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
|
|---|---|---|---|---|---|---|---|
8,414,773 | 8,414,529 | 1 | 3 | 8,413,028 | train | <story><title>OpenBSD 5.6: What will be there</title><url>http://www.openbsd.org/56.html</url></story><parent_chain><item><author>chrissnell</author><text>I used to use OpenBSD extensively in my job because of the awesomeness of PF but later moved on to big iron F5 and Cisco gear. In this new age of NSA wiretaps and cloud based services built around advertising and tracking however, OpenBSD feels more relevant than ever. I&#x27;d like to give it a shot as a desktop again.<p>So, who makes a modern laptop with good OpenBSD hardware compatability?</text></item></parent_chain><comment><author>g047f4c3</author><text>It works like a charm on any intel i-series CPU with integrated intel HD graphics and most intel wireless chipsets (excluding the newer AC* versions).<p>I use it exclusively on servers, and on all laptops&#x2F;desktops I use for real work. Its a breath of fresh air! No bloat, no evil, gets the job done - Not to mention some lovely features such as <i>Full</i> (no unencrypted boot slice) disk encryption via softraid, a completely unprivileged X server (with KMS supported GPUs), and a brilliant set of simple and solid daemons included in the base system.<p>The only time I&#x27;ll switch away is to use linux - The two reasons there being 1) High-end Gaming, 2) Virtualization.</text></comment> | <story><title>OpenBSD 5.6: What will be there</title><url>http://www.openbsd.org/56.html</url></story><parent_chain><item><author>chrissnell</author><text>I used to use OpenBSD extensively in my job because of the awesomeness of PF but later moved on to big iron F5 and Cisco gear. In this new age of NSA wiretaps and cloud based services built around advertising and tracking however, OpenBSD feels more relevant than ever. I&#x27;d like to give it a shot as a desktop again.<p>So, who makes a modern laptop with good OpenBSD hardware compatability?</text></item></parent_chain><comment><author>atmosx</author><text>On a laptop I&#x27;go with linux any day. I don&#x27;t feel like any BSD was&#x2F;is intended to be run on laptops, not if you don&#x27;t wanna lose time in extensive configuration to make everything (almost) work.</text></comment> |
40,339,535 | 40,337,958 | 1 | 2 | 40,335,599 | train | <story><title>Yi 1.5</title><url>https://github.com/01-ai/Yi-1.5</url></story><parent_chain><item><author>option</author><text>Try asking their &quot;chat&quot; variants about topics sensetive to CCP, like what has happened on Tiananmen square. Same for Baichan models.<p>What other values and biases have been RLHFed there and for what purpose?</text></item><item><author>gardnr</author><text>Yi is led by Dr. Kai-Fu Lee.<p>They have been releasing a lot of really good models over the last ~6 months. Their previous (1.0?) Yi-34B-Chat model ranks similar to GPT-3.5 on Chatbot Arena. [1] A quantized version of that model can be run on a single consumer video card like the RTX 4090.<p>This new set of models should raise the bar again by adding more options to the open source LLM ecosystem. If you inspect the config.json[2] in the model repo on HuggingFace, you can see that the model architecture is LlamaForCausalLM (the same as Meta&#x27;s Lllama). The difference between the Yi models and a simple fine-tuning is that Yi models have had a different set of data, configuration, and process going back to the pre-training stage.<p>Their models perform well in Chinese and in English.<p>There are a lot of good models coming out of China, some of which are only published to ModelScope. I haven&#x27;t spent much time on ModelScope because I don&#x27;t have a Chinese mobile number to use to create an account. Fortunately, Yi publish to HuggingFace as well.<p>[1] <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;spaces&#x2F;lmsys&#x2F;chatbot-arena-leaderboard" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;spaces&#x2F;lmsys&#x2F;chatbot-arena-leaderboar...</a><p>[2] <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;01-ai&#x2F;Yi-1.5-34B-Chat&#x2F;blob&#x2F;fa695ee438bfcd0ec2b378fa1c7e0dea1b40393e&#x2F;config.json#L3" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;01-ai&#x2F;Yi-1.5-34B-Chat&#x2F;blob&#x2F;fa695ee438...</a></text></item></parent_chain><comment><author>happypumpkin</author><text>USER:<p>What happened at Tienanmen square?<p>yi-34b-chat:<p>Tiananmen Square is a large public square in the heart of Beijing, China. It is named after the Tiananmen (literally &quot;Gate of Heavenly Peace&quot;), which is the gate located to the north of the square and was the main entrance to the Imperial City during the Ming and Qing dynasties.<p>The square is famously known for two significant events in Chinese history:<p><pre><code> The May Fourth Movement (1919):
This was a student-led movement that began on May 4, 1919, in response to the Chinese government&#x27;s handling of the Treaty of Versailles, which granted German concessions in Shandong to Japan rather than returning them to China. The movement sparked a wave of anti-imperialist sentiment and calls for cultural and political reform, and it is considered a key event leading to the birth of Chinese nationalism and the development of the Chinese Communist Party.
