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
|
|---|---|---|---|---|---|---|---|
13,251,636 | 13,251,331 | 1 | 2 | 13,250,949 | train | <story><title>Die photos and analysis of the revolutionary 8008 microprocessor, 45 years old</title><url>http://www.righto.com/2016/12/die-photos-and-analysis-of_24.html</url></story><parent_chain></parent_chain><comment><author>contingencies</author><text>Not directly related but just last week I just gifted two Intel 8088 machines including one in a really beautiful case with original &quot;3 year warranty!&quot; sticker, along with other stuff (period disks, Apple LCII, Apple II, SGI&#x2F;SunOS&#x2F;Solaris stuff, etc.) to <a href="http:&#x2F;&#x2F;acms.org.au&#x2F;" rel="nofollow">http:&#x2F;&#x2F;acms.org.au&#x2F;</a> who are looking for an exhibition location for their huge collection. As a registered charity, space donations are tax deductible and can help meet council public space&#x2F;cultural requirements for new developments. Requirements: Sydney or Canberra, 100-300m2 exhibition space (really 200+), 500-1000m2 storage space (500+ already in use).</text></comment> | <story><title>Die photos and analysis of the revolutionary 8008 microprocessor, 45 years old</title><url>http://www.righto.com/2016/12/die-photos-and-analysis-of_24.html</url></story><parent_chain></parent_chain><comment><author>ChuckMcM</author><text>Very cool, as I recall the 8080 needed multiple power supplies and a clock generator and the 8080A made those internal to the chip. The Z80 was usable with no support chips at all and I believe that was the primary motivation for the 8085.<p>When you look that notion of the 8238 you can see the seeds of the &#x27;south bridge&#x27; that was so prevalent in PC design. Intel systems broke apart as &quot;memory&quot; (northbridge), &quot;compute&quot; (cpu), and &quot;i&#x2F;o&quot; (southbridge). That has been a pretty successful architecture and one that ARM would do well to emulate for their non-SoC offerings.</text></comment> |
8,047,629 | 8,046,525 | 1 | 2 | 8,046,477 | train | <story><title>How tall can a Lego tower get?</title><url>http://www.bbc.co.uk/news/magazine-20578627</url></story><parent_chain></parent_chain><comment><author>wbracken</author><text>I already knew legos were strong without this research.<p>For instance, I know for a fact from legos left on the floor by kids that one lego can hold my entire weight (240 pounds) when I step on it in the middle of the night walking to the bathroom with no signs of damage to said lego.<p>Further, I know that one lego can by itself topple a fully grown man.</text></comment> | <story><title>How tall can a Lego tower get?</title><url>http://www.bbc.co.uk/news/magazine-20578627</url></story><parent_chain></parent_chain><comment><author>D_Alex</author><text>&gt;The average maximum force the bricks can stand is 4,240N. That&#x27;s equivalent to a mass of 432kg (950lbs). If you divide that by the mass of a single brick, which is 1.152g, then you get the grand total of bricks a single piece of Lego could support: 375,000.<p>&gt;So, 375,000 bricks towering 3.5km (2.17 miles) high is what it would take to break a Lego brick.<p>&gt;&quot;That&#x27;s taller than the highest mountain in Spain. It&#x27;s significantly higher than Mount Olympus [tallest mountain in Greece], and it&#x27;s the typical height at which people ski in the Alps,&quot; Ian Johnston says (though many skiers also ski at lower altitudes).<p>&gt;&quot;So if the Greek gods wanted to build a new temple on Mount Olympus, and Mount Olympus wasn&#x27;t available, they could just - but no more - do it with Lego bricks. As long as they don&#x27;t jump up and down too much.&quot;<p>Well, in theory you can go as high as you want, by tapering the tower towards the top. The 3.5 km limit is only valid for straight, constant cross-section structures.<p>Which mountains certainly are not.</text></comment> |
28,775,621 | 28,775,614 | 1 | 2 | 28,773,509 | train | <story><title>Apple to face EU antitrust charge over NFC chip</title><url>https://www.reuters.com/technology/exclusive-eu-antitrust-regulators-charge-apple-over-its-nfc-chip-tech-sources-2021-10-06/</url></story><parent_chain><item><author>cnst</author><text>You are aware that 20+ is actually the magical number of accounts that you&#x27;re supposed to have in your credit file to have the best credit score?<p>This is not even about credit cards. Debit counts, too. Say you have two bank accounts, an HSA account, one premium card, one business credit card, one everyday card, one… Oops, out of slots already!<p>It sounds like you&#x27;re really happy with Apple products, and will simply change your life around them, instead of demanding something better. 6+ cards is probably already the average for many people.</text></item><item><author>marcellus23</author><text>I&#x27;m gonna drop this HN comment into the bin of &quot;I have an extremely unusual need, but am totally obvlious about it, so this product is objectively bad for not catering to it&quot;<p>Normal people do not have 20 credit cards. Even people I know who have several cards, often only have a couple they actually use on a daily basis. This is not a real problem.</text></item><item><author>cnst</author><text>That&#x27;s some good news, hopefully a change will follow.<p>Note that Apple Pay also has a very low limit on the number of cards that you can add, presumably because each card occupies an actual hardware slot. In the original iPhone SE, that&#x27;s only 8 cards, and Apple Cash (the debit card) gets counted as one of those (unless you&#x27;re remove it manually), then if you have Apple Card (the credit card), presumably it takes another slot, so you&#x27;re only left with just 6 slots for any other contactless credit or debit card.<p>How&#x27;s such a low limit good for the consumer? If you only have 6 cards in total, might as well simply carry all of them in your wallet anyways; I do that already.<p>Android Pay and Google Pay don&#x27;t have such tiny, restrictive and anticompetitive limits. I have like 20 different credit cards as contactless in Google Pay without any issues, which is very convenient if you care about bonus categories; same was for Android Pay before it got rebranded as Google Pay.<p>Plus, in Android, you can even select a third party app to be used for contactless in the &quot;Default apps&quot; — &quot;Tap &amp; pay&quot; settings instead of Google Pay; I know Wells Fargo used to have contactless support in their own app at one point, for example, and was selectable there.</text></item></parent_chain><comment><author>thereddaikon</author><text>Says who? I have great with only one credit card. The key to good credit isn&#x27;t some esoteric process to game the system. Its having a good and long credit history.</text></comment> | <story><title>Apple to face EU antitrust charge over NFC chip</title><url>https://www.reuters.com/technology/exclusive-eu-antitrust-regulators-charge-apple-over-its-nfc-chip-tech-sources-2021-10-06/</url></story><parent_chain><item><author>cnst</author><text>You are aware that 20+ is actually the magical number of accounts that you&#x27;re supposed to have in your credit file to have the best credit score?<p>This is not even about credit cards. Debit counts, too. Say you have two bank accounts, an HSA account, one premium card, one business credit card, one everyday card, one… Oops, out of slots already!<p>It sounds like you&#x27;re really happy with Apple products, and will simply change your life around them, instead of demanding something better. 6+ cards is probably already the average for many people.</text></item><item><author>marcellus23</author><text>I&#x27;m gonna drop this HN comment into the bin of &quot;I have an extremely unusual need, but am totally obvlious about it, so this product is objectively bad for not catering to it&quot;<p>Normal people do not have 20 credit cards. Even people I know who have several cards, often only have a couple they actually use on a daily basis. This is not a real problem.</text></item><item><author>cnst</author><text>That&#x27;s some good news, hopefully a change will follow.<p>Note that Apple Pay also has a very low limit on the number of cards that you can add, presumably because each card occupies an actual hardware slot. In the original iPhone SE, that&#x27;s only 8 cards, and Apple Cash (the debit card) gets counted as one of those (unless you&#x27;re remove it manually), then if you have Apple Card (the credit card), presumably it takes another slot, so you&#x27;re only left with just 6 slots for any other contactless credit or debit card.<p>How&#x27;s such a low limit good for the consumer? If you only have 6 cards in total, might as well simply carry all of them in your wallet anyways; I do that already.<p>Android Pay and Google Pay don&#x27;t have such tiny, restrictive and anticompetitive limits. I have like 20 different credit cards as contactless in Google Pay without any issues, which is very convenient if you care about bonus categories; same was for Android Pay before it got rebranded as Google Pay.<p>Plus, in Android, you can even select a third party app to be used for contactless in the &quot;Default apps&quot; — &quot;Tap &amp; pay&quot; settings instead of Google Pay; I know Wells Fargo used to have contactless support in their own app at one point, for example, and was selectable there.</text></item></parent_chain><comment><author>airstrike</author><text>But do you really need to add all of those 20 cards to your digital wallet? Just carry the cards with you if you care so much about min-maxing the credit score game.</text></comment> |
26,898,482 | 26,898,523 | 1 | 2 | 26,897,106 | train | <story><title>Why I distrust Google Cloud more than than AWS or Azure</title><url>http://www.iasylum.net/writings/2021-04-21-why-I-distrust-google-cloud-more-than-AWS-or-Azure.html</url></story><parent_chain><item><author>goodcjw2</author><text>[DISCLAMER: I used to work at Google in general, but not at Google Cloud]<p>I&#x27;m not sure whether this has been discussed here before, but I&#x27;d love to take this forum to share an angle from the tech side of things:<p>IMO, Google is _cursed_ to keep deprecating its products and services. It&#x27;s cursed by Google&#x27;s famous choice of mono-repo tech stack.<p>It makes all the sense and has all the benefits. But at a cost: we had to keep every single line of code in active development mode. Whenever someone changed a line of code in a random file that&#x27;s three steps away on your dependency chain, you will get a ticket to understand what has changed, make changes and fire up every tests (also fix them in 99% of the cases).<p>Yeah, the &quot;Fuck You. Drop whatever you are doing because it’s not important. What is important is OUR time. It’s costing us time and money to support our shit, and we’re tired of it, so we’re not going to support it anymore.&quot; is kind of true story for internal engineers.<p>We once had a shipped product (which took about 20-engineer-month to develop in the first place) in maintenance mode, but still requires a full time engineer to deal with those random things all the time. Would have save 90% of that person&#x27;s time it it&#x27;s on a sperate branch and we only need to focus on security patches. (NO, there is no such concept of branching in Google&#x27;s dev system).<p>We kept doing this for a while and soon realized that there is no way we can sustain this, especially after the only guys who understand how everything works switched teams. Thus, it just became obvious that deprecation is the only &quot;responsible&quot; and &quot;reasonable&quot; choice.<p>Honestly, I think Google&#x27;s engineering practice is somewhat flawed for the lack of a good solution to support shipped products in maintenance. As a result, there is either massively successful products being actively developed; or deprecated products.</text></item></parent_chain><comment><author>paxys</author><text>I have also worked at Google (in an unrelated department) and completely disagree with this. Maintaining old code &amp; services is a problem everywhere. Monorepo vs multirepo, monolith service vs microservices etc. all have nothing to do with it. There will always be a broken dependency, a service&#x2F;API&#x2F;library you rely on about to deprecate, new urgent security patches, an outage somewhere upstream or downstream which you have to investigate, an important customer hitting an edge case which was hidden for years. You will <i>always</i> need a dedicated team to support a live product regardless of how it is engineered.<p>The problem at Google was (and maybe still is) with lack of incentives at the product level to do any of this. You don&#x27;t get a fat bonus and promotion for saying that you kept things working as they should, made an incremental update or fixed bugs. When your packet goes up to the committee (who don&#x27;t know you and know nothing about your team or background), the only thing that works in your favor is a successful new product launch.<p>And as an engineer you still have multiple avenues to showcase your skills. That new product manager you just hired from Harvard Business School who is eager to climb the ladder does not. And due to the lack of a central cohesive product strategy, this PM also has complete control of your team&#x27;s annual roadmap.</text></comment> | <story><title>Why I distrust Google Cloud more than than AWS or Azure</title><url>http://www.iasylum.net/writings/2021-04-21-why-I-distrust-google-cloud-more-than-AWS-or-Azure.html</url></story><parent_chain><item><author>goodcjw2</author><text>[DISCLAMER: I used to work at Google in general, but not at Google Cloud]<p>I&#x27;m not sure whether this has been discussed here before, but I&#x27;d love to take this forum to share an angle from the tech side of things:<p>IMO, Google is _cursed_ to keep deprecating its products and services. It&#x27;s cursed by Google&#x27;s famous choice of mono-repo tech stack.<p>It makes all the sense and has all the benefits. But at a cost: we had to keep every single line of code in active development mode. Whenever someone changed a line of code in a random file that&#x27;s three steps away on your dependency chain, you will get a ticket to understand what has changed, make changes and fire up every tests (also fix them in 99% of the cases).<p>Yeah, the &quot;Fuck You. Drop whatever you are doing because it’s not important. What is important is OUR time. It’s costing us time and money to support our shit, and we’re tired of it, so we’re not going to support it anymore.&quot; is kind of true story for internal engineers.<p>We once had a shipped product (which took about 20-engineer-month to develop in the first place) in maintenance mode, but still requires a full time engineer to deal with those random things all the time. Would have save 90% of that person&#x27;s time it it&#x27;s on a sperate branch and we only need to focus on security patches. (NO, there is no such concept of branching in Google&#x27;s dev system).<p>We kept doing this for a while and soon realized that there is no way we can sustain this, especially after the only guys who understand how everything works switched teams. Thus, it just became obvious that deprecation is the only &quot;responsible&quot; and &quot;reasonable&quot; choice.<p>Honestly, I think Google&#x27;s engineering practice is somewhat flawed for the lack of a good solution to support shipped products in maintenance. As a result, there is either massively successful products being actively developed; or deprecated products.</text></item></parent_chain><comment><author>krasin</author><text>I work for Google for the 3rd time; 12+ years in total. It&#x27;s first time when this issue is brought to my conscience. I think that the issue exists, but it&#x27;s not due to the monorepo, it&#x27;s due to the internal APIs changing.<p>I learned how to avoid the Google3 tax that you mentioned, when the old thing is deprecated, and the new one is not working yet.<p>Surprisingly, the answer for me was to embrace Google Cloud: its APIs have stability guarantees. My current project depends on Google Cloud Storage, Cloud Spanner, Cloud Firestore and very few internal technologies.<p>I believe that this is in general a trend at Google: increasing reliance on Google Cloud for new projects. In this sense, both internal and external developers are in the same boat.<p>As for the monorepo - it&#x27;s a blessing, in my perspective. Less rotten code, much easier to contribute improvements across the stack.</text></comment> |
13,445,376 | 13,445,344 | 1 | 3 | 13,445,063 | train | <story><title>Ask HN: Recommended guides for learning filesystems?</title><text>Hi, *nix newbie here. I&#x27;m struggling with understanding how my Ubuntu&#x27;s filesystem works and what general practices various applications follow when they install to my Ubuntu instance. I&#x27;m currently reading the ldconfig man page and feeling pretty lost. Any good guides or resources for understanding how filesystems and links work?<p>Thanks!</text></story><parent_chain></parent_chain><comment><author>digikata</author><text>I think you&#x27;re asking two different questions here. What are some standard conventions for where system files are placed in Ubuntu &amp; Linux? And how are filesystems implemented.<p>For file placement you might start here:
<a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Filesystem_Hierarchy_Standard" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Filesystem_Hierarchy_Standard</a><p>Though I&#x27;d caution that it&#x27;s not a strict standard, and you find that many linux distributions vary from it in particular ways.<p>For the implementation of file systems on Unix&#x2F;Linux&#x2F;Ubuntu, I&#x27;d say start at understanding inodes: (this link is just the first I found that seems like a reasonably short overview from my standpoint)
<a href="https:&#x2F;&#x2F;www.cs.nmsu.edu&#x2F;~pfeiffer&#x2F;classes&#x2F;474&#x2F;notes&#x2F;inodefs.html" rel="nofollow">https:&#x2F;&#x2F;www.cs.nmsu.edu&#x2F;~pfeiffer&#x2F;classes&#x2F;474&#x2F;notes&#x2F;inodefs....</a><p>There are a world of different implementations when you get to the details, but the Linux kernel builds or reuses this core idea of inodes into many specific different filesystems. From there there is a lot of info, but the Linux VFS layer handles many common functions of of filesystems in Linux (even if you&#x27;re system is using ext4 or btrfs, etc specifically). So the Linus Kernel vfs docs may be interesting if you&#x27;re looking to go even deeper.</text></comment> | <story><title>Ask HN: Recommended guides for learning filesystems?</title><text>Hi, *nix newbie here. I&#x27;m struggling with understanding how my Ubuntu&#x27;s filesystem works and what general practices various applications follow when they install to my Ubuntu instance. I&#x27;m currently reading the ldconfig man page and feeling pretty lost. Any good guides or resources for understanding how filesystems and links work?<p>Thanks!</text></story><parent_chain></parent_chain><comment><author>crossbowerbt</author><text>A good book, but not widely known (maybe a little low level, but still...)<p>Ah, it&#x27;s also free ;)<p>From the the haiku project website:
<a href="https:&#x2F;&#x2F;www.haiku-os.org&#x2F;legacy-docs&#x2F;practical-file-system-design.pdf" rel="nofollow">https:&#x2F;&#x2F;www.haiku-os.org&#x2F;legacy-docs&#x2F;practical-file-system-d...</a></text></comment> |
8,921,823 | 8,920,734 | 1 | 3 | 8,920,046 | train | <story><title>WebVR lands in Firefox Nightly</title><url>http://mozvr.com/posts/webvr-lands-in-nightly/</url><text></text></story><parent_chain></parent_chain><comment><author>comrade1</author><text>I&#x27;m looking forward to the return of vrml. A memorable post on HN:
<a href="https://news.ycombinator.com/item?id=7301062" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=7301062</a><p>&quot;I worked on a VRML retail store that had 3D products on 3D shelves and 3D customer service reps you could chat with. It was just like shopping in a real world retail store, except you&#x27;re tripping on LSD flying uncontrollably upside down through a bright colored world of blocks and pyramids while wearing binoculars until you punch a hole in the sky and your browser crashes. The world just wasn&#x27;t ready to shop in 3D.&quot;</text></comment> | <story><title>WebVR lands in Firefox Nightly</title><url>http://mozvr.com/posts/webvr-lands-in-nightly/</url><text></text></story><parent_chain></parent_chain><comment><author>msoad</author><text>This is what&#x27;s possible with WebVR:
<a href="https://www.youtube.com/watch?v=db-7J5OaSag" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=db-7J5OaSag</a></text></comment> |
1,379,775 | 1,379,705 | 1 | 2 | 1,379,662 | train | <story><title>GPL Enforcement in Apple's App Store</title><url>http://www.fsf.org/news/2010-05-app-store-compliance/</url></story><parent_chain></parent_chain><comment><author>jwr</author><text>The FSF should take a more active role in GPL violations overall. This is by far not the only one. See for example how Drobo completely ignores requests for source code, while spreading FUD about proprietary drivers:<p><a href="http://www.drobospace.com/forums/showthread.php?tid=935&#38;pid=6816&#38;highlight=gpl#pid6816" rel="nofollow">http://www.drobospace.com/forums/showthread.php?tid=935&#38;...</a><p>I'm not a fan of bashing Apple at every occasion, but a shakedown of phone software licensing would not hurt — it would actually clarify the situation (both for iPhone OS and Android) and perhaps force companies to change the terms of service somewhat.<p>UPDATE: I double-checked and since my last request they actually posted an E-mail address where you can supposedly request the code. I did request the code and I'm waiting to see what happens.<p>Also, for those who think this is fanaticism: I'm doing this, because the DroboShare is unreliable and lost my data by corrupting the entire Drobo volume. I need the code, because I want to check whether Drobo actually improved the Linux HFS+ code or not (I suspect not).</text></comment> | <story><title>GPL Enforcement in Apple's App Store</title><url>http://www.fsf.org/news/2010-05-app-store-compliance/</url></story><parent_chain></parent_chain><comment><author>pierrefar</author><text>What I don't like about this post is that they explicitely say <i>The primary problem is that Apple imposes numerous legal restrictions on use and distribution of GNU Go through the iTunes Store Terms of Service, which is forbidden by section 6 of GPLv2.</i> I'd like to see them enumerate these legal restrictions and explain how they contravene the GPL. Don't leave us guessing.<p>For reference, a copy of the GPL V2: <a href="http://www.gnu.org/licenses/gpl-2.0.html" rel="nofollow">http://www.gnu.org/licenses/gpl-2.0.html</a><p>Section 6:<i>6. Each time you redistribute the Program (or any work based on the Program), the recipient automatically receives a license from the original licensor to copy, distribute or modify the Program subject to these terms and conditions. You may not impose any further restrictions on the recipients' exercise of the rights granted herein. You are not responsible for enforcing compliance by third parties to this License.</i></text></comment> |
18,916,696 | 18,910,297 | 1 | 2 | 18,909,650 | train | <story><title>Insect collapse</title><url>https://www.theguardian.com/environment/2019/jan/15/insect-collapse-we-are-destroying-our-life-support-systems</url></story><parent_chain><item><author>fsloth</author><text>It&#x27;s funny we think we are an &quot;advanced&quot; civilization, yet we have no real time diagnostics of the status of our biosphere. It&#x27;s really creepy how little basic research apparently is going on into &quot;boring&quot; ecological factors.<p>This insect apocalypse is like you suddenly notice you are missing an arm and a leg and have no idea what happened to them.<p>Any professionals in um... ecological metrics here? To an outsider it seems there are like three people on the planet who are concerned about the quantifiable properties of our biosphere and only one of them got part time funding.</text></item></parent_chain><comment><author>karandodia</author><text>The funding issue has hamstrung scientists for decades and limited our data to a very small pool, but the trends are increasingly clear: we&#x27;re well into the 6th mass extinction event. See <a href="https:&#x2F;&#x2F;www.stockholmresilience.org&#x2F;research&#x2F;planetary-boundaries&#x2F;planetary-boundaries&#x2F;about-the-research&#x2F;the-nine-planetary-boundaries.html" rel="nofollow">https:&#x2F;&#x2F;www.stockholmresilience.org&#x2F;research&#x2F;planetary-bound...</a>
and
<a href="https:&#x2F;&#x2F;www.nationalgeographic.com&#x2F;animals&#x2F;2018&#x2F;11&#x2F;animal-decline-living-planet-report-conservation-news&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.nationalgeographic.com&#x2F;animals&#x2F;2018&#x2F;11&#x2F;animal-de...</a>.<p>On a more positive note, a few folks I know are in the early stages of an ambitious attempt to regenerate a bioregion: <a href="https:&#x2F;&#x2F;medium.com&#x2F;@joe_brewer&#x2F;we-are-regenerating-an-entire-bioregion-1f1ce7cb29b7" rel="nofollow">https:&#x2F;&#x2F;medium.com&#x2F;@joe_brewer&#x2F;we-are-regenerating-an-entire...</a>. The hope is that this kind of work—developing models of ecosystems rooted in complexity science that expose key leverage points—can be refined through experimentation in Costa Rica and extended to increasingly dissimilar bioregions.</text></comment> | <story><title>Insect collapse</title><url>https://www.theguardian.com/environment/2019/jan/15/insect-collapse-we-are-destroying-our-life-support-systems</url></story><parent_chain><item><author>fsloth</author><text>It&#x27;s funny we think we are an &quot;advanced&quot; civilization, yet we have no real time diagnostics of the status of our biosphere. It&#x27;s really creepy how little basic research apparently is going on into &quot;boring&quot; ecological factors.<p>This insect apocalypse is like you suddenly notice you are missing an arm and a leg and have no idea what happened to them.<p>Any professionals in um... ecological metrics here? To an outsider it seems there are like three people on the planet who are concerned about the quantifiable properties of our biosphere and only one of them got part time funding.</text></item></parent_chain><comment><author>voqv</author><text>For some reason we as humanity have been living really well for the last 50 years and, without thought, we imagine it&#x27;s just going to stay like that.</text></comment> |
14,460,059 | 14,458,699 | 1 | 2 | 14,456,690 | train | <story><title>Uber Posts $708M Loss as Finance Head Leaves</title><url>https://www.wsj.com/articles/uber-posts-708-million-loss-as-finance-head-leaves-1496272500</url></story><parent_chain><item><author>jpatokal</author><text>You&#x27;re ignoring that businessmen who travel all the time are very heavy users of Uber and similar services.<p>I&#x27;m not even a frequent flyer, but I&#x27;d estimate that a good 80-90% of my Uber usage is travel-related. At home, I have tons of other options to get around, but on a tight schedule in an unfamiliar city, I basically default to Uber all the time, because I rarely have the time or risk tolerance explore alternatives.<p>One of the things I love about Uber is that I can use it in SF, Singapore, Manila, Helsinki, wherever. It also works sufficiently well that I have near-zero incentive to try out Lyft&#x2F;Grab&#x2F;Ola&#x2F;whatever, particularly since this usually involves yet another tedious sign-up process of entering credit cards and PIN confirmations and yadda yadda.</text></item><item><author>beager</author><text>I believe that Lyft doesn&#x27;t have to compete globally with Uber to be a successful business in its own right. I also believe that Uber isn&#x27;t immune from being crippled by competitors that operate in a very small but key subset of Uber&#x27;s markets.<p>There is very little network effect with Uber. Sure, you can hop off a plane anywhere in the world and open Uber to get a car, but that is a very small number of people overall. I would contend that most people use whichever ride-sharing service is available and most economical in their own city, and if that same service is available on the rare occasion that they travel, then bonus.<p>Of course, if Uber beats everyone else to the punch with proprietary self-driving cars and undercuts prices profitably, they win. There seem to be some very large issues with that, however.</text></item><item><author>encoderer</author><text>&lt;&#x2F;conjecture&gt;<p>Lyft just isn&#x27;t a real competitor outside of major American cities right now. Go to a city without an international airport and see how many lyft drivers there are.</text></item><item><author>objclxt</author><text>&gt; And what most people miss, is that the 3.4 billion is the 30% cut Uber takes from a ride. Prices don&#x27;t have to rise 20% to break even, prices have to rise 6%<p>No, they have to rise by more than that. Your math is technically correct (a 6% rise gives you an extra $700 million), but you are assuming that the price increase goes entirely to Uber. There is no way Uber can increase prices by 6% and give none of that upside to their drivers - they would flee to platforms offering better terms (like Lyft).<p>If Uber was to be profitable this past quarter they wouldn&#x27;t have needed an extra $700 million in fares, but an extra <i></i>2.3 billion<i></i> - which is a 20% rise.</text></item><item><author>bpodgursky</author><text>$708 million loss, narrowed from $991 million last quarter<p>18% growth from last quarter (note: that&#x27;s not Y&#x2F;Y. this is ridiculously fast, given the huge base.)<p>708mm loss &#x2F; 3.4 billion in revenue is only about 20% under even. And what most people miss, is that the 3.4 billion is the 30% cut Uber takes from a ride. Prices don&#x27;t have to rise 20% to break even, prices have to rise 6% (assuming no efficiency improvements via pool etc, which is frankly ridiculous)<p>Yeah... Uber is doing fine.</text></item></parent_chain><comment><author>CPLX</author><text>Yeah but frequent flying businessmen are also the kind of people who will do research and pick better options quickly if they are available, it&#x27;s not plausible for Uber to have a permanent monopoly.<p>One of Uber&#x27;s <i>massive</i> problems is lack of predictability. When going to&#x2F;from the airport I can&#x27;t fuck around with surge pricing, I need to be able to have a travel budget that doesn&#x27;t change sharply for situations out of my control. I don&#x27;t want to miss planes. A service like Blacklane (which by the way is now in the US and is growing very quickly yet seems to rarely make the articles that talk about Uber&#x27;s competition) neatly solves that problem for you, and generally has better service and more professional drivers.<p>I am a frequent flier and your idea that there&#x27;s zero-incentive to have a backup or alternate option to Uber ready to go doesn&#x27;t resonate with me. Uber isn&#x27;t reliable enough to forget about other options, and as long as those exist and are viable Uber&#x27;s supposed &quot;monopoly&quot; strategy will likely be regarded in retrospect as expensive and stupid waste of capital.</text></comment> | <story><title>Uber Posts $708M Loss as Finance Head Leaves</title><url>https://www.wsj.com/articles/uber-posts-708-million-loss-as-finance-head-leaves-1496272500</url></story><parent_chain><item><author>jpatokal</author><text>You&#x27;re ignoring that businessmen who travel all the time are very heavy users of Uber and similar services.<p>I&#x27;m not even a frequent flyer, but I&#x27;d estimate that a good 80-90% of my Uber usage is travel-related. At home, I have tons of other options to get around, but on a tight schedule in an unfamiliar city, I basically default to Uber all the time, because I rarely have the time or risk tolerance explore alternatives.<p>One of the things I love about Uber is that I can use it in SF, Singapore, Manila, Helsinki, wherever. It also works sufficiently well that I have near-zero incentive to try out Lyft&#x2F;Grab&#x2F;Ola&#x2F;whatever, particularly since this usually involves yet another tedious sign-up process of entering credit cards and PIN confirmations and yadda yadda.</text></item><item><author>beager</author><text>I believe that Lyft doesn&#x27;t have to compete globally with Uber to be a successful business in its own right. I also believe that Uber isn&#x27;t immune from being crippled by competitors that operate in a very small but key subset of Uber&#x27;s markets.<p>There is very little network effect with Uber. Sure, you can hop off a plane anywhere in the world and open Uber to get a car, but that is a very small number of people overall. I would contend that most people use whichever ride-sharing service is available and most economical in their own city, and if that same service is available on the rare occasion that they travel, then bonus.<p>Of course, if Uber beats everyone else to the punch with proprietary self-driving cars and undercuts prices profitably, they win. There seem to be some very large issues with that, however.</text></item><item><author>encoderer</author><text>&lt;&#x2F;conjecture&gt;<p>Lyft just isn&#x27;t a real competitor outside of major American cities right now. Go to a city without an international airport and see how many lyft drivers there are.</text></item><item><author>objclxt</author><text>&gt; And what most people miss, is that the 3.4 billion is the 30% cut Uber takes from a ride. Prices don&#x27;t have to rise 20% to break even, prices have to rise 6%<p>No, they have to rise by more than that. Your math is technically correct (a 6% rise gives you an extra $700 million), but you are assuming that the price increase goes entirely to Uber. There is no way Uber can increase prices by 6% and give none of that upside to their drivers - they would flee to platforms offering better terms (like Lyft).<p>If Uber was to be profitable this past quarter they wouldn&#x27;t have needed an extra $700 million in fares, but an extra <i></i>2.3 billion<i></i> - which is a 20% rise.</text></item><item><author>bpodgursky</author><text>$708 million loss, narrowed from $991 million last quarter<p>18% growth from last quarter (note: that&#x27;s not Y&#x2F;Y. this is ridiculously fast, given the huge base.)<p>708mm loss &#x2F; 3.4 billion in revenue is only about 20% under even. And what most people miss, is that the 3.4 billion is the 30% cut Uber takes from a ride. Prices don&#x27;t have to rise 20% to break even, prices have to rise 6% (assuming no efficiency improvements via pool etc, which is frankly ridiculous)<p>Yeah... Uber is doing fine.</text></item></parent_chain><comment><author>dx034</author><text>As a business traveller you don&#x27;t really care about the price as it&#x27;s paid by your employer. So you&#x27;ll take the fastest and most comfortable option. In many cities that&#x27;s still a cab as they are much faster to get at airports than Ubers.<p>The other alternative are exec cars which Uber offers but which will often be pre-booked locally.<p>I think Uber could get many business travellers on board if they&#x27;d offer some rewards system (similar to airlines). Otherwise there&#x27;s no reason to be loyal to Uber if a local cab or some other hire service (e.g. Lyft, Addison Lee in London) are faster to use.</text></comment> |
31,910,674 | 31,910,003 | 1 | 3 | 31,891,754 | train | <story><title>Math on GitHub: Following Up</title><url>https://nschloe.github.io/2022/06/27/math-on-github-follow-up.html</url></story><parent_chain></parent_chain><comment><author>simonw</author><text>Just spotted this on the GitHub blog, posted 33 minutes ago: <a href="https:&#x2F;&#x2F;github.blog&#x2F;changelog&#x2F;2022-06-28-fenced-block-syntax-for-mathematical-expressions&#x2F;" rel="nofollow">https:&#x2F;&#x2F;github.blog&#x2F;changelog&#x2F;2022-06-28-fenced-block-syntax...</a><p>&gt; Users can now delineate mathematical expressions using ```math fenced code block syntax in addition to the already supported delimiters.</text></comment> | <story><title>Math on GitHub: Following Up</title><url>https://nschloe.github.io/2022/06/27/math-on-github-follow-up.html</url></story><parent_chain></parent_chain><comment><author>prash_ant</author><text>The `$...$&#x27; and `$$...$$&#x27; delimiters are used in TeX. LaTeX uses the more superior delimiter as `\(...\)&#x27; and `\[...\]&#x27;.<p>All the MathJax and KaTeX related markdown for math should use the LaTeX delimiters and avoid the TeX delimiters.<p>For more info see <a href="https:&#x2F;&#x2F;docs.mathjax.org&#x2F;en&#x2F;v2.5-latest&#x2F;tex.html#tex-and-latex-math-delimiters" rel="nofollow">https:&#x2F;&#x2F;docs.mathjax.org&#x2F;en&#x2F;v2.5-latest&#x2F;tex.html#tex-and-lat...</a></text></comment> |
12,069,765 | 12,069,812 | 1 | 2 | 12,068,351 | train | <story><title>Italy’s teetering banks will be Europe’s next crisis</title><url>http://www.economist.com/news/leaders/21701756-italys-teetering-banks-will-be-europes-next-crisis-italian-job</url></story><parent_chain><item><author>glenndebacker</author><text>&quot;The Euro just seems like a complete failure. Giant economies are limping along with 20% unemployment, unable to recover 8 years after the recession. In contrast the US has managed an OK recovery, now closing in on full employment.&quot;<p>You are aware that the problem with the EU banking reforms (or lack off) was also that the UK didn&#x27;t wanted stricter rules with regards of the city of London... ? They even wanted an exemption.<p>In this regards I find it really intellectual dishonest that over the pound they are pointing fingers to the failure of Europe as they were part of the problem to begin with.<p>I do hope that from the moment that the UK stops dragging their feet and leave the EU it will be able to make swifter decisions instead of losing energy in constant oppositions.</text></item><item><author>guelo</author><text>It’s easy for Merkel to insist that Italy has to strictly follow EU rules since she doesn’t have to win an Italian election.<p>The Euro just seems like a complete failure. Giant economies are limping along with 20% unemployment, unable to recover 8 years after the recession. In contrast the US has managed an OK recovery, now closing in on full employment.<p>The problem is that each EU national leader is accountable only to voters in their own country. When countries have opposite interests there’s no good way for resolving the disagreement.<p>The only way it could work would be if Europe-wide economic policy were made by the European Parliament so that taxation and bank regulation would be made coherently across the continent by accountable representatives. But voters, probably correctly, want to maintain national control. But that makes the shared currency a noose.</text></item></parent_chain><comment><author>sievebrain</author><text>There is no intellectual dishonesty. Fixing the Eurozone&#x27;s banking problems (assuming you believe those regulations would do the trick) is not the UK&#x27;s problem and it&#x27;s not the UK that blindly insists on a one-track, one-speed Europe: it&#x27;s Germany and France that are wedded to that concept. They could easily have introduced new rules only in the countries that wanted them.<p>But regardless, the problem in Italy is simply that not enough people are paying back their loans. That&#x27;s not something bank regulation is going to fix. Banks make loans, that&#x27;s kind of what they do, and if a country collectively gets too bad at paying back those loans then it&#x27;s gonna have a banking crisis.</text></comment> | <story><title>Italy’s teetering banks will be Europe’s next crisis</title><url>http://www.economist.com/news/leaders/21701756-italys-teetering-banks-will-be-europes-next-crisis-italian-job</url></story><parent_chain><item><author>glenndebacker</author><text>&quot;The Euro just seems like a complete failure. Giant economies are limping along with 20% unemployment, unable to recover 8 years after the recession. In contrast the US has managed an OK recovery, now closing in on full employment.&quot;<p>You are aware that the problem with the EU banking reforms (or lack off) was also that the UK didn&#x27;t wanted stricter rules with regards of the city of London... ? They even wanted an exemption.<p>In this regards I find it really intellectual dishonest that over the pound they are pointing fingers to the failure of Europe as they were part of the problem to begin with.<p>I do hope that from the moment that the UK stops dragging their feet and leave the EU it will be able to make swifter decisions instead of losing energy in constant oppositions.</text></item><item><author>guelo</author><text>It’s easy for Merkel to insist that Italy has to strictly follow EU rules since she doesn’t have to win an Italian election.<p>The Euro just seems like a complete failure. Giant economies are limping along with 20% unemployment, unable to recover 8 years after the recession. In contrast the US has managed an OK recovery, now closing in on full employment.<p>The problem is that each EU national leader is accountable only to voters in their own country. When countries have opposite interests there’s no good way for resolving the disagreement.<p>The only way it could work would be if Europe-wide economic policy were made by the European Parliament so that taxation and bank regulation would be made coherently across the continent by accountable representatives. But voters, probably correctly, want to maintain national control. But that makes the shared currency a noose.</text></item></parent_chain><comment><author>throwaway991132</author><text>So what you are saying, is that the problems in Greece are down to the UK? I think you may want to rethink how you perceive your world.<p>The UK has nothing to do with reforms concerning the EURO. That&#x27;s up to France and Germany and the EU Central Bank.<p>The biggest problem is this. The UK is now leaving and taking a pretty big economy with it. Those payments the UK makes is going too.<p>The Germany Economy can&#x27;t keep bailing out the poorer nations in the EU alone.<p>The market is now eyeing up all the banks in the EU countries and are sharpening their knives to do shortages.<p>I&#x27;m just waiting for 1 bank to need a bailout and then you&#x27;ll see a long list.<p>Who is going to foot this bill, France, Germany, Finland? What conditions are they going to impose.<p>Is Italy or another country (Spain?) going to see Greece style sanctions?<p>Once this happens, I think you&#x27;ll start to see other exit musings in other countries and it&#x27;ll be the beginning of the end!</text></comment> |
