np5ee/while_we_are_focusing_on_sopa_we_are_being/</url></story><parent_chain><item><author>fragsworth</author><text>I get a dreadful sense that there's really no stopping this. The entertainment industry has been around longer than the tech industry, their claws more deeply embedded in our political system. They will not cease until they get the controls they want. They'll stop at nothing - they will use every tactic they can come up with to get their laws passed. Maybe SOPA won't pass, maybe Protect IP won't pass, but later on it will be something else. The public gets bored with issues as they drone on - can we maintain our vigilance forever?</text></item></parent_chain><comment><author>alexqgb</author><text>Maintaining vigilance is one thing. Resisting a direct and perpetually sustained assault is another. In answer to that question, no, the public can't win. Like a body riddled with unchecked tumors, it will inevitably die - prematurely and horribly.<p>Make no mistake: private election finance is a cancer upon the Nation. We end it, or it ends us.</text></comment> | <story><title>While we are focusing on SOPA, we are being distracted from the Protect IP Act</title><url>http://www.reddit.com/r/technology/comments/np5ee/while_we_are_focusing_on_sopa_we_are_being/</url></story><parent_chain><item><author>fragsworth</author><text>I get a dreadful sense that there's really no stopping this. The entertainment industry has been around longer than the tech industry, their claws more deeply embedded in our political system. They will not cease until they get the controls they want. They'll stop at nothing - they will use every tactic they can come up with to get their laws passed. Maybe SOPA won't pass, maybe Protect IP won't pass, but later on it will be something else. The public gets bored with issues as they drone on - can we maintain our vigilance forever?</text></item></parent_chain><comment><author>rohit89</author><text>Perhaps work should be done to pass a law that prevents these sort of bills from popping up. Go on the offense and eliminate the threat instead of constantly having to defend variations of the problem.</text></comment> |
16,050,874 | 16,050,756 | 1 | 2 | 16,049,242 | train | <story><title>Clang runs in the browser and compiles C++ to WebAssembly</title><url>https://tbfleming.github.io/cib/</url></story><parent_chain><item><author>tzahola</author><text>Replace “WebAssembly VM” with “JVM” and you will see how it’s already available, and why it won’t catch on.</text></item><item><author>shalabhc</author><text>Next we&#x27;ll get to a webassembly-only VM that will replace the OS. All &#x27;apps&#x27; will run on this VM instead of being native, and most will be cross platform. They&#x27;ll talk to each other via messaging (using Javascript semantics) instead of bytes-over-pipes as they do today. An integrated globally available, namespaced data store API might replace the filesystem. Each app+version will be accessible by a distinct URL. &#x27;My computer&#x27; will finally be fully virtual - a well defined collection of &#x27;apps&#x2F;data&#x27; URLs that materializes wherever I can open one of these webassembly VMs.<p>With this webassembly VM, early bound (precompiled) lower level languages may not have a strong advantage over late bound, dynamic ones, because the compiler is part of the OS layer (as it should be).<p>The world seems to be slowly moving, in a roundabout way, towards the OS-browser idea from Alan Kay.</text></item></parent_chain><comment><author>int_19h</author><text>JVM had to be installed, and it was far from seamless the way OP describes it.<p>The advantage of wasm is that all the people running Chrome today already have it.</text></comment> | <story><title>Clang runs in the browser and compiles C++ to WebAssembly</title><url>https://tbfleming.github.io/cib/</url></story><parent_chain><item><author>tzahola</author><text>Replace “WebAssembly VM” with “JVM” and you will see how it’s already available, and why it won’t catch on.</text></item><item><author>shalabhc</author><text>Next we&#x27;ll get to a webassembly-only VM that will replace the OS. All &#x27;apps&#x27; will run on this VM instead of being native, and most will be cross platform. They&#x27;ll talk to each other via messaging (using Javascript semantics) instead of bytes-over-pipes as they do today. An integrated globally available, namespaced data store API might replace the filesystem. Each app+version will be accessible by a distinct URL. &#x27;My computer&#x27; will finally be fully virtual - a well defined collection of &#x27;apps&#x2F;data&#x27; URLs that materializes wherever I can open one of these webassembly VMs.<p>With this webassembly VM, early bound (precompiled) lower level languages may not have a strong advantage over late bound, dynamic ones, because the compiler is part of the OS layer (as it should be).<p>The world seems to be slowly moving, in a roundabout way, towards the OS-browser idea from Alan Kay.</text></item></parent_chain><comment><author>C14L</author><text>The big difference is that the &quot;Browser VM&quot; has well defined permissions to access resources on the host machine. Just like phone OSes do today. Bluetooth API, Files API, Location API, etc.</text></comment> |
19,354,124 | 19,353,238 | 1 | 2 | 19,352,740 | train | <story><title>In Estonian parliamentary election, 44% of the votes were cast online</title><url>https://www.zdnet.com/article/online-voting-now-estonia-teaches-the-world-a-lesson-in-electronic-elections/</url></story><parent_chain></parent_chain><comment><author>deogeo</author><text>&quot;The system has been designed to ensure that voters&#x27; computers are not infected by any kind of malware that could change or block their vote.&quot;<p>I&#x27;m sure this cannot be subverted by an attacker with the resources of USA&#x2F;China&#x2F;India&#x2F;.., or with access to the supply chain from the chip fab onward (don&#x27;t forget about malware hidden in USB cables!), or or,...<p>And you&#x27;d have to be <i>dead sure</i>, because, unlike with physical votes, there will be few-to-none signs of subversion. You can vote physically, but what do a few physical votes matter when the attacker can change the vote of 30, 50, 70% of the population.<p>And how do you change the system, when all parties promising to do so can&#x27;t get enough votes?<p>Edit: Example of what a voting system must be resistant against: <a href="https:&#x2F;&#x2F;www.schneier.com&#x2F;blog&#x2F;archives&#x2F;2018&#x2F;03&#x2F;adding_backdoor.html" rel="nofollow">https:&#x2F;&#x2F;www.schneier.com&#x2F;blog&#x2F;archives&#x2F;2018&#x2F;03&#x2F;adding_backdo...</a></text></comment> | <story><title>In Estonian parliamentary election, 44% of the votes were cast online</title><url>https://www.zdnet.com/article/online-voting-now-estonia-teaches-the-world-a-lesson-in-electronic-elections/</url></story><parent_chain></parent_chain><comment><author>HarryHirsch</author><text>That is worrying. How do you know that the voter could vote freely and didn&#x27;t sell their vote? Corruption around vote-selling is a concern in certain ethnic enclaves in Britain, and there were even elections annulled over that. The foremost concern shouldn&#x27;t be convenience, it should be that the vote is safe and secret.</text></comment> |
31,041,168 | 31,040,036 | 1 | 2 | 31,036,328 | train | <story><title>New on Reddit: Comment search, improved search results relevance, search design</title><url>https://www.redditinc.com/blog/new-on-reddit-comment-search-improved-search-results-relevance-updated-search-design</url></story><parent_chain><item><author>site-packages1</author><text>I have seen it happen through complaints reaching the all subreddit. However it only seemed to happen to subreddits that were peddling deep hatred against outgroups like people of color, overweight people, or were just vile. Your comment makes it seem like any given subreddit is in danger of quarantining, but anecdotally that doesn&#x27;t seem to be the case. However, I have an open mind: would you give me an example of a subreddit that was otherwise innocuous yet got quarantined?</text></item><item><author>dandellion</author><text>I&#x27;ve also been on reddit for more than 10 years and it&#x27;s also never happened to me, but I know what they&#x27;re talking about. Let&#x27;s not pretend like it doesn&#x27;t happen.</text></item><item><author>nvr219</author><text>Has this happened to you ever? I’ve been on reddit for 10 years, and this never happened to me.</text></item><item><author>honksillet</author><text>And hope it does not get quarantined then disappeared? No thanks.</text></item><item><author>czechdeveloper</author><text>I use Reddit long term and &#x2F;r&#x2F;all was always bad and you should find your subreddits to care for.</text></item><item><author>fareesh</author><text>Sometime around the night of the DNC primary in 2015 there was a dramatic shift in the content on Reddit. If you were a frequent visitor of the homepage and &#x2F;all at the time, you will know exactly what I am referring to.<p>The product has gone downhill ever since.<p>Comment search is nice because it enables users to find interesting content directly in the good niche subreddits.</text></item></parent_chain><comment><author>ravenstine</author><text>Though technically it wasn&#x27;t banned, r&#x2F;star_trek recently got locked from having new posts, and only just the other day became unlocked because the mod agreed to not allow discussion related to r&#x2F;startrek.<p>Wait, huh???<p>r&#x2F;startrek, without the underscore, is the official Star Trek community. r&#x2F;star_trek is an alternative community created because r&#x2F;startrek is very hostile to anyone who doesn&#x27;t just slobber over anything Star Trek.<p>So people would join the alternative community and bring up why they got banned on the official one, or how people were being ridiculous in general on the official one.<p>But I don&#x27;t buy that there was any meaningful amount of brigading that was happening. I think the official community, being its pious self, didn&#x27;t like that people were exposing the mods for being arbitrary and condescending, or that anyone was exposing the likely possibility that they were highly controlled by ViacomCBS.<p>When it got locked, for all intents and purposes it was banned, if not temporarily.</text></comment> | <story><title>New on Reddit: Comment search, improved search results relevance, search design</title><url>https://www.redditinc.com/blog/new-on-reddit-comment-search-improved-search-results-relevance-updated-search-design</url></story><parent_chain><item><author>site-packages1</author><text>I have seen it happen through complaints reaching the all subreddit. However it only seemed to happen to subreddits that were peddling deep hatred against outgroups like people of color, overweight people, or were just vile. Your comment makes it seem like any given subreddit is in danger of quarantining, but anecdotally that doesn&#x27;t seem to be the case. However, I have an open mind: would you give me an example of a subreddit that was otherwise innocuous yet got quarantined?</text></item><item><author>dandellion</author><text>I&#x27;ve also been on reddit for more than 10 years and it&#x27;s also never happened to me, but I know what they&#x27;re talking about. Let&#x27;s not pretend like it doesn&#x27;t happen.</text></item><item><author>nvr219</author><text>Has this happened to you ever? I’ve been on reddit for 10 years, and this never happened to me.</text></item><item><author>honksillet</author><text>And hope it does not get quarantined then disappeared? No thanks.</text></item><item><author>czechdeveloper</author><text>I use Reddit long term and &#x2F;r&#x2F;all was always bad and you should find your subreddits to care for.</text></item><item><author>fareesh</author><text>Sometime around the night of the DNC primary in 2015 there was a dramatic shift in the content on Reddit. If you were a frequent visitor of the homepage and &#x2F;all at the time, you will know exactly what I am referring to.<p>The product has gone downhill ever since.<p>Comment search is nice because it enables users to find interesting content directly in the good niche subreddits.</text></item></parent_chain><comment><author>Miner49er</author><text>&#x2F;r&#x2F;chapotraphouse wasn&#x27;t any worse then say &#x2F;r&#x2F;conservative or &#x2F;r&#x2F;politics, but it got banned.<p>&#x2F;r&#x2F;DarkNetMarkets. Just for discussing DNMs, AFAIK.<p>&#x2F;r&#x2F;shoplifting<p>&#x2F;r&#x2F;stealing<p>&#x2F;r&#x2F;beertrade: for trading beers<p>&#x2F;r&#x2F;gundeals for a bit. Several other gun buying subs are still banned.<p>&#x2F;r&#x2F;fakeid<p>&#x2F;r&#x2F;scotchswap: for trading Scotches<p>&#x2F;r&#x2F;cigarmarket<p>There&#x27;s more, too.</text></comment> |
22,528,365 | 22,528,300 | 1 | 2 | 22,527,921 | train | <story><title>Australia sues Facebook over Cambridge Analytica</title><url>https://techcrunch.com/2020/03/09/australia-sues-facebook-over-cambridge-analytica-fine-could-scale-to-529bn/</url></story><parent_chain></parent_chain><comment><author>poooogles</author><text>The fact that we (the UK) only fined Facebook £500k [1] is an utter scandal. You can probably say $529bn is too much, but the appropriate amount might be somewhere in the middle of the two...<p>1. <a href="https:&#x2F;&#x2F;techcrunch.com&#x2F;2019&#x2F;10&#x2F;30&#x2F;facebook-agrees-to-pay-uk-data-watchdogs-cambridge-analytica-fine-but-settles-without-admitting-liability&#x2F;" rel="nofollow">https:&#x2F;&#x2F;techcrunch.com&#x2F;2019&#x2F;10&#x2F;30&#x2F;facebook-agrees-to-pay-uk-...</a></text></comment> | <story><title>Australia sues Facebook over Cambridge Analytica</title><url>https://techcrunch.com/2020/03/09/australia-sues-facebook-over-cambridge-analytica-fine-could-scale-to-529bn/</url></story><parent_chain></parent_chain><comment><author>ztratar</author><text>No $529BN fine would ever actually happen.<p>That would be considered economic warfare and the US wouldn&#x27;t allow it.</text></comment> |