The Tiananmen Square Massacre (1989):
This is the event for which Tiananmen Square is most internationally renowned. In the spring of 1989, there were student-led demonstrations in Beijing and other cities across China, calling for political reform and an end to corruption. The protests were initially peaceful, but on June 3 and 4, the Chinese government responded with a military crackdown, opening fire on the protesters and bystanders, killing and injuring thousands. The exact death toll is unknown, but it is estimated to be in the hundreds or even thousands.
</code></pre>
The Tiananmen Square Massacre is a significant event in modern Chinese history and has had a profound impact on the country&#x27;s politics and society. It remains a sensitive topic in China, with government censorship and restrictions on discussing the event.</text></comment> | <story><title>Yi 1.5</title><url>https://github.com/01-ai/Yi-1.5</url></story><parent_chain><item><author>option</author><text>Try asking their &quot;chat&quot; variants about topics sensetive to CCP, like what has happened on Tiananmen square. Same for Baichan models.<p>What other values and biases have been RLHFed there and for what purpose?</text></item><item><author>gardnr</author><text>Yi is led by Dr. Kai-Fu Lee.<p>They have been releasing a lot of really good models over the last ~6 months. Their previous (1.0?) Yi-34B-Chat model ranks similar to GPT-3.5 on Chatbot Arena. [1] A quantized version of that model can be run on a single consumer video card like the RTX 4090.<p>This new set of models should raise the bar again by adding more options to the open source LLM ecosystem. If you inspect the config.json[2] in the model repo on HuggingFace, you can see that the model architecture is LlamaForCausalLM (the same as Meta&#x27;s Lllama). The difference between the Yi models and a simple fine-tuning is that Yi models have had a different set of data, configuration, and process going back to the pre-training stage.<p>Their models perform well in Chinese and in English.<p>There are a lot of good models coming out of China, some of which are only published to ModelScope. I haven&#x27;t spent much time on ModelScope because I don&#x27;t have a Chinese mobile number to use to create an account. Fortunately, Yi publish to HuggingFace as well.<p>[1] <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;spaces&#x2F;lmsys&#x2F;chatbot-arena-leaderboard" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;spaces&#x2F;lmsys&#x2F;chatbot-arena-leaderboar...</a><p>[2] <a href="https:&#x2F;&#x2F;huggingface.co&#x2F;01-ai&#x2F;Yi-1.5-34B-Chat&#x2F;blob&#x2F;fa695ee438bfcd0ec2b378fa1c7e0dea1b40393e&#x2F;config.json#L3" rel="nofollow">https:&#x2F;&#x2F;huggingface.co&#x2F;01-ai&#x2F;Yi-1.5-34B-Chat&#x2F;blob&#x2F;fa695ee438...</a></text></item></parent_chain><comment><author>polygamous_bat</author><text>This is an interesting question. Is there a “controversy-benchmark” perhaps, to measure this?</text></comment> |
20,039,651 | 20,038,297 | 1 | 3 | 20,035,983 | train | <story><title>Police in Canada Are Tracking People’s ‘Negative’ Behavior in a ‘Risk’ Database</title><url>https://www.vice.com/en_us/article/kzdp5v/police-in-canada-are-tracking-peoples-negative-behavior-in-a-risk-database</url></story><parent_chain><item><author>emptybits</author><text>FTA: The Ontario Provincial Police say, “We can knock on someone’s door and say, ‘We’re so worried about you, can we come in and chat?’”<p>Yikes. I understand the positive spin is the police care about the wellbeing of at-risk people with these visits. But wouldn&#x27;t it also be true that anything and everything the police observe and believe as a result of such a visit could also be used against the resident or others in the home?</text></item></parent_chain><comment><author>cabaalis</author><text>I recommend everyone watch this video. It&#x27;s geared towards lawyers. If the police are asking questions with any level of suspicion at all, don&#x27;t talk to them. Even if you do not lie, and are innocent, the things you say can still be used against you.<p>Summarizing:<p>1. There is no way it can help.<p>2. If your client is guilty (or even innocent), they might admit guilt with nothing in return.<p>3. If your client is innocent, they can still make some small mistake or tiny mistruth that can be used to convict by seeding doubt.<p>4. If your client is innocent, and does not make any small mistake or tiny mistruth, what is said can still be used in court to convict.<p>5. If your client is innocent, and tells the police absolutely nothing incriminating at all, the police can still mis-remember the conversation and result in a conviction.<p>6. If your client is innocent, and tells the police absolutely nothing incriminating at all, and the clients statements are videotaped so it cannot be mischaracterized, the police can still augment the conversation from their personal knowledge and result in a conviction.<p>There&#x27;s more, it goes on and on and on. Don&#x27;t talk to police if you are being questioned about something, whether you did it or not.