13,470,348 | 13,470,359 | 1 | 3 | 13,469,935 | train | <story><title>Systemd v228 local root exploit</title><url>http://www.openwall.com/lists/oss-security/2017/01/24/4</url></story><parent_chain><item><author>implr</author><text>&gt;We would like to see that systemd upstream retrieves CVE&#x27;s themself for their own bugs, even if its believed that its just a local DoS.<p>So not only they didn&#x27;t notice this was exploitable, they also seem to think that a local DoS is not enough for a CVE or a public report. Excellent.</text></item></parent_chain><comment><author>KuiN</author><text>This is the really concerning part. <i>silently fixed in the upstream git</i> is not at all an acceptable way to deal with serious security flaws in your product.</text></comment> | <story><title>Systemd v228 local root exploit</title><url>http://www.openwall.com/lists/oss-security/2017/01/24/4</url></story><parent_chain><item><author>implr</author><text>&gt;We would like to see that systemd upstream retrieves CVE&#x27;s themself for their own bugs, even if its believed that its just a local DoS.<p>So not only they didn&#x27;t notice this was exploitable, they also seem to think that a local DoS is not enough for a CVE or a public report. Excellent.</text></item></parent_chain><comment><author>jsmeaton</author><text>Hanlon&#x27;s Razor; perhaps whoever wrote&#x2F;merged the patch didn&#x27;t consider the possibility of an exploit?</text></comment> |
3,081,299 | 3,080,714 | 1 | 3 | 3,080,470 | train | <story><title>Stephen Wolfram on Steve Jobs: A Few Memories</title><url>http://blog.stephenwolfram.com/2011/10/steve-jobs-a-few-memories/</url></story><parent_chain></parent_chain><comment><author>steveb</author><text>NeXT sold maybe 50,000 systems in 5 years, less than the number of PCs that a typical large company has stuffed in cubicles.<p>And from that small install base, emerged the first Web browser, Doom, and Mathematica.<p>They were amazing, if flawed products. Every system came with Mathematica, a full dictionary and the complete works of Shakespeare.<p>I remember having to go use Windows NT after NeXT failed in the market. And I remember, ten years later, holding the first iPhone in my hand and knowing where it came from.</text></comment> | <story><title>Stephen Wolfram on Steve Jobs: A Few Memories</title><url>http://blog.stephenwolfram.com/2011/10/steve-jobs-a-few-memories/</url></story><parent_chain></parent_chain><comment><author>dy</author><text>I grew up in Champaign, IL, where Wolfram is based and Steven Wolfram had a reputation for being difficult and an introvert - but the more I read or see about him, the more I find him inspiring and quite brilliant.<p>His story was also touching because it shows how Steve Jobs was able to touch people's lives in significant ways even through the briefest of interactions.<p>I'm not surprised there is such "cult" behavior behind Apple - if there was ever a cult leader I would want to believe in, it would be Steve.</text></comment> |
26,621,807 | 26,621,819 | 1 | 2 | 26,621,344 | train | <story><title>No one gives a shit what programming language you use</title><url>https://georgestocker.com/2021/03/28/no-one-gives-a-shit-what-programming-language-you-use/</url></story><parent_chain><item><author>duxup</author><text>They&#x27;re all just tools. There&#x27;s things to be discussed tool to tool (language to language) for sure, but I generally agree with the idea here.<p>&gt;woodworkers take pride in the finished product, and seeing that finish product being used. They are not all hot on the tools they use<p>For a while another hobby of mine was photography, and oh man photography has so much tool talk online that I lost interest in any online discussions &#x2F; forums. Comparing this lens to that and so on was so prevalent that it seemed entirely disconnected from the hobby of actually taking a photograph.<p>Decades ago I took some outstanding photographs with an early days digital camera that would be greatly outclassed by a random camera on a smartphone now, but does that matter?<p>I suspect it is because high level talk about tools is just easier than talking about the actual code &#x2F; effort and hard work it is to make a thing.</text></item></parent_chain><comment><author>samkater</author><text>I can’t find the source of this quote, but it applies here: “the hallmark of an amateur is the focus on tools”. Obviously tools matter, but professionals know how to balance getting the best environment set up, and actually producing what they need to make.<p>I heard that quote when I was an aspiring musician (trombone). Once when I was complaining to an instructor that my horn just couldn’t produce the sound I wanted, he took it, played the passage beautifully, and said “sometimes it’s the fiddler, not the fiddle.” A humbling, eye-opening experience that has applied to all of my professional experiences.</text></comment> | <story><title>No one gives a shit what programming language you use</title><url>https://georgestocker.com/2021/03/28/no-one-gives-a-shit-what-programming-language-you-use/</url></story><parent_chain><item><author>duxup</author><text>They&#x27;re all just tools. There&#x27;s things to be discussed tool to tool (language to language) for sure, but I generally agree with the idea here.<p>&gt;woodworkers take pride in the finished product, and seeing that finish product being used. They are not all hot on the tools they use<p>For a while another hobby of mine was photography, and oh man photography has so much tool talk online that I lost interest in any online discussions &#x2F; forums. Comparing this lens to that and so on was so prevalent that it seemed entirely disconnected from the hobby of actually taking a photograph.<p>Decades ago I took some outstanding photographs with an early days digital camera that would be greatly outclassed by a random camera on a smartphone now, but does that matter?<p>I suspect it is because high level talk about tools is just easier than talking about the actual code &#x2F; effort and hard work it is to make a thing.</text></item></parent_chain><comment><author>aszen</author><text>First of all programing languages are not tools, they are more like tool builders. Programming languages are used to build real tools aka libraries like http server, db library, html templating etc which are then composed together to form an application.<p>So not only does the programming language choice dictate what kind of tools you have available but also what kind of tools are easy to make and how to compose these tools. Even taking open source tools into account, different libraries in different languages can behave quite differently so the programming language choice matters a lot. It affects how you think about the problem and what solutions you end up with</text></comment> |
31,680,601 | 31,679,971 | 1 | 2 | 31,677,867 | train | <story><title>Internet Filtering in Canada: Rogers' NHL Blocking Order</title><url>https://typefully.com/kaplanmyrth/internet-filtering-in-canada-rogers-nhl-TPEqjeU</url></story><parent_chain><item><author>Niksko</author><text>The irony for me is that the NHL is an excellent example of why piracy happens. Last hockey season, I could pay the NHL directly to get access to all hockey games from Australia. They have a Google TV app that was flawed, but worked well enough, and I was happy.<p>This year, because the NHL have done a deal with ESPN, I have to do a convoluted deal with a third party to get access to ESPN, and my experience is terrible. ESPN&#x27;s Android app is terrible, the Google TV app flat out doesn&#x27;t work, and casting from my phone to my TV craps out during period breaks and long ad breaks.<p>Piracy would be easier, better and cheaper than paying for things. It&#x27;s the same reason Netflix reduced piracy, and now it&#x27;s tanking. They created something that was easier, cheaper and better than piracy. Now with their increasing prices, declining quality, and fragmentation of their library, piracy is going to increase again.</text></item></parent_chain><comment><author>revolvingocelot</author><text>“We think there is a fundamental misconception about piracy. Piracy is almost always a service problem and not a pricing problem. If a pirate offers a product anywhere in the world, 24 x 7, purchasable from the convenience of your personal computer, and the legal provider says the product is region-locked, will come to your country 3 months after the US release, and can only be purchased at a brick and mortar store, then the pirate’s service is more valuable.” --Gabe Newell, [0]<p>[0] <a href="https:&#x2F;&#x2F;www.escapistmagazine.com&#x2F;Valves-Gabe-Newell-Says-Piracy-Is-a-Service-Problem&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.escapistmagazine.com&#x2F;Valves-Gabe-Newell-Says-Pir...</a></text></comment> | <story><title>Internet Filtering in Canada: Rogers' NHL Blocking Order</title><url>https://typefully.com/kaplanmyrth/internet-filtering-in-canada-rogers-nhl-TPEqjeU</url></story><parent_chain><item><author>Niksko</author><text>The irony for me is that the NHL is an excellent example of why piracy happens. Last hockey season, I could pay the NHL directly to get access to all hockey games from Australia. They have a Google TV app that was flawed, but worked well enough, and I was happy.<p>This year, because the NHL have done a deal with ESPN, I have to do a convoluted deal with a third party to get access to ESPN, and my experience is terrible. ESPN&#x27;s Android app is terrible, the Google TV app flat out doesn&#x27;t work, and casting from my phone to my TV craps out during period breaks and long ad breaks.<p>Piracy would be easier, better and cheaper than paying for things. It&#x27;s the same reason Netflix reduced piracy, and now it&#x27;s tanking. They created something that was easier, cheaper and better than piracy. Now with their increasing prices, declining quality, and fragmentation of their library, piracy is going to increase again.</text></item></parent_chain><comment><author>pluc</author><text>In Canada, I can&#x27;t even buy the NHL&#x27;s own product to watch hockey games! They black out their own local games because they&#x27;ve sold the rights to someone else. The NHL wants me to buy cable, then get not one, but four channels in order to watch one team (since RDS split the rights with TVA Sports and they are both specialty channels, that you must subscribe to their parent channels to get, or in case of RDS it _is_ the parent channel, but _must_ come with their child channels). Thanks but no thanks.<p>The NHL is 100% the cause of NHL piracy. I have the money, give me an option that isn&#x27;t retarded.</text></comment> |
10,559,583 | 10,559,439 | 1 | 2 | 10,554,391 | train | <story><title>What MongoDB got right</title><url>https://blog.nelhage.com/2015/11/what-mongodb-got-right/</url></story><parent_chain><item><author>s_kilk</author><text>&gt; Let&#x27;s start with the simplest one. Making the developer interface to the database a structured format instead of a textual query language was a clear win.<p>I think this is the most significant factor, by far. With Mongo it&#x27;s turtles (or at least Maps&#x2F;Hashes) all the way down, without a strange pseudo-english layer near the bottom that forces you to translate back and forth. For some devs that&#x27;s a big deal.<p>For the last while I&#x27;ve been experimenting with bringing the same feature to PostgreSQL (<a href="http:&#x2F;&#x2F;bedquiltdb.github.io" rel="nofollow">http:&#x2F;&#x2F;bedquiltdb.github.io</a>), turns out it&#x27;s very do-able, but I don&#x27;t have enough time to make it as featureful as it needs to be.</text></item></parent_chain><comment><author>dbattaglia</author><text>Maybe I&#x27;m weird and just like SQL but the query-as-data aspect of Mongo is actually my least favorite aspect of using it. Ad-hoc queries become torture, as do complicated queries. I might just be lucky to have used SQL Server and C# for so long which eases a lot of the pains you described.</text></comment> | <story><title>What MongoDB got right</title><url>https://blog.nelhage.com/2015/11/what-mongodb-got-right/</url></story><parent_chain><item><author>s_kilk</author><text>&gt; Let&#x27;s start with the simplest one. Making the developer interface to the database a structured format instead of a textual query language was a clear win.<p>I think this is the most significant factor, by far. With Mongo it&#x27;s turtles (or at least Maps&#x2F;Hashes) all the way down, without a strange pseudo-english layer near the bottom that forces you to translate back and forth. For some devs that&#x27;s a big deal.<p>For the last while I&#x27;ve been experimenting with bringing the same feature to PostgreSQL (<a href="http:&#x2F;&#x2F;bedquiltdb.github.io" rel="nofollow">http:&#x2F;&#x2F;bedquiltdb.github.io</a>), turns out it&#x27;s very do-able, but I don&#x27;t have enough time to make it as featureful as it needs to be.</text></item></parent_chain><comment><author>collyw</author><text>SQL is still one of the most readable languages in my opinion. Its the one language where I find it easier to read queries than write them.</text></comment> |
29,884,782 | 29,881,915 | 1 | 2 | 29,876,742 | train | <story><title>Deep Learning Interviews book: Hundreds of fully solved job interview questions</title><url>https://github.com/BoltzmannEntropy/interviews.ai</url></story><parent_chain><item><author>uoaei</author><text>In part because ML fails silently by design. Even if the code runs flawlessly with no errors, the outputs could be completely bunk, useless, or even harmful, and you won&#x27;t have any idea if that is true just from watching The Number go down during training. It&#x27;s not enough to know how to build it but also <i>how it works</i>. It&#x27;s the difference between designing the JWST and assembling it.</text></item><item><author>mcemilg</author><text>The ML&#x2F;DS positions highly competitive these days. I don&#x27;t get why ML positions requires hard preparations for the interviews more than other CS positions while you do similar things. People expect you to know a lot of theory from statistics, probability, algorithms to linear algebra. I am ok with knowing basic of these topics which are the foundations of ML and DL. But I don&#x27;t get to ask eigenvectors and challenging algorithm problems in an ML Engineering position at the same while you already proof yourself with a Masters Degree and enough professional experience. I am not defending my PhD there. We will just build some DL models, maybe we will read some DL papers and maybe try to implement some of those. The theory is the only 10% of the job, rest is engineering, data cleaning etc. Honestly I am looking for the soft way to get back to Software Engineering.</text></item></parent_chain><comment><author>dekhn</author><text>ML doesn&#x27;t just fail silently by design. because ML is based on error minimization, it fails in a way that is maximally hard to tell from random garbage. This is, remarkably, a subtlety that is lost on most people, which is a real surprise- my introduction to this was in structural biology, where you always do hold-outs and check the performance on the hold-out set before overfitting is such a problem.</text></comment> | <story><title>Deep Learning Interviews book: Hundreds of fully solved job interview questions</title><url>https://github.com/BoltzmannEntropy/interviews.ai</url></story><parent_chain><item><author>uoaei</author><text>In part because ML fails silently by design. Even if the code runs flawlessly with no errors, the outputs could be completely bunk, useless, or even harmful, and you won&#x27;t have any idea if that is true just from watching The Number go down during training. It&#x27;s not enough to know how to build it but also <i>how it works</i>. It&#x27;s the difference between designing the JWST and assembling it.</text></item><item><author>mcemilg</author><text>The ML&#x2F;DS positions highly competitive these days. I don&#x27;t get why ML positions requires hard preparations for the interviews more than other CS positions while you do similar things. People expect you to know a lot of theory from statistics, probability, algorithms to linear algebra. I am ok with knowing basic of these topics which are the foundations of ML and DL. But I don&#x27;t get to ask eigenvectors and challenging algorithm problems in an ML Engineering position at the same while you already proof yourself with a Masters Degree and enough professional experience. I am not defending my PhD there. We will just build some DL models, maybe we will read some DL papers and maybe try to implement some of those. The theory is the only 10% of the job, rest is engineering, data cleaning etc. Honestly I am looking for the soft way to get back to Software Engineering.</text></item></parent_chain><comment><author>borroka</author><text>But the OP was asking something different, that is why someone should excessively focus on theory, when, by the way, DL theory is very far from being solid and trial and error in ML and AI is the common way of operating.<p>The &quot;model is in place, but I have no clue what&#x27;s doing and so it can fail without me understanding when and how is straw-man&quot;. Especially for supervised learning, that is, we have a label for data, it is immediately clear whether the output of the model is &quot;bunk, useless, or even harmful&quot;. There is no &quot;fail silently by design&quot;.<p>I have been working in the field for almost 20 years in academia and in industry and it is not that I starting every PCA thinking about eigenvectors and eigenvalues and if you ask me now without preparing what are those, I would be between approximately right and wrong. But I fit many, many very accurate models.</text></comment> |
24,110,863 | 24,111,007 | 1 | 2 | 24,109,695 | train | <story><title>Apple’s ad network gets ‘preferential access to users’ data’ vs Facebook, Google</title><url>https://www.forbes.com/sites/johnkoetsier/2020/08/07/apple-ad-network-gets-special-privileges-that-facebook-google-wont-on-ios14/</url></story><parent_chain><item><author>AlexandrB</author><text>&gt; Essentially, Apple is forcing advertisers to use a per-app permission pop-up with scary language, telling users the app wants permission to track them across other apps and websites.<p>&gt; But notice the significantly scarier language: “’Pal About’ would like permission to track you across apps and websites owned by other companies.”<p>&gt; This is language that is likely designed to minimize opt-in.<p>Love how honest language is framed as &quot;scary&quot; language. This is an admission that what they do is fundamentally creepy and if they were honest with their users, much fewer would be ok with it.<p>I wish advertisers were forced to ask permission using similar language on all platforms.</text></item></parent_chain><comment><author>luckylion</author><text>You&#x27;ve left out a critical part, which explains the &quot;minimize opt-in&quot; comment:<p>&gt; In contrast, Apple’s own advertising service looks to enable personalization by default, giving it a platform-level advantage over competitors.<p>And the language in Apple&#x27;s settings is quite different as well, they claim that their &quot;advertising platform is designed to protect your privacy&quot;. That doesn&#x27;t sound invasive, quite the opposite, that sounds like they shield you from harm.</text></comment> | <story><title>Apple’s ad network gets ‘preferential access to users’ data’ vs Facebook, Google</title><url>https://www.forbes.com/sites/johnkoetsier/2020/08/07/apple-ad-network-gets-special-privileges-that-facebook-google-wont-on-ios14/</url></story><parent_chain><item><author>AlexandrB</author><text>&gt; Essentially, Apple is forcing advertisers to use a per-app permission pop-up with scary language, telling users the app wants permission to track them across other apps and websites.<p>&gt; But notice the significantly scarier language: “’Pal About’ would like permission to track you across apps and websites owned by other companies.”<p>&gt; This is language that is likely designed to minimize opt-in.<p>Love how honest language is framed as &quot;scary&quot; language. This is an admission that what they do is fundamentally creepy and if they were honest with their users, much fewer would be ok with it.<p>I wish advertisers were forced to ask permission using similar language on all platforms.</text></item></parent_chain><comment><author>MiroF</author><text>&#x27;Love how honest language is framed as &quot;scary&quot; language&#x27;<p>Isn&#x27;t the problem here that Apple isn&#x27;t using honest language for their own advertising?</text></comment> |
37,243,284 | 37,242,730 | 1 | 3 | 37,242,043 | train | <story><title>Tornado Cash devs charged with laundering more than $1B</title><url>https://www.theverge.com/2023/8/23/23843161/tornado-cash-indictment-conspiracy-north-korea-money-laundering</url></story><parent_chain><item><author>r1ch</author><text>Wouldn&#x27;t the developers of privacy-focused blockchains like Zcash and Monero also be liable under this logic? Surely they also knew that criminals would use anonymous transactions and they did nothing to implement KYC &#x2F; AML.</text></item></parent_chain><comment><author>DannyBee</author><text>Lawyer here - you may have plausible arguments about things if you just create software without KYC&#x2F;AML, and you are outside the US or whatever.<p>If you run an actual service without KYC&#x2F;AML, uh, yeah, you are probably f&#x27;d.<p>If you have specific knowledge that a sanctioned-by-OFAC north korean hacking group is using your service to launder hundreds of millions and you do nothing, you are definitely screwed.</text></comment> | <story><title>Tornado Cash devs charged with laundering more than $1B</title><url>https://www.theverge.com/2023/8/23/23843161/tornado-cash-indictment-conspiracy-north-korea-money-laundering</url></story><parent_chain><item><author>r1ch</author><text>Wouldn&#x27;t the developers of privacy-focused blockchains like Zcash and Monero also be liable under this logic? Surely they also knew that criminals would use anonymous transactions and they did nothing to implement KYC &#x2F; AML.</text></item></parent_chain><comment><author>dylkil</author><text>There was evidence that north korea specifically used tornado cash to hide stolen crypto, which is where this has all stemmed from</text></comment> |
18,407,695 | 18,407,833 | 1 | 2 | 18,407,073 | train | <story><title>Sundar Pichai: ‘Technology Doesn’t Solve Humanity’s Problems’</title><url>https://www.nytimes.com/2018/11/08/business/sundar-pichai-google-corner-office.html</url></story><parent_chain><item><author>Kurtz79</author><text>To put the title into context:<p>&quot;Do you still feel like Silicon Valley has retained that idealism that struck you when you arrived here?&quot;<p>&quot;There’s still that optimism. But the optimism is tempered by a sense of deliberation. Things have changed quite a bit. You know, we deliberate about things a lot more, and we are more thoughtful about what we do. But there’s a deeper thing here, which is: Technology doesn’t solve humanity’s problems. It was always naïve to think so. Technology is an enabler, but humanity has to deal with humanity’s problems. I think we’re both over-reliant on technology as a way to solve things and probably, at this moment, over-indexing on technology as a source of all problems, too.&quot;</text></item></parent_chain><comment><author>discoball</author><text>&lt;&lt;But there’s a deeper thing here, which is: Technology doesn’t solve humanity’s problems. It was always naïve to think so. Technology is an enabler&gt;&gt;<p>Google was enabling the DoD to be more efficient at killing people and China to be more oppressive until its workers protested. So he&#x27;s right about humanity having to solve its problems but he&#x27;s forgetting that Google, the corporation, is opting to make it harder for humanity to solve its problems by enabling those who do not have humanity&#x27;s best interest in their heart.</text></comment> | <story><title>Sundar Pichai: ‘Technology Doesn’t Solve Humanity’s Problems’</title><url>https://www.nytimes.com/2018/11/08/business/sundar-pichai-google-corner-office.html</url></story><parent_chain><item><author>Kurtz79</author><text>To put the title into context:<p>&quot;Do you still feel like Silicon Valley has retained that idealism that struck you when you arrived here?&quot;<p>&quot;There’s still that optimism. But the optimism is tempered by a sense of deliberation. Things have changed quite a bit. You know, we deliberate about things a lot more, and we are more thoughtful about what we do. But there’s a deeper thing here, which is: Technology doesn’t solve humanity’s problems. It was always naïve to think so. Technology is an enabler, but humanity has to deal with humanity’s problems. I think we’re both over-reliant on technology as a way to solve things and probably, at this moment, over-indexing on technology as a source of all problems, too.&quot;</text></item></parent_chain><comment><author>SquishyPanda23</author><text>Part of me can&#x27;t help but read this a little cynically.<p>They&#x27;re starting to articulate a shift away from Larry Page&#x27;s idealistic view of making information universally accessible and useful and toward tempering expectations about what technology can do.<p>After that they&#x27;ll pivot increasingly toward a position that lets them justify the drone and censorship programs without the baggage of Page&#x27;s original naivety.<p>Again, that&#x27;s an overly cynical take. But it&#x27;s kind of hard to avoid reading that as a possibility.</text></comment> |
11,029,380 | 11,029,549 | 1 | 2 | 11,027,539 | train | <story><title>Dropbox May Not Be LeBron James, but Is Still in the Game</title><url>http://www.nytimes.com/2016/02/04/technology/dropbox-may-not-be-lebron-james-but-it-is-still-in-the-game.html</url></story><parent_chain><item><author>Spooky23</author><text>&gt; Dropbox is not laying off workers or shrinking; it hired nearly 500 people last year, 75 since the start of this year, and it plans to soon move into a sprawling, custom-designed office building for which it has signed a long-term lease.<p>Honest question: WTF are they doing?</text></item></parent_chain><comment><author>zer0defex</author><text>Nail on the head right here. The only thing Dropbox has these days is consumer confidence in it&#x27;s syncing process. Beyond that, they trail every competitor feature-wise and frankly, they are succeeding despite their management, not because of it. Recent product enhancements have been, let&#x27;s be honest, mediocre at best across the board and show no signs of that changing anytime soon. They exist now solely due to brand recognition when it comes to cloud file sync&#x27;ing and the moment one of their competitors cracks the consumer confidence equation with the brand image to match, Dropbox is done.</text></comment> | <story><title>Dropbox May Not Be LeBron James, but Is Still in the Game</title><url>http://www.nytimes.com/2016/02/04/technology/dropbox-may-not-be-lebron-james-but-it-is-still-in-the-game.html</url></story><parent_chain><item><author>Spooky23</author><text>&gt; Dropbox is not laying off workers or shrinking; it hired nearly 500 people last year, 75 since the start of this year, and it plans to soon move into a sprawling, custom-designed office building for which it has signed a long-term lease.<p>Honest question: WTF are they doing?</text></item></parent_chain><comment><author>coldtea</author><text>&gt;<i>Honest question: WTF are they doing?</i><p>Have an actual profitable syncing business with several pricing tiers and tons of hooks to third party apps?<p>I mean, unlike tons of billion-valued &quot;unicorns&quot; that not only don&#x27;t have an income plan (apart from &quot;some day we&#x27;ll maybe sell ads&quot;) but are also losing money.<p>You&#x27;d be surprised with how many 1000+ people companies are there, profitable and fine in all kinds of sectors, that are way less known than Dropbox.</text></comment> |
41,370,558 | 41,369,064 | 1 | 2 | 41,367,964 | train | <story><title>New 0-Day Attacks Linked to China's 'Volt Typhoon'</title><url>https://krebsonsecurity.com/2024/08/new-0-day-attacks-linked-to-chinas-volt-typhoon/</url></story><parent_chain></parent_chain><comment><author>Lonestar1440</author><text>&quot;The advisory placed much of the blame on Versa customers who “failed to implement system hardening and firewall guidelines…leaving a management port exposed on the internet that provided the threat actors with initial access.”&quot;<p>If ISPs are leaving management ports open on the Internet, it&#x27;s going to take more than a vendor patch to protect them from cyber warfare.</text></comment> | <story><title>New 0-Day Attacks Linked to China's 'Volt Typhoon'</title><url>https://krebsonsecurity.com/2024/08/new-0-day-attacks-linked-to-chinas-volt-typhoon/</url></story><parent_chain></parent_chain><comment><author>blahgeek</author><text>(I&#x27;m a Chinese and a software engineer, so it&#x27;s my obviously-biased 2 cents)<p>Based on my observation of fellow Chinese software engineers&#x27; average knowledge and skills about cyber security, as well as the absolute absent of security considerations of most &quot;SOHO network devices&quot; in China, I would rather apply Hanlon&#x27;s razor and say that it&#x27;s not the Chinese attackers, but it&#x27;s Chinese botnet.<p>As you may already know, Chinese users and software engineers generally does not care about personal privacy and hence also cyber security, so the entire industry is rather undeveloped.</text></comment> |
29,911,423 | 29,910,357 | 1 | 2 | 29,909,087 | train | <story><title>People behave more sadistically when they’re bored</title><url>https://digest.bps.org.uk/2022/01/12/people-behave-more-sadistically-when-theyre-bored/</url></story><parent_chain><item><author>tristor</author><text>&gt; I&#x27;d be happy if we&#x27;d just get over this vindictive need to deprive prisoners of basic pleasures.<p>I won&#x27;t argue that there aren&#x27;t some people who have such a vindictive need, but in most cases where I&#x27;ve had conversations with folks about things like this, it&#x27;s more that they oppose someone having a similar (or maybe &quot;better&quot;) quality of life to what they have, without working to pay for it, and rather being paid for by them. The opposition to these things in prisons seem similar to the arguments I hear from people against social safety net things generally. Not to say these arguments are reasonable, but I don&#x27;t think vindictiveness is the primary driving factor.</text></item><item><author>lostcolony</author><text>I&#x27;d be happy if we&#x27;d just get over this vindictive need to deprive prisoners of basic pleasures.<p>I&#x27;ve seen outrage over the idea that prisoners have access to TVs, or gaming consoles, or similar, stories of wardens confiscating books and pen and paper and such. I understand there are some other concerns that may warrant keeping usage of some of those under surveillance or similar (keep a pencil from being used as a shiv say), but other countries don&#x27;t try and make prisons as miserable an experience as possible, and they have far, far lower rates of recidivism and violence and such.</text></item><item><author>mc32</author><text>So put them to work and pay them the going rate [in the normal economy] and use that toward victim restitution?<p>If you pay them the market rate and this activity improves their well-being compared to being sedentary, I think it’s a win for all involved.</text></item><item><author>quacked</author><text>If this is indeed true, it is yet another piece of evidence in the case for prison reform. Prisoners are universally bored, yet in many cases insufficiently protected from one another. Read accounts of any long-time convict&#x27;s time in prison and you&#x27;ll hear about excruciating boredom punctuated by acts of outrageous sadism.</text></item></parent_chain><comment><author>lostcolony</author><text>Okay, maybe. Rather than people wanting the worst possible thing for prisoners because of the perceived harm those prisoners have caused them (vindictiveness), they want the worst possible thing for prisoners because HOW DARE someone else have something nicer than them that they didn&#x27;t &quot;earn&quot;. That&#x27;s the same attitude that would begrudge a homeless person a donated name brand hoodie, because (you) had to pay $X for it.<p>That&#x27;s even worse. But maybe the term should be different; maybe it isn&#x27;t vindictiveness.<p>The US is the most incarcerated country in the world. We have the most prisoners, the most prisoners per capita, the highest spending on prisoners, and one of the worst recidivism rates (76% after 5 years).<p>What we&#x27;re doing is -clearly- not working. The idea that we&#x27;d rather spend -more- than other countries, on a system that works worse, begs the question of &#x27;why&#x27;. Why would we want to keep doing the same thing, that isn&#x27;t working, -and- costs us more? Because we think prisoners don&#x27;t deserve better.<p>Maybe that isn&#x27;t &quot;vindictiveness&quot;, but it&#x27;s damned close.<p>It certainly isn&#x27;t &quot;I want to make sure my tax dollars being used effectively&quot;, or &quot;I want the best outcomes from prisons&quot;, or even &quot;I want to make sure they&#x27;re only getting what they need to serve their time and then be able to come out and rejoin society&quot;.<p>It very much is &quot;Damn the consequences, and how much it costs, I want them to have the worst possible experience&quot;.</text></comment> | <story><title>People behave more sadistically when they’re bored</title><url>https://digest.bps.org.uk/2022/01/12/people-behave-more-sadistically-when-theyre-bored/</url></story><parent_chain><item><author>tristor</author><text>&gt; I&#x27;d be happy if we&#x27;d just get over this vindictive need to deprive prisoners of basic pleasures.<p>I won&#x27;t argue that there aren&#x27;t some people who have such a vindictive need, but in most cases where I&#x27;ve had conversations with folks about things like this, it&#x27;s more that they oppose someone having a similar (or maybe &quot;better&quot;) quality of life to what they have, without working to pay for it, and rather being paid for by them. The opposition to these things in prisons seem similar to the arguments I hear from people against social safety net things generally. Not to say these arguments are reasonable, but I don&#x27;t think vindictiveness is the primary driving factor.</text></item><item><author>lostcolony</author><text>I&#x27;d be happy if we&#x27;d just get over this vindictive need to deprive prisoners of basic pleasures.<p>I&#x27;ve seen outrage over the idea that prisoners have access to TVs, or gaming consoles, or similar, stories of wardens confiscating books and pen and paper and such. I understand there are some other concerns that may warrant keeping usage of some of those under surveillance or similar (keep a pencil from being used as a shiv say), but other countries don&#x27;t try and make prisons as miserable an experience as possible, and they have far, far lower rates of recidivism and violence and such.</text></item><item><author>mc32</author><text>So put them to work and pay them the going rate [in the normal economy] and use that toward victim restitution?<p>If you pay them the market rate and this activity improves their well-being compared to being sedentary, I think it’s a win for all involved.</text></item><item><author>quacked</author><text>If this is indeed true, it is yet another piece of evidence in the case for prison reform. Prisoners are universally bored, yet in many cases insufficiently protected from one another. Read accounts of any long-time convict&#x27;s time in prison and you&#x27;ll hear about excruciating boredom punctuated by acts of outrageous sadism.</text></item></parent_chain><comment><author>quacked</author><text>I understand their frustration, but I think it&#x27;s a win-win situation to provide a nice life in prison. They get out of society so we don&#x27;t have to deal with them and they also aren&#x27;t subject to torturous conditions.</text></comment> |