29,594,143 | 29,593,800 | 1 | 2 | 29,591,819 | train | <story><title>The Third Web</title><url>https://tante.cc/2021/12/17/the-third-web/</url></story><parent_chain></parent_chain><comment><author>riffic</author><text>I might have missed it but it&#x27;d be nice if this piece or any other web3 think-piece acknowledged the capabilities of tools such as Indieweb or the federated social web, showing the promise of distribution wholly without blockchains.</text></comment> | <story><title>The Third Web</title><url>https://tante.cc/2021/12/17/the-third-web/</url></story><parent_chain></parent_chain><comment><author>astoor</author><text>It is incredible how divisive web3 has made people. I don&#x27;t think I recall anything quite like it. I think it is because:<p>1. It is primarily about politics rather than technology. Those in favour of web3 typically come from the right-libertarian camp, often with a strong dislike of government, banks, taxes etc., which those against web3 associate with anti-social ideas such as anti-vax, permissive gun laws, conspiracy theories and the like.<p>2. It is an existential struggle. Those in favour of web3 have a vested interest now and don&#x27;t want to see the value of their coins and tokens fall, while those against web3 don&#x27;t want to see the last vestiges of the free and open web as we know it destroyed by the tokenisation and monetisation of every interaction.</text></comment> |
22,631,638 | 22,631,011 | 1 | 2 | 22,629,959 | train | <story><title>Machine Learning Flashcards</title><url>https://machinelearningflashcards.com/</url></story><parent_chain></parent_chain><comment><author>SpaceManNabs</author><text>There are people saying here that is not worth it. I tend to agree but for different reasons. Flashcards with spaced repetition can help you learn mathy concepts, as Michael Niesel and others have shown.<p>As high_derivative notes, to make the process worthwhile, you need to make the notes yourself in order to internalize chunks that are worthwhile to you. That means your own definitions that you are failing to remember, the questions you need to answer, the problem sets you want to review, etc.<p>You can only internalize with a method like flashcards w&#x2F; spaced repetition once you understand the argument, need, and narrative.</text></comment> | <story><title>Machine Learning Flashcards</title><url>https://machinelearningflashcards.com/</url></story><parent_chain></parent_chain><comment><author>high_derivative</author><text>This is not a good idea and definitely not worth the money.<p>If you want to pass a quiz-style interview (I interview for a FAANG ML research lab), you are much likely better served writing down the concepts yourself in a concise way. If you never wrote them down somewhere, you are not forced to actually digest the content. Cards you didn&#x27;t write yourself will fool yourself into believing you understand something if you can repeat the words.</text></comment> |
23,030,697 | 23,029,754 | 1 | 3 | 23,028,432 | train | <story><title>SoftBank to write down WeWork by $6.6B, compounding portfolio misery</title><url>https://mobile.reuters.com/article/idUSKBN22C011</url></story><parent_chain><item><author>Droobfest</author><text><i>The highly leveraged conglomerate has been forced into selling major assets to raise funds, but could receive a big boost from the Bank of Japan’s plan to expand corporate bond buying, which would support its predilection for borrowing.</i><p>The Japanese taxpayer (Yen-holder) having to support the losses of Adam Neumann&#x27;s personal money tree seems pretty crazy to me.</text></item></parent_chain><comment><author>LordOfWolves</author><text>This sounds a bit similar to - and just as ludicrous as - American taxpayers financially assisting or “bailing out” massive companies which were&#x2F;are so bad at cash flow management that their runway was&#x2F;is only 1-3 months, despite hundreds of millions - if not billions - in annual revenue and a varying chunk of that being profit.</text></comment> | <story><title>SoftBank to write down WeWork by $6.6B, compounding portfolio misery</title><url>https://mobile.reuters.com/article/idUSKBN22C011</url></story><parent_chain><item><author>Droobfest</author><text><i>The highly leveraged conglomerate has been forced into selling major assets to raise funds, but could receive a big boost from the Bank of Japan’s plan to expand corporate bond buying, which would support its predilection for borrowing.</i><p>The Japanese taxpayer (Yen-holder) having to support the losses of Adam Neumann&#x27;s personal money tree seems pretty crazy to me.</text></item></parent_chain><comment><author>Traster</author><text>Softbank walked away from the planned bailout of Neumann, so that $1Bn golden parachute for Neumann is long gone. Now he has to sue softbank to try and get it back but there&#x27;s just no way it&#x27;s ever going to happen.</text></comment> |
27,391,444 | 27,388,182 | 1 | 2 | 27,387,978 | train | <story><title>TinyPilot: Month 11</title><url>https://mtlynch.io/retrospectives/2021/06/</url></story><parent_chain></parent_chain><comment><author>solresol</author><text>I haven&#x27;t been in enterprise IT for a while, but the enterprise features that you could have closed-source that would encourage big corps to buy (and pay a premium) which hobbyist buyers couldn&#x27;t care less about:<p>- SNMP support (it&#x27;s on the network, it should report what it is)
- Raise SNMP trap (or other alert into $proprietary_monitoring system) when the screen looks like a BIOS screen
- timestamped video storage of any activity that happened (auditors will love this)
- integrated authentication with LDAP &#x2F; ActiveDirectory so that you can set up a group which has access to all TinyPilots</text></comment> | <story><title>TinyPilot: Month 11</title><url>https://mtlynch.io/retrospectives/2021/06/</url></story><parent_chain></parent_chain><comment><author>mtlynch</author><text>Author here! I didn&#x27;t expect to see this pop up on HN.<p>I&#x27;m happy to take any feedback or answer any questions about this post.</text></comment> |
14,184,216 | 14,184,001 | 1 | 3 | 14,183,699 | train | <story><title>Unroll.me</title><url>https://daringfireball.net/linked/2017/04/23/heartbreaking</url></story><parent_chain></parent_chain><comment><author>merricksb</author><text>Active discussion:<p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=14181152" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=14181152</a></text></comment> | <story><title>Unroll.me</title><url>https://daringfireball.net/linked/2017/04/23/heartbreaking</url></story><parent_chain></parent_chain><comment><author>HappyTypist</author><text>I looked on their website, Frequently Asked Questions, and even hovered over text like &quot;Unroll.me is a free service&quot; in order to find a disclosure.<p>I could not find ANY disclosures whatsoever.<p>Nowhere does Unroll.me disclose that they sell your emails to the highest bidder.<p>I wish we had a FTC that could bankrupt Unroll.me&#x27;s previous and current founders and executives. Absolutely despicable behaviour.</text></comment> |
30,588,610 | 30,588,809 | 1 | 3 | 30,586,211 | train | <story><title>Russia to legalize software piracy</title><url>https://writing.kemitchell.com/2022/03/05/Russia-to-Legalize-Software-Piracy.html</url></story><parent_chain><item><author>alin23</author><text>It’s not <i>screen dimming</i>. It is an app to fully control the monitor without using its physical buttons.<p>Lunar can change the hardware brightness, the same one that you can change using the monitor OSD. That in itself required a lot of reverse engineering and research about the DDC protocol.<p>Adaptive brightness, ambient light sensor integration and other automatic features also needed months of non-stop work.<p>Plus, the app is open source, trying to give something back to the community which gave me the inspiration to create this: <a href="https:&#x2F;&#x2F;github.com&#x2F;alin23&#x2F;Lunar" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;alin23&#x2F;Lunar</a><p>Even with $23 per license, after taxes I barely make half of what I made at my previous job where I worked less hours.<p>I don’t understand how you can dismiss this so simply.<p><pre><code> the people pirating your software probably wouldn&#x27;t have paid for it anyhow
</code></pre>
I heard this argument so many times.. it&#x27;s like saying to someone who just got their bike stolen while they were trying to sell it<p><pre><code> | the thief would have probably never bought it
</code></pre>
If you don&#x27;t need the Pro features, don&#x27;t pay for them and don&#x27;t use them. Simple as that. Why does it feel okay to steal them in the software world, but it&#x27;s clearly a crime in the real world?</text></item><item><author>jpalawaga</author><text>Not that you asked my opinion, but $23&#x2F;year for screendimming software--its no wonder people crack this.<p>The only realistic scenario that I&#x27;d pay that is if my employer was fronting the cost. Then again, maybe for some people it really is delivering that much value.<p>Lunar lite and rcmd seem priced fairly. If it makes you feel any better (probably not), the people pirating your software probably wouldn&#x27;t have paid for it anyhow. Or if they did pay for it, would pay for it with things like stolen app store giftcards.<p>In another life, I was quite money-limited, and so I downloaded basically every game, movie, song, and app. I didn&#x27;t feel badly about it either. I was never going to buy the media. I couldn&#x27;t. Once I got old enough and had enough disposable income to not have to pirate things, I stopped. But quashing my piracy would have never equated in more sales. Anyone who sees a pirate download and assume that&#x27;s a lost sale is deluded--its not happening.<p>I think the best methods are trying to get people to pay (who haven&#x27;t already) are probably guilt or a productive-spirited suggestion. If you can detect that someone is cracking your software or doesn&#x27;t have a valid license, put a donation link in the shape of a coffee cup in the corner of your software. At least people have the option to support you. Otherwise--you&#x27;ll never best the crackers.</text></item><item><author>alin23</author><text>I&#x27;m tired of the TnT Russian team cracking my macOS apps. Both Lunar (<a href="https:&#x2F;&#x2F;lunar.fyi" rel="nofollow">https:&#x2F;&#x2F;lunar.fyi</a>) and rcmd (<a href="https:&#x2F;&#x2F;lowtechguys.com&#x2F;rcmd" rel="nofollow">https:&#x2F;&#x2F;lowtechguys.com&#x2F;rcmd</a>) are now available for free on macOS piracy websites.<p>I made many attempts at discouraging this through anti-piracy measures I learned while working as a malware researcher a few years ago. But if I want my apps to also be available on offline devices, there&#x27;s really no way to combat this.<p>The apps are also targetted more toward power users which are more likely to know about cracked apps. This is really hurting indie devs.</text></item></parent_chain><comment><author>axg11</author><text>You&#x27;re describing the complexity of achieving the outcome. That is a great achievement - you spent months of work to achieve something technically complex. Congratulations, sincerely. However, to the end user, Lunar is a utility that controls screen brightness. I too am not surprised that many people are reluctant to pay a yearly subscription to control the brightness of their display.</text></comment> | <story><title>Russia to legalize software piracy</title><url>https://writing.kemitchell.com/2022/03/05/Russia-to-Legalize-Software-Piracy.html</url></story><parent_chain><item><author>alin23</author><text>It’s not <i>screen dimming</i>. It is an app to fully control the monitor without using its physical buttons.<p>Lunar can change the hardware brightness, the same one that you can change using the monitor OSD. That in itself required a lot of reverse engineering and research about the DDC protocol.<p>Adaptive brightness, ambient light sensor integration and other automatic features also needed months of non-stop work.<p>Plus, the app is open source, trying to give something back to the community which gave me the inspiration to create this: <a href="https:&#x2F;&#x2F;github.com&#x2F;alin23&#x2F;Lunar" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;alin23&#x2F;Lunar</a><p>Even with $23 per license, after taxes I barely make half of what I made at my previous job where I worked less hours.<p>I don’t understand how you can dismiss this so simply.<p><pre><code> the people pirating your software probably wouldn&#x27;t have paid for it anyhow
</code></pre>
I heard this argument so many times.. it&#x27;s like saying to someone who just got their bike stolen while they were trying to sell it<p><pre><code> | the thief would have probably never bought it
</code></pre>
If you don&#x27;t need the Pro features, don&#x27;t pay for them and don&#x27;t use them. Simple as that. Why does it feel okay to steal them in the software world, but it&#x27;s clearly a crime in the real world?</text></item><item><author>jpalawaga</author><text>Not that you asked my opinion, but $23&#x2F;year for screendimming software--its no wonder people crack this.<p>The only realistic scenario that I&#x27;d pay that is if my employer was fronting the cost. Then again, maybe for some people it really is delivering that much value.<p>Lunar lite and rcmd seem priced fairly. If it makes you feel any better (probably not), the people pirating your software probably wouldn&#x27;t have paid for it anyhow. Or if they did pay for it, would pay for it with things like stolen app store giftcards.<p>In another life, I was quite money-limited, and so I downloaded basically every game, movie, song, and app. I didn&#x27;t feel badly about it either. I was never going to buy the media. I couldn&#x27;t. Once I got old enough and had enough disposable income to not have to pirate things, I stopped. But quashing my piracy would have never equated in more sales. Anyone who sees a pirate download and assume that&#x27;s a lost sale is deluded--its not happening.<p>I think the best methods are trying to get people to pay (who haven&#x27;t already) are probably guilt or a productive-spirited suggestion. If you can detect that someone is cracking your software or doesn&#x27;t have a valid license, put a donation link in the shape of a coffee cup in the corner of your software. At least people have the option to support you. Otherwise--you&#x27;ll never best the crackers.</text></item><item><author>alin23</author><text>I&#x27;m tired of the TnT Russian team cracking my macOS apps. Both Lunar (<a href="https:&#x2F;&#x2F;lunar.fyi" rel="nofollow">https:&#x2F;&#x2F;lunar.fyi</a>) and rcmd (<a href="https:&#x2F;&#x2F;lowtechguys.com&#x2F;rcmd" rel="nofollow">https:&#x2F;&#x2F;lowtechguys.com&#x2F;rcmd</a>) are now available for free on macOS piracy websites.<p>I made many attempts at discouraging this through anti-piracy measures I learned while working as a malware researcher a few years ago. But if I want my apps to also be available on offline devices, there&#x27;s really no way to combat this.<p>The apps are also targetted more toward power users which are more likely to know about cracked apps. This is really hurting indie devs.</text></item></parent_chain><comment><author>AnonHP</author><text>Not GP.<p>&gt; Even with $23 per license, after taxes I barely make half of what I made at my previous job where I worked less hours.