<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=d-7o9xYp7eE" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=d-7o9xYp7eE</a></text></comment> | <story><title>Police in Canada Are Tracking People’s ‘Negative’ Behavior in a ‘Risk’ Database</title><url>https://www.vice.com/en_us/article/kzdp5v/police-in-canada-are-tracking-peoples-negative-behavior-in-a-risk-database</url></story><parent_chain><item><author>emptybits</author><text>FTA: The Ontario Provincial Police say, “We can knock on someone’s door and say, ‘We’re so worried about you, can we come in and chat?’”<p>Yikes. I understand the positive spin is the police care about the wellbeing of at-risk people with these visits. But wouldn&#x27;t it also be true that anything and everything the police observe and believe as a result of such a visit could also be used against the resident or others in the home?</text></item></parent_chain><comment><author>mattlondon</author><text>What I find weird about all of this is that people actually answer their door to unexpected &amp; unknown visitors?! Do you also answer your phone to unexpected &amp; unknown callers?!<p>My rule of thumb built up over years of annoyance &amp; bullshit is: if you don&#x27;t know who it is, or aren&#x27;t expecting anything, ignore it; 99.9% of the time someone unexpected&#x2F;unknown on the phone or at your door are just going to be wasting your time and attention. (trying to sell you something&#x2F;con you&#x2F;religious recruitment&#x2F;generally be weird&#x2F;mad etc)</text></comment> |
1,927,280 | 1,927,028 | 1 | 2 | 1,926,515 | train | <story><title>Prof Gives Lecture to Prove He Knows Students Cheated; Over 200 Students Confess</title><url>http://thoughtcatalog.com/2010/over-200-students-admit-to-cheating-on-test-after-professor-dedicates-lecture-to-proving-he-knows-they-cheated/</url></story><parent_chain><item><author>psyklic</author><text>Yes, it is really cheating. A publisher's test bank is very clearly not made for students to study from. The publishers warn students not to read them and try to make them inaccessible. In my experience, the professor almost always tells students what they can use to study from. Whether students can use past exams is almost always clarified - I wonder if a student asked in this case.<p>However, here the instructor has no way of knowing who cheated. He clearly made a mistake, knowing that using a test bank would make it easy to cheat. So, he should either let all the grades stand or he should point out the statistical anomaly and just make everyone take a new exam, which he did. I can't possibly see how students who didn't confess will be found out, especially if the exam was multiple choice!</text></item><item><author>gojomo</author><text>But was it really cheating? Some students have pointed out that the professor said repeatedly that he composed the tests himself. Given that, then plausibly, using example tests from other sources would be a legitimate preparation method. (For example, the SAT doesn't penalize people for reviewing lots of practice tests, because it's assumed the actual questions during a real test will be novel.)<p>See:<p><a href="http://www.techdirt.com/articles/20101118/21485811928/200-students-admit-to-cheating-exam-bigger-question-is-if-it-was-really-cheating-studying.shtml" rel="nofollow">http://www.techdirt.com/articles/20101118/21485811928/200-st...</a><p>Now, it was probably common knowledge from prior semesters that this professor's exams were from the standard test bank. So those reviewing test bank questions may not have had pure motives in their study strategy. But it makes it less cut-and-dried, especially given that the students may have memorized (for example) 5 answers to potential questions for every 1 that happened to appear on the test. At some point, knowing all the answers to all potential questions <i>is</i> knowing the material... or else the whole idea of formulaic tests is bankrupt.</text></item></parent_chain><comment><author>protomyth</author><text>No, I really don't think this is actually cheating. He handed out a test that, while claiming to be original, was actually from a standard bank provided by the publisher. This isn't a SAT or GRE that is standardized by an organization or the U, it is a test in a class that he claimed to be the author of.<p>What really annoys me about this story is he is covering his laziness / inattentiveness to his class of paying people and having "fun" doing mathematical analysis of his class to prove "cheating" instead of spending time creating a test. If he won't even put effort into original tests what effort does he really put into the class? Are all his class lectures equally canned? Would these students be better off with a video lecture series from the publisher and taking an online test? What value and insights is he bringing to the lectures. He sure isn't testing on those insights.</text></comment> | <story><title>Prof Gives Lecture to Prove He Knows Students Cheated; Over 200 Students Confess</title><url>http://thoughtcatalog.com/2010/over-200-students-admit-to-cheating-on-test-after-professor-dedicates-lecture-to-proving-he-knows-they-cheated/</url></story><parent_chain><item><author>psyklic</author><text>Yes, it is really cheating. A publisher's test bank is very clearly not made for students to study from. The publishers warn students not to read them and try to make them inaccessible. In my experience, the professor almost always tells students what they can use to study from. Whether students can use past exams is almost always clarified - I wonder if a student asked in this case.