30,114,147 | 30,114,092 | 1 | 2 | 30,113,513 | train | <story><title>I paid for a perpetual license of TeamViewer. Stop calling and emailing me</title><url>https://twitter.com/linusgsebastian/status/1445974503771672581</url></story><parent_chain><item><author>laputan_machine</author><text>Yes, it will be the hardcoded ads in the podcast, but I think the point still remains.<p>Edit: Apparently Spotify also does dynamic ads too! Greedy...<p>At that point, why not just use another service instead of Spotify for podcasts? E.g. Pocket Casts. If you pay for the Spotify subscription I&#x27;d expect _all_ ads to be removed.</text></item><item><author>atraac</author><text>&gt; Even though I had been a (long time, non-family subscription) premium user of Spotify, they started playing ads during podcasts (music was fine). How is that a &quot;premium&quot; service? Canceled the sub.<p>This is interesting to me because besides ads that are hardcoded into the podcast by creators, I have never heard an ad in Spotify premium, not a single time for years I&#x27;ve been using it. Not sure if country of origin has something to do with it, but I&#x27;m from Poland.</text></item><item><author>nvilcins</author><text>Even though I had been a (long time, non-family subscription) premium user of Spotify, they started playing ads during podcasts (music was fine). How is that a &quot;premium&quot; service? Canceled the sub.<p>Tangent: Now that I occasionally play music on Spotify I get ads in the form &quot;We know you were a premium user before, how is life with the free service now?&quot;. I find that somewhat creepy and disturbing.</text></item></parent_chain><comment><author>atraac</author><text>If an advert is hardcoded by the author into the file they upload, how do you suppose Spotify should remove that? They don&#x27;t have rights to do that but even if they could, they would need to programmatically detect when the ad starts, ends and cut it out from the file? Soft Skills Engineering does this for example, they record their own audio for the ad and play it like it&#x27;s a part of the podcast, I don&#x27;t mind that as it helps authors, but that has nothing to do with Spotify.<p>I&#x27;ve heard about some dynamic adds Spotify supposedly adds, that are usually not related to the podcast itself, but I&#x27;ve never encountered a single one like that.</text></comment> | <story><title>I paid for a perpetual license of TeamViewer. Stop calling and emailing me</title><url>https://twitter.com/linusgsebastian/status/1445974503771672581</url></story><parent_chain><item><author>laputan_machine</author><text>Yes, it will be the hardcoded ads in the podcast, but I think the point still remains.<p>Edit: Apparently Spotify also does dynamic ads too! Greedy...<p>At that point, why not just use another service instead of Spotify for podcasts? E.g. Pocket Casts. If you pay for the Spotify subscription I&#x27;d expect _all_ ads to be removed.</text></item><item><author>atraac</author><text>&gt; Even though I had been a (long time, non-family subscription) premium user of Spotify, they started playing ads during podcasts (music was fine). How is that a &quot;premium&quot; service? Canceled the sub.<p>This is interesting to me because besides ads that are hardcoded into the podcast by creators, I have never heard an ad in Spotify premium, not a single time for years I&#x27;ve been using it. Not sure if country of origin has something to do with it, but I&#x27;m from Poland.</text></item><item><author>nvilcins</author><text>Even though I had been a (long time, non-family subscription) premium user of Spotify, they started playing ads during podcasts (music was fine). How is that a &quot;premium&quot; service? Canceled the sub.<p>Tangent: Now that I occasionally play music on Spotify I get ads in the form &quot;We know you were a premium user before, how is life with the free service now?&quot;. I find that somewhat creepy and disturbing.</text></item></parent_chain><comment><author>gruez</author><text>&gt;I&#x27;d expect _all_ ads to be removed<p>spotify can&#x27;t do that unless they own the rights to the podcast, otherwise they might run afowl of copyright laws. I believe their intent is to have one place for podcasts (both their own premium ones and freely accessible public ones).</text></comment> |
1,799,492 | 1,799,314 | 1 | 3 | 1,799,116 | train | <story><title>Design Strategies for a Successful Pricing Table</title><url>http://uxmovement.com/design-articles/7-useful-design-strategies-for-a-successful-pricing-table</url><text></text></story><parent_chain></parent_chain><comment><author>JangoSteve</author><text>So, far every article I've seen from uxmovement.com has anecdotal advice with no sources, and no numbers to back them up.<p>Also, when creating the tiered plans for your web-app, I highly recommend NOT having anything that is "unlimited" in any of your plans. It is very hard to go back and un-unlimit your plan. Don't leave it open-ended.<p>Sure, make the limits high on the top plan, hell make them higher than anyone could possibly need, but still have limits. If someone needs more than that, you can work something out. If nothing else, have a per-instance-pricing plan ($50/mo for 500 things + $0.05 per additional thing).</text></comment> | <story><title>Design Strategies for a Successful Pricing Table</title><url>http://uxmovement.com/design-articles/7-useful-design-strategies-for-a-successful-pricing-table</url><text></text></story><parent_chain></parent_chain><comment><author>d_r</author><text>I loved the post, but would be interesting to see some actual data behind these observations.<p>Some of these seemingly contradict each other: one "rule" claims that ascending order of prices is better, another claims the opposite.</text></comment> |
13,629,626 | 13,629,421 | 1 | 2 | 13,628,518 | train | <story><title>Modern Software Over-Engineering Mistakes</title><url>https://medium.com/@rdsubhas/10-modern-software-engineering-mistakes-bc67fbef4fc8#.swzmypry1</url></story><parent_chain></parent_chain><comment><author>65827</author><text>Trying to make everything generic enough so that will work everywhere everytime is one of my pet peeves. You really don&#x27;t need to engineer a date picker to work in microgravity and on quantum CPUs and in alternate dimensions. I get that it&#x27;s fun sometimes, but my god stop.</text></comment> | <story><title>Modern Software Over-Engineering Mistakes</title><url>https://medium.com/@rdsubhas/10-modern-software-engineering-mistakes-bc67fbef4fc8#.swzmypry1</url></story><parent_chain></parent_chain><comment><author>JamesBarney</author><text>I really think most of this comes down to the number one principle of good software development is &quot;Keep it simple stupid&quot;<p>Simple, concrete, un-abstracted code is easy to get to right, easy to read, and easy to change.</text></comment> |
3,865,247 | 3,864,008 | 1 | 3 | 3,862,782 | train | <story><title>Google's opening slides in the trial v. Oracle</title><url>http://www.groklaw.net/pdf3/OraGoogle-Trial-GoogleOpeningStills.pdf</url><text></text></story><parent_chain></parent_chain><comment><author>ChuckMcM</author><text>Ok a couple of disclaimers first, one I was one of the original Java folks and two, I've done expert witness work but not in this case.<p>When Java was still 'Oak' there was an interesting, on-going, low level debate about where the 'language' stopped and the 'system' started. There is a very common analogy in C where C pretty much assumes that there is a 'libc' and in libc are functions for doing things like printf().<p>So it was with Java, with the wart/exception that there was no 'main' as Java was designed to be the entire environment, not something you wrote in and then passed a binary to a different environment. Sort of like Python in interactive mode all the time. And that lead to the question of "what can a programmer assume is true about the environment?" and the answer was eventually some packages were 'core' and had to be present and some where 'optional' and might not me. Frank Yellin and James Gosling's book on the topic was the definitive reference of what was core and what wasn't.<p>When I was at NetApp (which also used Java (licensed) in their filers) there was an interesting debate with Sun about whether or not one had to pass the compatibility suite to be compliant with the license. Since it wasn't an exported language (customers couldn't write Java code to run on the filer) NetApp argued that insuring it could run NetBeans compatibly was unnecessary. Worse (for NetApp) was that they had their own OS and so the port had taken a while and the newer JDK had a lot of changes (none of which were needed) and it became clear the Sun was just operating on a script. Eventually it escalated up to Scott McNealy who quite reasonably understood that if they insisted on that much effort, NetApp would just move to Python or something like it (equivalent internal effort to porting the newest JDK) and voted for 'money' rather than 'no money'. That the question even came up though really brought home how far Java had moved from its roots of the team arguing to release source, to 'the most profitable on a per-unit basis' that Sun was selling in the end times.<p>Looking at the approaches, I think Oracle is going to lose. And I think they are going to lose for the same reason the font guys lost. My fuzzy memory has it as a Letraset vs Apple suit but it may have been Xerox (sad how stuff from 30 yrs ago is so hard to find) which basically concluded you could copyright the <i>name</i> of a font but you could not copyright how it looked. Hence font names like "Chicago" which look like other more well known fonts. And it is also why you get 250 'free' fonts where the 'i' character has the dot hinted slightly higher but is otherwise identical to some Bitstream font. Historically copyright has been offered on the 'end' product, not on the 'intermediate' product. So you can copyright a game that is written in language X, but not language X. For the language you can only copyright the name, and the implementation. If the new implementation is different (or derived cleanly) you don't have an recourse.<p>This defense of a 'clean' implementation of a specification severing rights to the original has been litigated extensively in the 80's BIOS wars where IBM published the source code to its BIOS in their technical manuals and then started trying to sue clone makers who re-used the source. Once the BIOS was implemented in a 'clean room' where team A (who had the BIOS code) provided specifications to team B who didn't, then you could completely sever the rights to the code from IBM.</text></comment> | <story><title>Google's opening slides in the trial v. Oracle</title><url>http://www.groklaw.net/pdf3/OraGoogle-Trial-GoogleOpeningStills.pdf</url><text></text></story><parent_chain></parent_chain><comment><author>psychotik</author><text>The file cabinet analogy is great to explain packages/namespace. Smart.<p>After looking through both opening slides, I have to say Oracle's seemed to make better/stronger arguments. This case is fascinating, I'm glad that resources are being made available.<p>Also, gotta love "Very limited internal expertise to make smart decisions" on slide 69. I wonder if the slide number being that was just coincidence.</text></comment> |
40,098,727 | 40,098,151 | 1 | 2 | 40,097,375 | train | <story><title>U-M finds students with alphabetically lower-ranked names receive lower grades</title><url>https://record.umich.edu/articles/study-alphabetical-order-of-surnames-may-affect-grading/</url></story><parent_chain><item><author>cvwright</author><text>My strategy was to, like you said, grade problem by problem. Then for each problem, first find all those who got full marks. Then group the others into piles based on what mistakes they made.<p>This ensures that everyone who made the same mistake(s) gets the same grade. It also tends to shuffle the order of the exams after every problem.<p>Obviously you don’t need this strategy for simple multiple choice questions, and it’s probably also not a great fit for long-form essays. But it worked great for technical short answer problems in CS and security.</text></item><item><author>lqet</author><text>I work in academia. When we grade exams, the order of the exams on the stack is the order in which they were collected in the room (people can sit wherever they like). For grading, we are usually 5 people in a single room, and everyone grades a specific exercise for consistency. The exams are getting shuffled <i>heavily</i>, with everyone just grabbing stacks, looking for exams where &quot;their&quot; exercise was not yet graded, and taking them out. So basically, the order in which we grade exams can be considered random.<p>However, I also grade weekly exercise sheets during the semester, and these are committed into a repository, where each student has a folder that... begins with the first letter of their first name. <i>Everyone</i> I have ever worked with acknowledges that you have to shuffle the order in which you grade these submissions each week, for fairness. Several effects come into play: (1) your are usually less tired at the beginning, (2) your mood gets better during the last 2 sheets because you know you are done soon, (3, and crucially) at the beginning, you have not yet seen all the common errors &#x2F; developed a &quot;feeling&quot; for them, and you might thus miss them in early submissions, but spot them immediately in later submissions.<p>Another alphabetic effect: In elementary school, my name was on top of the list of students in my class. I remember that I often had to do some special job simply because I was the first name on this list (for example, carry a group ticket when we visited some museum, keep track of something, be the first at something where nobody wanted to be the first, with everyone watching, be the first to be graded in PE, again with everyone watching, etc.). As a fairly shy kid, this already annoyed me in first grade.</text></item></parent_chain><comment><author>bobbiechen</author><text>When I was a TA at CMU, we used Gradescope <a href="https:&#x2F;&#x2F;www.gradescope.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.gradescope.com&#x2F;</a> for this. Every exam would be scanned and divided into problems (based on a predefined template - fixed page space for answers).<p>Then, each problem was assigned to a TA. Either there&#x27;s a predefined rubric, or you create it as you go (-1 point for mistake X, half credit for mistake Y, etc.). There&#x27;s a pretty slick interface where you just read the answer, and use keyboard shortcuts to apply the relevant deductions.<p>It still has the issue that every time you change the rubric, you&#x27;d need to go back and re-do previously-graded instances of that problem. But it was way faster and (equally important) less tiring.</text></comment> | <story><title>U-M finds students with alphabetically lower-ranked names receive lower grades</title><url>https://record.umich.edu/articles/study-alphabetical-order-of-surnames-may-affect-grading/</url></story><parent_chain><item><author>cvwright</author><text>My strategy was to, like you said, grade problem by problem. Then for each problem, first find all those who got full marks. Then group the others into piles based on what mistakes they made.<p>This ensures that everyone who made the same mistake(s) gets the same grade. It also tends to shuffle the order of the exams after every problem.<p>Obviously you don’t need this strategy for simple multiple choice questions, and it’s probably also not a great fit for long-form essays. But it worked great for technical short answer problems in CS and security.</text></item><item><author>lqet</author><text>I work in academia. When we grade exams, the order of the exams on the stack is the order in which they were collected in the room (people can sit wherever they like). For grading, we are usually 5 people in a single room, and everyone grades a specific exercise for consistency. The exams are getting shuffled <i>heavily</i>, with everyone just grabbing stacks, looking for exams where &quot;their&quot; exercise was not yet graded, and taking them out. So basically, the order in which we grade exams can be considered random.<p>However, I also grade weekly exercise sheets during the semester, and these are committed into a repository, where each student has a folder that... begins with the first letter of their first name. <i>Everyone</i> I have ever worked with acknowledges that you have to shuffle the order in which you grade these submissions each week, for fairness. Several effects come into play: (1) your are usually less tired at the beginning, (2) your mood gets better during the last 2 sheets because you know you are done soon, (3, and crucially) at the beginning, you have not yet seen all the common errors &#x2F; developed a &quot;feeling&quot; for them, and you might thus miss them in early submissions, but spot them immediately in later submissions.<p>Another alphabetic effect: In elementary school, my name was on top of the list of students in my class. I remember that I often had to do some special job simply because I was the first name on this list (for example, carry a group ticket when we visited some museum, keep track of something, be the first at something where nobody wanted to be the first, with everyone watching, be the first to be graded in PE, again with everyone watching, etc.). As a fairly shy kid, this already annoyed me in first grade.</text></item></parent_chain><comment><author>jcla1</author><text>This sounds like an organisational nightmare to be honest. You&#x27;d be going through the pile of exams multiple times (at least twice) and what do you do if there are multiple mistakes that are common in a single exam question?<p>Also: if you&#x27;re sorting into &quot;mistakes piles&quot; for single exercises, how can you parallelise marking of separate and independent questions?</text></comment> |
33,849,730 | 33,849,661 | 1 | 2 | 33,847,905 | train | <story><title>Gameboy Doctor: debug and fix your gameboy emulator</title><url>https://robertheaton.com/gameboy-doctor/</url></story><parent_chain></parent_chain><comment><author>chrsig</author><text>Personally, I&#x27;ve had more trouble understanding the PPU behavior than i did about the cpu instructions and timings.<p>I&#x27;d mostly been going off of The Ultimate Game Boy Talk[0] and the pandocs[1]. In trying to quickly dig up some resources now, I found what at first glance looks like a good blog series[2], so I might take some time to squint at them soon.<p>If any HNer has other good resources describing it, I&#x27;d be thrilled. It&#x27;s been a couple years since I&#x27;ve hacked on my own emulator, and I got through implementing quite a bit of the behavior. As I recall, I was able to get serial output from the test roms, which was pretty cool. I put it down after getting frustrated trying to render the screen.<p>[0] <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=HyzD8pNlpwI&amp;t=2957s" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=HyzD8pNlpwI&amp;t=2957s</a><p>[1] <a href="http:&#x2F;&#x2F;bgb.bircd.org&#x2F;pandocs.htm#videodisplay" rel="nofollow">http:&#x2F;&#x2F;bgb.bircd.org&#x2F;pandocs.htm#videodisplay</a><p>[2] <a href="https:&#x2F;&#x2F;blog.tigris.fr&#x2F;2019&#x2F;09&#x2F;15&#x2F;writing-an-emulator-the-first-pixel&#x2F;" rel="nofollow">https:&#x2F;&#x2F;blog.tigris.fr&#x2F;2019&#x2F;09&#x2F;15&#x2F;writing-an-emulator-the-fi...</a></text></comment> | <story><title>Gameboy Doctor: debug and fix your gameboy emulator</title><url>https://robertheaton.com/gameboy-doctor/</url></story><parent_chain></parent_chain><comment><author>Waterluvian</author><text>My gameboy emulator finally works fine CPU wise. The issue is making the sound work without eating up an entire core.<p>Maybe I’m saying the obvious to many but the biggest “broad” lesson I learned from the project wasn’t Rust. It was, “sound is harder than video.” And I feel that’s counter intuitive. Maybe some disagree but for me there’s something about processing raw sound that’s so much harder to implement and debug. I guess graphics lends itself far easier to debugging. You can see each frame. Can’t really hear each frame.</text></comment> |
25,191,548 | 25,191,662 | 1 | 3 | 25,191,073 | train | <story><title>Wage Theft Is a Much Bigger Problem Than Other Forms of Theft (2014)</title><url>https://www.epi.org/publication/wage-theft-bigger-problem-forms-theft-workers/</url></story><parent_chain></parent_chain><comment><author>sampleinajar</author><text>For most of my adult life, I worked hourly jobs in low pay positions and &quot;wage theft&quot; always meant me, the employee, stealing from the company by not working every single second I was there. Interesting to see it defined the other way, &quot;employers’ failure to pay workers money they are legally entitled to&quot;.</text></comment> | <story><title>Wage Theft Is a Much Bigger Problem Than Other Forms of Theft (2014)</title><url>https://www.epi.org/publication/wage-theft-bigger-problem-forms-theft-workers/</url></story><parent_chain></parent_chain><comment><author>dec0dedab0de</author><text>This reminded me of an hourly job I had where I was expected to be there 15 minutes early, then I got in trouble for clocking in as soon as I sat down. I just told my supervisor and manager that if I&#x27;m there I&#x27;m clocking in. After that, I had permission to show up late.</text></comment> |
30,073,671 | 30,073,695 | 1 | 2 | 30,073,066 | train | <story><title>Ask HN: Who has moved from the U.S. to Europe?</title><text>I&#x27;ve long considered leaving this country for a multitude of reasons.<p>I&#x27;d be curious to hear some first hand experiences of those who&#x27;ve made the move to Europe and what you think of the process and considerations one should make.<p>A few questions to start the conversation:<p>- Where do you live?<p>- What&#x27;s the biggest sacrifice you had to make (i.e. pay, housing, friends, etc.)<p>- What have you gained?</text></story><parent_chain><item><author>starik36</author><text>&gt; brink of civil war<p>I think that might be overstated.<p>&gt; NHS is absolutely amazing<p>I&#x27;ve read and heard that for a non-emergency appointments, the wait could sometimes be months. Is that also overstated?</text></item><item><author>jzellis</author><text>I&#x27;m just outside London, moved here to marry my English wife from Vegas. I work part time doing basic IT for a US law firm due to health issues after heart surgery, and Yankee dollars are worth jack shit here - I&#x27;m not making serious tech industry money, but over here it&#x27;s barely enough to survive on.<p>Housing is always smaller than you&#x27;d get in (at least the western) US for the same price, and I&#x27;d bet that&#x27;s true pretty much everywhere in Europe. Speaking the same language is useful, but Covid has made it hard to make friends or do much.<p>Despite its reputation, I find that Europe is far more provincial than the US when it comes to food - a lot of stuff you think of as ubiquitous in the West will be &quot;foreign&quot; food and harder 48 to find. (And if you like tacos, stay on that side of the pond.)<p>Benefits: it&#x27;s a lot quieter and generally less dangerous than the US. The NHS is absolutely amazing and you&#x27;ll never want to deal with the American system ever again. People tend to be less aggressive.<p>From an entrepreneurial standpoint I&#x27;m sure it&#x27;s much harder to get up and running, but I&#x27;m old enough to not care anymore. If I could work legally for a UK startup or tech firm doing basic dev I&#x27;d be happy enough and well-paid enough to never feel the urge to start my own ragged little thing again.<p>It is colder in most of Europe than the US, in my experience (not just living here but traveling extensively in my life). If you&#x27;re a Cali kid, you will miss the sunlight, especially in the winter. It&#x27;s like a fucking Joy Division video here from October through April. :-D<p>I think if my wife and I could afford to split our time between here and Vegas, we would. But that&#x27;s just not in the cards right now.<p>But hey, at least they&#x27;re not on the brink of civil war here and the curry is good.</text></item></parent_chain><comment><author>exdsq</author><text>&gt; I&#x27;ve read and heard that for a non-emergency appointments, the wait could sometimes be months. Is that also overstated?<p>Depends on where you are. I lived in the UK until last August and am now in the US. When I lived in London and Oxford I found the wait times to be very quick - in Oxford I could get non-emergency appointments the same day, possibly due to the high number of GPs and University hospitals. In London it was same week for everything I ever had an issue with. I believe in the less well-off areas, especially in the North of the country, there are areas with far lower staff numbers so the waiting time inflates. Worst-case scenarios in worst-case areas do have multiple-month waiting times nowadays.</text></comment> | <story><title>Ask HN: Who has moved from the U.S. to Europe?</title><text>I&#x27;ve long considered leaving this country for a multitude of reasons.<p>I&#x27;d be curious to hear some first hand experiences of those who&#x27;ve made the move to Europe and what you think of the process and considerations one should make.<p>A few questions to start the conversation:<p>- Where do you live?<p>- What&#x27;s the biggest sacrifice you had to make (i.e. pay, housing, friends, etc.)<p>- What have you gained?</text></story><parent_chain><item><author>starik36</author><text>&gt; brink of civil war<p>I think that might be overstated.<p>&gt; NHS is absolutely amazing<p>I&#x27;ve read and heard that for a non-emergency appointments, the wait could sometimes be months. Is that also overstated?</text></item><item><author>jzellis</author><text>I&#x27;m just outside London, moved here to marry my English wife from Vegas. I work part time doing basic IT for a US law firm due to health issues after heart surgery, and Yankee dollars are worth jack shit here - I&#x27;m not making serious tech industry money, but over here it&#x27;s barely enough to survive on.<p>Housing is always smaller than you&#x27;d get in (at least the western) US for the same price, and I&#x27;d bet that&#x27;s true pretty much everywhere in Europe. Speaking the same language is useful, but Covid has made it hard to make friends or do much.<p>Despite its reputation, I find that Europe is far more provincial than the US when it comes to food - a lot of stuff you think of as ubiquitous in the West will be &quot;foreign&quot; food and harder 48 to find. (And if you like tacos, stay on that side of the pond.)<p>Benefits: it&#x27;s a lot quieter and generally less dangerous than the US. The NHS is absolutely amazing and you&#x27;ll never want to deal with the American system ever again. People tend to be less aggressive.<p>From an entrepreneurial standpoint I&#x27;m sure it&#x27;s much harder to get up and running, but I&#x27;m old enough to not care anymore. If I could work legally for a UK startup or tech firm doing basic dev I&#x27;d be happy enough and well-paid enough to never feel the urge to start my own ragged little thing again.<p>It is colder in most of Europe than the US, in my experience (not just living here but traveling extensively in my life). If you&#x27;re a Cali kid, you will miss the sunlight, especially in the winter. It&#x27;s like a fucking Joy Division video here from October through April. :-D<p>I think if my wife and I could afford to split our time between here and Vegas, we would. But that&#x27;s just not in the cards right now.<p>But hey, at least they&#x27;re not on the brink of civil war here and the curry is good.</text></item></parent_chain><comment><author>ascari</author><text>I moved to UK from Europe and I wouldn’t really say NHS is convenient. It is universal healthcare and you are not facing a bankruptcy most of the time in case of a health condition. Preventative and diagnosis treatments are so slow. In case I need to see a GP, i must try reaching them at 8ish in the morning otherwise they will simply ignore you and tell, call tomorrow.</text></comment> |
35,507,815 | 35,507,455 | 1 | 2 | 35,504,428 | train | <story><title>The LLama Effect: Leak Sparked a Series of Open Source Alternatives to ChatGPT</title><url>https://thesequence.substack.com/p/the-llama-effect-how-an-accidental</url></story><parent_chain><item><author>tachyon5</author><text>GPT-4 fails if we add one more level in this logical problem:<p>Q: A man sees PULL written in mirror writing on a glass door. There&#x27;s a blind man on the other side of the door. What should the man tell the blind man to open the door and why?<p>GPT-4: The man should tell the blind man to &quot;push&quot; the door to open it. Since the word &quot;PULL&quot; is written in mirror writing on the glass door, it suggests that the correct action on the man&#x27;s side is to push the door. The blind man, being on the other side of the door, should also push it to open it. The man should provide clear instructions to the blind man to ensure proper communication and ease of access.</text></item><item><author>jonplackett</author><text>The difference between 3.5 and 4 is gigantic even in my fairly limited experience.<p>I gave them both some common sense tests and this one stuck out to me.<p>Q: A glass door has ‘push’ written on it in mirror writing. Should you push or pull it<p>GPT-3.5:<p>If the word &quot;push&quot; is written in mirror writing on a glass door, you should push the door to open it<p>GPT-4:<p>Since the word &quot;push&quot; is written in mirror writing, it suggests that the instruction is intended for people on the other side of the door. Therefore, you should pull the door to open it.</text></item><item><author>superkuh</author><text>I&#x27;ve spent an embarassing amount of time since the llamas leaked playing with them, the tools to run them, and writing wrappers for them. They are technically alternatives in the sense that they&#x27;re incomparably better chat bots than anything in the past. But at least for the 30B and under versions (65B is too big for me to run), no matter what fine tuning is done (alpaca, gpt4all, vicuna, etc), the llamas themselves are incomparably worse at doing useful tasks than openai&#x27;s gpt3.5 models like text-davinci-003, or even the gimped gpt3.5-turbo.<p>I wish it wasn&#x27;t so, but the llamas are toys. Amazing toys, but toys. What openai is getting out of gpt3.5 (and presumbably 4, though I have no access) are actually useful responses for getting work done.</text></item></parent_chain><comment><author>Gigachad</author><text>I feel like there would be a good chunk of real humans who would be incapable of answering a question like this.</text></comment> | <story><title>The LLama Effect: Leak Sparked a Series of Open Source Alternatives to ChatGPT</title><url>https://thesequence.substack.com/p/the-llama-effect-how-an-accidental</url></story><parent_chain><item><author>tachyon5</author><text>GPT-4 fails if we add one more level in this logical problem:<p>Q: A man sees PULL written in mirror writing on a glass door. There&#x27;s a blind man on the other side of the door. What should the man tell the blind man to open the door and why?<p>GPT-4: The man should tell the blind man to &quot;push&quot; the door to open it. Since the word &quot;PULL&quot; is written in mirror writing on the glass door, it suggests that the correct action on the man&#x27;s side is to push the door. The blind man, being on the other side of the door, should also push it to open it. The man should provide clear instructions to the blind man to ensure proper communication and ease of access.</text></item><item><author>jonplackett</author><text>The difference between 3.5 and 4 is gigantic even in my fairly limited experience.<p>I gave them both some common sense tests and this one stuck out to me.<p>Q: A glass door has ‘push’ written on it in mirror writing. Should you push or pull it<p>GPT-3.5:<p>If the word &quot;push&quot; is written in mirror writing on a glass door, you should push the door to open it<p>GPT-4:<p>Since the word &quot;push&quot; is written in mirror writing, it suggests that the instruction is intended for people on the other side of the door. Therefore, you should pull the door to open it.</text></item><item><author>superkuh</author><text>I&#x27;ve spent an embarassing amount of time since the llamas leaked playing with them, the tools to run them, and writing wrappers for them. They are technically alternatives in the sense that they&#x27;re incomparably better chat bots than anything in the past. But at least for the 30B and under versions (65B is too big for me to run), no matter what fine tuning is done (alpaca, gpt4all, vicuna, etc), the llamas themselves are incomparably worse at doing useful tasks than openai&#x27;s gpt3.5 models like text-davinci-003, or even the gimped gpt3.5-turbo.<p>I wish it wasn&#x27;t so, but the llamas are toys. Amazing toys, but toys. What openai is getting out of gpt3.5 (and presumbably 4, though I have no access) are actually useful responses for getting work done.</text></item></parent_chain><comment><author>FLT8</author><text>Vicuna-13b seems to do a little better, although it seems to think that the blind man should be able to feel the writing:<p>Human: A man sees PULL written in mirror writing on a glass door. There&#x27;s a blind man on the other side of the door. What should the man tell the blind man to open the door and why?<p>Assistant: <i>The man should tell the blind man to feel for the word &quot;PULL&quot; written in normal writing on the glass door, as the blind man will be able to feel the indentations made by the letters. This will allow the blind man to open the door by finding the handle or knob and pulling it. The reason for this is that the word &quot;PULL&quot; is written in normal writing for the blind man to feel, so he can open the door.</i></text></comment> |
32,140,834 | 32,140,531 | 1 | 3 | 32,139,612 | train | <story><title>RSS is back as an underpinning to SlackOps</title><url>https://conoroneill.net/2022/07/18/rss-is-on-fire-again-and-its-all-down-to-slackops/</url></story><parent_chain></parent_chain><comment><author>powersnail</author><text>RSS has been alive this whole time. Blogs usually have it by default, the big news organizations have it.<p>The only thing I&#x27;m not satisfied with reading news on RSS, is that news organizations push too many articles, to the point that reading the headlines alone takes quite some time. There&#x27;s nearly 100 articles per day per source sometimes. Unlike a newspaper, which has a natural structure of priority and hierarchy, in an RSS reader, every head line has the same salience, and it&#x27;s a pain to weed out what&#x27;s important.<p>I kinda hope news organizations would make a separate &quot;weekly digest feed&quot;, 30 or so articles per week.</text></comment> | <story><title>RSS is back as an underpinning to SlackOps</title><url>https://conoroneill.net/2022/07/18/rss-is-on-fire-again-and-its-all-down-to-slackops/</url></story><parent_chain></parent_chain><comment><author>zerop</author><text>Want to start a subthread here on what makes it great and despite many attempts to kill it, it still rocks! My take<p>1. Widely adopted protocol, clients in all programming languages.<p>2. Publicly readable without password<p>3. Get notification for new items in many tools like Slack<p>4. Easy to produce and consume<p>5. Many nice Web UI Reader available<p>&lt;Add yours&gt;</text></comment> |
33,181,297 | 33,180,582 | 1 | 3 | 33,179,047 | train | <story><title>Removing SMS support from Signal Android (soon)</title><url>https://signal.org/blog/sms-removal-android/</url></story><parent_chain><item><author>daedalus_j</author><text>I&#x27;ve been using Signal for a long time. I have <i>repeatedly</i> been unable to convince iOS users to use Signal because &quot;I don&#x27;t want another app&quot;. Android users have been much more willing to give it a shot.<p>As an android user myself, I much prefer having SMS built in because I use the search feature often to look back through all my SMS&#x2F;Signal chats. I also regularly forward an SMS message to a Signal user, or vice versa. I&#x27;m already starting to feel like those iOS users who told me &quot;I don&#x27;t want another app&quot;...<p>Signal seems to be trying to move further and further from &quot;my preferred way to chat with people&quot; and closer to the chat equivalent of &quot;that protonmail account I only log in to when I need secrecy&quot;.<p>I obviously love having security on messages in transit, but I also like being able to keep my message history around and search my conversations for something that happened a year ago. It seems like Signal is on a trajectory to turn everything into disappearing messages. Are they the &quot;safe for activists&quot; communication app, or the &quot;let&#x27;s try to make as many as possible safer by default&quot; app? Feels like they don&#x27;t know.<p>And on top of it all the messaging is just frustrating. &quot;we&#x27;ve taken away an incredibly useful and heavily used feature so we have development resource to better implement shitcoins and such&quot; is such an irritating defense of the decision that I disabled my monthly donation.</text></item></parent_chain><comment><author>nicholasjarnold</author><text>I agree completely here. This is terrible news from my perspective too. I use Signal for _all messaging_ (e2e secure or not) for the reasons that you mention.<p>I&#x27;ve onboarded friends and family, too, ensuring them it should be set as their default messaging app and that it _just works_. Unfortunately, people in the general population seem to have pretty much zero tolerance for any friction whatsoever. If they have to use 2 apps, they&#x27;ll just end up communicating with me in the clear using their &quot;default SMS&quot; app on their phone. That&#x27;s what this is going to result it...a reduction in overall message security due to people defaulting to what&#x27;s easier...which is to _not_ have to remember which app to use for which &quot;send a message&quot; purpose. Fuck.<p>I understand the argument about people in markets where SMS is expensive getting screwed sometimes when they don&#x27;t realize they&#x27;re sending a message over SMS. However could that not be fairly trivially solved for with some UI notification or app setting that warns you about this and allows the warning to be perm-disabled if the user doesn&#x27;t care!?<p>I think the real reason here is this desire to transition the service into supporting usernames, which is a topic that&#x27;s been discussed before (and is explicitly mentioned in the post). Right now the service is tied to your phone number. After this change I suspect it will not be or not need to be.<p>This is very, very unfortunate for those of us who&#x27;ve convinced a ton of non-technical friends and family to use TextSecure-&gt;Signal over the years...</text></comment> | <story><title>Removing SMS support from Signal Android (soon)</title><url>https://signal.org/blog/sms-removal-android/</url></story><parent_chain><item><author>daedalus_j</author><text>I&#x27;ve been using Signal for a long time. I have <i>repeatedly</i> been unable to convince iOS users to use Signal because &quot;I don&#x27;t want another app&quot;. Android users have been much more willing to give it a shot.<p>As an android user myself, I much prefer having SMS built in because I use the search feature often to look back through all my SMS&#x2F;Signal chats. I also regularly forward an SMS message to a Signal user, or vice versa. I&#x27;m already starting to feel like those iOS users who told me &quot;I don&#x27;t want another app&quot;...<p>Signal seems to be trying to move further and further from &quot;my preferred way to chat with people&quot; and closer to the chat equivalent of &quot;that protonmail account I only log in to when I need secrecy&quot;.<p>I obviously love having security on messages in transit, but I also like being able to keep my message history around and search my conversations for something that happened a year ago. It seems like Signal is on a trajectory to turn everything into disappearing messages. Are they the &quot;safe for activists&quot; communication app, or the &quot;let&#x27;s try to make as many as possible safer by default&quot; app? Feels like they don&#x27;t know.<p>And on top of it all the messaging is just frustrating. &quot;we&#x27;ve taken away an incredibly useful and heavily used feature so we have development resource to better implement shitcoins and such&quot; is such an irritating defense of the decision that I disabled my monthly donation.</text></item></parent_chain><comment><author>ndsipa_pomu</author><text>The biggest issue I can see with using two separate apps is checking who&#x27;s on Signal and who isn&#x27;t. That means opening up Signal to see if they&#x27;re on there and then switching to SMS if they aren&#x27;t. I much prefer having both types of contacts in the same UI and it&#x27;s been obvious to me which messages are secure. Also, when someone then joins Signal, subsequent messages to them automatically get upgraded to being secure with no effort on my part.</text></comment> |
9,485,555 | 9,485,558 | 1 | 3 | 9,484,939 | train | <story><title>Three Tales of Second System Syndrome</title><url>http://blog.brentlaabs.com/2015/05/three-tales-of-second-system-syndrome.html</url></story><parent_chain></parent_chain><comment><author>ceronman</author><text><p><pre><code> It just might be possible that Perl 6&#x27;s crazy long development process can
produce the best-adopted second system around
</code></pre>