I don’t understand how you can dismiss this so simply.<p>Seeing the odd numbered price of $23, I presume you have tried different pricing tiers and options, since pricing is a matter of elasticity and finding the right price point to maximize your revenue would require some effort.<p>&gt; the people pirating your software probably wouldn&#x27;t have paid for it anyhow
I heard this argument so many times.. it&#x27;s like saying to someone who just got their bike stolen while they were trying to sell it
| the thief would have probably never bought it<p>Actually, that saying about piracy is true many a times. It doesn’t matter that it doesn’t work in your favor either way. Anecdotally, I decide what I’m willing to pay for something and what I’m not willing to pay for something. Have I pirated software? Yes, I have in the distant past. And during those times, I wouldn’t have bought them at those prices either.<p>Maybe you need to change your website messaging to encourage those who cannot or will not pay to use the Lite version and encourage those who want the Pro version to pay. Pricing doesn’t have to be static all the time.<p>I hope you find the best options that work well for you and your customers.</text></comment> |
36,254,450 | 36,254,485 | 1 | 2 | 36,254,172 | train | <story><title>ArchiveTeam has saved over 11.2B Reddit links</title><url>https://old.reddit.com/r/DataHoarder/comments/142l1i0/archiveteam_has_saved_over_108_billion_reddit/</url></story><parent_chain></parent_chain><comment><author>alboaie</author><text>From discussions it seems that the problem is that many subreddits will be going private to protest the recent Reddit API costs changes. Some will not come back unless the change is reverted. If the change is never reverted, they will be gone forever and this project is trying to save old posts so they can still be seen even though the subreddits are private. Not sure how usefull it will be... but somehow interesting as an example of reaction of policies changes of centralised social networks</text></comment> | <story><title>ArchiveTeam has saved over 11.2B Reddit links</title><url>https://old.reddit.com/r/DataHoarder/comments/142l1i0/archiveteam_has_saved_over_108_billion_reddit/</url></story><parent_chain></parent_chain><comment><author>agilob</author><text>Live leaderboard of archived links <a href="https:&#x2F;&#x2F;tracker.archiveteam.org&#x2F;reddit&#x2F;" rel="nofollow">https:&#x2F;&#x2F;tracker.archiveteam.org&#x2F;reddit&#x2F;</a><p>I&#x27;ve been contributing to this project for ~2 years now and I&#x27;ve never seen it running so fast</text></comment> |
6,129,156 | 6,128,201 | 1 | 3 | 6,127,895 | train | <story><title>MIT Report is a whitewash. My Statement in Response</title><url>http://tarensk.tumblr.com/post/56881327662/mit-report-is-a-whitewash-my-statement-in-response</url></story><parent_chain></parent_chain><comment><author>freyr</author><text><i>&quot;Aaron would be alive today if MIT had acted as JSTOR did. MIT had a moral imperative to do so.&quot;</i><p>It&#x27;s natural to look for someone to blame. Should we lay the blame on MIT? If they had called off an overzealous D.A. from throwing the book at him, he might be alive today. Why not blame the D.A.? Or JSTOR? In any case, aiding in prosecution did not cause his death directly.<p>The decision to commit suicide was ultimately his own. Of all the options he had available to him, he consciously chose that option. I&#x27;m reminded of a quote by Viktor Frankl:<p><i>&quot;Forces beyond your control can take away everything you possess except one thing, your freedom to choose how you will respond to the situation.&quot;</i><p>Aaron had the power to choose right until his last choice. Why do some people survive terrible hardships, and others don&#x27;t?<p>According to his close friends&#x27; personal accounts, Aaron suffered from suicidal thoughts and depression for many years. Long before the JSTOR case, and long before MIT ever got involved. As long as we&#x27;re speculating about things we can&#x27;t know for sure, I&#x27;m guessing depression was really to blame for his suicide. That won&#x27;t satisfy everyone, since it doesn&#x27;t give them a powerful organization to rage against. But reality doesn&#x27;t always work that way.</text></comment> | <story><title>MIT Report is a whitewash. My Statement in Response</title><url>http://tarensk.tumblr.com/post/56881327662/mit-report-is-a-whitewash-my-statement-in-response</url></story><parent_chain></parent_chain><comment><author>GrinningFool</author><text>This is probably going to cost me karma, but here goes:
&quot;Aaron would be alive today if MIT had acted as JSTOR did&quot;<p>So he has <i>no</i> responsibility for the decisions he made, up to and including the final one?<p>Yes, MIT&#x27;s actions may have had influence. Or they may have hastened the inevitable - a person who makes this choice is not untroubled to begin with, and it&#x27;s never about just one thing.<p>Ultimately, it was his choice in the end. The responsibility is his.</text></comment> |
35,375,616 | 35,370,754 | 1 | 2 | 35,370,357 | train | <story><title>The RWKV language model: An RNN with the advantages of a transformer</title><url>https://johanwind.github.io/2023/03/23/rwkv_overview.html</url></story><parent_chain></parent_chain><comment><author>Straw</author><text>Unfortunately its not very good at longer context lengths, which sort of defeats the point of efficient scaling with context. See <a href="https:&#x2F;&#x2F;twitter.com&#x2F;arankomatsuzaki&#x2F;status&#x2F;1639000379978403853" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;arankomatsuzaki&#x2F;status&#x2F;16390003799784038...</a><p>Its also not really an RNN. The best way to describe the key time mixing operation is a normalized exponentially weighted moving average (EMA)- no non-linearity. Once viewed this way, its not surprising that it struggles at longer contexts- everything decays, and it has limited space to put things. Of course, it does have some clever tricks, and can choose to remember things for a while by upweighting them, but not forever.</text></comment> | <story><title>The RWKV language model: An RNN with the advantages of a transformer</title><url>https://johanwind.github.io/2023/03/23/rwkv_overview.html</url></story><parent_chain></parent_chain><comment><author>imranq</author><text>The stats shown are pretty compelling that this transformer + RNN approach works. Looking back at the Llama paper (<a href="https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;2302.13971.pdf" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;2302.13971.pdf</a>), many of the results are comparable between llama and RWKV. E.g. Llama 13bn scores 80.1 on PIQA and RWKV scores 77.5<p>I wonder if RLHF would boost performance for this architecture in the same way</text></comment> |
10,900,204 | 10,899,928 | 1 | 3 | 10,891,546 | train | <story><title>Facebook and How UIs Twist Your Words</title><url>https://medium.com/user-experience-design-1/facebook-and-how-uis-twist-your-words-4ceedc5fd93#.uyy3wr30p</url></story><parent_chain></parent_chain><comment><author>morgante</author><text>I think it&#x27;s very important to note that the writer of this post deliberately split the chat version into 4 separate messages instead of one, while it&#x27;s really only a single message (and you can send a single message with line breaks on Facebook).<p>This changes the perception drastically and, more importantly, isn&#x27;t a fair comparison. The &quot;control&quot; wasn&#x27;t presented as 4 different messages and it makes total sense that sending more messages would appear more desperate.<p>Consider other mediums:<p>* Phone: someone leaving 4 voicemails in a row is perceived as <i>super</i> desperate in comparison to someone who leaves a single voicemail of the same total length. This is literally a sitcom trope.<p>* Email: someone sending 4 different emails (1 per paragraph) would definitely create a different (negative) impression than someone sending a single email<p>The author pretends to be demonstrating a way that the Facebook UI twists a message but is actually just affirming what is likely a universal trait of messaging: sending more messages before a response signals social awkwardness and desperation.</text></comment> | <story><title>Facebook and How UIs Twist Your Words</title><url>https://medium.com/user-experience-design-1/facebook-and-how-uis-twist-your-words-4ceedc5fd93#.uyy3wr30p</url></story><parent_chain></parent_chain><comment><author>pilif</author><text>I really think that the message can be adjusted to the medium it is conveyed over. Chat is meant for quick one line exchanges and I do believe that the long message was not appropriate for a chat exchange.<p>The same way an email is way less formal than a written letter or those rare SMSes from relatives that come full with salutation and signature.<p>Heck, even in a forum like this one: we don&#x27;t add the salutation nor signature, but in an email we would.<p>Context matters a lot and the ability to adjust the message to match the context is also part of communication skill.<p>The reason why I believe that chat is different from mail or a forum post is that chat messages cause your phone to make sounds and&#x2F;or vibrate. They are shown on your home screen where they also will share the screen estate with other people&#x27;s messages. Shorter messages are more useful.</text></comment> |
15,556,593 | 15,556,373 | 1 | 2 | 15,555,450 | train | <story><title>Video Games Are Destroying the People Who Make Them</title><url>https://www.nytimes.com/2017/10/25/opinion/work-culture-video-games-crunch.html</url></story><parent_chain><item><author>eksemplar</author><text>I never understood why people went into the gaming industry unless it was in a position where they did decision making and got credit.<p>Growing up in the 80&#x2F;90is I remember thinking a place like Bioware or Black Isle&#x2F;Troika would&#x27;ve been cool places to work, but as I reached adulthood and understood what went into working those places, the dream quickly faded.<p>Imagine having to work long hours at shit pay, to design&#x2F;build some loot crate system. Especially when your skill set is in high-demand and you could&#x27;ve gone into something like healthcare IT, where you could be improving people&#x27;s lives, at 37-45 hours a week at four times the pay.<p>I really don&#x27;t mean to be rude, I just can&#x27;t fathom the motivation you would have to work some anonymous job in the video gaming industry.</text></item></parent_chain><comment><author>sidlls</author><text>HN cracks me up sometimes. Compare the derision and skepticism hurled at would-be video game developers to the praise people working countless hours on pointless &quot;portfolio side projects&quot; on github or whatever get, just for a minor boost in the grueling interview process or because they&#x27;re so passionate about it or whatever.<p>At least these people (who are certainly being exploited, often in ways that violate labor laws) are getting some real work experience while they&#x27;re at it.</text></comment> | <story><title>Video Games Are Destroying the People Who Make Them</title><url>https://www.nytimes.com/2017/10/25/opinion/work-culture-video-games-crunch.html</url></story><parent_chain><item><author>eksemplar</author><text>I never understood why people went into the gaming industry unless it was in a position where they did decision making and got credit.<p>Growing up in the 80&#x2F;90is I remember thinking a place like Bioware or Black Isle&#x2F;Troika would&#x27;ve been cool places to work, but as I reached adulthood and understood what went into working those places, the dream quickly faded.<p>Imagine having to work long hours at shit pay, to design&#x2F;build some loot crate system. Especially when your skill set is in high-demand and you could&#x27;ve gone into something like healthcare IT, where you could be improving people&#x27;s lives, at 37-45 hours a week at four times the pay.<p>I really don&#x27;t mean to be rude, I just can&#x27;t fathom the motivation you would have to work some anonymous job in the video gaming industry.</text></item></parent_chain><comment><author>taneq</author><text>You go into the industry because you want to make games. You leave when you get sick of games companies taking advantage of your &quot;passion for games&quot; to offer you an exploitative deal.</text></comment> |
33,508,188 | 33,508,303 | 1 | 2 | 33,506,458 | train | <story><title>Toxic smog has turned India’s capital into a ‘gas chamber’</title><url>https://globalnews.ca/news/9252830/india-smog-new-delhi-gas-chamber-pollution/</url></story><parent_chain><item><author>bergenty</author><text>On a tangent, how does the rest of the world do this? Is it just machinery that tills the soil to bury the old plants?<p>Also, what are the downsides to just leaving the stubble on the land?</text></item><item><author>whywhywhydude</author><text>Despite being banned by the supreme court, farmers are still burning the crop stubbles. And nobody wants to enforce the rule because it’s a political suicide. Another instance of failed democracy where you need to appease to a vocal minority even if it means smog and deaths for the rest.</text></item></parent_chain><comment><author>itronitron</author><text>In the US most of the biomass is tilled into or left on the field to reduce erosion, and some is bundled and used as fuel in electrical generators.</text></comment> | <story><title>Toxic smog has turned India’s capital into a ‘gas chamber’</title><url>https://globalnews.ca/news/9252830/india-smog-new-delhi-gas-chamber-pollution/</url></story><parent_chain><item><author>bergenty</author><text>On a tangent, how does the rest of the world do this? Is it just machinery that tills the soil to bury the old plants?<p>Also, what are the downsides to just leaving the stubble on the land?</text></item><item><author>whywhywhydude</author><text>Despite being banned by the supreme court, farmers are still burning the crop stubbles. And nobody wants to enforce the rule because it’s a political suicide. Another instance of failed democracy where you need to appease to a vocal minority even if it means smog and deaths for the rest.</text></item></parent_chain><comment><author>SoftTalker</author><text>No-till farming is fairly widespread in the USA though certainly not exclusive.<p><a href="https:&#x2F;&#x2F;www.britannica.com&#x2F;topic&#x2F;till-less-agriculture" rel="nofollow">https:&#x2F;&#x2F;www.britannica.com&#x2F;topic&#x2F;till-less-agriculture</a></text></comment> |
11,339,863 | 11,339,220 | 1 | 2 | 11,338,276 | train | <story><title>Claims of Age Bias Rise, but Standards of Proof Are High</title><url>http://www.nytimes.com/2016/03/19/your-money/trying-to-make-a-case-for-age-discrimination.html?em_pos=large&emc=edit_nn_20160322&nl=morning-briefing&nlid=70045141&ref=todayspaper</url></story><parent_chain><item><author>huherto</author><text>I am 47. 27 years of professional experience. Got hooked in Basic. Fell in love with Pascal, C, C++, Smalltalk, Perl, and Java. Most new technologies are a re-encarnation of something that I did already the first time or second time around. I don&#x27;t think my resume looks trendy. Still, I feel my skills are better than almost all of my friends and coworkers. They are 21-35. But, I see things that they don&#x27;t. Subtle things like code organization, error handling, readability. I have a better CS background (compilers, networking,theory of languages,operating systems, relational theory, machine language). I know 100 ways in which a project can fail. My code is terse, I have been working on it for a long time.<p>Yet, I am scared to loose my job. I don&#x27;t know if the recruiter will look past my age and lack of trendy technologies in my resume.</text></item></parent_chain><comment><author>ryandrake</author><text>I&#x27;m right behind you! Some ideas I&#x27;ve tried, who knows whether they work or not:<p>1. Remove everything from your resume past 6 or so years in the past. Put a little note at the bottom saying that your extended work history is available upon request. Nobody wants to read a resume over 1 page anyway.<p>2. Don&#x27;t list any years on your education--just list the institutions. That&#x27;s an easy way to leak your age.<p>3. Regularly scrub for &quot;outdated&quot; technologies and topics. Instead of writing perl scripts to parse log files and output reports with Tcl&#x2F;Tk, you were a full-stack developer who processed data analytics from critical business infrastructure.</text></comment> | <story><title>Claims of Age Bias Rise, but Standards of Proof Are High</title><url>http://www.nytimes.com/2016/03/19/your-money/trying-to-make-a-case-for-age-discrimination.html?em_pos=large&emc=edit_nn_20160322&nl=morning-briefing&nlid=70045141&ref=todayspaper</url></story><parent_chain><item><author>huherto</author><text>I am 47. 27 years of professional experience. Got hooked in Basic. Fell in love with Pascal, C, C++, Smalltalk, Perl, and Java. Most new technologies are a re-encarnation of something that I did already the first time or second time around. I don&#x27;t think my resume looks trendy. Still, I feel my skills are better than almost all of my friends and coworkers. They are 21-35. But, I see things that they don&#x27;t. Subtle things like code organization, error handling, readability. I have a better CS background (compilers, networking,theory of languages,operating systems, relational theory, machine language). I know 100 ways in which a project can fail. My code is terse, I have been working on it for a long time.<p>Yet, I am scared to loose my job. I don&#x27;t know if the recruiter will look past my age and lack of trendy technologies in my resume.</text></item></parent_chain><comment><author>zippergz</author><text>This is one of the reasons I spend time on the weekends doing projects in new technologies. I can put Rails, React, Angular, Swift, etc. on my resume and answer questions about them (and point to projects I&#x27;ve used them on). I see keeping up with new technologies as an important part of my career development. If someone is truly biased against me because of my age, there&#x27;s not much I can do about that. But I definitely have control over whether someone is biased against me because I haven&#x27;t kept up with technical developments.</text></comment> |