<p>However, here the instructor has no way of knowing who cheated. He clearly made a mistake, knowing that using a test bank would make it easy to cheat. So, he should either let all the grades stand or he should point out the statistical anomaly and just make everyone take a new exam, which he did. I can't possibly see how students who didn't confess will be found out, especially if the exam was multiple choice!</text></item><item><author>gojomo</author><text>But was it really cheating? Some students have pointed out that the professor said repeatedly that he composed the tests himself. Given that, then plausibly, using example tests from other sources would be a legitimate preparation method. (For example, the SAT doesn't penalize people for reviewing lots of practice tests, because it's assumed the actual questions during a real test will be novel.)<p>See:<p><a href="http://www.techdirt.com/articles/20101118/21485811928/200-students-admit-to-cheating-exam-bigger-question-is-if-it-was-really-cheating-studying.shtml" rel="nofollow">http://www.techdirt.com/articles/20101118/21485811928/200-st...</a><p>Now, it was probably common knowledge from prior semesters that this professor's exams were from the standard test bank. So those reviewing test bank questions may not have had pure motives in their study strategy. But it makes it less cut-and-dried, especially given that the students may have memorized (for example) 5 answers to potential questions for every 1 that happened to appear on the test. At some point, knowing all the answers to all potential questions <i>is</i> knowing the material... or else the whole idea of formulaic tests is bankrupt.</text></item></parent_chain><comment><author>Estragon</author><text>To me, the morality of what they did is less interesting than the practical ethics of it. The assessment they gamed by accessing the test bank is meant to provide feedback for how well they are acquiring the material. Getting the answers from the test bank means they were more interested in gaming the system for the credential than they were in feedback about where they need to strengthen their understanding. That suggests to me that they're not really interested in the course material, and I wouldn't be interested in working with any of them in any context which used that material. That's an ethical failure. It could be a failure of the course and the educational system, rather than of the students themselves, but it's a problem, no matter who you assign the blame to.</text></comment> |
9,144,156 | 9,144,235 | 1 | 2 | 9,142,871 | train | <story><title>Stuff I've Messed Up While Interviewing</title><url>http://blog.ellenchisa.com/2014/04/13/stuff-ive-screwed-up-while-interviewing/</url></story><parent_chain><item><author>shalmanese</author><text>Holy hell, just reading that made me feel sympathetic anxiousness. Don&#x27;t do the things she&#x27;s suggesting, it&#x27;s a short walk to a lifetime of stress, anxiety and being underappreciated for your work.<p>The problem is that the OP is fundamentally approaching the interview process as a role in which she must please the interviewer in order to be granted the prize of a job. All of her advice is to prepare better and be more on your game so that the other person might perhaps like you more. Coming in with this mindset automatically puts you on a back footing and makes everything more difficult.<p>Instead, focus on flipping the status game around. When you&#x27;re with the interviewer, you&#x27;re with a peer. Talk to them as if you&#x27;re talking to a friend, not as if you&#x27;re in a high pressure, life or death situation. Take the VC interview, for example. Imagine if you&#x27;re catching up with your best friend from college and they ask you if you&#x27;ve made any friends in NYC yet. Do you freeze up and start blabbering incoherently? No, you laugh about it and bitch about how tough it is and ask them if they have any advice or whatever it is that you would do. Approaching it this way changes the entire tenor of the interview process.<p>This is where unskilled and unaware of it genuinely comes in handy. People who are just bad enough that they have no idea how they compare easily sail through interviews since they assume they&#x27;re above average while genuinely talented people spend so much time comparing themselves to others they get wracked by insecurity.<p>I know this is something easier said than done and that some people in particular find it especially challenging. So is learning Javascript or Photoshop, yet we don&#x27;t complain when a job requires us to know them to be hired. Learning social skills is as equally important to your career as technical skills so just nut up and do it.</text></item></parent_chain><comment><author>jghn</author><text>It&#x27;s well and good to say this, and this is always my tactic anyways (although it&#x27;s also how I naturally interact in any meeting).<p>However, that only gets you so far. I have a dirty little secret, I&#x27;m really bad at a lot of the types of whiteboard questions which get asked and while i have a good natural intuition on things like big O that intuition doesn&#x27;t translate well into actual words.