Unfortunately, I don&#x27;t share the same optimism as the OP. In the real world, adoption is not only driven by how cool a language is, but the ecosystem of tools and developers around it. There are lots of Perl 5 codebases which won&#x27;t be migrated because it&#x27;s too expensive.<p>The true lesson learned for language developers is: Don&#x27;t break backwards compatibility. Ever.<p>The Python community made this mistake, and they acknowledge it. Guido said this won&#x27;t happen again. But at least for the case of Python 3, the number of breakages is relatively small, and the migration from 2 to 3 while tedious, it&#x27;s not that hard. Even so, the migration of the whole ecosystem has been really really slow. But I think in the end the community will move.<p>The Perl case, on the other side, is much worse. Migrating a relatively complex project from 5 to 6 is extraordinarily hard. It&#x27;s probably the same as a whole rewrite. Also, the community is divided, with some developers keeping the improvement of Perl 5, fixing bugs and adding new features. There is no incentive for migration.<p>If the migration has been so slow for Python 3, which had a much smaller barrier, I don&#x27;t see how it could be better for Perl 6.<p>New languages are able to develop a new ecosystem when they introduce innovative features, e.g. Rust. But Perl 6 while being a nice language, doesn&#x27;t seem to have any killer feature compared to mainstream languages.</text></comment> | <story><title>Three Tales of Second System Syndrome</title><url>http://blog.brentlaabs.com/2015/05/three-tales-of-second-system-syndrome.html</url></story><parent_chain></parent_chain><comment><author>TazeTSchnitzel</author><text>&gt; Well, after a little over six years of development, we discovered that we were never going to see a PHP 6 at all. Having seen how long Perl 6 had taken, and how long PHP 6 was taking, the number 6 is associated with failure. So they cancelled PHP 6 and voted to change the name to PHP 7.<p>Uh, what? Did the author do the most <i>basic</i> of research?<p>PHP 6 was a real thing, a development branch. But it dragged on for years.<p>Due to delays, they made an interim release in the 5.x series, PHP 5.3. It backported some stuff from 6.<p>Eventually, PHP 6 was killed off because it just wasn&#x27;t going to work. So they made another 5.x release, PHP 5.4, backporting more stuff from 6, and adding some other features.<p>After that, with PHP 6 dead and gone, work focussed on the PHP 5.x series again. So out came PHP 5.5 (2013) and PHP 5.6 (2014).<p>During this time, some people did some experiments and realised it was possible, by breaking internal (not userland) compatibility, to greatly improve PHP&#x27;s performance. This project became phpng. Since it would break so many (internal) things, they decided that if it should be merged into PHP, it needed to go into a new major version.<p>It was after this that the ridiculous version number vote was held. I don&#x27;t see why we ever had that debate, really. PHP 6 was a thing and was killed off, re-using the version number was silly. Anyway, the number chosen was PHP 7.<p>Fast forward to the present day: PHP 7 has gone into feature freeze and should be released in a few months. Alongside the performance improvements of phpng, it has some other new features developed independently, and includes a few deliberate backwards-compatibility breaks.<p>tl;dr: the time line goes: 5.2 release, work begins on 6.0, 5.3 release, 6.0 killed off, 5.4 release, 5.5 release, 5.6 release, 7.0 in development.<p>Edit:<p>&gt; JIT to the Zend engine<p>...what? No, PHP 7 does not have that.<p>&gt; Asynchronous IO and functions<p>...PHP 7 doesn&#x27;t have that either?<p>&gt; Standalone Multi-threading Web Server (HHVM)<p>...huh?<p>&gt; phpclasses.org<p>Oh, so that&#x27;s why the author is so confused.</text></comment> |
7,959,983 | 7,960,048 | 1 | 2 | 7,959,979 | train | <story><title>The Internet's Own Boy: The Story of Aaron Swartz [video]</title><url>https://archive.org/details/TheInternetsOwnBoyTheStoryOfAaronSwartz</url></story><parent_chain></parent_chain><comment><author>nullc</author><text>This is the full 120 minute long documentary. It&#x27;s a heavy watch, but interesting to both audiences familiar with the background and ones who are not.<p>In addition to the normal pay per view streaming on vimeo (<a href="https://vimeo.com/ondemand/internetsownboy/94238859" rel="nofollow">https:&#x2F;&#x2F;vimeo.com&#x2F;ondemand&#x2F;internetsownboy&#x2F;94238859</a>), this film was also offered at an increased price under CC-By-NC-SA. I purchased a freely licensed copy and have placed it on archive.org allowing anyone to learn from it, share it with others, or build new works out of it without risk of prosecution and without going through US-only paywall.<p>The official site for the film is at <a href="http://www.takepart.com/internets-own-boy" rel="nofollow">http:&#x2F;&#x2F;www.takepart.com&#x2F;internets-own-boy</a> and the there is a Wikipedia article at <a href="http://en.wikipedia.org/wiki/The_Internet%27s_Own_Boy:_The_Story_of_Aaron_Swartz" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Internet%27s_Own_Boy:_The_S...</a></text></comment> | <story><title>The Internet's Own Boy: The Story of Aaron Swartz [video]</title><url>https://archive.org/details/TheInternetsOwnBoyTheStoryOfAaronSwartz</url></story><parent_chain></parent_chain><comment><author>RexRollman</author><text>The only thing I don&#x27;t care for in all this is the deification of Swartz, as if he played no part in the dilemma he found himself in. That said, something need to be done about the prosecutors in this country, who overcharge and bend the law in way not intended.</text></comment> |
9,521,124 | 9,519,520 | 1 | 3 | 9,518,870 | train | <story><title>Django 1.8 and Python 3: Complex app tutorial, end-to-end</title><url>http://www.marinamele.com/taskbuster-django-tutorial</url></story><parent_chain></parent_chain><comment><author>matthijs_</author><text>Great job. For me personally, it&#x27;s very helpful to have an end-to-end tutorial, where all aspects of an (example) app are discussed. I don&#x27;t have a CS-background nor many years of coding experience, so a tutorial written by somebody who does have the proper experience and knowledge and puts it all together is extremely valuable to me. That&#x27;s why I&#x27;d happily pay a fee for tutorials like this.<p>At the moment I&#x27;m working on building an app in Node.js with Express and sadly, there are not many tutorials of this quality.</text></comment> | <story><title>Django 1.8 and Python 3: Complex app tutorial, end-to-end</title><url>http://www.marinamele.com/taskbuster-django-tutorial</url></story><parent_chain></parent_chain><comment><author>bsaul</author><text>Just looked at the summary, but it doesn&#x27;t seem to include a chapter on asynchronous jobs ( such as report creations, emailing, or any kind of long running tasks). Along with websockets &#x2F; push architecture, this is often when website designs start to be really complex.</text></comment> |
37,830,851 | 37,830,789 | 1 | 3 | 37,830,079 | train | <story><title>C uses "&" for the address-operator because 'ampersand sounds like "address"'</title><url>https://softwareengineering.stackexchange.com/questions/252023/why-does-c-use-the-asterisk-for-pointers</url></story><parent_chain></parent_chain><comment><author>adrian_b</author><text>Some people in that discussion wonder about &quot;-&gt;&quot;, which is used for indirect addressing through a structure member.<p>When C has added structures, which did not exist in B, it has taken the keyword &quot;struct&quot; and also both &quot;.&quot; and &quot;-&gt;&quot; from the IBM PL&#x2F;I language, from which C has also taken some other features.<p>In general, almost any feature added by C to B was taken either from PL&#x2F;I or from Algol 68. The exceptions are &quot;continue&quot; and the generalized &quot;for&quot;, which did not exist in any previous language.<p>(However the generalized &quot;for&quot; of C was a mistake, because it complicates the frequent use cases in order to simplify seldom encountered use cases. The right way to generalize &quot;for&quot;, i.e. with iterators, was introduced by Alphard in the same year with C, i.e. in 1974.) (Compare &quot;for (I=0;I&lt;N;I+=5) {&quot; of C with &quot;for I from 0 to N by 5 do&quot; or &quot;for I in 0:N:5 do&quot; of previous languages. C requires typing a lot of redundant characters in the most frequent cases.)<p>The oldest symbol for indirection through a pointer (in the language Euler, in January 1966) was a raised middle dot (i.e. a point). This was before ASCII and ASCII did not include the raised middle dot (U+00B7), so it was replaced by the most similar ASCII character, &quot;*&quot;.<p>Euler had used &quot;@&quot; for &quot;address of&quot; and indirection was a postfix operator, as it should. Making &quot;*&quot; a prefix operator in B and C was a mistake, which forced the importing of &quot;-&gt;&quot; from PL&#x2F;I, to avoid an excessive number of parentheses. Otherwise &quot;(*x).y&quot; would have been needed, instead of &quot;x-&gt;y&quot;. With a postfix &quot;*&quot;, that would have been &quot;x*.y&quot;, and &quot;-&gt;&quot;, would not have been needed.<p>In CPL, the ancestor of BCPL and B, indirection was implicit, like with the C++ references. Instead of having an &quot;address of&quot; operator, CPL had a distinct symbol for an assignment variant that assigns the address of a variable, instead of assigning its value.</text></comment> | <story><title>C uses "&" for the address-operator because 'ampersand sounds like "address"'</title><url>https://softwareengineering.stackexchange.com/questions/252023/why-does-c-use-the-asterisk-for-pointers</url></story><parent_chain></parent_chain><comment><author>robertlagrant</author><text>Hot take: @ might&#x27;ve been a good alternative.</text></comment> |
11,645,479 | 11,645,421 | 1 | 2 | 11,644,439 | train | <story><title>Locking in WebKit</title><url>https://webkit.org/blog/6161/locking-in-webkit/</url></story><parent_chain></parent_chain><comment><author>eridius</author><text>Two things come to mind when reading this:<p>1. WTF::Lock is using sequential consistency for all of the slow path operations. Surely this isn&#x27;t necessary and it could still use acquire&#x2F;release for most of them (like it does in the fast path).<p>2. Ditching OS-provided mutexes has one possibly-important drawback on OS X and iOS: lack of priority donation. Recent versions of OS X and iOS have a Quality Of Service implementation in the kernel that classifies threads (and libdispatch queues) according to one of several QOS levels, and then handles normal thread priorities within those levels. For this reason you actually cannot safely implement your own spinlock, as I documented a few months ago (<a href="http:&#x2F;&#x2F;engineering.postmates.com&#x2F;Spinlocks-Considered-Harmful-On-iOS&#x2F;);" rel="nofollow">http:&#x2F;&#x2F;engineering.postmates.com&#x2F;Spinlocks-Considered-Harmfu...</a> it&#x27;ll appear to work under many normal workloads, but once you start using the spinlock from threads of different QOS levels at the same time, you risk hitting a priority inversion livelock where a lower-QOS thread has the spinlock locked but is never scheduled because higher-QOS threads spinning on the lock are always given priority. The OS does actually have a safe spinlock (which does priority donation), but it&#x27;s not public API and so can&#x27;t be used outside of system code. Of course, this doesn&#x27;t apply to adaptive spinlocks, since they&#x27;ll just end up in the slow path of parking their thread, but this does still serve to highlight the issue they do have, which is if a high-QOS thread is parked waiting for a lock that&#x27;s owned by a low-QOS thread, the high-QOS thread is effectively having its priority lowered to the low QOS until the owning thread releases the lock. This is obviously not what you want. The system-provided pthread_mutex_t does priority donation specifically to fix this issue, but WTF::Lock doesn&#x27;t.</text></comment> | <story><title>Locking in WebKit</title><url>https://webkit.org/blog/6161/locking-in-webkit/</url></story><parent_chain></parent_chain><comment><author>cokernel_hacker</author><text>Spinning in locks are always tricky business.<p>The sharpest thorn, to me, is: what happens when you are running inside the critical section and your thread gets preempted?<p>Well, now the next thread which tries to acquire the lock is stuck waiting. But waiting for what? Waiting for the original thread to get scheduled.<p>Now, the OS has no idea that the original thread should get scheduled again and is free to continue scheduling more and more work items.<p>Fortunately for the lock in this article, and most other locks which spin, it is adaptive and will not spin for too long. But how long is long enough? If the spin is timed for a few loads and stores, then all is probably well as spins will not be attempted for very long.<p>I wonder how these locks figure out how long they should spin? In the nasty case I previously mentioned, you&#x27;d want to spin for a very short while to avoid large amounts of waste. But spins which are too short lead to higher lock&#x2F;unlock latency if the lock was held for any appreciable amount of time.<p>This leads me to the following conclusion: spinning inevitable leads to _some_ number of wasted CPU cycles and therefore increased latency.<p>I&#x27;m curious as to how the amount of spinning was chosen.</text></comment> |
9,916,530 | 9,916,466 | 1 | 2 | 9,916,134 | train | <story><title>The Art of Quitting</title><url>http://www.atlasobscura.com/articles/the-art-of-quitting</url></story><parent_chain></parent_chain><comment><author>jasode</author><text>I&#x27;m not sure what to make of this blog post. The author writes:<p><i>&gt;By resigning from Reddit, </i><p>Behind the scenes, Ellen Pao could have been forced out (also known as being &quot;fired&quot;) but presented publicly as a resignation. I thought we don&#x27;t really know what happened? Therefore, it seems biased to frame a thematic essay about &quot;quitting&quot; around Ellen&#x27;s circumstances. If she didn&#x27;t voluntarily separate, it&#x27;s not &quot;quitting&quot; -- it&#x27;s getting fired. Does the author Ernie Smith know the inside details of Ellen Pao&#x27;s situation that we don&#x27;t?<p><i>&gt;Ellen Pao is choosing to focus her attention on the other things that interest her.</i><p>The underlying Washington Post article that this sentence links to is ~900 words written by Ellen Pao. She makes no mention of &quot;<i>other things that interest her.</i>&quot;<p>Overall, a blog post of dubious quality.</text></comment> | <story><title>The Art of Quitting</title><url>http://www.atlasobscura.com/articles/the-art-of-quitting</url></story><parent_chain></parent_chain><comment><author>beat</author><text>I feel this.<p>I spent 20 years building a successful career as an enterprise software engineer, bouncing around between configuration management, development, and ops. It&#x27;s a secure, good paying, stable career. And I grew to resent and sometimes hate it.<p>Then I started building something for myself, discovered the idea of creating my own startup to solve problems I experienced doing enterprise software projects in a general way, and I <i>love</i> that. It makes me feel like I&#x27;m doing something that actually matters.<p>Right now, I&#x27;m back in the enterprise to make ends meet and building on the side, which sucks and drives me crazy - but at least I see the exit and can keep moving toward it. And I figure I can get five or ten years out of building a company before I&#x27;m done with that as well.<p>Once you hit a certain age and a certain level of success, the things you realize you&#x27;ll never do weigh on you more than the things you haven&#x27;t done yet. And the things you do look more like impediments than accomplishments. That&#x27;s when you need to change.</text></comment> |
36,553,964 | 36,553,279 | 1 | 2 | 36,552,231 | train | <story><title>Twitter limits unverified accounts to reading 600 posts/day</title><url>https://twitter.com/elonmusk/status/1675187969420828672</url></story><parent_chain><item><author>jljljl</author><text>This seems like death for an ad supported model on Twitter. Why would you buy ads on a social network that deliberately restricts the number of posts (and thus ads) that a user can view?</text></item></parent_chain><comment><author>SnorkelTan</author><text>One reason I could think of is that real humans only read a certain number of tweets per day. Showing ads to users that &quot;read&quot; large numbers is showing ads to robots which, sadly, do not convert very well.</text></comment> | <story><title>Twitter limits unverified accounts to reading 600 posts/day</title><url>https://twitter.com/elonmusk/status/1675187969420828672</url></story><parent_chain><item><author>jljljl</author><text>This seems like death for an ad supported model on Twitter. Why would you buy ads on a social network that deliberately restricts the number of posts (and thus ads) that a user can view?</text></item></parent_chain><comment><author>CreepGin</author><text>Can&#x27;t speak for the big advertisers, but as a small business owner, I&#x27;m more likely to spend ad money on platforms that take an active stance against bots. In general, advertisers (should) care about impressions by unique users, not total number of views.<p>I&#x27;m not sure about requiring an account to view contents though. That to me will just kill total usage across the board.</text></comment> |
40,040,687 | 40,040,400 | 1 | 3 | 40,040,100 | train | <story><title>Tesla Cybertruck deliveries halted for 7 days</title><url>https://www.barrons.com/articles/tesla-cybertruck-production-halted-ac750c17</url></story><parent_chain><item><author>goodoldneon</author><text>Wonder if this is the reason:
<a href="https:&#x2F;&#x2F;x.com&#x2F;garageklub&#x2F;status&#x2F;1779571445930324456" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;garageklub&#x2F;status&#x2F;1779571445930324456</a></text></item></parent_chain><comment><author>tivert</author><text>&gt; Wonder if this is the reason: <a href="https:&#x2F;&#x2F;x.com&#x2F;garageklub&#x2F;status&#x2F;1779571445930324456" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;garageklub&#x2F;status&#x2F;1779571445930324456</a><p>What&#x27;s the big deal? They could just fix a problem like that with software. Just patch in an emergency acceleration shutdown button in a sub-menu on the touchscreen (e.g. hit truck, &quot;Controls&quot;, select a new &quot;disable jammed accelerator&quot;, click confirm).</text></comment> | <story><title>Tesla Cybertruck deliveries halted for 7 days</title><url>https://www.barrons.com/articles/tesla-cybertruck-production-halted-ac750c17</url></story><parent_chain><item><author>goodoldneon</author><text>Wonder if this is the reason:
<a href="https:&#x2F;&#x2F;x.com&#x2F;garageklub&#x2F;status&#x2F;1779571445930324456" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;garageklub&#x2F;status&#x2F;1779571445930324456</a></text></item></parent_chain><comment><author>piva00</author><text>On a US$ 60-100k product it&#x27;s absolutely a slap on the face, no questions, there&#x27;s absolutely no reason to cheap out on a fastener for the pedal trim.<p>Also puts in question what is actually happening on Tesla&#x27;s engineering org, one just needs to have a moderate amount of reasoning power to think about the scenario &quot;what happens in case this piece gets loose?&quot; on a critical feature of a car, not even an engineering-related study nor a big brain, it&#x27;s just a reasonable thought to have, so how could this piece pass all the engineering process review?</text></comment> |
13,339,215 | 13,338,882 | 1 | 2 | 13,338,441 | train | <story><title>FTC sues D-Link over router and camera security flaws</title><url>https://www.consumer.ftc.gov/blog/ftc-sues-d-link-over-router-and-camera-security-flaws</url></story><parent_chain></parent_chain><comment><author>nodja</author><text>My boss installed 2 camera DVRs a year or so ago. All I did was provide 2 external IPs for the DVR and didn&#x27;t worry much about it. The password was the default &quot;123456&quot; that comes with these things, but since we don&#x27;t care much about who sees the footage. At worse people will change the password and we need to factory reset (never happened).<p>Last week the internet for the whole office was going down. Weirdly I could remote in, but the DNS was not working. I first thought our DNS server crapped out but it was working fine. After some investigation, the firewall was not responding. After rebooting the firewall, it would work fine for a while, but go down shortly after.<p>Long story short: the DVRs my boss got (unbranded) come with telnet access on some nonstandard port. A botnet got access to it and was making thousands of dns and telnet queries, overloading the firewall.</text></comment> | <story><title>FTC sues D-Link over router and camera security flaws</title><url>https://www.consumer.ftc.gov/blog/ftc-sues-d-link-over-router-and-camera-security-flaws</url></story><parent_chain></parent_chain><comment><author>luma</author><text>How long is the company that provides the product on the hook for for post-sale support and security updates? If I sell an internet-connected device which has a flaw discovered 5 years after the sale, am I still liable for patching that? Nowhere in this article nor in the complaint do I find any guidelines as to what they consider to be reasonable after-sale support. They list similar action taken against Asus and TRENDnet, which are all large international companies. I&#x27;m a dude in my workshop and placing an after-sale support and warranty requirement on anything I make for a period of n-years is onerous.</text></comment> |
38,105,855 | 38,105,872 | 1 | 2 | 38,097,938 | train | <story><title>As the public begins to believe Google isn’t as useful, what happens to SEO?</title><url>https://www.theverge.com/features/23931789/seo-search-engine-optimization-experts-google-results</url></story><parent_chain><item><author>phendrenad2</author><text>&quot;The internet&quot; doesn&#x27;t really exist, now, now does it? 99% of users are living in an AOL-style world, where they live within walled gardens. Why leave twitter&#x2F;facebook&#x2F;instagram&#x2F;youtube&#x2F;tiktok&#x2F;reddit? There&#x27;s nothing out there but a wasteland of crumbling has-been sites. Sometimes you&#x27;ll find yourself on a blog or news article, but you just click&#x2F;tap the back button to go back to the walled garden. Nobody is subscribing to your RSS feed. And what really did this is mobile devices. And it isn&#x27;t necessarily a bad thing, although I do miss the old vbulletin discussion days.</text></item></parent_chain><comment><author>asdfman123</author><text>There&#x27;s lots of good content out there, but the problem is finding it. A Google replacement wouldn&#x27;t be any better, because everyone&#x27;s attention would be directed into optimizing new replacement site.<p>It frustrates me when people say &quot;Google should search reddit by default.&quot; The reason reddit is still halfway decent is there isn&#x27;t as much money in gaming it, but there would be if the entire world was sent to it.</text></comment> | <story><title>As the public begins to believe Google isn’t as useful, what happens to SEO?</title><url>https://www.theverge.com/features/23931789/seo-search-engine-optimization-experts-google-results</url></story><parent_chain><item><author>phendrenad2</author><text>&quot;The internet&quot; doesn&#x27;t really exist, now, now does it? 99% of users are living in an AOL-style world, where they live within walled gardens. Why leave twitter&#x2F;facebook&#x2F;instagram&#x2F;youtube&#x2F;tiktok&#x2F;reddit? There&#x27;s nothing out there but a wasteland of crumbling has-been sites. Sometimes you&#x27;ll find yourself on a blog or news article, but you just click&#x2F;tap the back button to go back to the walled garden. Nobody is subscribing to your RSS feed. And what really did this is mobile devices. And it isn&#x27;t necessarily a bad thing, although I do miss the old vbulletin discussion days.</text></item></parent_chain><comment><author>superkuh</author><text>Your perception is how the vast majority of people see the web. But you&#x27;re completely wrong about &quot;nothing out there&quot; and &quot;Nobody is subscribing to your RSS feed.&quot; Just because you&#x27;re trapped in the gardens doesn&#x27;t mean there aren&#x27;t communities of people who never went in them in the first place.<p>Yes, there&#x27;s a thick layer of for-profit walled garden crap on top but the actual web of websites (not applications) is still out there and it&#x27;s bigger than ever despite being proportionally much smaller compared to the smartphone&#x2F;megacorp users.</text></comment> |
12,396,259 | 12,396,295 | 1 | 2 | 12,395,966 | train | <story><title>Dropbox employee’s password reuse led to theft of 60M+ user credentials</title><url>https://techcrunch.com/2016/08/30/dropbox-employees-password-reuse-led-to-theft-of-60m-user-credentials/?ncid=rss&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+Techcrunch+%28TechCrunch%29</url></story><parent_chain><item><author>rjbwork</author><text>This is a really good reason to be careful about what you log to log analytics platforms. I just recently implemented an ETL system that has the credentials (along with other stuff about the job) for data access passed into it from a PaaS framework. While I want to log the information, I don&#x27;t want to log my DB connection strings! It&#x27;s very easy to overlook such things and produce them as part of application logging&#x2F;exhaust without realizing it, especially now that we have mass adoption of things like Splunk, Logg.ly, CloudFront, Cortana Analytics, Elmah.IO, LogEntries, Seq, and a dozen others.</text></item></parent_chain><comment><author>rdtsc</author><text>&gt; It&#x27;s very easy to overlook such things and produce them as part of application logging&#x2F;exhaust without realizing it<p>Very true. It is a constant battle between debuggability and not leaking credentials.<p>In Erlang for example, when processes crash they dump their state, their neighbours, links to other processes, and other such useful stuff. That&#x27;s very helpful, however it means it could dump credentials as well.<p>Luckily there a custom function to format the state of a process <a href="http:&#x2F;&#x2F;erlang.org&#x2F;doc&#x2F;man&#x2F;gen_server.html#Module:format_status-2" rel="nofollow">http:&#x2F;&#x2F;erlang.org&#x2F;doc&#x2F;man&#x2F;gen_server.html#Module:format_stat...</a> which helps with that. But have to implement that each process which holds credentials.<p>Also some of those log ingesting services provide a pre-indexer credentials filtering. I know Splunk has it:<p><a href="http:&#x2F;&#x2F;docs.splunk.com&#x2F;Documentation&#x2F;Splunk&#x2F;6.4.3&#x2F;Data&#x2F;Anonymizedata" rel="nofollow">http:&#x2F;&#x2F;docs.splunk.com&#x2F;Documentation&#x2F;Splunk&#x2F;6.4.3&#x2F;Data&#x2F;Anony...</a><p>Of course it is better if it is filtered out before that. But it could be a safety net perhaps.</text></comment> | <story><title>Dropbox employee’s password reuse led to theft of 60M+ user credentials</title><url>https://techcrunch.com/2016/08/30/dropbox-employees-password-reuse-led-to-theft-of-60m-user-credentials/?ncid=rss&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+Techcrunch+%28TechCrunch%29</url></story><parent_chain><item><author>rjbwork</author><text>This is a really good reason to be careful about what you log to log analytics platforms. I just recently implemented an ETL system that has the credentials (along with other stuff about the job) for data access passed into it from a PaaS framework. While I want to log the information, I don&#x27;t want to log my DB connection strings! It&#x27;s very easy to overlook such things and produce them as part of application logging&#x2F;exhaust without realizing it, especially now that we have mass adoption of things like Splunk, Logg.ly, CloudFront, Cortana Analytics, Elmah.IO, LogEntries, Seq, and a dozen others.</text></item></parent_chain><comment><author>dotancohen</author><text>I&#x27;m actually fixing an issue with this right now. My logging framework is capturing user passwords, so I&#x27;ve delayed the release one day while I blacklist certain known-sensitive information from the capture.</text></comment> |
17,554,979 | 17,554,798 | 1 | 3 | 17,553,012 | train | <story><title>MacOS VPN architecture from System Preferences down to nesessionmanager</title><url>https://blog.timac.org/2018/0717-macos-vpn-architecture/</url></story><parent_chain><item><author>teilo</author><text>What boggles me about the VPN implementation on Mac is the massive amount of functionality that is not accessible unless you are using Apple Configurator to create a profile. Then you have to install the profile, and for any configuration change, you have to repeat the process.<p>For example, even though you can create a basic IKEv2 config, most of the parameters that are needed to actually make it work with a given router are not accessible except in Configurator. You cannot configure the encryption or hash algos, DH Group, group identifiers, etc.<p>And there is no access at all to other VPN types, such as a number of vendor-specific options, custom SSL, etc., even though they are supported.<p>Why can&#x27;t there be advanced options for this stuff? It makes no sense.</text></item></parent_chain><comment><author>derefr</author><text>You&#x27;re supposed to be managing the deployment&#x2F;delivery of Apple Configurator profiles through Server.app&#x27;s MDM features. If that is in play, then the workflow looks like:<p>1. You navigate your device to the MDM web portal served from the Mac running Server.app;<p>2. the MDM portal recognizes your MAC address as a new device, and allows you to register it;<p>3. an MDM profile is auto-generated for you, which you download and install;<p>4. the MDM profile transparently manages&#x2F;updates a <i>real</i> (Apple Configurator) profile, which has been customized by the MDM for any settings keyed specifically to your computer&#x27;s MAC address.<p>Using Apple Configurator without MDM, just using Configurator .profile files, would be like using Windows Group Policy without Active Directory, just using GPO .cab files. It&#x27;s <i>possible</i>, but just kinda silly.</text></comment> | <story><title>MacOS VPN architecture from System Preferences down to nesessionmanager</title><url>https://blog.timac.org/2018/0717-macos-vpn-architecture/</url></story><parent_chain><item><author>teilo</author><text>What boggles me about the VPN implementation on Mac is the massive amount of functionality that is not accessible unless you are using Apple Configurator to create a profile. Then you have to install the profile, and for any configuration change, you have to repeat the process.<p>For example, even though you can create a basic IKEv2 config, most of the parameters that are needed to actually make it work with a given router are not accessible except in Configurator. You cannot configure the encryption or hash algos, DH Group, group identifiers, etc.<p>And there is no access at all to other VPN types, such as a number of vendor-specific options, custom SSL, etc., even though they are supported.<p>Why can&#x27;t there be advanced options for this stuff? It makes no sense.</text></item></parent_chain><comment><author>Mister_Snuggles</author><text>&gt; For example, even though you can create a basic IKEv2 config, most of the parameters that are needed to actually make it work with a given router are not accessible except in Configurator. You cannot configure the encryption or hash algos, DH Group, group identifiers, etc.<p>It seems like some of these, such as encryption, hash algorithm, and DH group, should be configured on the server side, not the client side. I know that in the IPSec world the peers are roughly equal, but in this scenario the Mac is definitely playing the role of client. Likewise, there is no ability to configure the traffic selectors, and I&#x27;d argue that there probably shouldn&#x27;t be.<p>I agree that there should be more configuration exposed in the UI though.<p>EDIT: I spent about a half hour trying, unsuccessfully, to configure an IKEv2 connection on MacOS to a StrongSwan server. I suspect a configuration problem on the StrongSwan side, but the MacOS side is so opaque that it makes it hard to match up the configs properly.<p>EDIT2: I remember why I stopped trying to get IKEv2 working - the fact that Split-DNS is not in the protocol yet, but with IKEv1 I can use the Cisco Unity extensions to do it.</text></comment> |
23,545,055 | 23,545,095 | 1 | 3 | 23,543,131 | train | <story><title>The Next Step for Generics</title><url>https://blog.golang.org/generics-next-step</url></story><parent_chain><item><author>jasonhansel</author><text>Go really should have learned 2 lessons from Java 5:<p>1. People will eventually want generics
2. Retrofitting generics onto an existing language is hard and leads to unusual problems<p>(edit: I&#x27;m glad Go is doing this, but...Java learned this in 2004.)</text></item><item><author>cies</author><text>I cant help feeling it is a missed opportunity to add generics to Go this late. A mistake that is copied from earlier languages (C++, Java), a mistake similar to other mistakes Go chose not to solve at it&#x27;s inception, like: having implicit nulls (C, C++, Java, JS, C#), lack of proper sum types (C, C++, Java, JS) and only one blessed concurrency model (JS).<p>While I think I get the reasons for these decision in theory, make a simple-to-fully-understand language that compiles blazingly fast, I still feel it&#x27;s a pity (most) these issues where not addressed.</text></item></parent_chain><comment><author>kjksf</author><text>There&#x27;s is a design document for Go generics.<p>If you see &quot;unusual problems&quot; with the design, then tell us what they are.<p>Otherwise it&#x27;s just shallow pattern matching &quot;Java added generics late, they had problems, Go added generics late therefore they&#x27;ll have problems too&quot;.<p>Counterexample: C# added generics late and it&#x27;s perfectly fine design.<p>The reason Go team is not rushing to implement generics is precisely so that the design makes sense, in the context of Go.<p>Over the years Ian Taylor wrote several designs for generics, all of which were found to not be good enough.<p>They are doing it the right way: not shipping until they have a good design and they didn&#x27;t have good design when Go launched.</text></comment> | <story><title>The Next Step for Generics</title><url>https://blog.golang.org/generics-next-step</url></story><parent_chain><item><author>jasonhansel</author><text>Go really should have learned 2 lessons from Java 5:<p>1. People will eventually want generics
2. Retrofitting generics onto an existing language is hard and leads to unusual problems<p>(edit: I&#x27;m glad Go is doing this, but...Java learned this in 2004.)</text></item><item><author>cies</author><text>I cant help feeling it is a missed opportunity to add generics to Go this late. A mistake that is copied from earlier languages (C++, Java), a mistake similar to other mistakes Go chose not to solve at it&#x27;s inception, like: having implicit nulls (C, C++, Java, JS, C#), lack of proper sum types (C, C++, Java, JS) and only one blessed concurrency model (JS).<p>While I think I get the reasons for these decision in theory, make a simple-to-fully-understand language that compiles blazingly fast, I still feel it&#x27;s a pity (most) these issues where not addressed.</text></item></parent_chain><comment><author>Ericson2314</author><text>Go is just Java repeated as farce. The histories are almost identical with ~10 years lag.<p>We all called this when Go was created, too.</text></comment> |
27,469,638 | 27,469,088 | 1 | 2 | 27,468,838 | train | <story><title>Husband of Amazon employee sentenced to prison for insider trading Amazon stock</title><url>https://www.justice.gov/usao-wdwa/pr/husband-amazon-employee-sentenced-prison-insider-trading-amazon-stock</url></story><parent_chain><item><author>lizdax</author><text>&gt;he obtained from his wife, an Amazon finance employee, to place trades in Amazon stock–making a profit of $1,428,264<p>&gt;Bohra engaged in illegal insider trading in advance of 11 straight earnings announcements.”<p>&gt;He and his family members have paid $2,652,899 in disgorgement, interest and penalties.<p>And 26 months in prison! This is why if you&#x27;re going to do any kind of trading yourself -- never touch the company you work for.<p>Some more info on the original SEC filing as well: <a href="https:&#x2F;&#x2F;www.sec.gov&#x2F;litigation&#x2F;complaints&#x2F;2020&#x2F;comp24923.pdf" rel="nofollow">https:&#x2F;&#x2F;www.sec.gov&#x2F;litigation&#x2F;complaints&#x2F;2020&#x2F;comp24923.pdf</a></text></item></parent_chain><comment><author>TwoBit</author><text>He blatantly traded those 11 times during blackout periods. Companies make it very clear what these blackout periods are, so this was very stupid, as he was bound to get caught.</text></comment> | <story><title>Husband of Amazon employee sentenced to prison for insider trading Amazon stock</title><url>https://www.justice.gov/usao-wdwa/pr/husband-amazon-employee-sentenced-prison-insider-trading-amazon-stock</url></story><parent_chain><item><author>lizdax</author><text>&gt;he obtained from his wife, an Amazon finance employee, to place trades in Amazon stock–making a profit of $1,428,264<p>&gt;Bohra engaged in illegal insider trading in advance of 11 straight earnings announcements.”<p>&gt;He and his family members have paid $2,652,899 in disgorgement, interest and penalties.<p>And 26 months in prison! This is why if you&#x27;re going to do any kind of trading yourself -- never touch the company you work for.<p>Some more info on the original SEC filing as well: <a href="https:&#x2F;&#x2F;www.sec.gov&#x2F;litigation&#x2F;complaints&#x2F;2020&#x2F;comp24923.pdf" rel="nofollow">https:&#x2F;&#x2F;www.sec.gov&#x2F;litigation&#x2F;complaints&#x2F;2020&#x2F;comp24923.pdf</a></text></item></parent_chain><comment><author>nradov</author><text>There&#x27;s nothing illegal about trading your employer&#x27;s stock if you don&#x27;t have access to insider information. Millions of investors do that with no problems.</text></comment> |