7,317,342 | 7,317,243 | 1 | 3 | 7,313,421 | train | <story><title>Testing at Airbnb</title><url>http://nerds.airbnb.com/testing-at-airbnb/</url></story><parent_chain><item><author>nchuhoai</author><text>Pretty interesting that according to him, Airbnb didn&#x27;t really have a functioning testing infrastructure only a year ago. So you really can hit a billion dollars in valuation without testing :)</text></item></parent_chain><comment><author>nostrademons</author><text>Google didn&#x27;t really have a culture of testing until around 2005-2006. At that point they were public and had a $100B+ market cap. I&#x27;m sure there are other public companies out there who don&#x27;t do automated testing <i>at all</i>.<p>The technical infrastructure and code quality of a company are secondary factors in its success. The biggest influence they have is in the ability to attract and retain brilliant engineers, because most brilliant engineers don&#x27;t want to work in a place where they&#x27;re just treading water with bugfixes (which is the situation you eventually get into without automated testing). But the mechanism is that brilliant engineers write features that your competitors can&#x27;t match, not that testing itself will make you successful.</text></comment> | <story><title>Testing at Airbnb</title><url>http://nerds.airbnb.com/testing-at-airbnb/</url></story><parent_chain><item><author>nchuhoai</author><text>Pretty interesting that according to him, Airbnb didn&#x27;t really have a functioning testing infrastructure only a year ago. So you really can hit a billion dollars in valuation without testing :)</text></item></parent_chain><comment><author>choonkeat</author><text>A public service announcement: There’s still a lot of pretty good programmers who don’t write tests… and programmers who write tests are not necessarily any good - <a href="http://blog.choonkeat.com/weblog/2012/06/tdd-for-those-who-dont-need-it.html" rel="nofollow">http:&#x2F;&#x2F;blog.choonkeat.com&#x2F;weblog&#x2F;2012&#x2F;06&#x2F;tdd-for-those-who-d...</a></text></comment> |
28,310,243 | 28,310,327 | 1 | 2 | 28,308,235 | train | <story><title>To save California, sacrifice single-family zoning</title><url>https://www.latimes.com/opinion/story/2021-08-22/editorial-sb9-sb10-california-housing</url></story><parent_chain><item><author>mjfl</author><text>California voters are probably totally fine with the housing supply being too low because it drives up the price of their houses.</text></item></parent_chain><comment><author>IIAOPSW</author><text>&quot;But for a beautiful moment in time, we created a lot of value for homeowners.&quot;<p><a href="http:&#x2F;&#x2F;www.derekchristensen.com&#x2F;wp-content&#x2F;uploads&#x2F;2014&#x2F;12&#x2F;shareholdervalue.jpg" rel="nofollow">http:&#x2F;&#x2F;www.derekchristensen.com&#x2F;wp-content&#x2F;uploads&#x2F;2014&#x2F;12&#x2F;s...</a></text></comment> | <story><title>To save California, sacrifice single-family zoning</title><url>https://www.latimes.com/opinion/story/2021-08-22/editorial-sb9-sb10-california-housing</url></story><parent_chain><item><author>mjfl</author><text>California voters are probably totally fine with the housing supply being too low because it drives up the price of their houses.</text></item></parent_chain><comment><author>paxys</author><text>I&#x27;d say people in the state being disadvantaged by the housing crisis vastly outnumber those profiting from it. It&#x27;s just that people in power (richer, older folks, those sitting on local councils, state legislatures, celebrities, corporations, pastors, power brokers, other influential figures) all fall into the latter category.</text></comment> |
39,566,704 | 39,564,873 | 1 | 2 | 39,561,356 | train | <story><title>The 'Atlanta Magnet Man' is saving our car tires, one bike ride at a time</title><url>https://www.wabe.org/the-atlanta-magnet-man-is-saving-our-car-tires-one-bike-ride-at-a-time/</url></story><parent_chain><item><author>ericmcer</author><text>How much do you think it would cost the city to implement something like this themselves? It would probably involve hiring 2-3 bike riders, a manager, some people to oversee&#x2F;analyze the efficacy of the program, an approved supply chain using approved vendors. They could probably get a couple bikes with magnets on them riding around the city for &lt; 3m year.</text></item><item><author>duxup</author><text>I really like stories of individual folks out there making the world a better place. A motivated individual with some level of exposure to the problem &#x2F; solution often seems so much more efficient than other solutions.<p>There&#x27;s a local group that helps folks find stolen bikes:<p><a href="https:&#x2F;&#x2F;www.wsj.com&#x2F;us-news&#x2F;your-bike-just-got-stolen-these-vigilantes-will-get-it-back-af45a9d0?st=36dqme79yig8m3z&amp;reflink=desktopwebshare_permalink" rel="nofollow">https:&#x2F;&#x2F;www.wsj.com&#x2F;us-news&#x2F;your-bike-just-got-stolen-these-...</a></text></item></parent_chain><comment><author>scrose</author><text>The city would extend a no-bid contract to run a 6-month pilot in a 3 block radius.<p>It’d go to a random company that never did anything related to trash pick up, but one of the board members would be loosely related to the mayor.<p>The mayor will then do a victory lap in front of journalists talking about this revolutionary project.<p>The winner would then sub-contract a series of shell companies to handle ‘planning the design and implementation’ of the vehicle used to pick up the debris.<p>3 months will pass and the first community board meeting about the pilot in the neighborhood will happen, where the project will hit vicious opposition from people citing gentrification, how this pilot will rip apart the fabric of the neighborhood, cause gridlock, be dangerous for kids (What if a kid runs infront of the magnet bike??), etc…<p>6 months and $5M later, the pilot gets extended and another $50M worth of funding having never picked up an ounce of trash.<p>Hello from NYC</text></comment> | <story><title>The 'Atlanta Magnet Man' is saving our car tires, one bike ride at a time</title><url>https://www.wabe.org/the-atlanta-magnet-man-is-saving-our-car-tires-one-bike-ride-at-a-time/</url></story><parent_chain><item><author>ericmcer</author><text>How much do you think it would cost the city to implement something like this themselves? It would probably involve hiring 2-3 bike riders, a manager, some people to oversee&#x2F;analyze the efficacy of the program, an approved supply chain using approved vendors. They could probably get a couple bikes with magnets on them riding around the city for &lt; 3m year.</text></item><item><author>duxup</author><text>I really like stories of individual folks out there making the world a better place. A motivated individual with some level of exposure to the problem &#x2F; solution often seems so much more efficient than other solutions.<p>There&#x27;s a local group that helps folks find stolen bikes:<p><a href="https:&#x2F;&#x2F;www.wsj.com&#x2F;us-news&#x2F;your-bike-just-got-stolen-these-vigilantes-will-get-it-back-af45a9d0?st=36dqme79yig8m3z&amp;reflink=desktopwebshare_permalink" rel="nofollow">https:&#x2F;&#x2F;www.wsj.com&#x2F;us-news&#x2F;your-bike-just-got-stolen-these-...</a></text></item></parent_chain><comment><author>munificent</author><text>Well, the better approach at city scale is to use actual street sweepers.<p>Magnets don&#x27;t pick up broken glass.</text></comment> |
15,809,980 | 15,809,969 | 1 | 2 | 15,808,549 | train | <story><title>Silicon Valley Software Engineer Salaries by Experience Level</title><url>https://triplebyte.com/software-engineer-salary</url></story><parent_chain><item><author>mrweasel</author><text>It really raises the question why anyone would put a software company in the Silicon Valley area. You could get cheaper and more experienced people pretty much anywhere in the world for at least 60 - 70% the price.</text></item><item><author>digitalsushi</author><text>My god this is just another universe to me. I&#x27;ve got 19 years on the clock doing stuff, right now extending the jenkins model to make a usable 2.0 pipeline, for a fortune 50 hiding on the new hampshire seacoast, senior-straddling-principal level and just barely squeaking out a 6 figure salary. I know it all comes out in the wash, but it just blows my mind how different money is across the country. or, i am a country bumpkin with absolutely no idea what is really out there.</text></item></parent_chain><comment><author>lloyd-christmas</author><text>Not as easily. There is a reason all the banks are based in NYC. Recruitment and networking is as easy as walking across the street.
The same holds for tech. Cost of hiring is extremely high no matter where you are, and it likely goes up even more when trying to recruit
someone to move to the middle of the country. I mean no disrespect to middle america by that statement, I just mean that the probability of
having to uproot is much higher when there are 2 companies in town vs. 200.</text></comment> | <story><title>Silicon Valley Software Engineer Salaries by Experience Level</title><url>https://triplebyte.com/software-engineer-salary</url></story><parent_chain><item><author>mrweasel</author><text>It really raises the question why anyone would put a software company in the Silicon Valley area. You could get cheaper and more experienced people pretty much anywhere in the world for at least 60 - 70% the price.</text></item><item><author>digitalsushi</author><text>My god this is just another universe to me. I&#x27;ve got 19 years on the clock doing stuff, right now extending the jenkins model to make a usable 2.0 pipeline, for a fortune 50 hiding on the new hampshire seacoast, senior-straddling-principal level and just barely squeaking out a 6 figure salary. I know it all comes out in the wash, but it just blows my mind how different money is across the country. or, i am a country bumpkin with absolutely no idea what is really out there.</text></item></parent_chain><comment><author>ng12</author><text>Quantity is the problem. I&#x27;m sure there are some blindingly talented developers in New Hampshire but there&#x27;s probably only a few of them and they&#x27;re more than likely gainfully employed by a company that appreciates their value. Hiring an engineer for 60% of the price doesn&#x27;t help when you can only fill a third of your headcount.</text></comment> |
18,329,000 | 18,328,062 | 1 | 2 | 18,327,342 | train | <story><title>With Proton and Steam Play, many Windows games now work on Linux</title><url>https://www.protondb.com</url></story><parent_chain><item><author>z3t4</author><text>We bought a Windows computer so the kids could play some old classics. Not a single game worked on Windows 10, not even in compatibility mode. But most of them worked in Linux&#x2F;Wine ...</text></item></parent_chain><comment><author>babypuncher</author><text>Must be some old titles, it&#x27;s pretty rare for a 32-bit Windows game to flat out not work in Windows 10. I&#x27;m even able to run Incredible Machine 3 (a game from 1995), albeit without CD audio. DOS and 16-bit Windows games however require an emulator like DOSBox.<p>Many 3D games from the mid-late &#x27;90s and early &#x27;00s relied on now esoteric hardware accelerators and APIs (like Glide) or GPU features that behave differently on modern hardware than the games expect. These might require a wrapper like nGlide or dgVoodoo 2.<p>Check the entries for your games on the PC Gaming Wiki (www.pcgamingwiki.com).</text></comment> | <story><title>With Proton and Steam Play, many Windows games now work on Linux</title><url>https://www.protondb.com</url></story><parent_chain><item><author>z3t4</author><text>We bought a Windows computer so the kids could play some old classics. Not a single game worked on Windows 10, not even in compatibility mode. But most of them worked in Linux&#x2F;Wine ...</text></item></parent_chain><comment><author>jamesgeck0</author><text>I&#x27;ve actually had to add Wine DLLs to a few older games to get them running on Windows. Games that use DirectDraw are the main suspects.</text></comment> |
23,339,972 | 23,340,133 | 1 | 3 | 23,338,742 | train | <story><title>Have you ever asked yourself “how did research get done before LateX?”</title><url>https://twitter.com/iraphas13/status/1262489387767480322</url></story><parent_chain><item><author>inimino</author><text>Knuth wrote TeX as a labor of love. The surest way to kill everything good about it would be a few million dollars, and a team, and to turn it into fucking Google Docs for science.<p>Ask Knuth to name one person who has the clearest vision for the future of TeX, and give that person a stipend to work on it for the next ten years, or for life, and you might actually do some good.</text></item><item><author>jessriedel</author><text>I&#x27;ve said it before and I&#x27;ll say it again: the single most cost effective way to speed up math and physics research by a philanthropist would be taking a few million dollars and hiring a team of developers to bring LaTeX into the 21st century: Take the 100 most popular packages and fold them into the main code base (so I don&#x27;t need to install conflicting packages just to get three columns!). Create a non-buggy desktop IDE&#x2F;wordprocessor that works seamlessly using a traditional interface or a LyX-like interface. Merge&#x2F;buy&#x2F;replace Overleaf with an online service that syncs reliably with the desktop IDE. And, most importantly and difficultly, create a standard way for generating beautiful web pages (including mobile) from the same LaTeX++ files that can be used to generate beautiful PDFs.<p>The annual NSF physics budget is roughly a quarter billion dollars. This only needs to make NSF-funded physicists 1% more productive over a decade to justify spending $20M, and the entire world would benefit.<p>EDIT: Lots of commenters worry that this will end up like various closed-source for-profit tools like Google Docs. But for a closer analogy they should look at some of the excellent free open-source science software being produced with philanthropic funding such as Zotero. Physicists will only adopt it if it makes their lives easier (and maybe not even then...).<p>EDIT 2: There are some pretty strong parallels between the commenters suggesting this can already be achieved with homegrown tools and the infamous HN Dropbox comment.</text></item></parent_chain><comment><author>scubbo</author><text>Can you elaborate on what you think is bad about Google Docs? Aside from the data privacy concerns from the fact that it&#x27;s owned and operated by Google (which I agree with), it seems like a fantastically usable, available, and powerful product. What do you fear would happen to LaTeX in this situation?</text></comment> | <story><title>Have you ever asked yourself “how did research get done before LateX?”