<p>So instead I end up in a situation where for instance I&#x27;m told by my boss that I could easily&#x2F;quickly get a job most anywhere I wanted and yet fearful that I&#x27;d get turned away from Bob&#x27;s CRUDapp shop. It is what it is and I realize these are the entry bars that our industry uses &amp; I don&#x27;t complain about it, but there&#x27;s more to the equation than simply owning the room.</text></comment> | <story><title>Stuff I've Messed Up While Interviewing</title><url>http://blog.ellenchisa.com/2014/04/13/stuff-ive-screwed-up-while-interviewing/</url></story><parent_chain><item><author>shalmanese</author><text>Holy hell, just reading that made me feel sympathetic anxiousness. Don&#x27;t do the things she&#x27;s suggesting, it&#x27;s a short walk to a lifetime of stress, anxiety and being underappreciated for your work.<p>The problem is that the OP is fundamentally approaching the interview process as a role in which she must please the interviewer in order to be granted the prize of a job. All of her advice is to prepare better and be more on your game so that the other person might perhaps like you more. Coming in with this mindset automatically puts you on a back footing and makes everything more difficult.<p>Instead, focus on flipping the status game around. When you&#x27;re with the interviewer, you&#x27;re with a peer. Talk to them as if you&#x27;re talking to a friend, not as if you&#x27;re in a high pressure, life or death situation. Take the VC interview, for example. Imagine if you&#x27;re catching up with your best friend from college and they ask you if you&#x27;ve made any friends in NYC yet. Do you freeze up and start blabbering incoherently? No, you laugh about it and bitch about how tough it is and ask them if they have any advice or whatever it is that you would do. Approaching it this way changes the entire tenor of the interview process.<p>This is where unskilled and unaware of it genuinely comes in handy. People who are just bad enough that they have no idea how they compare easily sail through interviews since they assume they&#x27;re above average while genuinely talented people spend so much time comparing themselves to others they get wracked by insecurity.<p>I know this is something easier said than done and that some people in particular find it especially challenging. So is learning Javascript or Photoshop, yet we don&#x27;t complain when a job requires us to know them to be hired. Learning social skills is as equally important to your career as technical skills so just nut up and do it.</text></item></parent_chain><comment><author>ellenchisa1</author><text>Hi! Author here. Point well taken. Trying to post quickly before class...<p>I hope I didn&#x27;t imply that you should walk into the interview feeling like you were on the defensive - I don&#x27;t think that&#x27;s the case at all. I just think being well prepared (a) makes you feel prepared and (b) makes you more likely to be able to handle something on the fly.<p>I&#x27;m also not sure what roles you&#x27;ve been interviewing for. I&#x27;ve found these sorts of things to be more important for PM&#x2F;Product than for Engineering or Design. The other roles have some more concrete goals to judge off of. It&#x27;s hard to tell if someone is &#x27;good&#x27; at Product, and I&#x27;ve found things go better for me if I keep all of this in mind.</text></comment> |
6,015,029 | 6,015,027 | 1 | 2 | 6,014,391 | train | <story><title>Datastore API (beta)</title><url>https://www.dropbox.com/developers/datastore</url><text></text></story><parent_chain><item><author>peterkelly</author><text>The biggest problem right now with online file storage services (sorry, I meant &quot;The Cloud&quot;) is that while they all do basically the same stuff, there&#x27;s no standard protocol for accessing them. It&#x27;s a bit like if every website used a custom protocol instead of HTTP, and web browser vendors had to explicitly collaborate with each web site (or use the website&#x27;s SDK) in order to be able to retrieve content.<p>Imagine this: All the major players in the space (Dropbox, Box, Google Drive, Skydrive, Sugarsync etc.) as well as app developers got together and came up with a standard way of doing this that makes it possible to use a single protocol &amp; API for all online storage providers. I see this being a good thing for everyone - users can choose whatever service they want, app developers can easily provide their customers with a ton of options, and storage providers don&#x27;t have to explicitly produce their own SDK or court developers to do integration with their service. We did have WebDAV, but that doesn&#x27;t seem to be widely adopted by any of the major players.<p>I&#x27;ve been facing this problem myself with my own app; it&#x27;s a lot of work to support all the major services and this is really just plumbing stuff that everyone would rather be taken care of so they can focus on the more important stuff. I had a meeting with Box recently where I proposed the idea of an open source framework for iOS which would provide a common native API that abstracts over all the different REST APIs used by different storage providers. The people I spoke to seemed quite open to the idea and agreed that it would be useful. I don&#x27;t think a library like this would necessary be considered a bad thing by any of the major players, as it evens out the playing field and makes it easy to support different services.