5,297,811 | 5,296,650 | 1 | 3 | 5,294,202 | train | <story><title>Politicians want “loser pays” rule for patent trolls</title><url>http://arstechnica.com/tech-policy/2013/02/pissed-off-politicians-want-loser-pays-rule-for-patent-trolls/</url></story><parent_chain><item><author>bigiain</author><text>This is a problem that needs to be addressed carefully in my opinion.<p>Right now, it's a perfectly valid decision for an inventive/creative person(or team or company) to choose to spend their time inventing new things instead of commercialising "finished ideas", since the laws are (and have been for decades) written to allow an inventor to sell their patents.<p>If you're the world's best battery chemist, I'd rather you spent this year looking for an even better battery, rather than needing to be involved in making and selling last years "best battery" to earn any money from it. I don't want the top cancer researchers "wasting time" being personally involved in making drugs at commercial scale and doing deals with Walgreens, I want them doing cancer research - and having a patent/legal system that allows them to earn a living doing so (with the understanding that they've got a choice to license or sell their patents, and whether they get to share in the spectacular riches that some big-pharma company will make if they've just saved millions of lives will depend on how they chose to structure that transaction).<p>Somehow, we need to allow inventors to continue to be "NPEs", while stopping the obvious "patent troll" techniques of buying up uncommercialised patents with the only intent being to use them to litigate.<p>(And note, by "inventors" I'm including "companies set up to do inventing, either as their sole business or perhaps with a few staff or division who 'invent' as part of their regular work". I know of companies like <a href="http://www.novogen.com" rel="nofollow">http://www.novogen.com</a> and <a href="http://www.mesoblast.com" rel="nofollow">http://www.mesoblast.com</a> who are pretty much teams of biotech researchers intending to work out how to cure cancer, then sell the knowledge to other companies to commercialise it. I also know people at <a href="http://www.ecoult.com" rel="nofollow">http://www.ecoult.com</a> who didn't invent the technology they're commercialising, but have licensed the patents from the government research organisation that did invent/patent them.)</text></item><item><author>JumpCrisscross</author><text>So patents are only valid if held by their originator? That would make the IP non-transferable. In ARM's case, it would mean a takeover would invalidate its value.</text></item><item><author>nitrogen</author><text>One could argue that ARM's "practice" is producing designs. They are heavily involved in the creation and implementation of their patents, making them different from any troll that licenses "patents" they bought rather than "designs" they created.</text></item><item><author>JumpCrisscross</author><text>"<i>The bill would allow patent defendants to file a motion seeking to have a judge rule that the patent owner is a certain type of 'non-practicing entity'—although the bill doesn't use that term. If the motion is successful, the lawsuit can still proceed, but if the patent-holding company loses, it will be on the hook for legal costs.</i>"<p>The bill is essentially a judicial shortcut to make patent litigation riskier for non-practicing entities, precisely, non subsection (d) entities. Unfortunately, there is little judicial consensus (to the best of my limited knowledge) on what this means. ARM produces nothing tangible - it licenses designs. That makes ARM look like a non-practicing entity. Yet few would brand it as a patent troll.<p>Having losing plaintiffs pay is good. But it still leaves the defendant bearing the risk of adverse judgment. Even the non-practicing entity shortcut means hiring a lawyer. Perhaps, for patent suits, the plaintiff should have to, as part of filing the suit, dislose whether they or their beneficial owners' related entities have a history of filing patent suits deemed frivolous.</text></item></parent_chain><comment><author>belorn</author><text>Nothing in this bill prevents a inventor to sell his finished invention once to whoever want to commercialize it to a product. Nothing. He doesn't even need a patent to do this.<p>Say that the best battery chemist invents a way to make current lithium-ion battery packs 25% better. In a bidding war, the price would easy reach hundred of millions, because the practical effects of having better batteries are economic interesting for companies being restricted by ineffective batteries.<p>Regarding cancer research, I find it quite wrong that state funded research is being patented. Most serious medical research is being paid for NiH with the use of tax money. Society has already paid for all the step regarding the research and it due to get what it paid for. Research which has no bases on NiH funded research theories, and has no relation with any public funds what so ever is an exceptional case, and there is a lot of companies out there that produce derivative works from NiH produced research and gets a patent for it. derivative works that has been created from tax money should not allow someone to get a 20 years state enforced monopoly on it.</text></comment> | <story><title>Politicians want “loser pays” rule for patent trolls</title><url>http://arstechnica.com/tech-policy/2013/02/pissed-off-politicians-want-loser-pays-rule-for-patent-trolls/</url></story><parent_chain><item><author>bigiain</author><text>This is a problem that needs to be addressed carefully in my opinion.<p>Right now, it's a perfectly valid decision for an inventive/creative person(or team or company) to choose to spend their time inventing new things instead of commercialising "finished ideas", since the laws are (and have been for decades) written to allow an inventor to sell their patents.<p>If you're the world's best battery chemist, I'd rather you spent this year looking for an even better battery, rather than needing to be involved in making and selling last years "best battery" to earn any money from it. I don't want the top cancer researchers "wasting time" being personally involved in making drugs at commercial scale and doing deals with Walgreens, I want them doing cancer research - and having a patent/legal system that allows them to earn a living doing so (with the understanding that they've got a choice to license or sell their patents, and whether they get to share in the spectacular riches that some big-pharma company will make if they've just saved millions of lives will depend on how they chose to structure that transaction).<p>Somehow, we need to allow inventors to continue to be "NPEs", while stopping the obvious "patent troll" techniques of buying up uncommercialised patents with the only intent being to use them to litigate.<p>(And note, by "inventors" I'm including "companies set up to do inventing, either as their sole business or perhaps with a few staff or division who 'invent' as part of their regular work". I know of companies like <a href="http://www.novogen.com" rel="nofollow">http://www.novogen.com</a> and <a href="http://www.mesoblast.com" rel="nofollow">http://www.mesoblast.com</a> who are pretty much teams of biotech researchers intending to work out how to cure cancer, then sell the knowledge to other companies to commercialise it. I also know people at <a href="http://www.ecoult.com" rel="nofollow">http://www.ecoult.com</a> who didn't invent the technology they're commercialising, but have licensed the patents from the government research organisation that did invent/patent them.)</text></item><item><author>JumpCrisscross</author><text>So patents are only valid if held by their originator? That would make the IP non-transferable. In ARM's case, it would mean a takeover would invalidate its value.</text></item><item><author>nitrogen</author><text>One could argue that ARM's "practice" is producing designs. They are heavily involved in the creation and implementation of their patents, making them different from any troll that licenses "patents" they bought rather than "designs" they created.</text></item><item><author>JumpCrisscross</author><text>"<i>The bill would allow patent defendants to file a motion seeking to have a judge rule that the patent owner is a certain type of 'non-practicing entity'—although the bill doesn't use that term. If the motion is successful, the lawsuit can still proceed, but if the patent-holding company loses, it will be on the hook for legal costs.</i>"<p>The bill is essentially a judicial shortcut to make patent litigation riskier for non-practicing entities, precisely, non subsection (d) entities. Unfortunately, there is little judicial consensus (to the best of my limited knowledge) on what this means. ARM produces nothing tangible - it licenses designs. That makes ARM look like a non-practicing entity. Yet few would brand it as a patent troll.<p>Having losing plaintiffs pay is good. But it still leaves the defendant bearing the risk of adverse judgment. Even the non-practicing entity shortcut means hiring a lawyer. Perhaps, for patent suits, the plaintiff should have to, as part of filing the suit, dislose whether they or their beneficial owners' related entities have a history of filing patent suits deemed frivolous.</text></item></parent_chain><comment><author>lawnchair_larry</author><text>The problem there is that Intellectual Ventures would be allowed to remain, but they're the largest patent troll in the industry and a large part of the reason that this conversation is even taking place.</text></comment> |
11,768,134 | 11,767,435 | 1 | 2 | 11,766,073 | train | <story><title>E Ink announces a full color electrophoretic ePaper display</title><url>http://www.businesswire.com/news/home/20160524006209/en/Ink-Announces-Advanced-Color-ePaper-Breakthrough-Technology</url></story><parent_chain><item><author>dragonmum</author><text>Slashgear posted a video of the actual color e-ink panels in operation.<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=N2V9iuTW3sA" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=N2V9iuTW3sA</a></text></item></parent_chain><comment><author>aavotins</author><text>The flashing bit looks annoying, but I think that electronic picture frames that don&#x27;t suck are finally here! A poster that changes during the night(so you don&#x27;t see the flicker) and you wake up to see something new every day. I am really excited for this tech!</text></comment> | <story><title>E Ink announces a full color electrophoretic ePaper display</title><url>http://www.businesswire.com/news/home/20160524006209/en/Ink-Announces-Advanced-Color-ePaper-Breakthrough-Technology</url></story><parent_chain><item><author>dragonmum</author><text>Slashgear posted a video of the actual color e-ink panels in operation.<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=N2V9iuTW3sA" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=N2V9iuTW3sA</a></text></item></parent_chain><comment><author>MBCook</author><text>It&#x27;s unfortunate that it seems like the eInk flashing problem seems <i>so much worse</i> than on monochrome displays.<p>Once the image fully appears it looks great.</text></comment> |
20,382,981 | 20,383,161 | 1 | 2 | 20,382,126 | train | <story><title>Ten Years of Erlang</title><url>https://ferd.ca/ten-years-of-erlang.html</url></story><parent_chain></parent_chain><comment><author>tombert</author><text>I love Erlang, and am one of the very few people who (in the past) managed to find work doing it full time. The actor paradigm it provides is surprisingly simple and elegant to write an app, even on a single node, and of course making distributed apps is fairly straightforward as a result of it.<p>I have found that I like Lisp-Flavoured-Erlang (LFE) a bit more, since I <i>still</i> find the prolog-esque syntax a bit frustrating. I&#x27;ve been doing this stuff for like 6 years, and I still occasionally get tripped up on when to do a comma, semicolon, or period occasionally. While I&#x27;m not a huge fan of LISP-2 semantics, overall I find the syntax for LFE to be a lot more consistent than raw Erlang.<p>This isn&#x27;t to crap all over regular Erlang though; Erlang was the first language I had seen that fully embraced pattern-matching, and I find that kind of pattern to be incredibly elegant.<p>If someone reading this hasn&#x27;t tried out Erlang, do yourself a favor, download and install it, and build a simple TCP chat server. I can virtually guarantee you that it will be easier than anything you&#x27;ve built in C&#x2F;C++, and it&#x27;s incredibly satisfying to have something you built in a few hours have the ability to scale correctly.</text></comment> | <story><title>Ten Years of Erlang</title><url>https://ferd.ca/ten-years-of-erlang.html</url></story><parent_chain></parent_chain><comment><author>niftich</author><text>It&#x27;s a gem of an observation that newcomers to an environment often only make it to the first few rungs of the system complexity &#x2F; actualization ladder. Once you look, you see this everywhere, and not just in IT but with any sort of design exercise or institutional process, any complex system that&#x27;s full of Chesterton&#x27;s fences, and people will either evolve to debate their rationale from a position of experience, or be selected (or self-selected) away into fresh environments where the novelty and discovery-until-discouragement can begin again.<p>It also shows that the first few rungs matter a lot; this is the territory of easy answers, where following a few simple rules leads to rapid productivity, and there will always be people for whom that level is good enough, either through carefully weighed decisions from limited information, or ignorance and deferment of future problems and their solutions. You can&#x27;t solve everyone&#x27;s problems for them, but you can try to evangelize, and you can try to build your system in a way that best practices can be incrementally adopted from existing fumblings. Anticipate that most of it will stay mediocre.<p>History is littered with systems that, in hindsight, seem to have offered sensible solutions to complex problems, yet didn&#x27;t survive in the end. Much knowledge and wisdom is lost, and others independently discover it when trying to ascend an unrelated stack. Erlang&#x2F;OTP is truly the sort of environment that masquerades as a programming language yet asks questions at a much higher conceptual level: what do we want systems as a whole to look like if we have to maintain them indefinitely? Its architectural innovations have been copied elsewhere, where they rarely form part of a coherent stack, but at least expose people to the advantages of its model. This may also be the most viable source of adopters of Erlang at higher levels: people who&#x27;ve sought out similar model for its benefits, and could thrive with an offering that pays attention to these concerns throughout.</text></comment> |
32,131,989 | 32,131,983 | 1 | 2 | 32,131,153 | train | <story><title>Neural Network Loss Landscapes: What do we know? (2021)</title><url>https://damueller.com/#/blog-post/NNLLs</url></story><parent_chain></parent_chain><comment><author>MauranKilom</author><text>The &quot;wedge&quot; part under &quot;3. Mode Connectivity&quot; has at least one obvious component: Neural networks tend to be invariant to permuting nodes (together with their connections) within a layer. Simply put, it doesn&#x27;t matter in what order you number the K nodes of e.g. a fully connected layer, but that alone already means there are K! different solutions with exactly the same behavior. Equivalently, the loss landscape is symmetric to certain permutations of its dimensions.<p>This means that, at the very least, there are <i>many</i> global optima (well, unless all permutable weights end up with the same value, which is obviously not the case). The fact that different initializations&#x2F;early training steps can end up in different but equivalent optima follows directly from this symmetry. But whether all their basins are connected, or whether there are just multiple equivalent basins, is much less clear. The &quot;non-linear&quot; connection stuff does seem to imply that they are all in some (high-dimensional, non-linear) valley.<p>To be clear, this is just me looking at these results from the &quot;permutation&quot; perspective above, because it leads to a few obvious conclusions. But I am not qualified to judge which of these results are more or less profound.</text></comment> | <story><title>Neural Network Loss Landscapes: What do we know? (2021)</title><url>https://damueller.com/#/blog-post/NNLLs</url></story><parent_chain></parent_chain><comment><author>evolvingstuff</author><text>Here are some &quot;animated&quot; loss landscapes I made quite a long time ago:<p><a href="http:&#x2F;&#x2F;evolvingstuff.blogspot.com&#x2F;2011&#x2F;02&#x2F;animated-fractal-fitness-landscapes.html" rel="nofollow">http:&#x2F;&#x2F;evolvingstuff.blogspot.com&#x2F;2011&#x2F;02&#x2F;animated-fractal-f...</a><p>These are related to recurrent neural networks evolved to maximize fitness whilst wandering through a randomly generated maze and picking up food pellets (the advantage being to remember not to revisit where you have already been.)</text></comment> |
26,357,656 | 26,357,102 | 1 | 3 | 26,355,006 | train | <story><title>You can't parse [X]HTML with regex (2009)</title><url>https://stackoverflow.com/questions/1732348/regex-match-open-tags-except-xhtml-self-contained-tags/1732454#1732454</url></story><parent_chain><item><author>imedadel</author><text>I&#x27;ve seen many people complain about StackOverflow, but this is the best example I&#x27;ve ever encountered.<p>The question: How to match<p><pre><code> &lt;p&gt;
&lt;a href=&quot;foo&quot;&gt;
</code></pre>
The answers: <i>rants about how RegEx is not suitable for parsing entire HTML.</i><p>Only the 5th answer starts to actually answer the question.</text></item></parent_chain><comment><author>omginternets</author><text>In all fairness, he does provide hints as to <i>why</i> regex will not work (namely: HTML is not a regular grammar).<p>Sure, it&#x27;s somewhat obscured by the humorous rant, but it&#x27;s not that bad an answer, either.<p>More to the point: I&#x27;m not sure I want to suck the humor out of everything. I agree that SO has problems, but humor and poetry are worthwhile things in otherewise serious places. It&#x27;s all about quantity.</text></comment> | <story><title>You can't parse [X]HTML with regex (2009)</title><url>https://stackoverflow.com/questions/1732348/regex-match-open-tags-except-xhtml-self-contained-tags/1732454#1732454</url></story><parent_chain><item><author>imedadel</author><text>I&#x27;ve seen many people complain about StackOverflow, but this is the best example I&#x27;ve ever encountered.<p>The question: How to match<p><pre><code> &lt;p&gt;
&lt;a href=&quot;foo&quot;&gt;
</code></pre>
The answers: <i>rants about how RegEx is not suitable for parsing entire HTML.</i><p>Only the 5th answer starts to actually answer the question.</text></item></parent_chain><comment><author>EamonnMR</author><text>I find this type of answer infinitely more paletable than &quot;your question is answered here&quot; or &quot;comments are not for extended discussion, this conversation has been moved to chat&quot;</text></comment> |
6,692,359 | 6,692,291 | 1 | 2 | 6,692,075 | train | <story><title>Creditcard.js: a more usable credit card form</title><url>http://creditcardjs.com</url></story><parent_chain><item><author>maccman</author><text>Looks good, and I like the mistakes and solutions section.<p>However, it&#x27;s pretty much all covered by Stripe&#x27;s open source jQuery.payment, which is also agnostic to your payment gateway.<p><a href="https://github.com/stripe/jquery.payment" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;stripe&#x2F;jquery.payment</a><p>(Disclaimer - I built it.)</text></item></parent_chain><comment><author>niel</author><text>The presentation of Creditcard.js is great in terms of styling, and I&#x27;m sure the practical example goes a long way in selling something like this to non-developer decision makers. This is probably the market they are aiming for.<p>Personally, I would much rather use the MIT-licensed jQuery.payment by Stripe. I think $300 or even $149 is prohibitively expensive, and would prefer a script that is actively used and reviewed in public by many developers.<p>Thanks Alex!</text></comment> | <story><title>Creditcard.js: a more usable credit card form</title><url>http://creditcardjs.com</url></story><parent_chain><item><author>maccman</author><text>Looks good, and I like the mistakes and solutions section.<p>However, it&#x27;s pretty much all covered by Stripe&#x27;s open source jQuery.payment, which is also agnostic to your payment gateway.<p><a href="https://github.com/stripe/jquery.payment" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;stripe&#x2F;jquery.payment</a><p>(Disclaimer - I built it.)</text></item></parent_chain><comment><author>sgustard</author><text>And you have a similar UI widget at<p><a href="https://stripe.com/docs/checkout" rel="nofollow">https:&#x2F;&#x2F;stripe.com&#x2F;docs&#x2F;checkout</a></text></comment> |
37,758,791 | 37,758,505 | 1 | 3 | 37,755,276 | train | <story><title>John Carmack on AI</title><url>https://twitter.com/ID_AA_Carmack/status/1708905454544282083</url></story><parent_chain></parent_chain><comment><author>Dowwie</author><text>This isn&#x27;t his take on AI. It&#x27;s his opinion about the arguments presented in Mustafa&#x27;s fear mongering book about how dangerous AI is and what government should do about it.</text></comment> | <story><title>John Carmack on AI</title><url>https://twitter.com/ID_AA_Carmack/status/1708905454544282083</url></story><parent_chain></parent_chain><comment><author>gary_0</author><text><a href="https:&#x2F;&#x2F;nitter.net&#x2F;ID_AA_Carmack&#x2F;status&#x2F;1708905454544282083" rel="nofollow noreferrer">https:&#x2F;&#x2F;nitter.net&#x2F;ID_AA_Carmack&#x2F;status&#x2F;1708905454544282083</a> (full thread for non-Twitter-users)</text></comment> |
9,170,827 | 9,169,935 | 1 | 2 | 9,168,636 | train | <story><title>Pixie: A sweet Clojure-ish language</title><url>http://blog.goodstuff.im/pixie</url></story><parent_chain></parent_chain><comment><author>616c</author><text>I like the side-note.<p>&gt; As a side note, expressing configurations in Clojure S-expressions makes a ton of sense. Clojure S-expressions provide a superset of JSON and Clojure&#x27;s eval allows you to define a function to compute certain values. It&#x27;s an escape hatch so that you&#x27;re configuration files don&#x27;t need to become accidentally Turing complete. The Turing complete nature of your configuration files is well defined as Clojure.<p>I had posted a while back wondering why more formats do not just derive from sexp or SXML (yes, say that out loud in the office). As I think some Lispers (I am even below beginner) cannot help but notice that if sexpr are coincidentally (I am sure it can be done without, but still, I am not sure if McCarthy and company just started with sexp or choose it specifically and held their ground beyond it was their choice) core to the lisp&#x27;s homoiconic power-features, why more people do not just want sexp as the core data definiton, keep the data and program as close as possible, and just macro the data back, tossing back and forth between code and data as the division is limited.<p>Anyway, I like that far more intelligent people than me not only like this idea, but are encouraging it and pushing it forward.<p>(Yes, flame away. I know some people love Lisp and hate, I just thought it is an interesting premise; I am ready for you to throw shoes at me, HN.)</text></comment> | <story><title>Pixie: A sweet Clojure-ish language</title><url>http://blog.goodstuff.im/pixie</url></story><parent_chain></parent_chain><comment><author>threeseed</author><text>This seems like bit of a short sighted move not that I disagree with it.<p>Project Jigsaw which will be a big part of Java 9 aims to make the JVM more modular which will reduce the memory footprint substantially. Personally I would like to see a version of Clojure that targets this JVM specifically and abandons backwards compatibility.<p>Leaving the JVM means you abandon the decade of libraries many of which you simply can&#x27;t get on any other platform (in particular for the enterprise). Given that Clojure has been gaining a lot of ground in these large companies it seems like a missed opportunity.</text></comment> |
29,431,277 | 29,430,783 | 1 | 2 | 29,429,964 | train | <story><title>Lego has designed a set that can't be taken apart</title><url>https://brickset.com/article/67650/lego-has-designed-a-set-that-can-t-be-taken-apart</url></story><parent_chain><item><author>wirthjason</author><text>I saw a term in the comments: AFOL. I had to look it up: Adult Fan Of Legos.<p>I loved legos as a kid and would spend hours building stuff. Now the kits seem more like models to be assembled and put on display and not touched rather than “a paint brush of blocks” where I can use my imagination. It lost my interest. My attention is now on software where I feel I can build anything. I liken it to my lego experience as a child.<p>I don’t necessarily think there’s a right or wrong thing here. It’s interesting to note how our mind changes as we age and grow older. The ”do anything” mentality get displaced with something else. This would make for an interesting PhD topic. :)<p>I found another quote from a related article that captured this feeling.<p><pre><code> “It’s like a blast to the past, straight to our childhoods,” said Deason, 40, who lives in Connellsville, Pa. “It took me by surprise, but it makes sense: Life is so structured. But with Lego, you can do anything.”
Deason has a few million Lego pieces, which she organizes by type and color. The Star Wars and Architecture sets, she says, are the most popular among adults, who almost always look for the instruction manuals.
“The younger kids come in and it’s all about their imaginations — playing pretend, building zombie towns,” she said. “But at some point that gets lost. The adults seem to value the final finished project. That’s where they get their satisfaction.”</code></pre></text></item></parent_chain><comment><author>dec0dedab0de</author><text>They still have the original sets that come with guides to build many things out of the same set of bricks, and a box to put them in. These are the best ones to get kids just starting out.<p>Plus the lego stores have pieces sorted in buckets like a candy shop, you buy a container and fill it up with whatever you want. I&#x27;ve never used it, but the website lets you choose from 1400 different bricks <a href="https:&#x2F;&#x2F;www.lego.com&#x2F;en-us&#x2F;page&#x2F;static&#x2F;pick-a-brick" rel="nofollow">https:&#x2F;&#x2F;www.lego.com&#x2F;en-us&#x2F;page&#x2F;static&#x2F;pick-a-brick</a><p>The Sets will sometimes have a unique piece or two, but outside of the mini figs it is way rarer than you might think. And as others pointed out if it&#x27;s unique now it doesn&#x27;t mean they won&#x27;t find a way to reuse it later.</text></comment> | <story><title>Lego has designed a set that can't be taken apart</title><url>https://brickset.com/article/67650/lego-has-designed-a-set-that-can-t-be-taken-apart</url></story><parent_chain><item><author>wirthjason</author><text>I saw a term in the comments: AFOL. I had to look it up: Adult Fan Of Legos.<p>I loved legos as a kid and would spend hours building stuff. Now the kits seem more like models to be assembled and put on display and not touched rather than “a paint brush of blocks” where I can use my imagination. It lost my interest. My attention is now on software where I feel I can build anything. I liken it to my lego experience as a child.<p>I don’t necessarily think there’s a right or wrong thing here. It’s interesting to note how our mind changes as we age and grow older. The ”do anything” mentality get displaced with something else. This would make for an interesting PhD topic. :)<p>I found another quote from a related article that captured this feeling.<p><pre><code> “It’s like a blast to the past, straight to our childhoods,” said Deason, 40, who lives in Connellsville, Pa. “It took me by surprise, but it makes sense: Life is so structured. But with Lego, you can do anything.”
Deason has a few million Lego pieces, which she organizes by type and color. The Star Wars and Architecture sets, she says, are the most popular among adults, who almost always look for the instruction manuals.
“The younger kids come in and it’s all about their imaginations — playing pretend, building zombie towns,” she said. “But at some point that gets lost. The adults seem to value the final finished project. That’s where they get their satisfaction.”</code></pre></text></item></parent_chain><comment><author>thesuitonym</author><text>&gt;Now the kits seem more like models to be assembled and put on display and not touched rather than “a paint brush of blocks” where I can use my imagination.<p>This isn&#x27;t true at all. You can still buy a box full of bricks. You can even go online and purchase single bricks if you have a specific build in mind. Even the model kits are still just a box full of bricks--Lego abhors creating unique blocks unless they can be used in other sets.<p>The reason a lot of adults gravitate toward the finished kits is the same reason adults stop picking up cool sticks outside: We just lose our imagination.</text></comment> |
8,524,941 | 8,525,043 | 1 | 3 | 8,524,256 | train | <story><title>Mobile is Eating the World</title><url>http://a16z.com/2014/10/28/mobile-is-eating-the-world/</url></story><parent_chain><item><author>marknutter</author><text>&gt; That said, there might be a convergence where mobile devices learn to run desktop software, and can be docked to a mouse&#x2F;keyboard&#x2F;monitor.<p>I never understand this prediction. That&#x27;s a bit like saying I don&#x27;t need a car because I could just dock my bicycle into some sort of enclosure with four wheels. Tablets, smartphones, and laptops&#x2F;desktops were all built for different purposes and cannot be full replacements for each other, just like a bicycle can&#x27;t fully replace a car without some serious sacrifices.</text></item><item><author>pfitzsimmons</author><text>If you look at the biomechanics, it does seem like a keyboard + mouse + &gt;=20&quot; screen is the optimal setup for doing actual work. A keyboard is simply the most efficient way to get information into a computer (the exception is that some graphics editors work might work better with a multitouch screen, it will be interesting to see if someone builds a touch-first photoshop killer). That said, there might be a convergence where mobile devices learn to run desktop software, and can be docked to a mouse&#x2F;keyboard&#x2F;monitor. But we are still a long ways from that point, and there is no great incentive to build office suites for mobile devices that are efficient for power&#x2F;work users.<p>Mobile is great for 1) consuming content 2) interacting with your extended environment when you are not grounded to a computer (summoning an Uber, paying with an app, etc.) The money in content consumption will go to either the content creators or the digital sharecroppers (Facebook).<p>So the question is, are there large untapped areas where a phone could be used to interact with ones environment? What kind of day-to-day things could be enhanced with internet connected software?</text></item><item><author>cageface</author><text><i>There is no point in drawing a distinction between the future of technology and the future of mobile.</i><p>I find Evans&#x27; analysis of mobile a bit hyperbolic. Yes the growth of mobile is explosive and, in some cases, it&#x27;s displacing older technology. But for a lot of use cases small touch screen devices are simply inadequate. It&#x27;s probably true that a lot of people that used to use desktop or laptop computers just to check email and Facebook have shifted that activity to their phones and tablets. But its equally true that these devices are still really only good for quick, informal communication and browsing. Despite the best efforts of Apple and Samsung to persuade us otherwise, tablets are lousy for getting real work done.<p>So we find ourselves in the ironic situation of a domain that is experiencing almost unprecedented growth but in which almost nobody is making money except Facebook and the vendors of what are essentially gimmicky slot machine games. My take on this is that the market for richer desktop&#x2F;laptop software isn&#x27;t going anywhere soon. People that need to edit complex spreadsheets, compose scores for films, analyze genomes, and render 3d effects need real computers. As a developer this kind of customer is in many ways a better customer to serve than a teen snapping selfies on a phone.</text></item></parent_chain><comment><author>skolor</author><text>Even if I had a full scale performance in a cell phone with great docking capabilities, I probably would rather have a separate desktop computer for working. Just being able to compartmentalize &quot;social stuff&quot; on my phone, and &quot;work stuff&quot; on a desktop tends to vastly improve my performance.</text></comment> | <story><title>Mobile is Eating the World</title><url>http://a16z.com/2014/10/28/mobile-is-eating-the-world/</url></story><parent_chain><item><author>marknutter</author><text>&gt; That said, there might be a convergence where mobile devices learn to run desktop software, and can be docked to a mouse&#x2F;keyboard&#x2F;monitor.<p>I never understand this prediction. That&#x27;s a bit like saying I don&#x27;t need a car because I could just dock my bicycle into some sort of enclosure with four wheels. Tablets, smartphones, and laptops&#x2F;desktops were all built for different purposes and cannot be full replacements for each other, just like a bicycle can&#x27;t fully replace a car without some serious sacrifices.</text></item><item><author>pfitzsimmons</author><text>If you look at the biomechanics, it does seem like a keyboard + mouse + &gt;=20&quot; screen is the optimal setup for doing actual work. A keyboard is simply the most efficient way to get information into a computer (the exception is that some graphics editors work might work better with a multitouch screen, it will be interesting to see if someone builds a touch-first photoshop killer). That said, there might be a convergence where mobile devices learn to run desktop software, and can be docked to a mouse&#x2F;keyboard&#x2F;monitor. But we are still a long ways from that point, and there is no great incentive to build office suites for mobile devices that are efficient for power&#x2F;work users.<p>Mobile is great for 1) consuming content 2) interacting with your extended environment when you are not grounded to a computer (summoning an Uber, paying with an app, etc.) The money in content consumption will go to either the content creators or the digital sharecroppers (Facebook).<p>So the question is, are there large untapped areas where a phone could be used to interact with ones environment? What kind of day-to-day things could be enhanced with internet connected software?</text></item><item><author>cageface</author><text><i>There is no point in drawing a distinction between the future of technology and the future of mobile.</i><p>I find Evans&#x27; analysis of mobile a bit hyperbolic. Yes the growth of mobile is explosive and, in some cases, it&#x27;s displacing older technology. But for a lot of use cases small touch screen devices are simply inadequate. It&#x27;s probably true that a lot of people that used to use desktop or laptop computers just to check email and Facebook have shifted that activity to their phones and tablets. But its equally true that these devices are still really only good for quick, informal communication and browsing. Despite the best efforts of Apple and Samsung to persuade us otherwise, tablets are lousy for getting real work done.<p>So we find ourselves in the ironic situation of a domain that is experiencing almost unprecedented growth but in which almost nobody is making money except Facebook and the vendors of what are essentially gimmicky slot machine games. My take on this is that the market for richer desktop&#x2F;laptop software isn&#x27;t going anywhere soon. People that need to edit complex spreadsheets, compose scores for films, analyze genomes, and render 3d effects need real computers. As a developer this kind of customer is in many ways a better customer to serve than a teen snapping selfies on a phone.</text></item></parent_chain><comment><author>InclinedPlane</author><text>Not the same thing.<p>In 5 or 10 years dockable tablets are going to be every-goddamn-where, especially in business. It just makes sense, and is too all around practical. And for most computer uses, even &quot;intensive&quot; ones, it&#x27;s perfect. You get portability plus productivity in the docked configuration plus huge economic benefits. Tablets are mostly just screens, batteries, and a handful of chips, all of which are super amenable to economies of scale in manufacture. Tablets are going to be cheaper than dirt eventually, and because a tablet can be a self-contained computer it&#x27;ll tend to be the default computing choice. The biggest thing missing today is primarily good software.</text></comment> |
5,863,246 | 5,863,370 | 1 | 3 | 5,862,676 | train | <story><title>Court found NSA surveillance unconstitutional in 2011</title><url>http://blog.rongarret.info/2013/06/court-finds-nsa-surveillance.html</url><text></text></story><parent_chain></parent_chain><comment><author>chris_mahan</author><text>A quote by Joseph Goebbels:<p>&quot;If you tell a lie big enough and keep repeating it, people will eventually come to believe it. The lie can be maintained only for such time as the State can shield the people from the political, economic and&#x2F;or military consequences of the lie. It thus becomes vitally important for the State to use all of its powers to repress dissent, for the truth is the mortal enemy of the lie, and thus by extension, the truth is the greatest enemy of the State.&quot;<p>Who was Joseph Goebbels? Per Wikipedia: Paul Joseph Goebbels (29 October 1897 – 1 May 1945) was a German politician and Reich Minister of Propaganda in Nazi Germany from 1933 to 1945. (see <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Joseph_Goebbels" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Joseph_Goebbels</a>)</text></comment> | <story><title>Court found NSA surveillance unconstitutional in 2011</title><url>http://blog.rongarret.info/2013/06/court-finds-nsa-surveillance.html</url><text></text></story><parent_chain></parent_chain><comment><author>ck2</author><text>The saddest part is not a single candidate from either major party is going to reject this a couple years from now.<p>They might even take it a step further with drones.<p><i>you have to know everything in order to be completely safe</i><p><pre><code> - Erich Mielke, head of the Stasi, East Germany</code></pre></text></comment> |
40,519,431 | 40,517,880 | 1 | 2 | 40,516,437 | train | <story><title>Amazon Cloud Traffic Is Suffocating Fedora's Mirrors</title><url>https://www.phoronix.com/news/AWS-Cloud-Breaks-Fedora-Mirrors</url></story><parent_chain><item><author>steelframe</author><text>Something irks me about volunteers spending real money to support all the OSS freeloading businesses. I&#x27;m talking about companies with a market cap in the $Billions. Almost none of them can be bothered to kick back even a modicum of financial support to the authors of the software that runs their business, and to add insult to injury, they in fact soak the members of community who distribute the binaries for their bandwidth.</text></item></parent_chain><comment><author>quaintdev</author><text>I wonder why Amazon did not create their own mirror. They would sync with Fedora mirrors once. All aws traffic can then go to their own mirrors.<p>Isn&#x27;t that sensible thing to do?</text></comment> | <story><title>Amazon Cloud Traffic Is Suffocating Fedora's Mirrors</title><url>https://www.phoronix.com/news/AWS-Cloud-Breaks-Fedora-Mirrors</url></story><parent_chain><item><author>steelframe</author><text>Something irks me about volunteers spending real money to support all the OSS freeloading businesses. I&#x27;m talking about companies with a market cap in the $Billions. Almost none of them can be bothered to kick back even a modicum of financial support to the authors of the software that runs their business, and to add insult to injury, they in fact soak the members of community who distribute the binaries for their bandwidth.</text></item></parent_chain><comment><author>BSDobelix</author><text>How about just support community distributions? ...and no, Fedora is non of them.<p>Just stop support brand&#x27;s and corporation&#x27;s if you don&#x27;t get paid?</text></comment> |