</title><url>https://twitter.com/iraphas13/status/1262489387767480322</url></story><parent_chain><item><author>inimino</author><text>Knuth wrote TeX as a labor of love. The surest way to kill everything good about it would be a few million dollars, and a team, and to turn it into fucking Google Docs for science.<p>Ask Knuth to name one person who has the clearest vision for the future of TeX, and give that person a stipend to work on it for the next ten years, or for life, and you might actually do some good.</text></item><item><author>jessriedel</author><text>I&#x27;ve said it before and I&#x27;ll say it again: the single most cost effective way to speed up math and physics research by a philanthropist would be taking a few million dollars and hiring a team of developers to bring LaTeX into the 21st century: Take the 100 most popular packages and fold them into the main code base (so I don&#x27;t need to install conflicting packages just to get three columns!). Create a non-buggy desktop IDE&#x2F;wordprocessor that works seamlessly using a traditional interface or a LyX-like interface. Merge&#x2F;buy&#x2F;replace Overleaf with an online service that syncs reliably with the desktop IDE. And, most importantly and difficultly, create a standard way for generating beautiful web pages (including mobile) from the same LaTeX++ files that can be used to generate beautiful PDFs.<p>The annual NSF physics budget is roughly a quarter billion dollars. This only needs to make NSF-funded physicists 1% more productive over a decade to justify spending $20M, and the entire world would benefit.<p>EDIT: Lots of commenters worry that this will end up like various closed-source for-profit tools like Google Docs. But for a closer analogy they should look at some of the excellent free open-source science software being produced with philanthropic funding such as Zotero. Physicists will only adopt it if it makes their lives easier (and maybe not even then...).<p>EDIT 2: There are some pretty strong parallels between the commenters suggesting this can already be achieved with homegrown tools and the infamous HN Dropbox comment.</text></item></parent_chain><comment><author>jessriedel</author><text>Obviously everything that can be built by an individual is better that way than if built by a team. But at some point the amount of work becomes too much for one person to finish in a reasonable amount of time (e.g., a lifetime, or before their project becomes out of date).<p>What I&#x27;m describing is not do-able by one person, and the result of refusing to coordinate a team around the project (and instead having a hodge-podge of tools built by various people) is the current LaTeX ecosystem mess.</text></comment> |
17,515,557 | 17,515,538 | 1 | 3 | 17,513,828 | train | <story><title>MacBook Pro with faster performance and new features for pros</title><url>https://www.apple.com/newsroom/2018/07/apple-updates-macbook-pro-with-faster-performance-and-new-features-for-pros/</url></story><parent_chain><item><author>mbesto</author><text>&gt; They didn&#x27;t do that because it is not what most people want.<p>&gt; Better to focus on the 90% of customers who buy products<p>So either you&#x27;re wrong, or Apple&#x27;s PR team is really bad positioning their product. From the Press Release itself in the first few paragraphs:<p><i>ideal for manipulating large data sets, performing complex simulations, creating multi-track audio projects or doing advanced image processing or film editing.</i><p><i>Already the most popular notebook for developers around the world, the new MacBook Pro can compile code faster and run multiple virtual machines and test environments easier than before.</i><p><i>MacBook Pro now delivers faster performance for complex simulations and data manipulation.</i><p><i>With the new MacBook Pro, developers can compile code faster and more easily run multiple virtual machines and test environments.</i><p>Aren&#x27;t those all features described exactly for the &quot;niche developer&#x2F;macrumors posters&quot;?!</text></item><item><author>r0fl</author><text>They didn&#x27;t do that because it is not what most people want. Apple has to make changes that will sell more laptops to the masses to maximize shareholder value.<p>The niche developer&#x2F;macrumors posters will never be happy regardless of what Apple does. Better to focus on the 90% of customers who buy products and make up 10% of the complaints then to focus on the 10% of customers who make up 90% of the complaints.</text></item><item><author>no1youknowz</author><text>&gt; The new keyboard has the same dimensions and look as its two predecessors, but the keys feel just a little bit different. They&#x27;re quieter, for one thing. They have a softer, less click-y feel that is a little closer to the pre-2016 models&#x27; chiclet keys. We found the new keyboard to be a little nicer to type on, but it&#x27;s not a radical difference. It&#x27;s unlikely to convert the detractors, but it&#x27;s a welcome iteration for those who liked or didn&#x27;t mind the previous butterfly keyboards.<p>I&#x27;m going to wait a year, maybe 18 months for feedback before I consider upgrading. Why they couldn&#x27;t grab a 2012-2015 model and upgrade the guts? No touchbar, smaller touchpad than the newer macbooks, but updated specs? Call it Macbook Developer... We build the software for the &quot;Pros&quot; after all.<p>I just don&#x27;t get it.</text></item></parent_chain><comment><author>gervase</author><text>I believe this is a case of a disparity between who they say their products are for (power users), and who they are actually for (people who want to think of themselves as power users).<p>This would be similar to, for example, many sportswear brands who say they are for professional athletes, but whose primary consumer base is... not.<p>In both cases, they may still attract the audience they claim to target, but in practice, that niche market makes up only a small fraction of their total sales.</text></comment> | <story><title>MacBook Pro with faster performance and new features for pros</title><url>https://www.apple.com/newsroom/2018/07/apple-updates-macbook-pro-with-faster-performance-and-new-features-for-pros/</url></story><parent_chain><item><author>mbesto</author><text>&gt; They didn&#x27;t do that because it is not what most people want.<p>&gt; Better to focus on the 90% of customers who buy products<p>So either you&#x27;re wrong, or Apple&#x27;s PR team is really bad positioning their product. From the Press Release itself in the first few paragraphs:<p><i>ideal for manipulating large data sets, performing complex simulations, creating multi-track audio projects or doing advanced image processing or film editing.</i><p><i>Already the most popular notebook for developers around the world, the new MacBook Pro can compile code faster and run multiple virtual machines and test environments easier than before.</i><p><i>MacBook Pro now delivers faster performance for complex simulations and data manipulation.</i><p><i>With the new MacBook Pro, developers can compile code faster and more easily run multiple virtual machines and test environments.</i><p>Aren&#x27;t those all features described exactly for the &quot;niche developer&#x2F;macrumors posters&quot;?!</text></item><item><author>r0fl</author><text>They didn&#x27;t do that because it is not what most people want. Apple has to make changes that will sell more laptops to the masses to maximize shareholder value.<p>The niche developer&#x2F;macrumors posters will never be happy regardless of what Apple does. Better to focus on the 90% of customers who buy products and make up 10% of the complaints then to focus on the 10% of customers who make up 90% of the complaints.</text></item><item><author>no1youknowz</author><text>&gt; The new keyboard has the same dimensions and look as its two predecessors, but the keys feel just a little bit different. They&#x27;re quieter, for one thing. They have a softer, less click-y feel that is a little closer to the pre-2016 models&#x27; chiclet keys. We found the new keyboard to be a little nicer to type on, but it&#x27;s not a radical difference. It&#x27;s unlikely to convert the detractors, but it&#x27;s a welcome iteration for those who liked or didn&#x27;t mind the previous butterfly keyboards.<p>I&#x27;m going to wait a year, maybe 18 months for feedback before I consider upgrading. Why they couldn&#x27;t grab a 2012-2015 model and upgrade the guts? No touchbar, smaller touchpad than the newer macbooks, but updated specs? Call it Macbook Developer... We build the software for the &quot;Pros&quot; after all.<p>I just don&#x27;t get it.</text></item></parent_chain><comment><author>SPBS</author><text>They trumpet those features only because it doesn&#x27;t conflict with their MacBook Pro aesthetic that&#x27;s meant to appeal the the wider audience.<p>Given a choice between a sexy MacBook Pro design and a pro-developer feature, Apple will choose the sexy design everytime.</text></comment> |
6,349,591 | 6,349,441 | 1 | 2 | 6,349,347 | train | <story><title>Startup Ideas Every Nerd Has (That Never Work)</title><url>http://swombat.com/2010/11/30/no-new-ideas</url></story><parent_chain></parent_chain><comment><author>7Figures2Commas</author><text>The problem with so many &quot;startup ideas&quot; is that they are a solution to the problem, &quot;I want to create a startup and don&#x27;t have an idea.&quot; Not surprisingly, this tends to produce copycat concepts, products with no real market fit, services that target sexy but oversaturated markets, etc.<p>There are lots and lots of problems that are either unsolved or are being solved in ways that are less efficient and cost-effective than they could be, particularly outside of the consumer space. In many cases, these problems can be solved with relatively unsophisticated applications. But the folks who sit around thinking about the usual consumer internet suspects (Facebook, Twitter, Instagram, etc.) never discover these problems because more often than not, they have no domain expertise.<p>Sadly, it seems to me that many technical wantrepreneurs have no real interest in developing domain expertise because they believe there&#x27;s more value in mastering the framework du jour than focusing in on a vertical and developing a real understanding of it over time.</text></comment> | <story><title>Startup Ideas Every Nerd Has (That Never Work)</title><url>http://swombat.com/2010/11/30/no-new-ideas</url></story><parent_chain></parent_chain><comment><author>lisper</author><text>This is a three-year-old blog post about a three-year-old HN comment about a different three-year-old blog post. Just sayin&#x27;.</text></comment> |
28,202,179 | 28,202,509 | 1 | 3 | 28,201,547 | train | <story><title>Computer simulation helps test land management techniques to help bumblebees</title><url>https://www.exeter.ac.uk/news/research/title_872443_en.html</url></story><parent_chain></parent_chain><comment><author>throw149102</author><text>I spent a few minutes looking at this &quot;BEE-Steward&quot; and it&#x27;s corresponding models, BEEHAVE and BEESCOUT, and the underlying NetLogo language that is used to model these things.<p>I guess I immediately have a few questions - How do we know that the model corresponds to reality at all? I mean, I know we have experiments to confirm what impacts the bees, but it seems like there could be a massive amount of variety depending on different factors. I&#x27;d love to see some research showing that BEE-Steward can work in real scenarios. Right now, they just have a simulation showing &quot;hey, if we change x and y we can get 5x more bees&quot;, but does that actually correspond to reality?<p>Secondly, how do we make farmers actually <i>want</i> to use this? Do they get paid for taking care of bees on their land? I know this is just a policy question, but it&#x27;s still important to answer. Do farmers need any training to use this? Can we collect data in an automated fashion to reduce the work the farmers have to do? This almost sounds like a deep learning problem - use a camera to map + classify areas of farmland, how many pollinators they have, the presence of bees, etc.<p>Finally, what is the fundamental problem of bee modeling? Is it fundamentally a computational problem (where we know the rules, but computing the model can be hard) or is it a data problem (where we know how to compute how the bees will behave, we can do it efficiently, but coming up with rules that bees actually follow is hard)? I&#x27;ve noted that the NetLogo environment by default will only take up 1GB of RAM, which is already not very much considering the JVM itself will take a pretty big chunk to run just about anything.<p>It would be interesting to start building some sort of &quot;National bee model&quot;, rather than just working farmland by farmland. Is there any project like this in the works?<p>Either way, I&#x27;m sure all of my questions and more are already being asked&#x2F;answered by people much more involved with the conservationist field. Just my 2 cents.</text></comment> | <story><title>Computer simulation helps test land management techniques to help bumblebees</title><url>https://www.exeter.ac.uk/news/research/title_872443_en.html</url></story><parent_chain></parent_chain><comment><author>mcdonje</author><text>Cool project. Confusing headline. They made models to help research land management strategies that would be potentially helpful for bees.</text></comment> |
2,190,638 | 2,190,470 | 1 | 3 | 2,190,166 | train | <story><title>How My School and District Failed its Students</title><url>http://www.anurbanteacherseducation.com/2011/02/tfa-alumnus-describes-barriers-to.html</url></story><parent_chain><item><author>maxharris</author><text>My solution? Make attendance voluntary by abolishing truancy laws. Disruptive students don't want to be there, and forcing them to go doesn't teach them anything.<p>Human beings can't be forced to think. This runs absolutely counter to all kinds of notions and traditions, but it's how nature is. Wishing, legislating and expecting that facts be otherwise won't work any better here than it would in the physical sciences (imagine how you might react to such a stance against thermodynamics or the inverse square law).<p>Edit: if you disagree, say <i>why</i> instead of just voting me down.</text></item></parent_chain><comment><author>michaelchisari</author><text>From my knowledge of radical education approaches like Summerhill or Ferrer's Modern School, I would agree with that, with one caveat:<p>Students don't have to attend class. They just have to go to school. They can choose, on a daily basis, what class they want to be in. If they disrupt, they're kicked out of class for the day, since attendance at that class is a voluntary association.<p>To get credit and a grade for a class, you have to complete X homework assignments and pass Y amount of tests.<p>If a kid decides they wants to hang out all day in the cafeteria, good for them. Teachers might want to check in on them and see why or offer books or computer access to do some self-education.<p>You'd also want to diversify the classes if possible. Add classes in video game design, automotive engineering, etc. Make these classes enticing, and <i>hard</i>. Rope the kids in to hard classes by making them seem like blow-offs.<p>But most of all, let the kid choose to learn, and you have a lot more power over the kids who come in just to disrupt. You also have the added social pressure of the other kids, who will recognize that the disruptors <i>don't have to be there</i> and are only ruining it for everyone.<p>Never underestimate the motivating power of boredom.</text></comment> | <story><title>How My School and District Failed its Students</title><url>http://www.anurbanteacherseducation.com/2011/02/tfa-alumnus-describes-barriers-to.html</url></story><parent_chain><item><author>maxharris</author><text>My solution? Make attendance voluntary by abolishing truancy laws. Disruptive students don't want to be there, and forcing them to go doesn't teach them anything.<p>Human beings can't be forced to think. This runs absolutely counter to all kinds of notions and traditions, but it's how nature is. Wishing, legislating and expecting that facts be otherwise won't work any better here than it would in the physical sciences (imagine how you might react to such a stance against thermodynamics or the inverse square law).<p>Edit: if you disagree, say <i>why</i> instead of just voting me down.</text></item></parent_chain><comment><author>jmm</author><text>Ha. The pickle here is that we (the government, the bleeding hearts, those capable of compassion) have to acknowledge that these kids were dealt a pretty bad hand, and that they are, after all, still kids. So we owe them a fair shot and some patience -- it's not acceptable to give up on them as products of the system. Because in one way or another we're part of the system. <i>And they're kids.</i><p>My sister participated in the New York Teaching Fellows program (similar to TFA) and worked in Spanish Harlem and her experience was much the same as the author's. So I'm not saying the current situation and the current programs are ideal or well managed, but there are interesting hope-inducing projects and people out there.<p>p.s. Go watch season 4 of The Wire and see if it tugs at your heartstrings a bit. It also paints a good picture of how screwed up the school system itself is in poor urban communities. Not to mention how pedogogical innovation is treated in the academic setting...<p>p.p.s. If you're curious about the role of academic philanthropy and the Broad Foundation which the author mentions, have a read: <a href="http://dissentmagazine.org/article/?article=3781" rel="nofollow">http://dissentmagazine.org/article/?article=3781</a> . I haven't read a counterpoint to that piece yet, so I'm not sure how well the criticisms stand up.</text></comment> |