<p>If you&#x27;re interested in taking part and&#x2F;or using such an API in your iOS app, I&#x27;d love to hear your thoughts on the matter. I have some code already (which I haven&#x27;t released yet) and am looking to clean up the API a bit, but I think it would be useful to a lot of developers.</text></item></parent_chain><comment><author>davidjgraph</author><text>That&#x27;s exactly the idea of Remote Storage [0]. The problem is here that the lowest common denominator of functionality isn&#x27;t actually very much.<p>Anything but fairly trivial apps quickly run into problems with application data (how relevant), file patching, file intents (Google have this),<p>Google have, IMO, the most advanced solution in the space, so you could argue have the most the lose from standardising. But in fairness, some of their stuff (I&#x27;m thinking the real-time collaboration part of the Drive API) is so complex, there&#x27;s no way you&#x27;d ever see it in a common standard.<p>That said, it&#x27;d be really nice to see a common API over the lower stuff.<p>[0] <a href="http://remotestorage.io/" rel="nofollow">http:&#x2F;&#x2F;remotestorage.io&#x2F;</a></text></comment> | <story><title>Datastore API (beta)</title><url>https://www.dropbox.com/developers/datastore</url><text></text></story><parent_chain><item><author>peterkelly</author><text>The biggest problem right now with online file storage services (sorry, I meant &quot;The Cloud&quot;) is that while they all do basically the same stuff, there&#x27;s no standard protocol for accessing them. It&#x27;s a bit like if every website used a custom protocol instead of HTTP, and web browser vendors had to explicitly collaborate with each web site (or use the website&#x27;s SDK) in order to be able to retrieve content.<p>Imagine this: All the major players in the space (Dropbox, Box, Google Drive, Skydrive, Sugarsync etc.) as well as app developers got together and came up with a standard way of doing this that makes it possible to use a single protocol &amp; API for all online storage providers. I see this being a good thing for everyone - users can choose whatever service they want, app developers can easily provide their customers with a ton of options, and storage providers don&#x27;t have to explicitly produce their own SDK or court developers to do integration with their service. We did have WebDAV, but that doesn&#x27;t seem to be widely adopted by any of the major players.<p>I&#x27;ve been facing this problem myself with my own app; it&#x27;s a lot of work to support all the major services and this is really just plumbing stuff that everyone would rather be taken care of so they can focus on the more important stuff. I had a meeting with Box recently where I proposed the idea of an open source framework for iOS which would provide a common native API that abstracts over all the different REST APIs used by different storage providers. The people I spoke to seemed quite open to the idea and agreed that it would be useful. I don&#x27;t think a library like this would necessary be considered a bad thing by any of the major players, as it evens out the playing field and makes it easy to support different services.<p>If you&#x27;re interested in taking part and&#x2F;or using such an API in your iOS app, I&#x27;d love to hear your thoughts on the matter. I have some code already (which I haven&#x27;t released yet) and am looking to clean up the API a bit, but I think it would be useful to a lot of developers.</text></item></parent_chain><comment><author>icebraining</author><text>Big players aren&#x27;t interested in anything that reduces lock-in. Seamless integration is one of the keypoints they have to get you to use their services.<p>Obligatory presentation by Bruce Schneier on the online feudalism: <a href="http://www.infoq.com/presentations/cloud-security" rel="nofollow">http:&#x2F;&#x2F;www.infoq.com&#x2F;presentations&#x2F;cloud-security</a></text></comment> |
9,039,201 | 9,039,275 | 1 | 3 | 9,038,888 | train | <story><title>New Tesla battery could power your home, and maybe the electric grid too</title><url>http://www.washingtonpost.com/blogs/the-switch/wp/2015/02/12/this-new-tesla-battery-will-power-your-home-and-maybe-the-electric-grid-too/</url></story><parent_chain><item><author>xxxyy</author><text>Doing arbitrage on the power network by storing energy during off-period, and releasing it during high-period is a relatively old concept (eg. [0]). What I don&#x27;t see happening is the price of this battery going low enough to make this kind of arbitrage profitable in a reasonable amount of time. The article does not mention the cost aspect of such an investment.<p>Germany along with a few other EU countries are currently high on renewable energy. As far as I know the most profitable way to utilize electric solar panels is to sell excessive energy back to the grid, not store it in batteries.