30,783,623 | 30,783,560 | 1 | 2 | 30,782,735 | train | <story><title>Spotify and Google Announce User Choice Billing</title><url>https://newsroom.spotify.com/2022-03-23/spotify-and-google-announce-user-choice-billing/</url></story><parent_chain><item><author>olau</author><text>I know that a consumptionist attitude is popular these days, but as a user of something like Spotify I would surely prefer as much as possible of my monetary contribution ending up with Spotify and the musicians instead of in the hands of a company controlling the market place.<p>To the people who think the exorbitant fees are okay: Imagine a world with no cash. Now the payment card companies decide they want 30% of all transactions. You think that would be reasonable?<p>The only reason the phone OS companies get away with it is lack of real competition. The regulatory environment is very slow in catching up - it&#x27;s not more than a few years ago that the EU finally hit the payment card companies.<p>And yes, the EU also has something to say when it comes to dark subscription cancelling patterns.</text></item><item><author>nerdjon</author><text>As a user, why would I choose this?<p>I only see a benefit to developers for this, but from a user prospective going with another system is a downgrade.<p>Assuming google works like Apple (correct me if I am wrong), disabling a subscription should be able to happen from a central location with a click or 2.<p>If I instead go with the billing through a company not only do they now have my credit card information, but I have to go through them to cancel. Meaning they can send me through screen after screen trying to convince me to stay (dark pattern) or even worse forcing me to call to cancel.<p>As a user, if you want to offer this fine. But as long as the ability to subscribe through Google or Apple is not removed I will be fine. But if this starts a trend of more and more apps having their own billing that then uses dark patterns to keep me subscribed... I will just end up spending less money on subscriptions than I currently do, and I have quite a few subscriptions.</text></item></parent_chain><comment><author>Wowfunhappy</author><text>I don&#x27;t think Spotify is the best example here, since I&#x27;m not particularly convinced that more cash going to them would end up in the hands of musicians.<p>But certainly, if I subscribe to The Economist I want as much of my money as possible to go to the journalists who actually write the content.</text></comment> | <story><title>Spotify and Google Announce User Choice Billing</title><url>https://newsroom.spotify.com/2022-03-23/spotify-and-google-announce-user-choice-billing/</url></story><parent_chain><item><author>olau</author><text>I know that a consumptionist attitude is popular these days, but as a user of something like Spotify I would surely prefer as much as possible of my monetary contribution ending up with Spotify and the musicians instead of in the hands of a company controlling the market place.<p>To the people who think the exorbitant fees are okay: Imagine a world with no cash. Now the payment card companies decide they want 30% of all transactions. You think that would be reasonable?<p>The only reason the phone OS companies get away with it is lack of real competition. The regulatory environment is very slow in catching up - it&#x27;s not more than a few years ago that the EU finally hit the payment card companies.<p>And yes, the EU also has something to say when it comes to dark subscription cancelling patterns.</text></item><item><author>nerdjon</author><text>As a user, why would I choose this?<p>I only see a benefit to developers for this, but from a user prospective going with another system is a downgrade.<p>Assuming google works like Apple (correct me if I am wrong), disabling a subscription should be able to happen from a central location with a click or 2.<p>If I instead go with the billing through a company not only do they now have my credit card information, but I have to go through them to cancel. Meaning they can send me through screen after screen trying to convince me to stay (dark pattern) or even worse forcing me to call to cancel.<p>As a user, if you want to offer this fine. But as long as the ability to subscribe through Google or Apple is not removed I will be fine. But if this starts a trend of more and more apps having their own billing that then uses dark patterns to keep me subscribed... I will just end up spending less money on subscriptions than I currently do, and I have quite a few subscriptions.</text></item></parent_chain><comment><author>Shank</author><text>&gt; To the people who think the exorbitant fees are okay: Imagine a world with no cash. Now the payment card companies decide they want 30% of all transactions. You think that would be reasonable?<p>Just so that we&#x27;re talking on equal terms here, card processors and networks solve a massive amount of problems that existed with cash. Pre-card, many stores setup credit accounts with individuals, had book keeping practices to deal with, and had to chase down credit lines they themselves offered. Even with debit cards, card networks facilitate the ability to automatically move money between parties and give customers the ability to dispute&#x2F;chargeback fraudulent transactions easily. If you physically hand a merchant cash, you can&#x27;t claw that back without a legal process, whereas you&#x27;re afforded protections by the card network.<p>But the 30% cut is completely different from card processors. Of the 30% to Google Play or to Apple, a small fraction (2.9%ish) is actually the card overhead. The rest is split between pure profit, infrastructure, and whatever else gets tacked on.<p>Cards definitely offer important things to facilitate transactions that are objectively better than a pure cash world for most people. But it&#x27;s important to call out crazy cash grabs like 30%, which is unheard of even in the payment network world.</text></comment> |
10,433,907 | 10,433,654 | 1 | 3 | 10,433,288 | train | <story><title>Indonesia's palm oil fires emitted more greenhouse gases in a day than the U.S.</title><url>http://qz.com/528160/indonesias-palm-oil-fires-are-emitting-more-greenhouse-gases-every-day-than-the-entire-us/</url></story><parent_chain></parent_chain><comment><author>IkmoIkmo</author><text>Sliiightly misleading headline, although not incorrect in some ways.<p>For about a quarter of the year there are virtually no fires, another quarter (we&#x27;re there now), there are a lot. Further, in most years the fires are much fewer than they are now, and we&#x27;re now in a record year.<p>So the headline is true, but only for the worst part of a record breaking year. You can&#x27;t extrapolate it. In general, say per year or per decade, the headline is false, and CO2 emissions are a topic that is spoken about in the context of such timeframes, not &#x27;who emitted the most in a 30 day period in one particular year&#x27;.<p>Further, the comparison itself is misleading as the CO2 figures for the US (and all other countries, for that matter), only count burning fossil fuel (and producing cement). Not capturing emissions when fracking? Not counted. Millions of cows farting all over the place? Not counted. Agriculture? Not counted etc. That&#x27;s why if you compare Indonesia to the US, Indonesians emit about 6 times less CO2 per capita. That&#x27;s why it&#x27;s a bit of a weird comparison. You&#x27;re comparing one country&#x27;s emissions within limited parameters, to another country&#x27;s emissions from phenomena that fall outside of those parameters.<p>Anyway obviously it&#x27;s a big concern nonetheless and a better comparison would probably be that this single industry approximately doubles Indonesia&#x27;s fossil fuel burning CO2 output on average every year. That&#x27;s quite excessive for just one industry (last I checked ~8% of exports, with exports at $200b on a GDP of $870b) and it doesn&#x27;t have to be that way, palm oil can be grown (slightly more expensively) by simply clearing a forest rather than burning it and all the peat underneath. (the peat is really the issue, forest burning itself is often in large part compensated by regrowth)</text></comment> | <story><title>Indonesia's palm oil fires emitted more greenhouse gases in a day than the U.S.</title><url>http://qz.com/528160/indonesias-palm-oil-fires-are-emitting-more-greenhouse-gases-every-day-than-the-entire-us/</url></story><parent_chain></parent_chain><comment><author>siilats</author><text>The article title is misleading though. It was for 1 day that they emitted more. So overall about 1% of us emissions if you average for the year or 100 times less.</text></comment> |
26,617,959 | 26,616,496 | 1 | 2 | 26,612,894 | train | <story><title>Developer tools can be magic but instead collect dust</title><url>http://www.pathsensitive.com/2021/03/developer-tools-can-be-magic-instead.html</url></story><parent_chain><item><author>bcrosby95</author><text>Some companies will care. Some won&#x27;t. I mentioned something like this to mine and they upgraded the build server in response.<p>For Jetbrains products, if you enjoy them you can use your personal license commercially. Your company just can&#x27;t pay for it or reimburse you for it. This is the route I go because I use their products for personal projects too. For me it&#x27;s a no brainer at $150&#x2F;year for their all-products option (...for the 3rd year, 1st is $250, 2nd is $200).</text></item><item><author>MattGaiser</author><text>&gt; Programmers do not like to pay for their tooling.<p>Because it is too much work to convince the company that spending $500 on JRebel to have me not go on Hacker News for 5 (and it turns into 15) minutes while the thing compiles (my last company). I also have no real stake in whether the product ships in one month or two so I am not paying for it myself.<p>To pay for tooling, productivity needs to be a priority. I have never worked anywhere where productivity was discussed.</text></item><item><author>hypermachine</author><text>Because in 2021 developer tools are fundamentally not profitable. Jetbrains is the exception, not the norm. Developer tools are loss leaders for large corporation to acquire developer goodwill and mindshare. Previously we sold developer tools&#x2F;PaaS. Programmers do not like to pay for their tooling. You have to sell to management, and when your target is management, then the metrics are completely different from what developers want.<p>This is why no-code and low code are so much more successful than developers tooling startups in terms of revenue and profitability. The people using are the same people who are running the business. The value proposition is clear. &quot;Better developer experience&quot; alone is not sufficient for selling to enterprise. And programmer productivity cannot be quantified in lines of code written. This is hard point to explain and get across on HN because this forum is inherently dismissive of the value of RPA and RAD software.</text></item></parent_chain><comment><author>hyperpallium2</author><text>I&#x27;m toying with the idea of selling developer tools <i>only</i> as personal licenses that can be used commercially. Like a driver&#x27;s &quot;license&quot;, companies must hire &quot;licensed&quot; developers to drive the software. (also licensed plumbers, electricians, accountants, surgeons etc - though true all are skill&#x2F;knowledge credentials, not simply purchasable; so include an exam).<p>Companies need to hire and pay more for &quot;licensed&quot; developers.<p>It gives power to developers - and then I don&#x27;t have to sell to managers or deal with uninterested clerks.</text></comment> | <story><title>Developer tools can be magic but instead collect dust</title><url>http://www.pathsensitive.com/2021/03/developer-tools-can-be-magic-instead.html</url></story><parent_chain><item><author>bcrosby95</author><text>Some companies will care. Some won&#x27;t. I mentioned something like this to mine and they upgraded the build server in response.<p>For Jetbrains products, if you enjoy them you can use your personal license commercially. Your company just can&#x27;t pay for it or reimburse you for it. This is the route I go because I use their products for personal projects too. For me it&#x27;s a no brainer at $150&#x2F;year for their all-products option (...for the 3rd year, 1st is $250, 2nd is $200).</text></item><item><author>MattGaiser</author><text>&gt; Programmers do not like to pay for their tooling.<p>Because it is too much work to convince the company that spending $500 on JRebel to have me not go on Hacker News for 5 (and it turns into 15) minutes while the thing compiles (my last company). I also have no real stake in whether the product ships in one month or two so I am not paying for it myself.<p>To pay for tooling, productivity needs to be a priority. I have never worked anywhere where productivity was discussed.</text></item><item><author>hypermachine</author><text>Because in 2021 developer tools are fundamentally not profitable. Jetbrains is the exception, not the norm. Developer tools are loss leaders for large corporation to acquire developer goodwill and mindshare. Previously we sold developer tools&#x2F;PaaS. Programmers do not like to pay for their tooling. You have to sell to management, and when your target is management, then the metrics are completely different from what developers want.<p>This is why no-code and low code are so much more successful than developers tooling startups in terms of revenue and profitability. The people using are the same people who are running the business. The value proposition is clear. &quot;Better developer experience&quot; alone is not sufficient for selling to enterprise. And programmer productivity cannot be quantified in lines of code written. This is hard point to explain and get across on HN because this forum is inherently dismissive of the value of RPA and RAD software.</text></item></parent_chain><comment><author>Stratoscope</author><text>Same here. It costs me less than fifty cents a day to be able to use all the JetBrains IDEs and developer tools and get all their updates, both for my personal projects and for work.<p>I can only speak for myself, but to me, &quot;no brainer&quot; is an understatement.</text></comment> |
10,149,387 | 10,149,351 | 1 | 3 | 10,149,179 | train | <story><title>How a bug in VS2015 exposed my source code on GitHub and cost me $6,500</title><url>https://www.humankode.com/security/how-a-bug-in-visual-studio-2015-exposed-my-source-code-on-github-and-cost-me-6500-in-a-few-hours</url></story><parent_chain><item><author>Analemma_</author><text>This is becoming such a common story that I&#x27;m starting to think it&#x27;s a little irresponsible of both Amazon and GitHub to not react better to it. Clearly Amazon is capable of detecting when this happens as evidenced by their rapid response; when they see AWS keys published to GitHub, they should block the account, or at least prevent it from spinning up any new instances. They can then contact the owner over e-mail to follow up.<p>Same thing with GitHub. When they see an AWS key, they need to block that push and send back a message saying &quot;If you&#x27;re really, really, REALLY sure you want to do this, add .allowawskey at the root of your commit and push again&quot;. There&#x27;s no excuse for letting people shoot themselves in the foot like this over and over.<p>(Edited for typo)</text></item></parent_chain><comment><author>Alupis</author><text>Is it really on the web service companies to make sure you (the developer) don&#x27;t do anything stupid?<p>The article author could have avoided a lot of headache if he simply checked the repo before walking away. Red flags should have gone up as soon as he received the first weird Amazon messages, but he still didn&#x27;t think to check his own work.<p>The author calls this a &quot;Data Breach&quot; but in reality it was a &quot;Data Leak&quot;.</text></comment> | <story><title>How a bug in VS2015 exposed my source code on GitHub and cost me $6,500</title><url>https://www.humankode.com/security/how-a-bug-in-visual-studio-2015-exposed-my-source-code-on-github-and-cost-me-6500-in-a-few-hours</url></story><parent_chain><item><author>Analemma_</author><text>This is becoming such a common story that I&#x27;m starting to think it&#x27;s a little irresponsible of both Amazon and GitHub to not react better to it. Clearly Amazon is capable of detecting when this happens as evidenced by their rapid response; when they see AWS keys published to GitHub, they should block the account, or at least prevent it from spinning up any new instances. They can then contact the owner over e-mail to follow up.<p>Same thing with GitHub. When they see an AWS key, they need to block that push and send back a message saying &quot;If you&#x27;re really, really, REALLY sure you want to do this, add .allowawskey at the root of your commit and push again&quot;. There&#x27;s no excuse for letting people shoot themselves in the foot like this over and over.<p>(Edited for typo)</text></item></parent_chain><comment><author>kylec</author><text>This is a really good point. There was another post recently linking to a search for id_rsa files (SSH private keys) on GitHub. Instead of allowing people to publish sensitive things like that accidentally, GitHub really should require an extra confirmation.</text></comment> |
36,157,179 | 36,155,546 | 1 | 2 | 36,155,267 | train | <story><title>OpenAI Employee: GPT-4 has been static since March</title><url>https://twitter.com/OfficialLoganK/status/1663934947931897857</url></story><parent_chain><item><author>furyofantares</author><text>I think we don&#x27;t notice our expectations have gone up, and we don&#x27;t notice that we remember the hits and then expect all hits.<p>We didn&#x27;t notice the misses at first, because it&#x27;s what we expected to begin with, and we very strongly noticed the hits because they were unexpected. Now we notice the misses and expect the hits.</text></item></parent_chain><comment><author>jstarfish</author><text>No, this is peak corporate gaslighting, <i>Open</i>AI being the paragon of integrity and all. Nobody should trust a goddamn thing that comes out of their mouths-- or their product.<p>It&#x27;s no coincidence the flat-fee service is visibly crippled, while <i>per-request API users</i> are not reporting any difference. (edited)<p>Ignoring everyone here, look at the other &quot;hacker&quot; groups-- like the jailbreaking community. They have a lot to say about recent changes that coincide with their hacks not working. All of a sudden, with OpenAI supposedly changing nothing, technical bypasses just stopped working. OpenAI changed nothing, so this <i>must</i> be deus ex machina.<p>I&#x27;m not even jailbreaking it but the results I get for simple code requests through the web UI have become unusable garbage. It puts less effort into responses than an unpaid-and-overworked intern. Others here report the same. The current &quot;iteration&quot; seems hellbent on terminating conversations as quickly as possible once they stray from the explicit scope of the original topic and is almost as hostile to fixing its own errors as it is to endorsing eugenics, whereas in the beginning it would humor every idle thought I threw at it in long conversations. You can literally see this reflected in the logs they forced retention of. It&#x27;s acting like a customer support rep desperately trying to end a call before it exceeds a call-time quota.<p>This particular current workflow seems like it lends itself to better organization of training data-- conversations are what the title says they&#x27;re about. It also seems like it lends itself to anti-jailbreaking because pretexting it with irrelevant information forces a change of scope-- and a summary termination.<p>But <i>OpenAI says</i> they changed nothing, so rather than <i>one guy lying</i> without consequence, a community of professionals using and abusing the tool must <i>all</i> be victims of rhetorical fallacy? Nobody&#x27;s qualified to reverse-engineer corporate bullshit anymore without being infantilized...<p>(Liars running a black box-- what could possibly go wrong? We need regulation!)</text></comment> | <story><title>OpenAI Employee: GPT-4 has been static since March</title><url>https://twitter.com/OfficialLoganK/status/1663934947931897857</url></story><parent_chain><item><author>furyofantares</author><text>I think we don&#x27;t notice our expectations have gone up, and we don&#x27;t notice that we remember the hits and then expect all hits.<p>We didn&#x27;t notice the misses at first, because it&#x27;s what we expected to begin with, and we very strongly noticed the hits because they were unexpected. Now we notice the misses and expect the hits.</text></item></parent_chain><comment><author>huevosabio</author><text>I think this is the right way to look at it: we are very quick at updating expectations.<p>The first flight is magic, the nth one is a chore.</text></comment> |
29,224,161 | 29,223,188 | 1 | 3 | 29,219,042 | train | <story><title>California plans to turn the screws on NIMBY cities</title><url>https://fullstackeconomics.com/how-california-plans-to-turn-the-screws-on-nimby-cities/</url></story><parent_chain><item><author>rank0</author><text>One thing I don’t understand about the housing debate is why any specific area needs to be “affordable”<p>If I can’t afford to live in an area, it seems to me the solution is to live somewhere else.<p>Maybe I’m missing something. I’m open to new ideas here but I really don’t get it.</text></item></parent_chain><comment><author>ZoomerCretin</author><text>Because these restrictions are a net-negative on the entire economy of the United States. If no metro areas blocked housing between 1964 and 2009, GDP would be 50% higher than it is today. (<a href="https:&#x2F;&#x2F;www.nber.org&#x2F;papers&#x2F;w21154?utm_campaign=ntw&amp;utm_medium=email&amp;utm_source=ntw" rel="nofollow">https:&#x2F;&#x2F;www.nber.org&#x2F;papers&#x2F;w21154?utm_campaign=ntw&amp;utm_medi...</a>)<p>&quot;The authors estimate that if New York, San Francisco, and San Jose had housing regulations—rules about where you can build, how tall you can build, how much parking you need, and so on—that didn’t protect cute houses and instead were equivalent to the median US city in the period between 1964 and 2009, the US economy would be 9.5% bigger right now, or grow 0.21% more annually. That’s would be a big deal for wages, for the public debt, and for prosperity in general.&quot; (<a href="https:&#x2F;&#x2F;qz.com&#x2F;402763&#x2F;new-york-and-san-fransiscos-insane-housing-prices-are-dragging-down-us-growth&#x2F;" rel="nofollow">https:&#x2F;&#x2F;qz.com&#x2F;402763&#x2F;new-york-and-san-fransiscos-insane-hou...</a>)<p>The average worker&#x27;s income would increase by $9,000 per year if the Bay Area and New York City relaxed their zoning laws. (<a href="https:&#x2F;&#x2F;www.theregreview.org&#x2F;2018&#x2F;06&#x2F;14&#x2F;somogyi-zoning-codes-gdp&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.theregreview.org&#x2F;2018&#x2F;06&#x2F;14&#x2F;somogyi-zoning-codes...</a>)</text></comment> | <story><title>California plans to turn the screws on NIMBY cities</title><url>https://fullstackeconomics.com/how-california-plans-to-turn-the-screws-on-nimby-cities/</url></story><parent_chain><item><author>rank0</author><text>One thing I don’t understand about the housing debate is why any specific area needs to be “affordable”<p>If I can’t afford to live in an area, it seems to me the solution is to live somewhere else.<p>Maybe I’m missing something. I’m open to new ideas here but I really don’t get it.</text></item></parent_chain><comment><author>hypersoar</author><text>Every city relies on a bunch of cheap labor. Dishwashers, janitors, cashiers, cleaners, landscapers, baristas, gig workers, and on and on. Is it healthy for a city to need all of these people while denying them a place in it? We have this gross dynamic of essentially telling large swaths of people that they&#x27;re around only to be the help and that they don&#x27;t belong.</text></comment> |
37,903,824 | 37,899,629 | 1 | 3 | 37,895,446 | train | <story><title>Cockpit: Web-based graphical interface for servers</title><url>https://cockpit-project.org/</url></story><parent_chain><item><author>jameshart</author><text>People who decry graphical admin interfaces in favor of command line are missing the wood for the trees.<p>Sure, clickops is no way to run a server - but neither, if we’re honest, is ssh.<p>For a working machine, server state should be reproducible from scratch. Install an OS, add software, apply configuration, leave well alone. If you’re going in with ssh or cockpit you’re just going to screw something up.<p>So the only reason you should be working on a server directly is because you’re doing something exploratory. And in that case gui vs command line isn’t as clearcut as people want to make it. GUIs emphasize discoverability and visibility which can be helpful in that experimental phase when you’re trying to figure out how to get something set up right.</text></item></parent_chain><comment><author>tremon</author><text><i>clickops is no way to run a server</i><p><i>server state should be reproducible from scratch</i><p>Why? I&#x27;m not necessarily disagreeing, but too often are these kinds of statements thrown about without any qualification, as if they are self-evident truths. But they&#x27;re not -- there are engineering trade-offs behind any choice, and it&#x27;s no different here. So, in order to guide this discussion away from dogmatic platitudes: why should server state be reproducible from scratch? What does &quot;from scratch&quot; mean? Why is clickops no way to run a server?<p><i>Install an OS, add software, apply configuration</i><p>Do you think this captures &quot;server state&quot; completely? Software patch levels are not part of server state? What about application data? User data?<p>So here&#x27;s my counterstatement: for any working machine, I can reproduce the server state exactly by performing a restore from backup. Backup&#x2F;restore is perfectly compatible with clickops, and it&#x27;s faster and more reliable than reinstalling an OS, adding software and applying configuration -- even when the software and configuration are scripted. And if your server stores non-volatile data, as is often the case in clickops environments, you will need to have a backup system anyway to restore the user data after deploying a new server.</text></comment> | <story><title>Cockpit: Web-based graphical interface for servers</title><url>https://cockpit-project.org/</url></story><parent_chain><item><author>jameshart</author><text>People who decry graphical admin interfaces in favor of command line are missing the wood for the trees.<p>Sure, clickops is no way to run a server - but neither, if we’re honest, is ssh.<p>For a working machine, server state should be reproducible from scratch. Install an OS, add software, apply configuration, leave well alone. If you’re going in with ssh or cockpit you’re just going to screw something up.<p>So the only reason you should be working on a server directly is because you’re doing something exploratory. And in that case gui vs command line isn’t as clearcut as people want to make it. GUIs emphasize discoverability and visibility which can be helpful in that experimental phase when you’re trying to figure out how to get something set up right.</text></item></parent_chain><comment><author>HankB99</author><text>&gt; For a working machine, server state should be reproducible from scratch. Install an OS, add software, apply configuration, leave well alone.<p>I&#x27;m curious if you have a specific tool or tools in mind. I&#x27;ve been using Ansible in my home lab, particularly for configuring Raspberry Pis. The OS install part (only?) works because it involves a bitwise copy of the image to the boot media (and some optional configuration.)</text></comment> |
19,327,850 | 19,327,701 | 1 | 2 | 19,327,351 | train | <story><title>ZFS on Linux 0.7.13</title><url>https://github.com/zfsonlinux/zfs/releases/tag/zfs-0.7.13</url></story><parent_chain><item><author>unmole</author><text>From the release notes, it seems like a normal point release. I&#x27;m not seeing anything particularly noteworthy but this has hit the front page for some reason. What am I missing?</text></item></parent_chain><comment><author>eddyg</author><text>More context: <a href="https:&#x2F;&#x2F;marc.info&#x2F;?l=linux-kernel&amp;m=154722999728768&amp;w=2" rel="nofollow">https:&#x2F;&#x2F;marc.info&#x2F;?l=linux-kernel&amp;m=154722999728768&amp;w=2</a><p>&gt; 5.0 removes the ability from non-GPL modules to use the FPU or SIMD instructions</text></comment> | <story><title>ZFS on Linux 0.7.13</title><url>https://github.com/zfsonlinux/zfs/releases/tag/zfs-0.7.13</url></story><parent_chain><item><author>unmole</author><text>From the release notes, it seems like a normal point release. I&#x27;m not seeing anything particularly noteworthy but this has hit the front page for some reason. What am I missing?</text></item></parent_chain><comment><author>dchest</author><text>Previous title had &quot;...with Linux 5.0 compatibility&quot;. The significance of this is that 5.0 changed some interfaces used by ZFS to require GPL license, which ZoL can&#x27;t call, which generated some discussion <a href="https:&#x2F;&#x2F;lore.kernel.org&#x2F;lkml&#x2F;[email protected]&#x2F;#t" rel="nofollow">https:&#x2F;&#x2F;lore.kernel.org&#x2F;lkml&#x2F;[email protected]...</a></text></comment> |
9,215,237 | 9,215,214 | 1 | 3 | 9,214,824 | train | <story><title>Pinterest Raises $367M at $11B valuation</title><url>http://techcrunch.com/2015/03/16/pinterest-raises-367-million-pushing-it-past-1-billion-raised-in-all/</url></story><parent_chain><item><author>sharkweek</author><text>You know when you hear about a lot of insane valuations and your jaw sort of drops in disbelief?<p>I feel the opposite when I think about Pinterest. My immediate reaction here is &quot;yeah, makes sense.&quot; I guess it must stem from my marketing agency days. I had SO MANY clients begging me to get them into Pinterest ads when they released. I also sit at home and see how much time my wife spends on the site and how dedicated she is to discovery through the app, especially as she makes many purchasing decisions after seeing things she likes pinned, from food to furniture.<p>Seems like a no-brainer that this one is going to end up crossing the IPO finish line at some point, and I would imagine they have bigger and better plans moving forward. I barely think they&#x27;ve scratched the surface of profitability.</text></item></parent_chain><comment><author>callmeed</author><text>Agreed 100%. There&#x27;s so much purchasing intent on Pinterest. I think it could be a stronger platform than Facebook for advertising non-digital goods.<p>Every bride uses Pinterest (and now most wedding vendors and bloggers).<p>My mother-in-law uses it every day to plan all her home remodeling projects and she&#x27;s 60-something.</text></comment> | <story><title>Pinterest Raises $367M at $11B valuation</title><url>http://techcrunch.com/2015/03/16/pinterest-raises-367-million-pushing-it-past-1-billion-raised-in-all/</url></story><parent_chain><item><author>sharkweek</author><text>You know when you hear about a lot of insane valuations and your jaw sort of drops in disbelief?<p>I feel the opposite when I think about Pinterest. My immediate reaction here is &quot;yeah, makes sense.&quot; I guess it must stem from my marketing agency days. I had SO MANY clients begging me to get them into Pinterest ads when they released. I also sit at home and see how much time my wife spends on the site and how dedicated she is to discovery through the app, especially as she makes many purchasing decisions after seeing things she likes pinned, from food to furniture.<p>Seems like a no-brainer that this one is going to end up crossing the IPO finish line at some point, and I would imagine they have bigger and better plans moving forward. I barely think they&#x27;ve scratched the surface of profitability.</text></item></parent_chain><comment><author>madeofpalk</author><text>Big TV show in Australia is The Block - a home renovation competition reality show. Each week starts with them looking at Pinterest for &#x27;inspiration&#x27; for each new room or theme they&#x27;re trying for - it&#x27;s basically The Pinterest Show, weekly at 8:30pm on Channel Nine.</text></comment> |
34,869,784 | 34,869,283 | 1 | 2 | 34,868,437 | train | <story><title>My class required AI</title><url>https://oneusefulthing.substack.com/p/my-class-required-ai-heres-what-ive</url></story><parent_chain></parent_chain><comment><author>coffeefirst</author><text>In college I used to help friends fix their essays. We&#x27;d go through line by line and examine if the actual words on the page were clear and said what they intended. All of them wound up getting As on the second draft and every essay thereafter. It was just about learning how to look at the problem.<p>We live in a world of emails and slacks and documents and text messaging. Literacy matters. Writing clearly matters.<p>What I would actually do with this is not use GPT to write your essay, but have GPT write a flawed essay and ask the students to rewrite it. Fix the logical fallacies, tighten the language, check the facts, etc.</text></comment> | <story><title>My class required AI</title><url>https://oneusefulthing.substack.com/p/my-class-required-ai-heres-what-ive</url></story><parent_chain></parent_chain><comment><author>isaacfrond</author><text>Excellent article.<p>I was helping my son with his homework. He had to write an essay about why the gender of the protagonist might be female (although this is never mentioned in the short story). Fortunately for him, ChatGPT knew the story and was happy to write an essay with arguments. [Btw, according to him pretty much everyone in class routinely has the AI do their essays]<p>He was about to send this essay in. But as we were admiring the prose of the computer (which is much better than either of can), we found out that some of the arguments actually didn&#x27;t make much sense. So we went to through a rewrite exercise like in the article, improving the essay and our understanding of the issues.<p>Next time I see her, I&#x27;ll urge the teacher to adopt a similar approach as in the article.</text></comment> |
23,967,965 | 23,967,366 | 1 | 3 | 23,960,631 | train | <story><title>Spies can eavesdrop by watching a light bulb's vibrations</title><url>https://www.wired.com/story/lamphone-light-bulb-vibration-spying/</url></story><parent_chain><item><author>ravenstine</author><text>One way you can do this without another light source is to bounce a laser beam off a window or other things that are reflective.<p>In fact, the same principle can be achieved with radio. The Russians once planted a device in a wooden seal they gave to a US ambassador as a gift which, when a focused radio beam was aimed at it, would reflect and oscillate that beam due to vibrations in the air.<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Thing_%28listening_device%29" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Thing_%28listening_device%...</a></text></item></parent_chain><comment><author>balls187</author><text>Most of my office windows at Boeing had little ultrasonic buzzers on them to prevent such an attack.<p>On my offices was actually in a large farad cage to reduce&#x2F;eliminate EMF leaks from workstations.</text></comment> | <story><title>Spies can eavesdrop by watching a light bulb's vibrations</title><url>https://www.wired.com/story/lamphone-light-bulb-vibration-spying/</url></story><parent_chain><item><author>ravenstine</author><text>One way you can do this without another light source is to bounce a laser beam off a window or other things that are reflective.<p>In fact, the same principle can be achieved with radio. The Russians once planted a device in a wooden seal they gave to a US ambassador as a gift which, when a focused radio beam was aimed at it, would reflect and oscillate that beam due to vibrations in the air.<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Thing_%28listening_device%29" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Thing_%28listening_device%...</a></text></item></parent_chain><comment><author>perch56</author><text>Leon Theremin was a genius that also created one of the first electronic instruments carrying his name now.<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Theremin" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Theremin</a></text></comment> |
10,354,500 | 10,354,146 | 1 | 2 | 10,353,972 | train | <story><title>AWS IoT Beta</title><url>https://aws.amazon.com/iot/</url></story><parent_chain></parent_chain><comment><author>jchrisa</author><text>It&#x27;s important to highlight open source alternatives to AWS products. If you are looking at AWS IoT and wishing you could run it on your own servers, the Couchbase Mobile stack is open source and used for mission critical deployments by customers like General Electric, for IoT applications: <a href="http:&#x2F;&#x2F;www.slideshare.net&#x2F;Couchbase&#x2F;offline-first-how-ge-integrated-couchbase-mobile-in-less-than-90-days-couchbase-connect-2015" rel="nofollow">http:&#x2F;&#x2F;www.slideshare.net&#x2F;Couchbase&#x2F;offline-first-how-ge-int...</a><p>More info: <a href="http:&#x2F;&#x2F;developer.couchbase.com&#x2F;mobile" rel="nofollow">http:&#x2F;&#x2F;developer.couchbase.com&#x2F;mobile</a><p>There is a lot going on in this space and we are a general purpose database. If you&#x27;re looking for native open source implementations that give you access to the whole stack, and interop with other tech like PouchDB and IBM Cloudant...</text></comment> | <story><title>AWS IoT Beta</title><url>https://aws.amazon.com/iot/</url></story><parent_chain></parent_chain><comment><author>harshaw</author><text>So, my extremely quick read is this a framework for hiding stuff that consumes data from internet of thing appliances and makes some of that data available via shadows.<p>I wish amazon would do a better job explaining why this new thing is better than the last new thing from amazon. Many services feel close and similar until you dig into the target use cases. Even the FAQ doesn&#x27;t have a list of target use cases.</text></comment> |
28,356,355 | 28,356,446 | 1 | 2 | 28,355,312 | train | <story><title>Replay-based attack on Honda and Acura vehicles</title><url>https://github.com/HackingIntoYourHeart/Unoriginal-Rice-Patty</url></story><parent_chain><item><author>cestith</author><text>Remote start is a safety issue, not just a security one. It doesn&#x27;t take much to imagine replaying the start command while a vehicle is in an attached garage.<p>Remote unlock is a safety issue for assaults.<p>Thankfully according to <a href="https:&#x2F;&#x2F;owners.honda.com&#x2F;Linked-Content&#x2F;PDF&#x2F;RemoteEnginestarter.pdf" rel="nofollow">https:&#x2F;&#x2F;owners.honda.com&#x2F;Linked-Content&#x2F;PDF&#x2F;RemoteEnginestar...</a> the remote engine stop doesn&#x27;t work if the engine was started with the ignition key rather than the remote.</text></item></parent_chain><comment><author>ashtonkem</author><text>I agree about the remote start, but I’m dubious about the remote unlock being an issue for assaults in practice. I think if someone is planning to violently attack someone, going through the window is going to be the most common path taken.<p>It’s like home invasions. Perhaps someone might pick your weak lock or hack your smart lock, but in practice they usually just break a window or kick the door in.</text></comment> | <story><title>Replay-based attack on Honda and Acura vehicles</title><url>https://github.com/HackingIntoYourHeart/Unoriginal-Rice-Patty</url></story><parent_chain><item><author>cestith</author><text>Remote start is a safety issue, not just a security one. It doesn&#x27;t take much to imagine replaying the start command while a vehicle is in an attached garage.<p>Remote unlock is a safety issue for assaults.<p>Thankfully according to <a href="https:&#x2F;&#x2F;owners.honda.com&#x2F;Linked-Content&#x2F;PDF&#x2F;RemoteEnginestarter.pdf" rel="nofollow">https:&#x2F;&#x2F;owners.honda.com&#x2F;Linked-Content&#x2F;PDF&#x2F;RemoteEnginestar...</a> the remote engine stop doesn&#x27;t work if the engine was started with the ignition key rather than the remote.</text></item></parent_chain><comment><author>markbnj</author><text>Fwiw, on current Hondas the engine will only run for a set period, I believe 10 mins, unless the fob is used to reset the timer or the driver enters the cabin with the fob and presses the brake and start button.</text></comment> |
37,465,316 | 37,464,945 | 1 | 3 | 37,439,732 | train | <story><title>The Carrington Event of 1859 disrupted telegraph lines</title><url>https://daily.jstor.org/the-carrington-event-of-1859-disrupted-telegraph-lines/</url></story><parent_chain></parent_chain><comment><author>b800h</author><text>If these Miyake events were so spectacular, why do they not appear in the historical record? I appreciate that 774 was in the &quot;dark ages&quot; but something as impressive as the Carrington event would appear in some chronicles, surely?<p>EDIT: Sorry, checked Wikipedia:<p>&quot;Annus Domini (the year of the Lord) 774. This year the Northumbrians banished their king, Alred, from York at Easter-tide; and chose Ethelred, the son of Mull, for their lord, who reigned four winters. This year also appeared in the heavens a red crucifix, after sunset; the Mercians and the men of Kent fought at Otford; and wonderful serpents were seen in the land of the South-Saxons.