35,743,490 | 35,743,638 | 1 | 3 | 35,742,606 | train | <story><title>Tell HN: Cloudflare verification is breaking the internet</title><text>Across many different pages including science journals, ChatGPT, and many others, CloudFlare verification goes into an infinite loop of:<p>1. &quot;Verify you are a human&quot;<p>2. Check the box or perform some other type of rain dance<p>3. &quot;Please stand by, while we are checking your browser...&quot;<p>4. Repeat step 1<p>I&#x27;m on Fedora Linux 37 using Firefox 110.<p>The workaround is to use Chrome.<p>After experiencing this dozens of times and getting annoyed of needing to use Chrome, I finally went and deleted all my cookies and cache which I had been dreading to do.<p>It did not help.<p>I don&#x27;t have a CloudFlare account so I wrote up a detailed post on their community forums. I offered a HAR file and was willing to do diagnostics. It received no responses and it was auto-closed.<p>It&#x27;s unacceptable that CloudFlare is breaking the internet while offering no community support.<p>Edit: I&#x27;m in Texas. I&#x27;m not using a VPN or Tor, just AT&amp;T Fiber. I don&#x27;t have ad-blockers. No weird extensions. Nothing special (besides being on Linux).<p>Edit2: Since this got traction, I opened a new community post: https:&#x2F;&#x2F;community.cloudflare.com&#x2F;t&#x2F;infinite-verify-you-are-a-human-loop&#x2F;503065<p>To be clear, I&#x27;m not against CloudFlare doing DDoS protection, etc., but it can&#x27;t be breaking the internet <i>while ignoring community posts on it</i>.<p>Edit3: The CloudFlare team has engaged. Thank you HN!</text></story><parent_chain><item><author>ryandrake</author><text>&gt; I&#x27;m not using a VPN or Tor, just AT&amp;T Fiber. I don&#x27;t have ad-blockers. No weird extensions. Nothing special (besides being on Linux).<p>Even if you were doing any, or all of these things, you are no less a legitimate internet user than anyone else. This whole &quot;rain dance&quot; supplication to show you are worthy of browsing a web site has got to go. Stop visiting sites who treat their users this badly!</text></item></parent_chain><comment><author>kevincox</author><text>This reminds me of the origin of &quot;jaywalking&quot;. People used to walk wherever they wanted but when cars became a thing they found that people where in their way. So they started to blame people for &quot;jaywalking&quot; to turn it into a bad thing that the pedestrians are doing rather than framing it as cars wanting to take some of the road away from pedestrians.<p>We are trying to frame people who are trying to protect their privacy as &quot;suspicious&quot; rather than saying that we want to track them better.</text></comment> | <story><title>Tell HN: Cloudflare verification is breaking the internet</title><text>Across many different pages including science journals, ChatGPT, and many others, CloudFlare verification goes into an infinite loop of:<p>1. &quot;Verify you are a human&quot;<p>2. Check the box or perform some other type of rain dance<p>3. &quot;Please stand by, while we are checking your browser...&quot;<p>4. Repeat step 1<p>I&#x27;m on Fedora Linux 37 using Firefox 110.<p>The workaround is to use Chrome.<p>After experiencing this dozens of times and getting annoyed of needing to use Chrome, I finally went and deleted all my cookies and cache which I had been dreading to do.<p>It did not help.<p>I don&#x27;t have a CloudFlare account so I wrote up a detailed post on their community forums. I offered a HAR file and was willing to do diagnostics. It received no responses and it was auto-closed.<p>It&#x27;s unacceptable that CloudFlare is breaking the internet while offering no community support.<p>Edit: I&#x27;m in Texas. I&#x27;m not using a VPN or Tor, just AT&amp;T Fiber. I don&#x27;t have ad-blockers. No weird extensions. Nothing special (besides being on Linux).<p>Edit2: Since this got traction, I opened a new community post: https:&#x2F;&#x2F;community.cloudflare.com&#x2F;t&#x2F;infinite-verify-you-are-a-human-loop&#x2F;503065<p>To be clear, I&#x27;m not against CloudFlare doing DDoS protection, etc., but it can&#x27;t be breaking the internet <i>while ignoring community posts on it</i>.<p>Edit3: The CloudFlare team has engaged. Thank you HN!</text></story><parent_chain><item><author>ryandrake</author><text>&gt; I&#x27;m not using a VPN or Tor, just AT&amp;T Fiber. I don&#x27;t have ad-blockers. No weird extensions. Nothing special (besides being on Linux).<p>Even if you were doing any, or all of these things, you are no less a legitimate internet user than anyone else. This whole &quot;rain dance&quot; supplication to show you are worthy of browsing a web site has got to go. Stop visiting sites who treat their users this badly!</text></item></parent_chain><comment><author>justizin</author><text>&gt; Stop visiting sites who treat their users this badly!<p>The problem is the individual sites aren’t making these highly technical decisions, people are using what seems to them an innocuous security product.<p>Not visiting a random website places no pressure on CloudFlare to change, since there’s no way to correlate your choice with the decision to use CloudFlare.</text></comment> |
17,115,810 | 17,113,009 | 1 | 2 | 17,110,819 | train | <story><title>History of Symbolics Lisp Machines (2007)</title><url>https://danluu.com/symbolics-lisp-machines/</url></story><parent_chain></parent_chain><comment><author>pholloway83</author><text>My uncle was one of the founders. My dad had a lisp machine in his home office for years. I never got to use it much, but I certainly spent a lot of time programming in LISP as a teenager.<p>I should see if my dad still has it, curious if it would still work?</text></comment> | <story><title>History of Symbolics Lisp Machines (2007)</title><url>https://danluu.com/symbolics-lisp-machines/</url></story><parent_chain></parent_chain><comment><author>svat</author><text>Correction to the date in the title: this is a concatenation of blog posts from 2007 (not 2017). Specifically, these three posts:<p><a href="https:&#x2F;&#x2F;web.archive.org&#x2F;web&#x2F;20120909104608&#x2F;http:&#x2F;&#x2F;danweinreb.org&#x2F;blog&#x2F;rebuttal-to-stallmans-story-about-the-formation-of-symbolics-and-lmi" rel="nofollow">https:&#x2F;&#x2F;web.archive.org&#x2F;web&#x2F;20120909104608&#x2F;http:&#x2F;&#x2F;danweinreb...</a> (Sunday, November 11th, 2007)<p><a href="https:&#x2F;&#x2F;web.archive.org&#x2F;web&#x2F;20120909104443&#x2F;http:&#x2F;&#x2F;danweinreb.org&#x2F;blog&#x2F;why-did-symbolics-fail" rel="nofollow">https:&#x2F;&#x2F;web.archive.org&#x2F;web&#x2F;20120909104443&#x2F;http:&#x2F;&#x2F;danweinreb...</a> (Friday, November 16th, 2007)<p><a href="http:&#x2F;&#x2F;web.archive.org&#x2F;web&#x2F;20120909110022&#x2F;http:&#x2F;&#x2F;danweinreb.org&#x2F;blog&#x2F;15" rel="nofollow">http:&#x2F;&#x2F;web.archive.org&#x2F;web&#x2F;20120909110022&#x2F;http:&#x2F;&#x2F;danweinreb....</a> (Friday, December 21st, 2007)<p>There is other interesting stuff on that blog and in the comments etc.<p>Dan Weinreb died in 2012: <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;w&#x2F;index.php?title=Daniel_Weinreb&amp;oldid=838230506" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;w&#x2F;index.php?title=Daniel_Weinreb&amp;ol...</a></text></comment> |
40,174,430 | 40,174,454 | 1 | 2 | 40,171,551 | train | <story><title>The brutal business practices of Amazon</title><url>https://www.vanityfair.com/news/story/inside-amazon-business-practices</url></story><parent_chain><item><author>ScoobleDoodle</author><text>&quot;Defund the police&quot; doesn&#x27;t mean what you think it means here.<p>It doesn&#x27;t mean removing all funds from the police as the name implies. It actually means reallocating funds from the police to trained professionals for appropriate situations. Like having a government division that hires psychologist &#x2F; mental health workers to respond to mental wellness checks. Having mental health &#x2F; homelessness services workers respond to calls about vagrants. So instead of getting a boot to the teeth or death as seen in the news, those at risk groups and people get the directed help and support they need.<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Defund_the_police" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Defund_the_police</a></text></item><item><author>xanderlewis</author><text>The notion of luxury beliefs isn’t just about plain old hypocrisy (though of course there’s plenty of that) — I think it’s more about beliefs one can <i>only</i> hold because of one’s position of privilege.<p>The usual example given is ‘defund the police’. If you’re rich enough to hire your own security or otherwise live safely in a world without police, you can advocate for this and win social points for doing so. Meanwhile, the actual consequences of such an idea, were it to be implemented, would be catastrophic. Unlimited immigration&#x2F;open borders is another one: if you’re relatively poor, your ability to make a living (among other things) is potentially threatened by this. If you’re rich, you needn’t worry. You can live in your fancy neighbourhood far detached from the consequences of such policies, so you can freely hold such positions and even frown upon those who don’t.<p>Luxury beliefs are just like tangible luxuries [*] — you have them not because you want them or really believe in them, but because they signal to others that you’re of a certain class. Poor people can’t have them, so they’re desirable as status indicators.<p>[*] OK — some ‘luxuries’ are worth it and aren’t just for showing off. But I’m talking about the ones that are.</text></item><item><author>cxr</author><text>The writer Rob K. Henderson has covered the hypocrisy of the upper and upper-middle classes in several of his pieces on what he calls &quot;luxury beliefs&quot;. The case of Amazon def. fits into a similar theme.<p>You can broach the topic with uppercrust folks (without even really trying) of whether supporting Walmart by shopping there is conscionable or not, and you&#x27;ll get one set of responses&#x2F;reactions. Meanwhile, it&#x27;s nowhere near socially unacceptable to talk about all the stuff you order from Amazon, despite Amazon appearing to be by and large worse in its compensation&#x2F;treatment of its employees and its effect on the economy and the environment—all things that aspiring bougie types ostensibly profess to rank highly in their meditations when it comes to Walmart.</text></item></parent_chain><comment><author>rpjt</author><text>I&#x27;m not sure this distinction matters much to most people, though. People hear &quot;defund the police&quot; and draw their own conclusions as to what that means, and it&#x27;s not a far leap to go from &quot;defund the police&quot; to &quot;welp, guess they want to tie the hands of cops and take away all of their funding so they can&#x27;t do their jobs&quot;</text></comment> | <story><title>The brutal business practices of Amazon</title><url>https://www.vanityfair.com/news/story/inside-amazon-business-practices</url></story><parent_chain><item><author>ScoobleDoodle</author><text>&quot;Defund the police&quot; doesn&#x27;t mean what you think it means here.<p>It doesn&#x27;t mean removing all funds from the police as the name implies. It actually means reallocating funds from the police to trained professionals for appropriate situations. Like having a government division that hires psychologist &#x2F; mental health workers to respond to mental wellness checks. Having mental health &#x2F; homelessness services workers respond to calls about vagrants. So instead of getting a boot to the teeth or death as seen in the news, those at risk groups and people get the directed help and support they need.<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Defund_the_police" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Defund_the_police</a></text></item><item><author>xanderlewis</author><text>The notion of luxury beliefs isn’t just about plain old hypocrisy (though of course there’s plenty of that) — I think it’s more about beliefs one can <i>only</i> hold because of one’s position of privilege.<p>The usual example given is ‘defund the police’. If you’re rich enough to hire your own security or otherwise live safely in a world without police, you can advocate for this and win social points for doing so. Meanwhile, the actual consequences of such an idea, were it to be implemented, would be catastrophic. Unlimited immigration&#x2F;open borders is another one: if you’re relatively poor, your ability to make a living (among other things) is potentially threatened by this. If you’re rich, you needn’t worry. You can live in your fancy neighbourhood far detached from the consequences of such policies, so you can freely hold such positions and even frown upon those who don’t.<p>Luxury beliefs are just like tangible luxuries [*] — you have them not because you want them or really believe in them, but because they signal to others that you’re of a certain class. Poor people can’t have them, so they’re desirable as status indicators.<p>[*] OK — some ‘luxuries’ are worth it and aren’t just for showing off. But I’m talking about the ones that are.</text></item><item><author>cxr</author><text>The writer Rob K. Henderson has covered the hypocrisy of the upper and upper-middle classes in several of his pieces on what he calls &quot;luxury beliefs&quot;. The case of Amazon def. fits into a similar theme.<p>You can broach the topic with uppercrust folks (without even really trying) of whether supporting Walmart by shopping there is conscionable or not, and you&#x27;ll get one set of responses&#x2F;reactions. Meanwhile, it&#x27;s nowhere near socially unacceptable to talk about all the stuff you order from Amazon, despite Amazon appearing to be by and large worse in its compensation&#x2F;treatment of its employees and its effect on the economy and the environment—all things that aspiring bougie types ostensibly profess to rank highly in their meditations when it comes to Walmart.</text></item></parent_chain><comment><author>xanderlewis</author><text>Fair enough. I&#x27;ve heard &#x27;abolish the police&#x27; and &#x27;all cops are bastards&#x27; (whatever that means) too, so such a sentiment definitely exists. Either way, those usually espousing such things don&#x27;t seem to have much of a concrete plan in mind (and don&#x27;t have to, because offering concrete solutions isn&#x27;t the purpose of such rhetoric).<p>&gt; According to the New York Times, the slogan and movement failed to result in any meaningful policy change. This was attributed to the slogan having no clear definition of its goals.<p>(from the Wikipedia page you linked to)</text></comment> |