<p>[0] <a href="http://en.wikipedia.org/wiki/Pumped-storage_hydroelectricity" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Pumped-storage_hydroelectricity</a></text></item><item><author>dangrossman</author><text>There are already widespread programs where utilities pay customers a rebate in exchange for remotely turning off their A&#x2F;C compressors at the peak of a heat wave in order to chop the top off consumption spikes. Paying high-consumption commercial customers to turn off entirely for a few hours to avoid spinning up another generation plant happens too.<p>It&#x27;s not too far-fetched to imagine a rebate program on home battery systems if the utility got the same remote control power to disconnect homes from the grid when needed, or even have their batteries dump power back onto it at those times. Essentially, individual homes become part of &quot;smart grid&quot; management systems.</text></item></parent_chain><comment><author>JshWright</author><text>The problem is, selling it back to the grid only works when it&#x27;s a fairly small fraction of the customer base that&#x27;s doing it. We can&#x27;t _all_ sell power back to the grid.<p>EDIT: Why the downvotes? This is a real issue... The current model of &#x27;buy solar panels and pay for them by selling power back to the grid&#x27; will not scale forever...</text></comment> | <story><title>New Tesla battery could power your home, and maybe the electric grid too</title><url>http://www.washingtonpost.com/blogs/the-switch/wp/2015/02/12/this-new-tesla-battery-will-power-your-home-and-maybe-the-electric-grid-too/</url></story><parent_chain><item><author>xxxyy</author><text>Doing arbitrage on the power network by storing energy during off-period, and releasing it during high-period is a relatively old concept (eg. [0]). What I don&#x27;t see happening is the price of this battery going low enough to make this kind of arbitrage profitable in a reasonable amount of time. The article does not mention the cost aspect of such an investment.<p>Germany along with a few other EU countries are currently high on renewable energy. As far as I know the most profitable way to utilize electric solar panels is to sell excessive energy back to the grid, not store it in batteries.<p>[0] <a href="http://en.wikipedia.org/wiki/Pumped-storage_hydroelectricity" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Pumped-storage_hydroelectricity</a></text></item><item><author>dangrossman</author><text>There are already widespread programs where utilities pay customers a rebate in exchange for remotely turning off their A&#x2F;C compressors at the peak of a heat wave in order to chop the top off consumption spikes. Paying high-consumption commercial customers to turn off entirely for a few hours to avoid spinning up another generation plant happens too.<p>It&#x27;s not too far-fetched to imagine a rebate program on home battery systems if the utility got the same remote control power to disconnect homes from the grid when needed, or even have their batteries dump power back onto it at those times. Essentially, individual homes become part of &quot;smart grid&quot; management systems.</text></item></parent_chain><comment><author>eigenvector</author><text>Not only will the batteries need to get cheaper, but the available arbitrage opportunity will need to account for the necessary upgrades to utility distribution systems to accommodate large amounts of distributed energy storage (DES). DES, particularly at high penetrations, generally violates the design assumptions of distribution protection systems and requires non-trivial upgrades to protective relaying and SCADA systems to maintain adequate real-time control.</text></comment> |
26,361,006 | 26,359,924 | 1 | 2 | 26,357,389 | train | <story><title>Zola: A fast static site generator in a single binary</title><url>https://www.getzola.org/</url></story><parent_chain><item><author>regus</author><text>I though this was about the wedding registry site at first.<p>Anyway, I liked this line from the Github:<p><i>&gt; Hugo gets ehh for the template engine because while it is probably the most powerful template engine in the list (after Jinja2) it personally drives me insane, to the point of writing my own template engine and static site generator. Yes, this is a bit biased.</i><p>This seems to be the life cycle of static site generators (SSG). It works at first, but you end up wanting to design your own custom SSG once you run up against something that goes against your mental model of how things should work.<p>I did this exact thing when I got frustrated with Hugo. I made my own custom SSG in order to create my blog.<p>The other thing that tends to happen with SSGs is that it can be a lot more fun to play around with the tech than actually writing blog posts!<p>If you&#x27;re interested you can read here to see how I made an SSG for my blog:<p><a href="https:&#x2F;&#x2F;joelregus.com&#x2F;posts&#x2F;blog&#x2F;index.html" rel="nofollow">https:&#x2F;&#x2F;joelregus.com&#x2F;posts&#x2F;blog&#x2F;index.html</a></text></item></parent_chain><comment><author>spf13</author><text>I did this exact thing when I got frustrated with Jekyll (and friends) and created Hugo. Of course, at the time all SSGs were in dynamic languages and very VERY slow.