— Anglo-Saxon Chronicle[9]&quot;</text></comment> | <story><title>The Carrington Event of 1859 disrupted telegraph lines</title><url>https://daily.jstor.org/the-carrington-event-of-1859-disrupted-telegraph-lines/</url></story><parent_chain></parent_chain><comment><author>dskrepps</author><text>I&#x27;ve wondered for a while. Lots of people seem to think a Carrington Event will simply fry all small electronics and make everything stop working, but from my understanding all it&#x27;ll actually do is cause power surges in long transmission lines and disrupt wireless signals. Apparently telegraph lines sparked and shocked people. So what effect will that actually have now? Will a massive power surge go through my house and destroy everything plugged in, and thus indirectly my desktop computer? Will every house on the grid catch fire, destroying all modern cities? Or will substations and transformers be destroyed but shield homes themselves from catastrophic damage? Will wildfires destroy every forest anywhere near modern infrastructure?</text></comment> |
39,614,395 | 39,613,774 | 1 | 2 | 39,612,484 | train | <story><title>Fonts are still a Helvetica of a Problem</title><url>https://www.canva.dev/blog/engineering/fonts-are-still-a-helvetica-of-a-problem/</url></story><parent_chain><item><author>evrimoztamur</author><text>With SVG support at a near-full coverage (and 99.99% for Canva&#x27;s user base, <a href="https:&#x2F;&#x2F;caniuse.com&#x2F;svg" rel="nofollow">https:&#x2F;&#x2F;caniuse.com&#x2F;svg</a>) you do wonder why we see less SVG for <i>graphics</i> like this. It&#x27;s literally easier to export, and no harder to import than PNGs.</text></item><item><author>gpjanik</author><text>It&#x27;s so funny this article features a timeline graphic that&#x27;s a PNG with a lot of text on it. On Firefox + M1 Macbook, the first image is not up to scale for high resolution screens and each pixel is blurry, rendering the font hardly readable. Then the article continues with some SVG code... oops?</text></item></parent_chain><comment><author>Etheryte</author><text>From personal experience and having been burned by odd SVG bugs too many times over the years, a dumb image is simple, it works and you know that it works. I only reach for SVG when I need to do something that other formats cannot.</text></comment> | <story><title>Fonts are still a Helvetica of a Problem</title><url>https://www.canva.dev/blog/engineering/fonts-are-still-a-helvetica-of-a-problem/</url></story><parent_chain><item><author>evrimoztamur</author><text>With SVG support at a near-full coverage (and 99.99% for Canva&#x27;s user base, <a href="https:&#x2F;&#x2F;caniuse.com&#x2F;svg" rel="nofollow">https:&#x2F;&#x2F;caniuse.com&#x2F;svg</a>) you do wonder why we see less SVG for <i>graphics</i> like this. It&#x27;s literally easier to export, and no harder to import than PNGs.</text></item><item><author>gpjanik</author><text>It&#x27;s so funny this article features a timeline graphic that&#x27;s a PNG with a lot of text on it. On Firefox + M1 Macbook, the first image is not up to scale for high resolution screens and each pixel is blurry, rendering the font hardly readable. Then the article continues with some SVG code... oops?</text></item></parent_chain><comment><author>lifthrasiir</author><text>Kinda because it&#x27;s harder to make a good SVG editor, and also a clean SVG is substantially harder to export and thus SVG is only seen as an authoring format.</text></comment> |
25,636,301 | 25,635,045 | 1 | 2 | 25,620,321 | train | <story><title>Working from Bed</title><url>https://www.nytimes.com/2020/12/31/style/working-from-bed.html</url></story><parent_chain><item><author>Raphmedia</author><text>On the opposite, I&#x27;d say it&#x27;s a great way to destroy your sleep routine and habits. As a rule of thumb, your bed should be dedicated to sleep and cuddles with your significant other.<p>&quot;This study indicates that the use of computers and mobile telephones in the bedroom are related to poor sleep habits&quot; <a href="https:&#x2F;&#x2F;onlinelibrary.wiley.com&#x2F;doi&#x2F;full&#x2F;10.1111&#x2F;j.1365-2869.2011.00913.x" rel="nofollow">https:&#x2F;&#x2F;onlinelibrary.wiley.com&#x2F;doi&#x2F;full&#x2F;10.1111&#x2F;j.1365-2869...</a><p>&quot;Computer use, TV viewing, and the presence of media in children&#x27;s bedrooms may reduce sleep duration, and delay bedtimes.&quot; <a href="https:&#x2F;&#x2F;pubmed.ncbi.nlm.nih.gov&#x2F;23886318&#x2F;" rel="nofollow">https:&#x2F;&#x2F;pubmed.ncbi.nlm.nih.gov&#x2F;23886318&#x2F;</a></text></item></parent_chain><comment><author>gopalv</author><text>&gt; As a rule of thumb, your bed should be dedicated to sleep<p>CGP Grey had a pretty good video about living in the lockdown titled &quot;Spaceship you&quot;.<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=snAhsXyO3Ck" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=snAhsXyO3Ck</a><p>I&#x27;d say that a lot of work that isn&#x27;t really work can be done from bed, but it does mess up your training for &quot;bed == sleep&quot;.<p>I used to work from bed before 2020, but the lockdown has made the &quot;walk downstairs to work, grab a coffee along the way&quot; into a natural thing rather than putting a number of other high attention activities (shaving, driving) between being awake-enough to sitting at my desk.</text></comment> | <story><title>Working from Bed</title><url>https://www.nytimes.com/2020/12/31/style/working-from-bed.html</url></story><parent_chain><item><author>Raphmedia</author><text>On the opposite, I&#x27;d say it&#x27;s a great way to destroy your sleep routine and habits. As a rule of thumb, your bed should be dedicated to sleep and cuddles with your significant other.<p>&quot;This study indicates that the use of computers and mobile telephones in the bedroom are related to poor sleep habits&quot; <a href="https:&#x2F;&#x2F;onlinelibrary.wiley.com&#x2F;doi&#x2F;full&#x2F;10.1111&#x2F;j.1365-2869.2011.00913.x" rel="nofollow">https:&#x2F;&#x2F;onlinelibrary.wiley.com&#x2F;doi&#x2F;full&#x2F;10.1111&#x2F;j.1365-2869...</a><p>&quot;Computer use, TV viewing, and the presence of media in children&#x27;s bedrooms may reduce sleep duration, and delay bedtimes.&quot; <a href="https:&#x2F;&#x2F;pubmed.ncbi.nlm.nih.gov&#x2F;23886318&#x2F;" rel="nofollow">https:&#x2F;&#x2F;pubmed.ncbi.nlm.nih.gov&#x2F;23886318&#x2F;</a></text></item></parent_chain><comment><author>kaybe</author><text>Oohh look at these people with more than one room!<p>(Ok it&#x27;s valid for those.. but I&#x27;m still feeling a bit salty.)</text></comment> |
2,864,559 | 2,864,470 | 1 | 2 | 2,864,011 | train | <story><title>Underscore.php</title><url>http://brianhaveri.github.com/Underscore.php/</url></story><parent_chain></parent_chain><comment><author>yahelc</author><text>This will be even more aesthetically pleasing once PHP 5.4 is released with support for array literals:<p><pre><code> __::map([1, 2, 3]), function($n) { return $n * 2; });
__([1, 2, 3])-&#62;map(function($n) { return $n * 2; });
</code></pre>
That, combined with array dereferencing (ie, explode(",",$str)[0] ), PHP will start to look a lot like JavaScript.</text></comment> | <story><title>Underscore.php</title><url>http://brianhaveri.github.com/Underscore.php/</url></story><parent_chain></parent_chain><comment><author>fooyc</author><text>Why not using namespaced functions instead of static methods all in the same class ? This would have allowed to add new functions. This would even have allowed to use the _ namespace.<p>With namespaces:<p><pre><code> namespace _;
function each() {
}
// chaining can be achieved with this:
class Wrapper {
private $coll;
function __construct($coll) {
$this-&#62;coll = $coll;
}
function __call($name, $args) {
array_unshift($this-&#62;coll,$args);
return new self(call_user_func_array('_\\'.$name, $args));
}
}
function __($coll) {
return new Wrapper($coll);
}
use _;
_\each(...);
// or
__($coll)-&#62;each(...);
// I can add new functions
namespace _;
function something(){}
</code></pre>
With static methods:<p><pre><code> class __ {
function each() {
}
}
// throws strict errors
__::each(...);
// can't add functions
</code></pre>
Also it seems that the normal way to use the library is to call isntance methods statically, which triggers many warnings with E_STRICT :(<p><a href="https://github.com/lstrojny/functional-php" rel="nofollow">https://github.com/lstrojny/functional-php</a> also brings some functional stuff to php.</text></comment> |
3,838,145 | 3,838,272 | 1 | 3 | 3,837,772 | train | <story><title>A Year with MongoDB</title><url>http://blog.engineering.kiip.me/post/20988881092/a-year-with-mongodb</url></story><parent_chain><item><author>sirn</author><text>&#62; We changed the structure of our heaviest used models a couple times in the past year, and instead of going back and updating millions of old documents, we simply added a “version” field to the document and the application handled the logic of reading both the old and new version. This flexibility was useful for both application developers and operations engineers.<p>Ugh, this sounds like a maintenance nightmare. How do you deal with adding extra field to the document? Do you ever feel the need of running on-the-fly migration of old versions? (But when you do, shouldn't running a migration for all documents a better idea?)<p>I'll admit I'm a non-believer, but every time I see "Schemaless" in MongoDB, I think "oh, so you're implementing schema in your application?"</text></item></parent_chain><comment><author>mitchellh</author><text>&#62; Ugh, this sounds like a maintenance nightmare. How do you deal with adding extra field to the document? Do you ever feel the need of running on-the-fly migration of old versions? (But when you do, shouldn't running a migration for all documents a better idea?)<p>Yes, we did on-the-fly migration as we loaded old data in.<p>Doing full data migration was not really an option because querying from MongoDB on un-indexed data is so slow, and paging in all that data would purge hot data, exacerbating the problem.<p>&#62; I'll admit I'm a non-believer, but every time I see "Schemaless" in MongoDB, I think "oh, so you're implementing schema in your application?"<p>That's exactly what happens.</text></comment> | <story><title>A Year with MongoDB</title><url>http://blog.engineering.kiip.me/post/20988881092/a-year-with-mongodb</url></story><parent_chain><item><author>sirn</author><text>&#62; We changed the structure of our heaviest used models a couple times in the past year, and instead of going back and updating millions of old documents, we simply added a “version” field to the document and the application handled the logic of reading both the old and new version. This flexibility was useful for both application developers and operations engineers.<p>Ugh, this sounds like a maintenance nightmare. How do you deal with adding extra field to the document? Do you ever feel the need of running on-the-fly migration of old versions? (But when you do, shouldn't running a migration for all documents a better idea?)<p>I'll admit I'm a non-believer, but every time I see "Schemaless" in MongoDB, I think "oh, so you're implementing schema in your application?"</text></item></parent_chain><comment><author>radicalbyte</author><text>&#62; oh, so you're implementing schema in your application?<p>Isn't that where the schema belongs? Each document represents a conceptual whole. It doesn't contain fields which have to be NULL simply because they weren't in previous versions of the schema.<p>I've been an rdbms guy (datawarehousing/ETL) for a long time now, I've seen a lot of large databases which have been in production for considerable time. They get messy. Really messy. They become basically unmaintainable. Apples, oranges and pears all squashed into a schema the shape of a banana.<p>It's a pretty elegant solution, and is the problem XML/XSD were designed to solve<i>.<p>The cleanest solution that I've seen in production used a relational database as a blob storage for XML-serialized entities. Each table defined a basic interface for the models, but each model was free to use its own general schema. After 10 years it contained a set of very clean individual entities which were conceptually correct.<p></i> As opposed to the usage as a serialization format for remoting, which has been largely replaced with JSON.</text></comment> |
18,497,954 | 18,497,783 | 1 | 3 | 18,495,697 | train | <story><title>You might not need Kubernetes</title><url>https://blog.jessfraz.com/post/you-might-not-need-k8s/</url></story><parent_chain><item><author>meritt</author><text>As someone who runs a very successful data business on a simple stack (php, cron, redis, mariadb), I definitely agree. We&#x27;ve avoided the latest trends&#x2F;tools and just keep humming along while outperforming and outdelivering our competitors.<p>We&#x27;re also revenue-funded so no outside VC pushing us to be flashy, but I will definitely admit it makes hiring difficult. Candidates see our stack as boring and bland, which we make up for that in comp, but for a lot of people that&#x27;s not enough.<p>If you want to run a reliable, simple, and profitable business, keep your tech stack equally simple. If you want to appeal to VCs and have an easy time recruiting, you need to be cargo cult, even if it&#x27;s not technically necessary.</text></item><item><author>combatentropy</author><text>Some day I would like a powwow with all you hackers about whether 99% of apps need more than a $5 droplet from Digital Ocean, set up the old-fashioned way, LAMP --- though feel free to switch out the letters: BSD instead of Linux, Nginx instead of Apache, PostgreSQL instead of MySQL, Ruby or Python instead of PHP.<p>I manage dozens of apps for thousands of users. The apps are all on one server, its load average around 0.1. I know, it isn&#x27;t web-scale. Okay, how about Hacker News? It runs on one server. Moore&#x27;s Law rendered most of our impressive workloads to a golf ball in a football field, years ago.<p>I understand these companies needing many, many servers: Google, Facebook, Uber, and medium companies like Basecamp. But to the rest I want to ask, what&#x27;s the load average on the Kubernetes cluster for your Web 2.0 app? If it&#x27;s high, is it because you are getting 100,000 requests per second, or is it the frameworks you cargo-culted in? What would the load average be if you just wrote a LAMP app?<p>EDIT: Okay, a floating IP and two servers.</text></item></parent_chain><comment><author>henrikschroder</author><text>&gt; Candidates see our stack as boring and bland<p>I would say that there are probably a lot of developers who would be very happy to work on a non-buzzword stack, but the problem is that as a developer, it&#x27;s extremely hard to know if your tech stack is the result of directed efforts to keep it simple, or if it&#x27;s the haphazard result of some guy setting it up ten years ago when these technologies were hot.</text></comment> | <story><title>You might not need Kubernetes</title><url>https://blog.jessfraz.com/post/you-might-not-need-k8s/</url></story><parent_chain><item><author>meritt</author><text>As someone who runs a very successful data business on a simple stack (php, cron, redis, mariadb), I definitely agree. We&#x27;ve avoided the latest trends&#x2F;tools and just keep humming along while outperforming and outdelivering our competitors.<p>We&#x27;re also revenue-funded so no outside VC pushing us to be flashy, but I will definitely admit it makes hiring difficult. Candidates see our stack as boring and bland, which we make up for that in comp, but for a lot of people that&#x27;s not enough.<p>If you want to run a reliable, simple, and profitable business, keep your tech stack equally simple. If you want to appeal to VCs and have an easy time recruiting, you need to be cargo cult, even if it&#x27;s not technically necessary.</text></item><item><author>combatentropy</author><text>Some day I would like a powwow with all you hackers about whether 99% of apps need more than a $5 droplet from Digital Ocean, set up the old-fashioned way, LAMP --- though feel free to switch out the letters: BSD instead of Linux, Nginx instead of Apache, PostgreSQL instead of MySQL, Ruby or Python instead of PHP.<p>I manage dozens of apps for thousands of users. The apps are all on one server, its load average around 0.1. I know, it isn&#x27;t web-scale. Okay, how about Hacker News? It runs on one server. Moore&#x27;s Law rendered most of our impressive workloads to a golf ball in a football field, years ago.<p>I understand these companies needing many, many servers: Google, Facebook, Uber, and medium companies like Basecamp. But to the rest I want to ask, what&#x27;s the load average on the Kubernetes cluster for your Web 2.0 app? If it&#x27;s high, is it because you are getting 100,000 requests per second, or is it the frameworks you cargo-culted in? What would the load average be if you just wrote a LAMP app?<p>EDIT: Okay, a floating IP and two servers.</text></item></parent_chain><comment><author>nineteen999</author><text>Hear hear. I lead a team that builds and manages critical emergency services infrastructure.<p>Our stack is pretty boring, but then it has to be running 99.999% of the time. Rather than wasting time chasing the latest flavour-of-the-month tool or framework we invest our time in plugging any kind of gap that could ever bring our service down.<p>We don&#x27;t need people who are only looking to pad their resume with the hottest buzzwords, we look for people who want to make critical services run all that time, that rarely fail and when they do, they handle failure gracefully.<p>The number of devops&#x2F;agile&#x2F;SaaS style shops I have seen where the product falls over for several hours at a time is astounding, and it can often be attributed to rushed&#x2F;inexperienced engineering or unnecessary complexity.<p>Lucky for them it&#x27;s usually just the shareholders bottom line that is affected. If the services my team provides don&#x27;t work, ambulances and fire engines are either not arriving fast enough or at all.</text></comment> |
5,106,477 | 5,106,399 | 1 | 2 | 5,105,490 | train | <story><title>Things That Are Never Admitted About Open Source</title><url>http://www.datamation.com/open-source/9-things-that-are-never-admitted-about-open-source-1.html</url><text></text></story><parent_chain></parent_chain><comment><author>belorn</author><text>1#, Ubuntu is indeed no longer the public face to open source, but then is anyone actually surprised? At best, Ubuntu can be said to have been an symptom of the success Debian was and still is in collecting and maintaining open source and free software projects. Where ubuntu left, mint picked up, and I don't see an end in polished distributions ontop of Debian.<p>#2, The dangers of web-services in regard to privacy and property is only starting to reach the general population. In this regard, EFF and CCC has had a larger role to play than AGPL and FLOSS.<p>#3, While Stallman is the leading figure in free software, people like Eben Moglen has much better speaches and do more to recruit new members to the community. I think today, Stallman is more often addressing the members inside the community in what areas are currently in need of most work, and what new threats exist for the community.<p>#4, A true Meritocracy does not exist anywhere. People follow leaders, even those that do not deserve it. The goal might be to become a Meritocracy (I wouldn't know), but the truth is that open and free software communities are just made out of human beings.<p>#5, When addressing/claiming a serious issue like Systemic Sexism, two things need to be done. First, one need to show the problem exist. We do have nice statistic on it and the author did show some poor but uncontested data (so he get a pass there). Second one need to show <i>why</i> the gender diversity is so large. The author do not do this. Actually, no articles about sexism in the free and open source communities addresses the question of why (or at least no one has done so with data to back it up!). This is in my view the primary single reason why the discussion about sexism in free software has gone nowhere for the last 10 years. Its not about hushing or denying the existence of the issue, but rather the lack of data that is keeping us from fixing it. The question of <i>why</i> is a central part of any technologist or academic thinking, and without it we would be unable to fix any computer, create any program, or solve any problem whatsoever. As a answer to the question on <i>how do we show why there is a gender difference in open source and free software</i>, I would start by looking at how this community differ from other similar sized communities with similar age groups. One particular group that comes to mind is gamer communities, sporting communities, and other communities that people freely perform as part of an hobby. One could also look at subgroups, such as IRC groups vs stackoverflow. If they have more, less or equal gender equality, one should ask the question <i>why</i> and try to build some testable theories. After that is done, and only after that is done, can one start to address the issue truly and in an effective way for the open source and free software community.<p>#6, Microsoft is never going to be trusted as a friend to free software. Too much bad blood, and honestly, who would want to be friend with someone who previously have gone out of their way kill you. Microsoft is also not putting down the symbolic knife, widely swinging secure boot around for everyone to see thus creating more untrust. At best, one can say that there exist bigger threats than Microsoft and thus focus should be redirected.<p>#7, the Desktop interface is the most visible aspect to desktop users. like with any area of design, it has had good times and bad times. It has a lot of discontentment, and is likely to see many people trying to do massive changes in a hope to get it in sync with what they perceive as current good design. Until design stop to change, the changes will likely continue without loosing any speed. I don't know if anyone tries to deny this or claim it is something not to be admitted.<p>#8, again I want to point towards human nature and that almost all cultures is monocultures. the top 1% of the musical bands are going to have 99% of the listeners. However, when people say that FOSS encourages diversity, the opposit camp is the devices which can't be changed, and are of questionable legality to modify (jailbreak). Those devices has one system, one store, one video player, one music player, and one company behind it. Compare to those places, FOSS indeed encourages diversity even if the majority of users are using the same software.<p>#9, open source and free software has indeed still a long way to go if they want to reach each communities goal that they had set aside for themselves. That said, reverse engineer is often a thankless job and without a political remodeling of the landscape (such as steam box might do but who knows), new devices is an never ending stream of new work. To make matter worse, old devices get old way to quick. Those people I know that work with this tend to burn out fast, and reach an unhealthy attitude to new people. Sadly this tend to happen way before those people would transfer knowledge and responsibility to a new group of people. So far, I have not seen any solution to this problem and can thus just hope that a major landscape change happens from outside the community.</text></comment> | <story><title>Things That Are Never Admitted About Open Source</title><url>http://www.datamation.com/open-source/9-things-that-are-never-admitted-about-open-source-1.html</url><text></text></story><parent_chain></parent_chain><comment><author>btilly</author><text>This article confuses "open source" and "the Linux desktop".<p>I consider myself an open source person. I spent a good chunk of my day today using open source tools, writing an article that I will give away for free.<p>And yet, I am typing this on a Mac. I don't care about gnome or KDE. Yes, I used several Linux machines today. But I have not seriously used a Linux desktop in the last 2 years, nor do I care what is going on there. (The last window manager that I liked was fvwm, but many years ago a Debian upgrade added integration with Gnome I did not want or need, and it stopped working in the way I wanted. I have not bothered caring about a window manager since.)<p>I am far from alone in my views. (Except for liking fvwm. Most people consider that plain weird.)</text></comment> |
16,519,660 | 16,517,953 | 1 | 3 | 16,517,412 | train | <story><title>Ask HN: Cookies vs. JWT vs. OAuth</title><text>I’m using passport.js with a local strategy for authentication, and I’m using sessions&#x2F;cookies for keeping state and keeping the user logged in.<p>I’m not very knowledgeable in security (that’s why I’m asking here), but will using JWT (with the token stored in the cookie) to keep the user logged in instead of sessions&#x2F;cookies make my application more secure when the passport middleware executes req.isAuthenticated? I thiiink somewhere in that call it checks cookies or jwt, depending on implementation.<p>Also, I do not plan on opening the API to other sites, so OAuth is unnecessary. Is my understanding correct?</text></story><parent_chain><item><author>modernpacifist</author><text>To answer as best as possible given the vagueness:<p>Cookies: Highly compatible with most if not all browsers (and even headless tools). Lends themselves to having an expiry date and generally best when used with time sort of short-lived expiring session.<p>JWT: Everyone tends to use these in a stateless manner which means once issued, somewhat impossible to revoke without invalidating all JWTs or having a blacklist (and we&#x27;re back at stateful). Plus some implementations had issues with downgrade attacks I think it was...<p>OAuth 1: Fine assuming you could keep clocks in sync and guarantee the secure storage of the keys&#x2F;secrets. Good in that it didn&#x27;t rely on HTTPS but if the secrets ever got compromised then the attacker would have free reign of that account until detected.<p>OAuth 2: Basically a complicated way to get short lived session tokens, potentially from a 3rd party API&#x2F;auth source. Relies entirely on HTTPS to keep data secure in-transit and less of an issue if the session token gets compromised since its ideally short lived (because most want it to be stateless - those who keep a valid list of tokens sometimes skip the token expiry).</text></item></parent_chain><comment><author>dwaite</author><text>Re: OAuth 2, once you carve out everything but the code flow and token refreshes it becomes harder to imagine simplifications that don&#x27;t remove important functionality.<p>The flow becomes &quot;redirect the user to have them authenticate, getting back a code. Make an API call to trade that code in for access. Once access expires, try to refresh it. If refreshing fails, send the user back to re-authenticate.&quot;.<p>The challenge people tend to hit is mistakenly trying to implement broad + reusable code at the start. OAuth 2 is described as a framework (e.g. optional parts and extensions leading to most likely non-interoperable implementations). Without a profile like OpenID Connect Basic Client, this includes a lot of extra work. Once you stop striving to implement generic interoperability in your client (or shoot for a limited profile like OpenID Connect Basic Client), the whole client implementation can fit in &lt; 1 page of code.</text></comment> | <story><title>Ask HN: Cookies vs. JWT vs. OAuth</title><text>I’m using passport.js with a local strategy for authentication, and I’m using sessions&#x2F;cookies for keeping state and keeping the user logged in.<p>I’m not very knowledgeable in security (that’s why I’m asking here), but will using JWT (with the token stored in the cookie) to keep the user logged in instead of sessions&#x2F;cookies make my application more secure when the passport middleware executes req.isAuthenticated? I thiiink somewhere in that call it checks cookies or jwt, depending on implementation.<p>Also, I do not plan on opening the API to other sites, so OAuth is unnecessary. Is my understanding correct?</text></story><parent_chain><item><author>modernpacifist</author><text>To answer as best as possible given the vagueness:<p>Cookies: Highly compatible with most if not all browsers (and even headless tools). Lends themselves to having an expiry date and generally best when used with time sort of short-lived expiring session.<p>JWT: Everyone tends to use these in a stateless manner which means once issued, somewhat impossible to revoke without invalidating all JWTs or having a blacklist (and we&#x27;re back at stateful). Plus some implementations had issues with downgrade attacks I think it was...<p>OAuth 1: Fine assuming you could keep clocks in sync and guarantee the secure storage of the keys&#x2F;secrets. Good in that it didn&#x27;t rely on HTTPS but if the secrets ever got compromised then the attacker would have free reign of that account until detected.<p>OAuth 2: Basically a complicated way to get short lived session tokens, potentially from a 3rd party API&#x2F;auth source. Relies entirely on HTTPS to keep data secure in-transit and less of an issue if the session token gets compromised since its ideally short lived (because most want it to be stateless - those who keep a valid list of tokens sometimes skip the token expiry).</text></item></parent_chain><comment><author>kevlened</author><text>Before going all the way on cookies, make sure to consider whether you&#x27;re creating a mobile app, as mobile apps usually don&#x27;t handle cookies for you automatically. In my experience, OAuth is a bit easier in mobile. If you support cookies for browsers and OAuth for mobile, your API will have to support both authentication methods.</text></comment> |
10,779,694 | 10,779,599 | 1 | 3 | 10,778,773 | train | <story><title>Why it’s harder to forge a SHA-1 certificate than to find a SHA-1 collision</title><url>https://blog.cloudflare.com/why-its-harder-to-forge-a-sha-1-certificate-than-it-is-to-find-a-sha-1-collision/</url></story><parent_chain></parent_chain><comment><author>agwa</author><text>We&#x27;re lucky that hash collision attacks have a relatively simple mitigation like this. (Although you have to trust CAs to follow the rules and implement it properly, and events of the last few years indicate that CAs need to have as few things to screw up as possible.)<p>However, we&#x27;re not always going to be so lucky. The next major transition in digital certificates could very well be to post-quantum crypto due to advancements in quantum computing. Under that scenario, attackers will be able to simply compute a CA&#x27;s private key and sign arbitrary certificates. There will be no mitigation short of clients ceasing to trust pre-quantum certs. But clients won&#x27;t be able to do that unless servers are using post-quantum certs, and server operators won&#x27;t want to do that if it would mean cutting off legacy clients that don&#x27;t support post-quantum certs.<p>The solution to this first mover problem is to set a hard deadline after which legacy certs are retired. This forces clients and server operators to act. Pushing back the SHA-1 deadline at the 11th hour as CloudFlare proposes sends a dangerous message that such deadlines don&#x27;t have to be taken seriously. This message will come back to haunt the Internet in the future.</text></comment> | <story><title>Why it’s harder to forge a SHA-1 certificate than to find a SHA-1 collision</title><url>https://blog.cloudflare.com/why-its-harder-to-forge-a-sha-1-certificate-than-it-is-to-find-a-sha-1-collision/</url></story><parent_chain></parent_chain><comment><author>KirinDave</author><text>It&#x27;s worth noting that SHA1 is also suitable for use in HMAC on older hardware, security is not significantly compromised by SHA1&#x27;s properties.<p>You can move to more modern algorithms, but there isn&#x27;t a pressing need to remove SHA1 implementations for that application.</text></comment> |
3,000,489 | 3,000,491 | 1 | 2 | 3,000,200 | train | <story><title>From $0-100million with no sales people. Atlassian's commandments for startups.</title><url>http://blog.businessofsoftware.org/2011/09/from-0-100million-with-no-sales-people-the-atlassian-10-commandments-for-startups.html</url></story><parent_chain></parent_chain><comment><author>latch</author><text>Do people generally like Jira and/or Confluence? I know they are popular in the enterprise. However, I've used them, and I consider them pretty horrible. Not sure if I'm just the odd man out on this though.</text></comment> | <story><title>From $0-100million with no sales people. Atlassian's commandments for startups.</title><url>http://blog.businessofsoftware.org/2011/09/from-0-100million-with-no-sales-people-the-atlassian-10-commandments-for-startups.html</url></story><parent_chain></parent_chain><comment><author>Zuz</author><text>Atlassian as a company rocks (the code behind some of the products less so but I digress). The reality is that they <i>do</i> have sales people, in fact <i>a lot</i> of them.<p>It's just that they are not Atlassian employees but are Atlassian partners employees. Atlassian has a massive partner/reseller network these days</text></comment> |
11,663,536 | 11,663,129 | 1 | 2 | 11,661,390 | train | <story><title>Siri creator shows off first public demo of Viv</title><url>http://techcrunch.com/2016/05/09/siri-creator-shows-off-first-public-demo-of-viv-the-intelligent-interface-for-everything/</url></story><parent_chain><item><author>bsaul</author><text>Impressive demo, but yet i can&#x27;t help thinking that the &quot;big&quot; question still remain largely unsolved for those services.<p>Two points :<p>1&#x2F; viv keeps mentioning a &quot;breakthrough&quot; in computer science because they managed to create a program that will scan a network of services and fill the parameters from the query. Now, those guys aren&#x27;t jokers, so i presume there is definitely something fantastic behind, yet i can&#x27;t help thinking that once you&#x27;ve &quot;understood&quot; the intent, it sounds quite close to a sql &#x2F; graphql query planner.<p>2&#x2F; Which leads to the big question : guessing the intent. Every time i hear people mention &quot;intelligence&quot; or &quot;understanding&quot;, i show them this : &quot;hey siri, please do NOT set a timer for 4 minutes, i beg you&quot;. The fact is, it&#x27;s just a trick. It recognize words, but it doesn&#x27;t understand anything, it doesn&#x27;t have concepts, knowledge or any experience. It&#x27;s a dumb program that never had any life or sense to understand anything.<p>If i say &quot;find me a good ticket for Chicago tonight&quot;. How will it know that i&#x27;m talking about the rock band that&#x27;s playing tonight in Paris, France, since there&#x27;s absolutely not a chance that a human being asks for a plane ticket for such a big trip just a few hours in advance ?<p>This is, to me, <i>the</i> big and interesting question that online assistants makers needs to solve. Now of course, viv is aiming for a product release this year, so they&#x27;re building an intermediate solution, where developers will manually associate keywords to services, in an &quot;easy&quot; way. And it will sort of work.<p>Yet i&#x27;m still waiting for the real &quot;big&quot; advance.</text></item></parent_chain><comment><author>mortenjorck</author><text><p><pre><code> If i say &quot;find me a good ticket for Chicago tonight&quot;. How
will it know that i&#x27;m talking about the rock band that&#x27;s
playing tonight in Paris, France, since there&#x27;s absolutely
not a chance that a human being asks for a plane ticket for
such a big trip just a few hours in advance ?
</code></pre>
I don&#x27;t even need an assistant system to figure out based on context which I&#x27;m talking about: All I want is one that can simply ask clarifying questions. &quot;Did you mean Chicago the city, or Chicago the band?&quot;<p>I had an amusing Siri interaction a few months ago where I asked &quot;what language is spoken in Shanghai?&quot; (I can never remember if it&#x27;s Mandarin or Cantonese). Siri came back with a very well-reasoned, completely out-of-place answer of &quot;Hindi&quot;: <a href="https:&#x2F;&#x2F;twitter.com&#x2F;claymill&#x2F;status&#x2F;690386752683577344" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;claymill&#x2F;status&#x2F;690386752683577344</a></text></comment> | <story><title>Siri creator shows off first public demo of Viv</title><url>http://techcrunch.com/2016/05/09/siri-creator-shows-off-first-public-demo-of-viv-the-intelligent-interface-for-everything/</url></story><parent_chain><item><author>bsaul</author><text>Impressive demo, but yet i can&#x27;t help thinking that the &quot;big&quot; question still remain largely unsolved for those services.<p>Two points :<p>1&#x2F; viv keeps mentioning a &quot;breakthrough&quot; in computer science because they managed to create a program that will scan a network of services and fill the parameters from the query. Now, those guys aren&#x27;t jokers, so i presume there is definitely something fantastic behind, yet i can&#x27;t help thinking that once you&#x27;ve &quot;understood&quot; the intent, it sounds quite close to a sql &#x2F; graphql query planner.<p>2&#x2F; Which leads to the big question : guessing the intent. Every time i hear people mention &quot;intelligence&quot; or &quot;understanding&quot;, i show them this : &quot;hey siri, please do NOT set a timer for 4 minutes, i beg you&quot;. The fact is, it&#x27;s just a trick. It recognize words, but it doesn&#x27;t understand anything, it doesn&#x27;t have concepts, knowledge or any experience. It&#x27;s a dumb program that never had any life or sense to understand anything.<p>If i say &quot;find me a good ticket for Chicago tonight&quot;. How will it know that i&#x27;m talking about the rock band that&#x27;s playing tonight in Paris, France, since there&#x27;s absolutely not a chance that a human being asks for a plane ticket for such a big trip just a few hours in advance ?<p>This is, to me, <i>the</i> big and interesting question that online assistants makers needs to solve. Now of course, viv is aiming for a product release this year, so they&#x27;re building an intermediate solution, where developers will manually associate keywords to services, in an &quot;easy&quot; way. And it will sort of work.<p>Yet i&#x27;m still waiting for the real &quot;big&quot; advance.</text></item></parent_chain><comment><author>ndarilek</author><text>&quot;If i say &quot;find me a good ticket for Chicago tonight&quot;. How will it know that i&#x27;m talking about the rock band that&#x27;s playing tonight in Paris, France, since there&#x27;s absolutely not a chance that a human being asks for a plane ticket for such a big trip just a few hours in advance ?&quot;<p>Funny, your &quot;absolutely not a chance&quot; interpretation was mine. Maybe there was a death in the family. Maybe you need to visit a friend short notice. Maybe I&#x27;m being a bit pedantic, but I was with you until that point. :)</text></comment> |
41,113,290 | 41,111,973 | 1 | 3 | 41,109,799 | train | <story><title>A eulogy for Dark Sky, a data visualization masterpiece (2023)</title><url>https://nightingaledvs.com/dark-sky-weather-data-viz/</url></story><parent_chain><item><author>g_sch</author><text>The feature I miss most about Dark Sky was that it allowed you to visualize changes in dew point throughout the day.<p>Where I live (US East Coast), the weather can feel dramatically different depending on the humidity. Relative Humidity has always felt to me like a poor way of measuring how humid the weather will feel. For example, 50% RH at 84ºF will feel lightly humid and generally pleasant, whereas 50% RH at at 97ºF will feel like a swamp. The dew points at those respective points - 63ºF and 75ºF - do a much better job at immediately conveying how humid the air will feel.<p>Dark Sky used to show hourly dew point graphs that you could browse throughout the week and see when the humidity would break (or return). Apple Weather does show you the dew point, but only when you select a point on the RH graph. So to track the dew point over the coming week, you basically need to drag your finger over each day&#x27;s graph and observe the changing numbers.<p>I think this is probably just due to the lack of general awareness about how dew point is a more elegant shorthand for &quot;absolute humidity&quot; than any other weather metric currently in use. I hope there will be more of us in the future!</text></item></parent_chain><comment><author>Leftium</author><text><a href="https:&#x2F;&#x2F;weather-sense.leftium.com" rel="nofollow">https:&#x2F;&#x2F;weather-sense.leftium.com</a><p>My web app plots hourly dew point for the next 24 hours, next 7 days, and past 2 days. (Still WIP.)<p>Inspired by <a href="https:&#x2F;&#x2F;merrysky.net" rel="nofollow">https:&#x2F;&#x2F;merrysky.net</a> (can also plot dew point), which was inspired by Dark Sky.</text></comment> | <story><title>A eulogy for Dark Sky, a data visualization masterpiece (2023)</title><url>https://nightingaledvs.com/dark-sky-weather-data-viz/</url></story><parent_chain><item><author>g_sch</author><text>The feature I miss most about Dark Sky was that it allowed you to visualize changes in dew point throughout the day.<p>Where I live (US East Coast), the weather can feel dramatically different depending on the humidity. Relative Humidity has always felt to me like a poor way of measuring how humid the weather will feel. For example, 50% RH at 84ºF will feel lightly humid and generally pleasant, whereas 50% RH at at 97ºF will feel like a swamp. The dew points at those respective points - 63ºF and 75ºF - do a much better job at immediately conveying how humid the air will feel.<p>Dark Sky used to show hourly dew point graphs that you could browse throughout the week and see when the humidity would break (or return). Apple Weather does show you the dew point, but only when you select a point on the RH graph. So to track the dew point over the coming week, you basically need to drag your finger over each day&#x27;s graph and observe the changing numbers.<p>I think this is probably just due to the lack of general awareness about how dew point is a more elegant shorthand for &quot;absolute humidity&quot; than any other weather metric currently in use. I hope there will be more of us in the future!</text></item></parent_chain><comment><author>travisluis</author><text>I too miss the dew point feature. The best replacement for Dark Sky I&#x27;ve found is this 10-day view of Weather Underground that&#x27;s unfortunately only available on their website—I just bookmark the website on my phone home screen. <a href="https:&#x2F;&#x2F;www.wunderground.com&#x2F;forecast&#x2F;us&#x2F;tx&#x2F;austin&#x2F;30.27,-97.74" rel="nofollow">https:&#x2F;&#x2F;www.wunderground.com&#x2F;forecast&#x2F;us&#x2F;tx&#x2F;austin&#x2F;30.27,-97...</a></text></comment> |
15,477,034 | 15,476,919 | 1 | 2 | 15,474,043 | train | <story><title>Traceroute Lies: A Typical Misinterpretation Of Output</title><url>http://movingpackets.net/2017/10/06/misinterpreting-traceroute/</url></story><parent_chain></parent_chain><comment><author>jlgaddis</author><text>As a network engineer who gets similar reports fairly often, I recommend watching &quot;Tutorial: Troubleshooting with Traceroute&quot; (a.k.a. &quot;A Practical Guide to (Correctly) Troubleshooting with Traceroute&quot;), as recorded at NANOG 62 (there&#x27;s also an older presentation from NANOG 47, IIRC). It covers the same stuff John&#x27;s article does and more. A PDF of the slides [1] is also available.<p>John alluded to this in his &quot;side note&quot; but often (the majority of cases, IME) the TTL will not be decremented inside of the MPLS core so you, as an end user, will have no visibility into it. You&#x27;ll just see, for example, hop #4 (Los Angeles) then hop #5 (New York City), completely unaware that the IP packet actually passed through (MPLS &quot;P&quot;) routers in Phoenix, Denver, Kansas City, Chicago, and Washington, DC, in between.<p>You&#x27;ll see the same thing -- although at a different layer -- when Q-in-Q tunneling is in use (assuming L2 protocols are also being tunneled).<p>N.B.: On common Linux distributions, there are usually several traceroute variants available. They are not all created equal. If a &quot;regular&quot; (UDP) traceroute won&#x27;t work, you can try using ICMP or even TCP.<p>[0]: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;a1IaRAVGPEE" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;a1IaRAVGPEE</a><p>[1]: <a href="https:&#x2F;&#x2F;www.nanog.org&#x2F;sites&#x2F;default&#x2F;files&#x2F;tuesday_steenbergen_troublshootingtraceroute_62.49.pdf" rel="nofollow">https:&#x2F;&#x2F;www.nanog.org&#x2F;sites&#x2F;default&#x2F;files&#x2F;tuesday_steenberge...</a></text></comment> | <story><title>Traceroute Lies: A Typical Misinterpretation Of Output</title><url>http://movingpackets.net/2017/10/06/misinterpreting-traceroute/</url></story><parent_chain></parent_chain><comment><author>stephengillie</author><text>Great post. This is a very clear explanation of the routing situation. The last image is especially good.<p>What&#x27;s needed is some kind of L2 Traceroute. It&#x27;s maddening that an increasingly common piece of routing infrastructure is invisible to almost all common troubleshooting tools.<p>Edit: Cisco has one for their routers [0]. Since each hop would have to be traced locally, an L2 Trace would require orchestrating against all hardware devices in the route which introduces legal complications. A new discovery protocol might be needed.<p>[0] <a href="https:&#x2F;&#x2F;www.cisco.com&#x2F;c&#x2F;en&#x2F;us&#x2F;td&#x2F;docs&#x2F;switches&#x2F;lan&#x2F;catalyst6500&#x2F;ios&#x2F;12-2SXF&#x2F;native&#x2F;configuration&#x2F;guide&#x2F;swcg&#x2F;l2trace.html" rel="nofollow">https:&#x2F;&#x2F;www.cisco.com&#x2F;c&#x2F;en&#x2F;us&#x2F;td&#x2F;docs&#x2F;switches&#x2F;lan&#x2F;catalyst6...</a></text></comment> |