4,274,025 | 4,274,008 | 1 | 2 | 4,273,034 | train | <story><title>New Programming Jargon</title><url>http://www.codinghorror.com/blog/2012/07/new-programming-jargon.html</url></story><parent_chain><item><author>SiVal</author><text>I can't help noticing how often I've<p>-- had a programming question<p>-- googled it<p>-- found the very first (most relevant) link to be to StackOverflow<p>-- jumped to it<p>-- found that some other programmer had also asked the same question<p>-- found that other SO members had given the question and its answers hundreds of bonus points (useful!)<p>-- and found that the SO mod-nazis had shut it down as "Not considered a good, on-topic question"<p>An example might be, what are the differences between git and mercurial, where the answer is not a line of code but may include informed judgments by the people whose judgments I'm most interested in. As a developer, I have to make a lot of decisions, and not all of them are about which characters to type.<p>So I have to live with whatever answers well-informed SO members managed to sneak onto the page before they were chased away and the gate was locked.<p>Does it seem to anyone else as though there might be something wrong when this happens over and over again?</text></item></parent_chain><comment><author>codinghorror</author><text>+1 for providing an example, but "Git vs. Mercurial" belongs on someone's blog, or on Wikipedia as a comparison matrix.<p>Now if you have a specific question about some <i>aspect</i> of Git compared to Mercurial, that can work on SE. But as a broad kitchen sink, catch-all, "compare these two giant things kthx", you'd end up with Gorilla vs. Shark.<p><a href="http://blog.stackoverflow.com/2011/08/gorilla-vs-shark/" rel="nofollow">http://blog.stackoverflow.com/2011/08/gorilla-vs-shark/</a></text></comment> | <story><title>New Programming Jargon</title><url>http://www.codinghorror.com/blog/2012/07/new-programming-jargon.html</url></story><parent_chain><item><author>SiVal</author><text>I can't help noticing how often I've<p>-- had a programming question<p>-- googled it<p>-- found the very first (most relevant) link to be to StackOverflow<p>-- jumped to it<p>-- found that some other programmer had also asked the same question<p>-- found that other SO members had given the question and its answers hundreds of bonus points (useful!)<p>-- and found that the SO mod-nazis had shut it down as "Not considered a good, on-topic question"<p>An example might be, what are the differences between git and mercurial, where the answer is not a line of code but may include informed judgments by the people whose judgments I'm most interested in. As a developer, I have to make a lot of decisions, and not all of them are about which characters to type.<p>So I have to live with whatever answers well-informed SO members managed to sneak onto the page before they were chased away and the gate was locked.<p>Does it seem to anyone else as though there might be something wrong when this happens over and over again?</text></item></parent_chain><comment><author>stevvooe</author><text>At risk of being banned forever, yes, this has been my experience with the site since its inception. Judgement is one quality of a solid developer and SO fails to impart The additive judgement of its participants.</text></comment> |
37,932,280 | 37,931,809 | 1 | 3 | 37,931,287 | train | <story><title>Bank of America's unrealized losses on securities rose to $131.6B</title><url>https://www.reuters.com/business/finance/bank-americas-unrealized-losses-securities-rose-1316-bln-2023-10-17/</url></story><parent_chain></parent_chain><comment><author>paxys</author><text>&gt; &quot;All of these are unrealized losses are on government- guaranteed securities,&quot; Bank of America&#x27;s chief financial officer, Alastair Borthwick, told reporters on conference call discussing third-quarter earnings. &quot;Because we&#x27;re holding them to maturity, we will anticipate that we&#x27;ll have zero losses over time.&quot;</text></comment> | <story><title>Bank of America's unrealized losses on securities rose to $131.6B</title><url>https://www.reuters.com/business/finance/bank-americas-unrealized-losses-securities-rose-1316-bln-2023-10-17/</url></story><parent_chain></parent_chain><comment><author>Dowwie</author><text>Non-issue.<p>&gt;&quot;All of these are unrealized losses are on government- guaranteed securities,&quot; Bank of America&#x27;s chief financial officer, Alastair Borthwick, told reporters on conference call discussing third-quarter earnings. &quot;Because we&#x27;re holding them to maturity, we will anticipate that we&#x27;ll have zero losses over time.&quot;</text></comment> |
33,851,938 | 33,851,686 | 1 | 2 | 33,851,406 | train | <story><title>Apple to move 40-45% iPhone production to India</title><url>https://www.wsj.com/articles/apple-china-factory-protests-foxconn-manufacturing-production-supply-chain-11670023099</url></story><parent_chain><item><author>Reubend</author><text>I&#x27;m surprised it&#x27;s so low. I know that they already have very established processes in China, and their contractors have probably invested a lot in tooling for those factories, but it seems interesting that they would still prefer to move less that 50% of their capacity there.<p>Maybe they see India as carrying its own risks?</text></item><item><author>akmittal</author><text>&gt; Apple’s longer-term goal is to ship 40% to 45% of iPhones from India, compared with a single-digit percentage currently, according to Ming-chi Kuo, an analyst at TF International Securities who follows the supply chain. Suppliers say Vietnam is expected to shoulder more of the manufacturing for other Apple products such as AirPods, smartwatches and laptops.</text></item></parent_chain><comment><author>spaceman_2020</author><text>India, being a democracy, means that governments have to give in to demands of voter groups. The two largest voter groups are farmers and low wage labor. This has ensured that acquiring land for large scale projects or changing labor laws carries massive political risk.<p>Changes to India’s farm laws now seem next to impossible. I doubt India will have a more popular government than it has today. Yet, it had to cave in and withdraw a farm law reform bill.<p>If even this government couldn’t pull it off, there’s little chance future governments will do any better.</text></comment> | <story><title>Apple to move 40-45% iPhone production to India</title><url>https://www.wsj.com/articles/apple-china-factory-protests-foxconn-manufacturing-production-supply-chain-11670023099</url></story><parent_chain><item><author>Reubend</author><text>I&#x27;m surprised it&#x27;s so low. I know that they already have very established processes in China, and their contractors have probably invested a lot in tooling for those factories, but it seems interesting that they would still prefer to move less that 50% of their capacity there.<p>Maybe they see India as carrying its own risks?</text></item><item><author>akmittal</author><text>&gt; Apple’s longer-term goal is to ship 40% to 45% of iPhones from India, compared with a single-digit percentage currently, according to Ming-chi Kuo, an analyst at TF International Securities who follows the supply chain. Suppliers say Vietnam is expected to shoulder more of the manufacturing for other Apple products such as AirPods, smartwatches and laptops.</text></item></parent_chain><comment><author>mikymoothrowa</author><text>&gt; they would still prefer to move less that 50% of their capacity there<p>It is not Apple saying this. So, this is some Analyst doing a linear regression. So we can&#x27;t read too much into this. It could be possible that India starts manufacturing 80% of iPhones. Or It could be less than the claimed 45% too.<p>Also, if there&#x27;s no reason for Foxconn to dismantle existing manufacturing facilities all at once.</text></comment> |
27,249,899 | 27,249,688 | 1 | 2 | 27,248,406 | train | <story><title>Antibody levels highly predictive of immune protection from symptomatic Covid</title><url>https://www.nature.com/articles/s41591-021-01377-8</url></story><parent_chain><item><author>xiphias2</author><text>My father tested negative for spike specific antibodies 2 weeks after the 2nd Pfizer vaccine (he&#x27;s not the only one), and as I didn&#x27;t find any data on people who test negative (and I know that the vaccine has 94% efficiency preventing COVID), he&#x27;s still mostly not leaving his apartment.<p>He&#x27;ll have a test against the viruses themselves next week, but he&#x27;ll need to wait 2 weeks for the result for that test.</text></item></parent_chain><comment><author>azinman2</author><text>That doesn’t mean he doesn’t have protection. The antibody tests only look For one thing, but the body has many mechanisms of protection from the vaccine. That is one of the reasons why they’re not suggested to be used for the general population.</text></comment> | <story><title>Antibody levels highly predictive of immune protection from symptomatic Covid</title><url>https://www.nature.com/articles/s41591-021-01377-8</url></story><parent_chain><item><author>xiphias2</author><text>My father tested negative for spike specific antibodies 2 weeks after the 2nd Pfizer vaccine (he&#x27;s not the only one), and as I didn&#x27;t find any data on people who test negative (and I know that the vaccine has 94% efficiency preventing COVID), he&#x27;s still mostly not leaving his apartment.<p>He&#x27;ll have a test against the viruses themselves next week, but he&#x27;ll need to wait 2 weeks for the result for that test.</text></item></parent_chain><comment><author>yosito</author><text>I wonder if an expert could chime in on this. If someone tests negative for antibodies a few weeks after a vaccine, should that person get vaccinated again? Maybe with a different vaccine?</text></comment> |
11,226,609 | 11,224,660 | 1 | 3 | 11,224,381 | train | <story><title>Poor Sleep Gives You the Munchies, Study Says</title><url>http://www.nytimes.com/2016/03/05/science/sleep-eating-craving-food.html?module=WatchingPortal&region=c-column-middle-span-region&pgType=Homepage&action=click&mediaId=wide&state=standard&contentPlacement=4&version=internal&contentCollection=www.nytimes.com&contentId=http%3A%2F%2Fwww.nytimes.com%2F2016%2F03%2F05%2Fscience%2Fsleep-eating-craving-food.html&eventName=Watching-article-click</url></story><parent_chain></parent_chain><comment><author>ergothus</author><text>One thing that doesn&#x27;t get a lot of attention is the _quality_ of sleep, not just the duration.<p>After years of being a fairly thin kid and teen, I start packing on the pounds. When I saw an allergist and got on allergy shots (plus antihistamines, plus HEPA filters, plus dust mite covers on the mattress) my world changed. I wasn&#x27;t tired all the time. Everything was brighter, and I was in a better mood. I wanted to snack less and had more energy.<p>Piecing it together over the last few years, I had near-constant drainage in the back of my throat even when I wasn&#x27;t showing stronger allergy symptoms (e.g. itchiness, sneezing, watery eyes). As a result, I slept poorly even when I was getting plenty of hours of sleep.<p>Now, I&#x27;m allergic to pretty much everything that doesn&#x27;t kill you (no food allergies, but dust, mold, our cats...) so I can&#x27;t call this a solved problem, but knowing about it lets me work on solving it.</text></comment> | <story><title>Poor Sleep Gives You the Munchies, Study Says</title><url>http://www.nytimes.com/2016/03/05/science/sleep-eating-craving-food.html?module=WatchingPortal&region=c-column-middle-span-region&pgType=Homepage&action=click&mediaId=wide&state=standard&contentPlacement=4&version=internal&contentCollection=www.nytimes.com&contentId=http%3A%2F%2Fwww.nytimes.com%2F2016%2F03%2F05%2Fscience%2Fsleep-eating-craving-food.html&eventName=Watching-article-click</url></story><parent_chain></parent_chain><comment><author>JustSomeNobody</author><text>I thought this was understood for a long time. One of the TOP pieces of advice for anyone wanting to lose weight has, as far as I can remember, been to get adequate amounts of sleep.</text></comment> |
30,504,103 | 30,503,057 | 1 | 2 | 30,501,500 | train | <story><title>A Winner-Takes-All MMO-SAT</title><url>https://mschfboard.org/</url></story><parent_chain><item><author>skulk</author><text>Given the &quot;no-holds-barred, first-past-the-post&quot; nature of this, the winner will be a group of people who split the test and each solved their part.</text></item></parent_chain><comment><author>zucker42</author><text>Given that one question missed means you lose, you have to be very careful to choose a good team. I&#x27;ve gotten a perfect score on a standardized test (during high school) but while I know a lot of smart people, I know no one who has also gotten a perfect score. And it&#x27;s hard to know how to quickly distribute the test since the online format hasn&#x27;t been released.</text></comment> | <story><title>A Winner-Takes-All MMO-SAT</title><url>https://mschfboard.org/</url></story><parent_chain><item><author>skulk</author><text>Given the &quot;no-holds-barred, first-past-the-post&quot; nature of this, the winner will be a group of people who split the test and each solved their part.</text></item></parent_chain><comment><author>SteveDR</author><text>Definitely. But how will they split the 154 questions? The prize pool is already big enough ($13k just a couple hours after the announcement and 5 days before the registration deadline) that 50 people could take it together and walk away with $260 each.</text></comment> |
9,306,182 | 9,305,233 | 1 | 3 | 9,304,807 | train | <story><title>Poor land use in the world’s greatest cities carries a huge cost</title><url>http://www.economist.com/news/leaders/21647614-poor-land-use-worlds-greatest-cities-carries-huge-cost-space-and-city</url></story><parent_chain></parent_chain><comment><author>dankohn1</author><text>I may live in the densest neighborhood of any HN participant: North Battery Park City [1] in Lower Manhattan. As an example, my son&#x27;s 500 kid elementary school serves <i>9</i> buildings.<p>And I&#x27;m here to tell you, the future feels great. Specifically, living vertically has all sorts of wonderful aspects in terms of community (the kids can trick-or-treat without leaving the building), access to resources (my kids can ride the elevator barefoot to the waterpark out the back door in the summer) and environmentally (we live in the first LEED platinum residential building in the US).<p>The only problem is that it is expensive, and it doesn&#x27;t need to be as expensive as it is. Building lots more residential skyscrapers, eliminating parking minimums [2], and reducing the incentive to warehouse vacant lots through land taxes or similar can all make New York City even more livable than it already is.<p>[1] <a href="http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Battery_Park_City" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Battery_Park_City</a>
[2] <a href="http:&#x2F;&#x2F;www.streetsblog.org&#x2F;2012&#x2F;03&#x2F;21&#x2F;report-details-how-onerous-nycs-parking-regressive-minimums-really-are&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.streetsblog.org&#x2F;2012&#x2F;03&#x2F;21&#x2F;report-details-how-one...</a></text></comment> | <story><title>Poor land use in the world’s greatest cities carries a huge cost</title><url>http://www.economist.com/news/leaders/21647614-poor-land-use-worlds-greatest-cities-carries-huge-cost-space-and-city</url></story><parent_chain></parent_chain><comment><author>rayiner</author><text>&gt; Lifting all the barriers to urban growth in America could raise the country’s GDP by between 6.5% and 13.5%, or by about $1 trillion-2 trillion. It is difficult to think of many other policies that would yield anything like that.<p>And it would also reduce the real but unaccounted-for environmental and social externalities of our sprawling homogenous suburbs. Someone living in New York has half the energy footprint of the average American. And while the city is pretty segregated, the New York subway is a unique setting of rich and poor people of all races utilizing a public service together.</text></comment> |