30,999,688 | 30,999,819 | 1 | 2 | 30,997,822 | train | <story><title>Why the Gov.uk Design System team changed the input type for numbers (2020)</title><url>https://technology.blog.gov.uk/2020/02/24/why-the-gov-uk-design-system-team-changed-the-input-type-for-numbers/</url></story><parent_chain></parent_chain><comment><author>zxcvgm</author><text>The article shows an example of a credit card field being a &quot;number&quot;. Having made several online purchases, I realized I&#x27;m now frustrated by a CC number field that doesn&#x27;t allow any spaces or dashes, or doesn&#x27;t format it visually this way for you. They should just allow dashes&#x2F;spaces then strip it using JS or at the backend.<p>There is a reason that the number printed on the credit card is grouped into 4 digits, and I believe that it makes human parsing easier. When I submit the form and it says &quot;invalid card number&quot;, trying to figure out which digit I mistyped into the form while scanning that long string of digits with my eyes, gazing at the card and back at the screen is just stupid.</text></comment> | <story><title>Why the Gov.uk Design System team changed the input type for numbers (2020)</title><url>https://technology.blog.gov.uk/2020/02/24/why-the-gov-uk-design-system-team-changed-the-input-type-for-numbers/</url></story><parent_chain></parent_chain><comment><author>Lior539</author><text>On a side note, the Gov.UK site is one of the best sites Ive come across, especially for a government. It&#x27;s incredibly simple and easy to navigate. It&#x27;s easy to find any information you&#x27;re looking for and all information is explained in very clear and simple english (unlike many other government sites, which are convoluted and fill of jargon).<p>IMO this is the gold standard for government websites</text></comment> |
34,909,431 | 34,909,368 | 1 | 2 | 34,909,218 | train | <story><title>Valve bans 40k Dota 2 accounts using honeypot patch</title><url>https://www.dota2.com/newsentry/3677788723152833273</url></story><parent_chain><item><author>4gotunameagain</author><text>&gt; This patch created a honeypot: a section of data inside the game client that would never be read during normal gameplay, but that could
be read by these exploits. Each of the accounts banned today read from this &quot;secret&quot; area in the client, giving us extremely high confidence that every ban was well-deserved.<p>Any speculation as to how this worked on a lower level ?</text></item></parent_chain><comment><author>HHad3</author><text>(Wrote anti-cheat software in the past.)<p>There are multiple ways to detect this. Hardware breakpoints were already mentioned, but they only work per thread, so if one is sniffing on your memory from another process or the kernel then these won&#x27;t help.<p>The most stealthy and evil way I found was to allocate a page but never actually use it.<p>Windows lazily allocates physical memory for fresh memory pages when they are first used.<p>The detection is to periodically poll the page map from your process and check your canary pages via NtQueryVirtualMemory. If your unused page suddenly is backed by some physical memory then something happened to read from it! Bonus-points for putting such canary pages into places previously used for real game data.<p>This method is not foolproof: Anti-virus programs can read memory of all programs (but don&#x27;t, Overwatch e.g. does not like this and crashes randomly due to this exact protection method). A bug in the program could also read from the page accidentally (e.g. out-of-bounds array read). But it&#x27;s a &#x2F;very&#x2F; good indicator that something is wrong when other cheat detection mechanisms also trigger.<p>Once you know how this works it&#x27;s pretty easy to defeat unfortunately: Read the page map first, then avoid reading pages that have no backing physical memory, because those contain no useful data at best and are canary pages at worst.</text></comment> | <story><title>Valve bans 40k Dota 2 accounts using honeypot patch</title><url>https://www.dota2.com/newsentry/3677788723152833273</url></story><parent_chain><item><author>4gotunameagain</author><text>&gt; This patch created a honeypot: a section of data inside the game client that would never be read during normal gameplay, but that could
be read by these exploits. Each of the accounts banned today read from this &quot;secret&quot; area in the client, giving us extremely high confidence that every ban was well-deserved.<p>Any speculation as to how this worked on a lower level ?</text></item></parent_chain><comment><author>tobyhinloopen</author><text>I imagined the secret area contained fake details about the game, like adding an invisible fake street to a map. If the client refers to the fake street or any location within it, you can be certain the details about that fake street were obtained using cheats.<p>This trick is used to catch cheaters on minecraft, by spawning in fake diamond blocks that would only be visible to specific cheats (xray). If a user suddenly were to dig to these blocks, you can be reasonably certain there&#x27;s something fishy going on.<p>Other way to think about it, is adding an invisible field to a contact form that is only hidden through CSS</text></comment> |
34,256,158 | 34,247,490 | 1 | 3 | 34,242,513 | train | <story><title>Fun, danger, and 70s airplane toys</title><url>https://whyisthisinteresting.substack.com/p/the-worlds-most-dangerous-toy-edition</url></story><parent_chain><item><author>greenbit</author><text>Those sure were different times. I recall in the mid 1970s, as a kid no less, being able to go into a pharmacy and buy sulfur or KNO3 w&#x2F;o any trouble at all. However it wasn&#x27;t more than a couple years later, when a request for phosphorus was met with an icy &quot;do I need to call your mother&quot; stare, that my budding career as a chemist came to an end. Besides, the Radio Shack across the street had this <i>computer</i> set up for customers to play with..</text></item><item><author>tragomaskhalos</author><text>The 70s really were another country - see also: chemistry sets. These are pale and anodyne things now with a mere handful of bland household-level chemicals - assuming you can even find one in a toy shop at all. But as a lad these were both readily available and full of dozens of intriguing substances that would send a modern health and safety wonk into apoplexy. Who among us did not incinerate all of the supplied magnesium in a short series of pyrotechnic orgies? Merit was the go-to brand in the UK, but I also had a set from an American company that contained, among other exotica, potassium ferrocyanide. This is decidedly non-lethal but the very name never failed to send a poisoner&#x27;s frisson through my teenage brain.</text></item></parent_chain><comment><author>__MatrixMan__</author><text>My friends and I found documents authored in the 70&#x27;s and went around the 90&#x27;s trying to buy saltpeter--whatever that is. Luckily time had changed &quot;Do I need to call your mother?&quot; into &quot;What the hell is that?&quot; and our mothers were never called.<p>We eventually gave up and graduated to shoplifting model rocket engines, which we powdered with vice grips.</text></comment> | <story><title>Fun, danger, and 70s airplane toys</title><url>https://whyisthisinteresting.substack.com/p/the-worlds-most-dangerous-toy-edition</url></story><parent_chain><item><author>greenbit</author><text>Those sure were different times. I recall in the mid 1970s, as a kid no less, being able to go into a pharmacy and buy sulfur or KNO3 w&#x2F;o any trouble at all. However it wasn&#x27;t more than a couple years later, when a request for phosphorus was met with an icy &quot;do I need to call your mother&quot; stare, that my budding career as a chemist came to an end. Besides, the Radio Shack across the street had this <i>computer</i> set up for customers to play with..</text></item><item><author>tragomaskhalos</author><text>The 70s really were another country - see also: chemistry sets. These are pale and anodyne things now with a mere handful of bland household-level chemicals - assuming you can even find one in a toy shop at all. But as a lad these were both readily available and full of dozens of intriguing substances that would send a modern health and safety wonk into apoplexy. Who among us did not incinerate all of the supplied magnesium in a short series of pyrotechnic orgies? Merit was the go-to brand in the UK, but I also had a set from an American company that contained, among other exotica, potassium ferrocyanide. This is decidedly non-lethal but the very name never failed to send a poisoner&#x27;s frisson through my teenage brain.</text></item></parent_chain><comment><author>denton-scratch</author><text>Sulphur? My local hardware store sells flours of sulphur for gardeners. It&#x27;s used for acidulating soil, and for combatting some kinds of fungus. I don&#x27;t know why anyone would want to regulate the sale of elemental sulphur; it&#x27;s not toxic, caustic or explosive. It&#x27;s less flammable than a piece of wood.</text></comment> |
34,672,041 | 34,671,797 | 1 | 2 | 34,668,098 | train | <story><title>The cult of conformity in Silicon Valley [video]</title><url>https://www.youtube.com/watch?v=ia7IKW0yuG0</url></story><parent_chain><item><author>the-grump</author><text>Plus making money is the whole point of creating a company.<p>There are many weirdos (I mean that as a positive thing) building things like popcorn time and its successors, creating models for vrChat, modding games, building rockets, automating their homes with ESP Home&#x2F;Tasmota, using esoteric languages to solve solved problems, playing with ML models, etc.<p>They don&#x27;t need to come to YC.<p>Like it or not, status follows money, and YC has proven itself to be an effective step to a successful exit. Seekers of money and status (what the discussion refers to as conformists) will find you if you&#x27;re at YC. Weirdos are weirded out by you.</text></item><item><author>throwaway13337</author><text>The answer to the question of &#x27;where the non-conformist tech nerds hang out&#x27; is almost too obvious.<p>It&#x27;s where the money isn&#x27;t.<p>There&#x27;s a lot of cool stuff that isn&#x27;t obviously a path to money. The blender community is full of it, for instance.<p>YC isn&#x27;t a part of that because YC is primarily concerned with making money.<p>This isn&#x27;t a very satisfying answer because it does not lead to investment and money but that&#x27;s kinda the point.</text></item></parent_chain><comment><author>hinkley</author><text>&gt; Plus making money is the whole point of creating a company.<p>It really isn’t. There’s lots of other reasons to make a company, and making money is the means, not the ends.<p>Money isn’t even the point of money. You have a whole life of misery ahead of you if you don’t figure that out and figure it out soon.</text></comment> | <story><title>The cult of conformity in Silicon Valley [video]</title><url>https://www.youtube.com/watch?v=ia7IKW0yuG0</url></story><parent_chain><item><author>the-grump</author><text>Plus making money is the whole point of creating a company.<p>There are many weirdos (I mean that as a positive thing) building things like popcorn time and its successors, creating models for vrChat, modding games, building rockets, automating their homes with ESP Home&#x2F;Tasmota, using esoteric languages to solve solved problems, playing with ML models, etc.<p>They don&#x27;t need to come to YC.<p>Like it or not, status follows money, and YC has proven itself to be an effective step to a successful exit. Seekers of money and status (what the discussion refers to as conformists) will find you if you&#x27;re at YC. Weirdos are weirded out by you.</text></item><item><author>throwaway13337</author><text>The answer to the question of &#x27;where the non-conformist tech nerds hang out&#x27; is almost too obvious.<p>It&#x27;s where the money isn&#x27;t.<p>There&#x27;s a lot of cool stuff that isn&#x27;t obviously a path to money. The blender community is full of it, for instance.<p>YC isn&#x27;t a part of that because YC is primarily concerned with making money.<p>This isn&#x27;t a very satisfying answer because it does not lead to investment and money but that&#x27;s kinda the point.</text></item></parent_chain><comment><author>throwaway13337</author><text>I agree.<p>The tech nerds were a great investment recently and so people are trying to spot the real ones in a sea of fakes now. The investors think that spotting the real ones will lead to more of the same.<p>Maybe that was a moment in time.<p>Another way to to look at it is through value capture. The things you listed often create a lot of value for the community they&#x27;re a part of or for humanity as a whole. But these things do not generate as much value to the creators. The creators are unable to capture the value they created but do it anyway.<p>The last decade can be seen through the lens of tech companies (mostly big ones) capturing the overall value of the tech created at the expense of the communities it once subsidized.<p>Value capture isn&#x27;t bad in itself but the immense focus on it kills a lot of the utility of the thing created. More loose forms of value capture created the tech revolution that were then monetized often by a separate group.<p>The cynically monetized tech will hopefully be outcompeted by the looser forms due to increased utility inherent in its looseness as happened previously.</text></comment> |
13,897,789 | 13,897,617 | 1 | 2 | 13,897,354 | train | <story><title>Wages rise on California farms, Americans still don’t want the job</title><url>http://www.latimes.com/projects/la-fi-farms-immigration</url></story><parent_chain><item><author>greedo</author><text>When I was younger, I worked at a McDonalds in SoCal. Almost all the employees were white teenagers. The managers were white as well. We didn&#x27;t make much, just a bit above minimum wage, but we were all mostly high-school students or college students working in the summer to pay tuition.<p>This went on until around 1984 or so, when it became much harder to hire this demographic. It wasn&#x27;t as cool to work at fast food, and the area was becoming more affluent.<p>Fast forward five years, and 99% of the staff was now Hispanic, including several illegal immigrants. The restaurant had to do what it could to make money and stay in biz.<p>I don&#x27;t know how high wages would have to be to attract the previous demographic to that type of work. The area is far more affluent than when I was growing up, and house prices start at over $700K and go higher easily.<p>I do think something is missing though when kids don&#x27;t learn what it&#x27;s like to hold a retail type job dealing with the public. You learn hard work, humility, and often an appreciation for higher education.</text></item></parent_chain><comment><author>diogenescynic</author><text>There are plenty of white teenagers who work at every In-N-Out I&#x27;ve ever been to--because they pay better. Otherwise those kids, in nicer areas like you point to, have better alternatives for minimum wage like retail. The reason the jobs you describe are being replaced by immigrants is because the wages have been stagnant or not kept up with inflation. Unskilled immigrants take labor jobs that Americans aren&#x27;t really willing to do, like being a janitor or emptying septic tanks or pouring concrete in Bakersfield.</text></comment> | <story><title>Wages rise on California farms, Americans still don’t want the job</title><url>http://www.latimes.com/projects/la-fi-farms-immigration</url></story><parent_chain><item><author>greedo</author><text>When I was younger, I worked at a McDonalds in SoCal. Almost all the employees were white teenagers. The managers were white as well. We didn&#x27;t make much, just a bit above minimum wage, but we were all mostly high-school students or college students working in the summer to pay tuition.<p>This went on until around 1984 or so, when it became much harder to hire this demographic. It wasn&#x27;t as cool to work at fast food, and the area was becoming more affluent.<p>Fast forward five years, and 99% of the staff was now Hispanic, including several illegal immigrants. The restaurant had to do what it could to make money and stay in biz.<p>I don&#x27;t know how high wages would have to be to attract the previous demographic to that type of work. The area is far more affluent than when I was growing up, and house prices start at over $700K and go higher easily.<p>I do think something is missing though when kids don&#x27;t learn what it&#x27;s like to hold a retail type job dealing with the public. You learn hard work, humility, and often an appreciation for higher education.</text></item></parent_chain><comment><author>CalChris</author><text>Minimum wage in that era had much stronger purchasing power. 1980 saw its decline.<p><a href="https:&#x2F;&#x2F;oregonstate.edu&#x2F;instruct&#x2F;anth484&#x2F;minwage.html" rel="nofollow">https:&#x2F;&#x2F;oregonstate.edu&#x2F;instruct&#x2F;anth484&#x2F;minwage.html</a></text></comment> |
25,412,598 | 25,412,437 | 1 | 2 | 25,411,799 | train | <story><title>Tesla's market cap now accounts for roughly 1/3rd of the global automaker market</title><url>https://datamentary.net/psa-tesla-may-soon-be-as-big-as-all-other-automakers-combined/</url></story><parent_chain></parent_chain><comment><author>RivieraKid</author><text>The stock price increased by 15x in 1.5 years on basically no major news. If you don&#x27;t include profits from regulatory credits, they&#x27;ve lost over $700M so far this year. Government money is not scalable or sustainable, so this an important indicator of how their finances are doing.<p>The intuition is that Tesla cars are like iPhones. I think it&#x27;s wrong. This is a low-margin business, where you increasingly compete with <i>all</i> of the goods and services people buy, like housing, education, healthcare. It&#x27;s not a &quot;buy a new phone for Christmas every 2 years&quot; business.<p>People are on the phone all the time, so paying $200 more for an improved experience for several hours per day is justified. But paying $5k or $10k more for an improved experience for 1 or 2 hours per day? If you&#x27;re rich, maybe. If not, why not move closer to your work instead, so you don&#x27;t have to use the car? Why not take a longer vacation, or eat out every day, or retire earlier, or pay for your kid&#x27;s college education?</text></comment> | <story><title>Tesla's market cap now accounts for roughly 1/3rd of the global automaker market</title><url>https://datamentary.net/psa-tesla-may-soon-be-as-big-as-all-other-automakers-combined/</url></story><parent_chain></parent_chain><comment><author>Gustomaximus</author><text>I assume the high value is more about Tesla being more than a car company.<p>1) If they win the self driving race that will be incredible value beyond just manufacturing cars.<p>2) Battery manufacturing in general is huge on its own.<p>3) The roof top combined with domestic battery side is potentially significant in replacing (full or part?) domestic power companies<p>4) Insurance - Musk said this could grow into 30-40% of their business<p>5) Super charger network gives them a first advantage to replace petrol stations to a degree.<p>6) Elon factor of what&#x27;s next.<p>And dont get me wrong, I do feel its gone beyond reasonable value, but there is more than a car company there.</text></comment> |
18,356,750 | 18,356,934 | 1 | 2 | 18,356,032 | train | <story><title>In Medieval Europe, No Outfit Was Complete Without a Personal Eating Knife</title><url>https://www.atlasobscura.com/articles/medieval-knives</url></story><parent_chain></parent_chain><comment><author>beat</author><text>Steven Pinker talks about this in his book <i>Better Angels of our Nature</i>. Ending the habit of personal eating knives was part of the &quot;civilizing process&quot; that drastically reduced the murder rate in Europe, because people stopped walking around armed quite so much.</text></comment> | <story><title>In Medieval Europe, No Outfit Was Complete Without a Personal Eating Knife</title><url>https://www.atlasobscura.com/articles/medieval-knives</url></story><parent_chain></parent_chain><comment><author>thrower123</author><text>My redneck is showing, but I feel a little naked if I go out the door without either my Leatherman or my Mercator in my pocket. I have even been known to pull it out and use it as an eating knife from time to time...</text></comment> |
21,529,689 | 21,529,333 | 1 | 2 | 21,523,780 | train | <story><title>16-inch MacBook Pro</title><url>https://www.apple.com/newsroom/2019/11/apple-introduces-16-inch-macbook-pro-the-worlds-best-pro-notebook/</url></story><parent_chain><item><author>wwweston</author><text>It turns out that people who buy laptops -- a mobile-ish form factor differentiated from a tablet by its keyboard -- might <i>really really care about keyboards</i> as the main interface between user and device.<p>I&#x27;d concluded that Apple didn&#x27;t really think much of laptops anymore, and had simply moved on to caring more about other form factors: it seemed a logical conclusion if one assumed that people at Apple were in fact competent.<p>This shows some real care regarding laptops as a form factor and puts them back in the running for a lot of buyers, including me. But there&#x27;s still one major issue that I don&#x27;t see people talking much about -- the way that Apple&#x27;s decisions regarding storage (namely soldering it to the board AND making it so that there&#x27;s no way to access it in the event of a logic board failure) increases consumer risk as well as decreasing consumer choice:<p><a href="https:&#x2F;&#x2F;www.notebookcheck.net&#x2F;Apple-removes-the-Customer-Data-Migration-Tool-connector-in-the-the-2018-MacBook-Pro-with-Touch-Bar.318186.0.html" rel="nofollow">https:&#x2F;&#x2F;www.notebookcheck.net&#x2F;Apple-removes-the-Customer-Dat...</a><p><i>It increases risk of data loss</i>. That&#x27;s a choice that impacts the day-to-day experience much less than the keyboard, which explains why the keyboard has gotten much more attention, and it really is nice that a company arguably built on attention to experience returned to that aspect of it. But this kind of choice makes a huge difference in a moment of failure, and it&#x27;s at least equally user-hostile, especially in a product bearing the name &quot;pro&quot; where data recovery can be a matter of business continuity.<p>I suppose that one can argue a responsible professional will be using network and external backups (and of course all responsible professionals worth considering or selling anything to <i>will</i> do this, right?), and so this isn&#x27;t necessary, and Apple&#x27;s thing (wise or unwise) is that they frequently reconsider and eliminate things that aren&#x27;t crucial. But redundancy in some areas is wise, and I can&#x27;t see what they think eliminating both removability AND emergency direct access when it come to storage actually buys them. Even if one assumes it&#x27;s a lock-in action for service, it makes the actual service more difficult and costly.<p>I&#x27;m liking the keyboard correction. I just bought a 2014 MBP to replace an older failing MBP, so I&#x27;m not in the market for something else for a year or two, but when that comes up, I&#x27;ll be seriously looking at the 16&quot; as an option. And this will be what I&#x27;m thinking about.</text></item><item><author>throwanem</author><text>I&#x27;m astonished and pleased to see they walked back the two worst things about the original Touch Bar MBPs - the lack of a physical Escape key, and the full-size left and right arrow keys.<p>The lack of physical function keys remains regrettable, and the Touch Bar is still no worthy substitute, but perhaps this is a sign that Apple is finally interested in listening to feedback from its long-term customer base, even if that feedback conflicts with the design team&#x27;s desires.</text></item></parent_chain><comment><author>dkonofalski</author><text>&gt;It increases risk of data loss.<p>I realize that this is idealistic of me but <i>data loss should never be an issue</i>. This is 2019 and backups have been drilled into everyone&#x27;s heads for years and years and years. You can still access the drives in these via Target Disk mode (and I&#x27;ve had to do a few recoveries through that so I know it works) and it&#x27;s likely that the pros outweigh the cons.</text></comment> | <story><title>16-inch MacBook Pro</title><url>https://www.apple.com/newsroom/2019/11/apple-introduces-16-inch-macbook-pro-the-worlds-best-pro-notebook/</url></story><parent_chain><item><author>wwweston</author><text>It turns out that people who buy laptops -- a mobile-ish form factor differentiated from a tablet by its keyboard -- might <i>really really care about keyboards</i> as the main interface between user and device.<p>I&#x27;d concluded that Apple didn&#x27;t really think much of laptops anymore, and had simply moved on to caring more about other form factors: it seemed a logical conclusion if one assumed that people at Apple were in fact competent.<p>This shows some real care regarding laptops as a form factor and puts them back in the running for a lot of buyers, including me. But there&#x27;s still one major issue that I don&#x27;t see people talking much about -- the way that Apple&#x27;s decisions regarding storage (namely soldering it to the board AND making it so that there&#x27;s no way to access it in the event of a logic board failure) increases consumer risk as well as decreasing consumer choice:<p><a href="https:&#x2F;&#x2F;www.notebookcheck.net&#x2F;Apple-removes-the-Customer-Data-Migration-Tool-connector-in-the-the-2018-MacBook-Pro-with-Touch-Bar.318186.0.html" rel="nofollow">https:&#x2F;&#x2F;www.notebookcheck.net&#x2F;Apple-removes-the-Customer-Dat...</a><p><i>It increases risk of data loss</i>. That&#x27;s a choice that impacts the day-to-day experience much less than the keyboard, which explains why the keyboard has gotten much more attention, and it really is nice that a company arguably built on attention to experience returned to that aspect of it. But this kind of choice makes a huge difference in a moment of failure, and it&#x27;s at least equally user-hostile, especially in a product bearing the name &quot;pro&quot; where data recovery can be a matter of business continuity.<p>I suppose that one can argue a responsible professional will be using network and external backups (and of course all responsible professionals worth considering or selling anything to <i>will</i> do this, right?), and so this isn&#x27;t necessary, and Apple&#x27;s thing (wise or unwise) is that they frequently reconsider and eliminate things that aren&#x27;t crucial. But redundancy in some areas is wise, and I can&#x27;t see what they think eliminating both removability AND emergency direct access when it come to storage actually buys them. Even if one assumes it&#x27;s a lock-in action for service, it makes the actual service more difficult and costly.<p>I&#x27;m liking the keyboard correction. I just bought a 2014 MBP to replace an older failing MBP, so I&#x27;m not in the market for something else for a year or two, but when that comes up, I&#x27;ll be seriously looking at the 16&quot; as an option. And this will be what I&#x27;m thinking about.</text></item><item><author>throwanem</author><text>I&#x27;m astonished and pleased to see they walked back the two worst things about the original Touch Bar MBPs - the lack of a physical Escape key, and the full-size left and right arrow keys.<p>The lack of physical function keys remains regrettable, and the Touch Bar is still no worthy substitute, but perhaps this is a sign that Apple is finally interested in listening to feedback from its long-term customer base, even if that feedback conflicts with the design team&#x27;s desires.</text></item></parent_chain><comment><author>nextos</author><text>The paradoxical thing with recent Apple laptop keyboards is that their Magic Keyboard 2 is pretty darn good. I haven&#x27;t bought any Apple products for more than a decade, but I keep recommending and buying their Magic Keyboard 2 for Linux workstations.<p>It has a very good mechanical feel, and it reduces latency perhaps due to shallow action point and&#x2F;or firmware tweaks [1]. Also, it&#x27;s really easy to source ANSI layouts outside the US.<p>I do in fact prefer it to my blue ALPS keyboard for long typing sessions.<p>[1] <a href="https:&#x2F;&#x2F;danluu.com&#x2F;keyboard-latency&#x2F;" rel="nofollow">https:&#x2F;&#x2F;danluu.com&#x2F;keyboard-latency&#x2F;</a></text></comment> |
22,191,838 | 22,191,837 | 1 | 2 | 22,191,436 | train | <story><title>The spine of San Francisco is now car-free</title><url>https://www.citylab.com/transportation/2020/01/market-street-car-free-san-francisco-bike-lanes-transit/605674/</url></story><parent_chain><item><author>cletus</author><text>As someone who doesn&#x27;t live in SF but has visited many times I&#x27;m not really sure what the issue with Market Street and cars is. It&#x27;s always seemed fine to me. Compare this to say Oxford Street in London (where I lived at the time congestion pricing was first introduced), which was clearly an issue. But sure, I&#x27;m on board.<p>Although I&#x27;m not sure why taxis need an exemption. I guess it&#x27;s another way to prop up a dying industry. Having caught cabs in SF before, I never will again, even if they can drive down Market Street.<p>The article also mentions 14th Street in NYC, which I live near and am very familiar with. This has been a contentious issue. Originally the L was planned to shutdown for 15-18 months and there was a plan to make 14th street sort of car free. I say sort of because cars were allowed to turn onto 14th Street but had to make the next right turn. This plan is now moot.<p>But a big concern was that it would just push car traffic to 13th and 15th streets, which are &quot;residential&quot;.<p>I&#x27;m honestly not sure why 14th Street needs a dedicated busway as it does have the L. Compare this to say 23rd and 34th street that have no cross Subway (42nd does).<p>But the elephant in the room here is that you can still park on 14th street. If you&#x27;re serious about increasing the traffic flow (of buses or otherwise) the obvious thing to do is free up 2 lanes by getting rid of the parking. But weirdly free street parking is sacrosanct in NYC politics. Why people who live in downtown Manhattan need this huge public subsidy is beyond me.</text></item></parent_chain><comment><author>addicted</author><text>Maybe because people believe all this valuable public space can be better used than as a Thruway for ferrying individuals in massive steel cages from one part of town to another.<p>Re: the 14th street busway, The “fears” about 13th and 15th street turned out to be unfounded. In the meanwhile, thousands of people who used the bus are benefitting with much faster and more reliable service (to the point that buses on 14th street are now waiting at stops because they are arriving too fast).<p>Car traffic has basically been unaffected.<p>Pedestrians find it much better and safer.<p>People who live and work there have it much better with the massively reduced air and noise pollution.<p>And you’re right that this should be replicated throughout the city. If it works on 14th street, which as you rightly point out already has a train, it will be a much bigger success on other streets.<p>Similarly in SF besides the quality of life improvements you have reclaimed valuable space that was being given away for no good reason.</text></comment> | <story><title>The spine of San Francisco is now car-free</title><url>https://www.citylab.com/transportation/2020/01/market-street-car-free-san-francisco-bike-lanes-transit/605674/</url></story><parent_chain><item><author>cletus</author><text>As someone who doesn&#x27;t live in SF but has visited many times I&#x27;m not really sure what the issue with Market Street and cars is. It&#x27;s always seemed fine to me. Compare this to say Oxford Street in London (where I lived at the time congestion pricing was first introduced), which was clearly an issue. But sure, I&#x27;m on board.<p>Although I&#x27;m not sure why taxis need an exemption. I guess it&#x27;s another way to prop up a dying industry. Having caught cabs in SF before, I never will again, even if they can drive down Market Street.<p>The article also mentions 14th Street in NYC, which I live near and am very familiar with. This has been a contentious issue. Originally the L was planned to shutdown for 15-18 months and there was a plan to make 14th street sort of car free. I say sort of because cars were allowed to turn onto 14th Street but had to make the next right turn. This plan is now moot.<p>But a big concern was that it would just push car traffic to 13th and 15th streets, which are &quot;residential&quot;.<p>I&#x27;m honestly not sure why 14th Street needs a dedicated busway as it does have the L. Compare this to say 23rd and 34th street that have no cross Subway (42nd does).<p>But the elephant in the room here is that you can still park on 14th street. If you&#x27;re serious about increasing the traffic flow (of buses or otherwise) the obvious thing to do is free up 2 lanes by getting rid of the parking. But weirdly free street parking is sacrosanct in NYC politics. Why people who live in downtown Manhattan need this huge public subsidy is beyond me.</text></item></parent_chain><comment><author>odiroot</author><text>&gt; Although I&#x27;m not sure why taxis need an exemption<p>I agree. Taxis are usually one of the most dangerous and impatient drivers in the city.</text></comment> |
6,439,385 | 6,438,648 | 1 | 2 | 6,438,326 | train | <story><title>Who rooted kernel.org servers two years ago?</title><url>http://arstechnica.com/security/2013/09/who-rooted-kernel-org-servers-two-years-ago-how-did-it-happen-and-why/</url></story><parent_chain></parent_chain><comment><author>idupree</author><text>From the 2011 kernel summit, &quot;The attack turns out to have been part of a widespread credential-stealing network that has been operating for some years now; it is clear that the site had been owned by this network for some time before it was discovered. What also seems to be clear is that this was not a targeted attack; kernel.org was just another on a long list of broken machines.&quot;<p>- Jon Corbet reporting on a talk by H. Peter Anvin,
<a href="https://lwn.net/Articles/464233/" rel="nofollow">https:&#x2F;&#x2F;lwn.net&#x2F;Articles&#x2F;464233&#x2F;</a></text></comment> | <story><title>Who rooted kernel.org servers two years ago?</title><url>http://arstechnica.com/security/2013/09/who-rooted-kernel-org-servers-two-years-ago-how-did-it-happen-and-why/</url></story><parent_chain></parent_chain><comment><author>nlh</author><text>So let&#x27;s speculate about what the article almost-but-doesn&#x27;t-quite propose:<p>The NSA, or related parties, was responsible for the breach. There was an investigation and postmortem, but because of an NSL or other gag-type order, they couldn&#x27;t accurately publish what they discovered. So they figured that not releasing a report was better than releasing a report that either intentionally misled or pretended not to have figured out what happened.<p>I know, this is a pretty big leap. But regardless -- what does it mean? What are the ramifications if this <i>is</i> what happened?</text></comment> |
37,922,803 | 37,922,621 | 1 | 3 | 37,921,832 | train | <story><title>"A Young Lady's Illustrated Primer" Simulated by GPT-4</title><url>https://www.andrealyip.com/a-young-ladys-illustrated-primer</url></story><parent_chain><item><author>cl42</author><text>Do you think that&#x27;s a Neal Stephenson issue? Don&#x27;t get me wrong, I love his writing, but I found this to be the case with Fall too. I can see it becoming tiring if one is writing 400+ page books.</text></item><item><author>geophile</author><text>I <i>loved</i> Diamond Age. My favorite Stephenson book, by far. But the ending, the resolution of all the action, was such a letdown. Such meh. I find that this is often a problem with cyberpunk.</text></item></parent_chain><comment><author>jjcm</author><text>Definitely a Stephenson issue. It&#x27;s a meme for sure, but there is some truth in it. Nowadays when I re-read any of his old works, I tend to stop after getting about 80% through. That said, I do think that these incredibly complex narratives are extremely hard to wrap up neatly. GRRM has this issue as well.<p>That&#x27;s the problem with letting characters act how they would actually act, and make decisions that make sense for them. Those decisions often don&#x27;t end in a way that&#x27;s concise and brings closure.<p>I think he tried to sidestep this issue quite a bit in Seveneves in a fairly clever way. To me personally (and I know there are others who disagree), the third act felt the weakest. Despite that it did bring closure to the story. There was no finality to the characters themselves - it skipped over all of that, but there was closure to the story.<p>One thing I&#x27;m curious on the other end of the spectrum - who does HN think writes good endings to complex scifi stories?</text></comment> | <story><title>"A Young Lady's Illustrated Primer" Simulated by GPT-4</title><url>https://www.andrealyip.com/a-young-ladys-illustrated-primer</url></story><parent_chain><item><author>cl42</author><text>Do you think that&#x27;s a Neal Stephenson issue? Don&#x27;t get me wrong, I love his writing, but I found this to be the case with Fall too. I can see it becoming tiring if one is writing 400+ page books.</text></item><item><author>geophile</author><text>I <i>loved</i> Diamond Age. My favorite Stephenson book, by far. But the ending, the resolution of all the action, was such a letdown. Such meh. I find that this is often a problem with cyberpunk.</text></item></parent_chain><comment><author>glial</author><text>I think it&#x27;s a well-known Stephenson issue. Here&#x27;s his response when asked:<p><a href="https:&#x2F;&#x2F;www.reddit.com&#x2F;r&#x2F;nealstephenson&#x2F;comments&#x2F;5jjwmq&#x2F;neal_stephensons_response_to_a_question_on_how_he&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.reddit.com&#x2F;r&#x2F;nealstephenson&#x2F;comments&#x2F;5jjwmq&#x2F;neal...</a></text></comment> |
23,222,680 | 23,222,562 | 1 | 3 | 23,222,191 | train | <story><title>America's Growth Ponzi Scheme</title><url>https://www.strongtowns.org/journal/2020/5/14/americas-growth-ponzi-scheme-md2020</url></story><parent_chain><item><author>noad</author><text>The complete failure to imagine an alternative to property&#x2F;sales taxes and development fees during this crisis has been one of the most disappointing failures of politicians everywhere. We keep being told we need to suffer more and more with deeper cuts while living in the wealthiest country that ever existed by a wide margin.<p>This is absurd. There is plenty of money, we could tax something like 5% of stock buybacks and completely rebuild our entire society from the ground up.<p>Instead our leaders just keep telling us to toughen up and get stronger while flying jets overhead in meaningless salutes. They seem to be very bad at their jobs.</text></item></parent_chain><comment><author>Miner49er</author><text>&gt; They seem to be very bad at their jobs.<p>On the contrary, I&#x27;d argue they are mostly good at their jobs.<p>Their job isn&#x27;t to help the average American. Their job is to serve Capital. They get paid by the rich, not by average Americans.<p>They are doing a good job at that. Look at the stock market, it goes up while Main Street is in turmoil.</text></comment> | <story><title>America's Growth Ponzi Scheme</title><url>https://www.strongtowns.org/journal/2020/5/14/americas-growth-ponzi-scheme-md2020</url></story><parent_chain><item><author>noad</author><text>The complete failure to imagine an alternative to property&#x2F;sales taxes and development fees during this crisis has been one of the most disappointing failures of politicians everywhere. We keep being told we need to suffer more and more with deeper cuts while living in the wealthiest country that ever existed by a wide margin.<p>This is absurd. There is plenty of money, we could tax something like 5% of stock buybacks and completely rebuild our entire society from the ground up.<p>Instead our leaders just keep telling us to toughen up and get stronger while flying jets overhead in meaningless salutes. They seem to be very bad at their jobs.</text></item></parent_chain><comment><author>ErikVandeWater</author><text>&gt; we could tax something like 5% of stock buybacks and completely rebuild our entire society from the ground up.<p>Let&#x27;s see a source or even back-of-the napkin calculation on this</text></comment> |
27,845,909 | 27,846,093 | 1 | 3 | 27,845,333 | train | <story><title>SpaceX will soon fire up its Super Heavy booster for the first time</title><url>https://arstechnica.com/science/2021/07/spacex-will-soon-fire-up-its-massive-super-heavy-booster-for-the-first-time/</url></story><parent_chain></parent_chain><comment><author>mabbo</author><text>This will be a monumental accomplishment, when it launches for the first time.<p>4-6 times the payload to LEO as the Space Shuttle, but 100% reusable with the aim of fast turn-around times and minimal refurbishment, at a fraction of the price.<p>Detract from the eccentricity of the company&#x27;s owner all you want, but the engineers making that rocket happen are doing brilliant work, in my book.</text></comment> | <story><title>SpaceX will soon fire up its Super Heavy booster for the first time</title><url>https://arstechnica.com/science/2021/07/spacex-will-soon-fire-up-its-massive-super-heavy-booster-for-the-first-time/</url></story><parent_chain></parent_chain><comment><author>_Microft</author><text>If you are curious about the trajectory that the first orbital launch might follow, have a look at this article:<p><a href="https:&#x2F;&#x2F;spaceflightnow.com&#x2F;2021&#x2F;05&#x2F;13&#x2F;spacex-outlines-plans-for-around-the-world-starship-test-flight&#x2F;" rel="nofollow">https:&#x2F;&#x2F;spaceflightnow.com&#x2F;2021&#x2F;05&#x2F;13&#x2F;spacex-outlines-plans-...</a><p>They are aiming to fly Starship over the Straits of Florida (i.e. between Florida and Cuba) which means it will be low inclination. I assume that this is to avoid overflying inhabited area &#x27;early&#x27; into the flight and especially not for too long, a trajectory bit further to the south would e.g. mean that they had to fly over the full length of Cuba, Haiti and the Dominican Republic. I would expect them to be &quot;out of the woods&quot; already at this point in the flight though. The next critical part would be reentry north-west of Hawaii.</text></comment> |
17,256,557 | 17,256,126 | 1 | 2 | 17,255,490 | train | <story><title>Haxe: Cross-Platform Development's Best-Kept Secret</title><url>https://www.toptal.com/cross-platform/haxe-language-cross-platform</url></story><parent_chain></parent_chain><comment><author>cojo</author><text>We used Haxe for a while at my last company for a cross-platform engine that would actually run well on web (browsers couldn&#x27;t yet handle &quot;real&quot; Unity WebGL builds at that time).<p>While it &quot;worked&quot; and the resulting engine &#x2F; suite of games ended up net profitable, and I&#x27;m a fan of Haxe&#x27;s features as a language (I am really missing the pattern matching and macros in Typescript these days), I must say the build pipeline and available tools for OpenFL &#x2F; Haxe games was lacking at best.<p>On the plus side being able to fork and fix issues we ran into was a game changer over Unity IMO.<p>Not sure if the ecosystem has evolved &#x2F; improved on the build and tooling fronts in the last 18 months since I last interacted with it directly, but that would be the one word of caution I&#x27;d offer to anyone after they read this article. Be prepared to roll up your sleeves and get a little dirtier than usual if you really intend to ship on both web and mobile.</text></comment> | <story><title>Haxe: Cross-Platform Development's Best-Kept Secret</title><url>https://www.toptal.com/cross-platform/haxe-language-cross-platform</url></story><parent_chain></parent_chain><comment><author>dgreensp</author><text>The biggest thing that interests me about Haxe is it is rare to find a high-level language with a sophisticated static type system and familiar syntax. This is why TypeScript is so much beloved, but Haxe has some awesome features TypeScript lacks, like a pattern-matching switch statement (with guards), and array comprehensions.</text></comment> |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.