12,557,889 | 12,557,324 | 1 | 2 | 12,556,848 | train | <story><title>Where will the next major advance towards general purpose AI come from?</title><url>http://www.nowozin.net/sebastian/blog/where-will-artificial-intelligence-come-from.html</url></story><parent_chain><item><author>JoeAltmaier</author><text>A hard problem to be sure. But much of a human brain is a uniform matrix that self-programs. If we duplicate that blindly, we won&#x27;t have to figure out how that works or have to program it.<p>Still a lot to do before that I guess. But 500 years? What else in human history has taken that long to figure out? The age of technology is shorter than that.</text></item><item><author>Balgair</author><text>This is a bad title, it should be &quot;Where will advances in AI come from now?&quot;, In the first paragraph, the author states that AI is here, but asks where new AI advances will be from.<p>On that, in 2, the author talks about Brain Simulations and states that it&#x27;ll take up to 500 years. I think that is a good upper estimate actually. Though optogenetics is a great tool, we need more. Mammalian brains can be up to 50% (at the low estimate, some say 90%) made out of astrocytes and glia. We know pretty much nothing about how they affect neuro processes, outside that they do, sometimes. We do know that is a huge problem with our understanding though, which is something I guess. Optogenetics should help tease out some of those glia methods, but as usual, it will raise more questions than answers. Another issue is potentation and its molecular mechanisms in more than just the hippocampus. That work is incredibly tough, but we really only focus on the anatomically &#x27;easy&#x27; areas for memory. We have to do more to understand. In short, we don&#x27;t even know the correct questions to ask when it comes to the brain and understanding it. A full simulation, or a &#x27;80%&#x27; approximation even, is a few paradigm shifts away still (maybe, we cant know yet). It will likely have to be a &#x27;full world&#x27; simulation too, where you have to control all the inputs to the brain and therefore have to model a world first. The brain&#x27;s best feature is that it is all connected and a giant spaghetti mess. This is, obviously, a long ways away.</text></item></parent_chain><comment><author>sangnoir</author><text>&gt; But 500 years? What else in human history has taken that long to figure out?<p>Powered, heavier than air flight falls into that ball park. da Vinci was making doodles in the (late) 15th century, but this was only accomplished by the Wright brothers in the (early) 20th century.<p>Edit: After additional research, I discovered that <i>recorded</i> attempts at manned flight can be found as far back as the 11th[1] century! So it took roughly 700 years to figure out, if not longer as earlier attempts were likely not recorded.<p>1. <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Ornithopter" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Ornithopter</a></text></comment> | <story><title>Where will the next major advance towards general purpose AI come from?</title><url>http://www.nowozin.net/sebastian/blog/where-will-artificial-intelligence-come-from.html</url></story><parent_chain><item><author>JoeAltmaier</author><text>A hard problem to be sure. But much of a human brain is a uniform matrix that self-programs. If we duplicate that blindly, we won&#x27;t have to figure out how that works or have to program it.<p>Still a lot to do before that I guess. But 500 years? What else in human history has taken that long to figure out? The age of technology is shorter than that.</text></item><item><author>Balgair</author><text>This is a bad title, it should be &quot;Where will advances in AI come from now?&quot;, In the first paragraph, the author states that AI is here, but asks where new AI advances will be from.<p>On that, in 2, the author talks about Brain Simulations and states that it&#x27;ll take up to 500 years. I think that is a good upper estimate actually. Though optogenetics is a great tool, we need more. Mammalian brains can be up to 50% (at the low estimate, some say 90%) made out of astrocytes and glia. We know pretty much nothing about how they affect neuro processes, outside that they do, sometimes. We do know that is a huge problem with our understanding though, which is something I guess. Optogenetics should help tease out some of those glia methods, but as usual, it will raise more questions than answers. Another issue is potentation and its molecular mechanisms in more than just the hippocampus. That work is incredibly tough, but we really only focus on the anatomically &#x27;easy&#x27; areas for memory. We have to do more to understand. In short, we don&#x27;t even know the correct questions to ask when it comes to the brain and understanding it. A full simulation, or a &#x27;80%&#x27; approximation even, is a few paradigm shifts away still (maybe, we cant know yet). It will likely have to be a &#x27;full world&#x27; simulation too, where you have to control all the inputs to the brain and therefore have to model a world first. The brain&#x27;s best feature is that it is all connected and a giant spaghetti mess. This is, obviously, a long ways away.</text></item></parent_chain><comment><author>dmd</author><text>&gt; But much of a human brain is a uniform matrix that self-programs.<p>Speaking as a neuroscience PhD ... no. Not remotely close, sorry.</text></comment> |
14,757,477 | 14,756,960 | 1 | 3 | 14,754,614 | train | <story><title>ClojureScript Is Not An Island: Integrating Node Modules</title><url>https://clojurescript.org/news/2017-07-12-clojurescript-is-not-an-island-integrating-node-modules</url></story><parent_chain></parent_chain><comment><author>priornix</author><text>One thing I really like about Clojure is how the language has basically stayed the same, but I can use it on the heavy server-side stuffs like working with Hadoop, Spark, ElasticSearch to the front-end stuff like React, React Native, to CLR and now into nodejs, while staying sane [1] in the process. It feels like comparing a nice tropical island paradise to a crowded, hectic, mutating market, where everyone is competing for your attention and selling their newest wares.<p>[1] <a href="https:&#x2F;&#x2F;hackernoon.com&#x2F;how-it-feels-to-learn-javascript-in-2016-d3a717dd577f" rel="nofollow">https:&#x2F;&#x2F;hackernoon.com&#x2F;how-it-feels-to-learn-javascript-in-2...</a></text></comment> | <story><title>ClojureScript Is Not An Island: Integrating Node Modules</title><url>https://clojurescript.org/news/2017-07-12-clojurescript-is-not-an-island-integrating-node-modules</url></story><parent_chain></parent_chain><comment><author>lilactown</author><text>This is awesome. CLJS is amazingly close to having as good host-interop with JavaScript as plain Clojure does with Java.<p>Will be interesting to see how this impacts things like the React Native and Node.js service-side stories.</text></comment> |
32,908,540 | 32,908,552 | 1 | 2 | 32,907,726 | train | <story><title>Deadlines are pointless – what to do instead</title><url>https://lucasfcosta.com/2022/09/15/deadlines.html</url></story><parent_chain><item><author>sooyoo</author><text>Yes, imagine air travel was run without deadlines.<p>You&#x27;ve booked a flight on dec 1 at 3pm. You check in, sit at the gate. At 2:40pm you are informed that, sorry, the plane isn&#x27;t actually there yet. It&#x27;s still on route. We&#x27;ll fly at 7pm instead. You sit and wait. At 6:45pm you are informed that the plane is there, but the airport is out of fuel. More fuel will be there tomorrow. Rescheduled for next morning at 8am. You wait. At 7:40am next morning you are informed that the pilots are not awake yet. They had a long day yesterday, then went for some drinks, they just had to sleep in today. Rescheduled to 11am. At 10:30am somebody tells you that, well, things are in place but ATC went to a team building event, all flights grounded, but will be back at 4pm. You finally lift off, 25 hours late.<p>Entirely preventable had a deadline be set and all necessary components be scheduled correctly to meet that deadline.<p>Deadlines serve a purpose beyond coersion. There is misuse, but if you widen your horizon then you may realize that not all of it is.</text></item><item><author>ahaproudowl</author><text>Yes, imagine air travel wasrun like that: &quot;The plane must be ready by December 1st!&quot;<p>Proper safety checks wouldn&#x27;t let the plane leave the ground. Delays in that critical state are inconvenient, but you accept them because the alternative is not acceptable.<p>We should treat software in exactly the same way, It&#x27;s ready when it&#x27;s ready.<p>The issue is the illusion of control. A bad CEO will measure the performance of his CTO by productivity alone. A good CEO will measure the CTO&#x27;s output by consistently increasing quality.</text></item><item><author>arnvald</author><text>Most deadlines in my career so far were arbitrary. Sure, some deadlines were driven by fixed events, for example Christmas promotion has to be launched before Christmas.<p>But in most cases when I asked managers about the reason behind the deadline, the answer was something like &quot;oh,I promised this team&#x2F;director we&#x27;ll do it by then&quot;. When I dug deeper to see what happens if we miss the deadline, it appeared the said team would be just fine, there were no real life consequences, just that they wanted to finish their part of work by certain time, and they depended on us.<p>I&#x27;m not saying deadlines are useless, but they&#x27;re very often driven by some arbitrary promises made by managers before even consulting developers about the complexity of work to be done.</text></item><item><author>PragmaticPulp</author><text>It’s always fascinating to read these anti-deadline articles that assume deadlines are arbitrary things that exist for no reason.<p>That might be moderately true for, say, someone developing a new app feature that gets shipped to users who aren’t expecting it. However, it’s not true at all when the software development output is a gating feature for real-world contractual obligations and other such business drivers. In that case, target dates must be carefully forecasted and estimates must be performed with great care and detain. This doesn’t guarantee that a target date will be hit, of course, but it’s not impossible to produce estimates that are reasonable accurate a large percentage of the time.<p>Estimation, planning, and progress tracking are difficult skills that must be learned, but they’re not impossible. I suspect many of the developers who believe that target dates are always arbitrary, pointless, and impossible to estimate have mostly worked in big cash-rich environments where it didn’t really matter when a feature shipped. If you go to the other end of the spectrum and talk to engineers who work in industries where target dates are critical you’ll discover a lot of people who are very good at breaking down projects and accurately estimating dates without relying on crunch time to get things done. It may sound impossible if you’ve never worked in an industry that requires such precision, but it makes sense after you’ve worked in such an environment for a while.</text></item></parent_chain><comment><author>selcuka</author><text>Obviously the OP is talking about developing and manufacturing a plane, not flying it. Your example is a schedule, not a deadline.</text></comment> | <story><title>Deadlines are pointless – what to do instead</title><url>https://lucasfcosta.com/2022/09/15/deadlines.html</url></story><parent_chain><item><author>sooyoo</author><text>Yes, imagine air travel was run without deadlines.<p>You&#x27;ve booked a flight on dec 1 at 3pm. You check in, sit at the gate. At 2:40pm you are informed that, sorry, the plane isn&#x27;t actually there yet. It&#x27;s still on route. We&#x27;ll fly at 7pm instead. You sit and wait. At 6:45pm you are informed that the plane is there, but the airport is out of fuel. More fuel will be there tomorrow. Rescheduled for next morning at 8am. You wait. At 7:40am next morning you are informed that the pilots are not awake yet. They had a long day yesterday, then went for some drinks, they just had to sleep in today. Rescheduled to 11am. At 10:30am somebody tells you that, well, things are in place but ATC went to a team building event, all flights grounded, but will be back at 4pm. You finally lift off, 25 hours late.<p>Entirely preventable had a deadline be set and all necessary components be scheduled correctly to meet that deadline.<p>Deadlines serve a purpose beyond coersion. There is misuse, but if you widen your horizon then you may realize that not all of it is.</text></item><item><author>ahaproudowl</author><text>Yes, imagine air travel wasrun like that: &quot;The plane must be ready by December 1st!&quot;<p>Proper safety checks wouldn&#x27;t let the plane leave the ground. Delays in that critical state are inconvenient, but you accept them because the alternative is not acceptable.<p>We should treat software in exactly the same way, It&#x27;s ready when it&#x27;s ready.<p>The issue is the illusion of control. A bad CEO will measure the performance of his CTO by productivity alone. A good CEO will measure the CTO&#x27;s output by consistently increasing quality.</text></item><item><author>arnvald</author><text>Most deadlines in my career so far were arbitrary. Sure, some deadlines were driven by fixed events, for example Christmas promotion has to be launched before Christmas.<p>But in most cases when I asked managers about the reason behind the deadline, the answer was something like &quot;oh,I promised this team&#x2F;director we&#x27;ll do it by then&quot;. When I dug deeper to see what happens if we miss the deadline, it appeared the said team would be just fine, there were no real life consequences, just that they wanted to finish their part of work by certain time, and they depended on us.<p>I&#x27;m not saying deadlines are useless, but they&#x27;re very often driven by some arbitrary promises made by managers before even consulting developers about the complexity of work to be done.</text></item><item><author>PragmaticPulp</author><text>It’s always fascinating to read these anti-deadline articles that assume deadlines are arbitrary things that exist for no reason.<p>That might be moderately true for, say, someone developing a new app feature that gets shipped to users who aren’t expecting it. However, it’s not true at all when the software development output is a gating feature for real-world contractual obligations and other such business drivers. In that case, target dates must be carefully forecasted and estimates must be performed with great care and detain. This doesn’t guarantee that a target date will be hit, of course, but it’s not impossible to produce estimates that are reasonable accurate a large percentage of the time.<p>Estimation, planning, and progress tracking are difficult skills that must be learned, but they’re not impossible. I suspect many of the developers who believe that target dates are always arbitrary, pointless, and impossible to estimate have mostly worked in big cash-rich environments where it didn’t really matter when a feature shipped. If you go to the other end of the spectrum and talk to engineers who work in industries where target dates are critical you’ll discover a lot of people who are very good at breaking down projects and accurately estimating dates without relying on crunch time to get things done. It may sound impossible if you’ve never worked in an industry that requires such precision, but it makes sense after you’ve worked in such an environment for a while.</text></item></parent_chain><comment><author>makeitdouble</author><text>You&#x27;re not describing a &quot;creative&quot; situation where you are building something new.<p>If you had to reexplore and reinvent flight routes every single time, yes deadline in that scenario would also become meaningless as you&#x27;d have no idea what lies ahead each time. It would be the same as setting a deadline on how long Columbus should take to reach India.</text></comment> |
8,254,311 | 8,254,106 | 1 | 2 | 8,253,979 | train | <story><title>Plants in offices increase happiness and productivity</title><url>http://www.theguardian.com/money/2014/aug/31/plants-offices-workers-productive-minimalist-employees</url></story><parent_chain></parent_chain><comment><author>IvyMike</author><text>Funny enough, when the plants show up, in my experience it&#x27;s a bad sign. I have no proof this conversation happened at the last two places I worked... but I&#x27;m pretty sure it did happen.<p>Upper-level manager #1: &quot;The results of the employee morale survey are back. Morale is at an all time low. The employees feel that upper-level management is clueless, they are increasingly unable to do their jobs efficiently because of process and bureaucracy, and the raises we gave this year were below industry average.&quot;<p>Upper-level manager #2: &quot;I just googled &#x27;how to raise morale&#x27; and it said &#x27;plants&#x27;&quot;<p>Upper-level manager #1: &quot;Let&#x27;s do that!&quot;</text></comment> | <story><title>Plants in offices increase happiness and productivity</title><url>http://www.theguardian.com/money/2014/aug/31/plants-offices-workers-productive-minimalist-employees</url></story><parent_chain></parent_chain><comment><author>dominotw</author><text>I have this[1] closed ecosystem on my desk that I share with a coworker. Best decision ever.<p>1. <a href="http://www.amazon.com/gp/product/B005IZOB5M/" rel="nofollow">http:&#x2F;&#x2F;www.amazon.com&#x2F;gp&#x2F;product&#x2F;B005IZOB5M&#x2F;</a></text></comment> |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.