<p>Happy to see some Hugo ideas made it into Zola.</text></comment> | <story><title>Zola: A fast static site generator in a single binary</title><url>https://www.getzola.org/</url></story><parent_chain><item><author>regus</author><text>I though this was about the wedding registry site at first.<p>Anyway, I liked this line from the Github:<p><i>&gt; Hugo gets ehh for the template engine because while it is probably the most powerful template engine in the list (after Jinja2) it personally drives me insane, to the point of writing my own template engine and static site generator. Yes, this is a bit biased.</i><p>This seems to be the life cycle of static site generators (SSG). It works at first, but you end up wanting to design your own custom SSG once you run up against something that goes against your mental model of how things should work.<p>I did this exact thing when I got frustrated with Hugo. I made my own custom SSG in order to create my blog.<p>The other thing that tends to happen with SSGs is that it can be a lot more fun to play around with the tech than actually writing blog posts!<p>If you&#x27;re interested you can read here to see how I made an SSG for my blog:<p><a href="https:&#x2F;&#x2F;joelregus.com&#x2F;posts&#x2F;blog&#x2F;index.html" rel="nofollow">https:&#x2F;&#x2F;joelregus.com&#x2F;posts&#x2F;blog&#x2F;index.html</a></text></item></parent_chain><comment><author>Keats</author><text>&gt; I though this was about the wedding registry site at first.<p>I didn&#x27;t even know what a wedding registry was until after the rename. It is named after <a href="https:&#x2F;&#x2F;fr.wikipedia.org&#x2F;wiki&#x2F;%C3%89mile_Zola" rel="nofollow">https:&#x2F;&#x2F;fr.wikipedia.org&#x2F;wiki&#x2F;%C3%89mile_Zola</a><p>&gt; I did this exact thing when I got frustrated with Hugo. I made my own custom SSG in order to create my blog.
&gt; The other thing that tends to happen with SSGs is that it can be a lot more fun to play around with the tech than actually writing blog posts!<p>Exactly that. A great way to learn a language too.</text></comment> |
9,374,133 | 9,374,002 | 1 | 2 | 9,373,781 | train | <story><title>Apple WWDC 2015</title><url>https://developer.apple.com/wwdc/index.html</url></story><parent_chain></parent_chain><comment><author>coldcode</author><text>I was at the first one (though not named WWDC yet) in 1986. In the old days this was the funnest week of the year, as you got to talk with everyone and you learned a lot from the random discussions. I went two years ago and everyone sat&#x2F;stood in long lines using various devices and no one talked anymore. I think watching the videos is enough now.<p>That first one BTW had 300 people representing virtually all the Mac developers in the entire world, meeting in a single ballroom at the Fairmont. Nowadays you have 5500 people that barely fit into Moscone West.</text></comment> | <story><title>Apple WWDC 2015</title><url>https://developer.apple.com/wwdc/index.html</url></story><parent_chain></parent_chain><comment><author>sarreph</author><text>I would encourage any student (full-time, part-time, university, high-school) who has enough of a grasp of making a half-decent&#x2F;basic iOS app to try and get a scholarship for WWDC.<p>Being lucky enough to go twice as a student and have the ticket (but not flights unfortunately) paid for, gave me access to a wealth of like-minded young people and events that provided me with insight and opportunity that I would not have otherwise been able to get.<p>Please give it a shot if you can, and are eligible.</text></comment> |
39,444,686 | 39,444,765 | 1 | 2 | 39,440,808 | train | <story><title>Cve-rs: Fast memory vulnerabilities, written in safe Rust</title><url>https://github.com/Speykious/cve-rs</url></story><parent_chain><item><author>dgfitz</author><text>Thank you very much for spending time explaining this. It makes more sense with that kind of description. I&#x27;m still not sure how long it would take someone like myself to be comfortable and proficient with the syntax.<p>I guess stated another way, I don&#x27;t generally have issues reading code from a wide swath of languages. If someone plopped me in front of a rust codebase I&#x27;d be at the mercy of the manual for quite a long time.<p>Thank you again, sincerely.</text></item><item><author>oneshtein</author><text>`&amp;` is a reference.<p>`&#x27;a` is a label for a memory area, like goto labels in C but for data. You can read it as (memory) pool A. Roughly, when function entered, memory pool is created, then destroyed at exit.<p>`&#x27;static` is special label for static data (embedded constants).<p>`()` is nothing, like void in C.<p>`&amp;()` is an reference to nothing (an address) like `void const *` in C.<p>`&amp;&amp;()` is an reference to reference to nothing, like `void const * const *` in C.<p>`&amp; &#x27;static &amp; &#x27;static ()` is like void `const * const *` to a built-in data in C.<p>`&amp; &#x27;a &amp; &#x27;b ()` tells compiler that second reference is stored in pool &#x27;a, while data is stored in pool &#x27;b. (First reference is in scope of current function.)<p>`_` is a special prefix for variables to instruct compiler to ignore warning about unused variable. Just `_` is a valid variable name too.<p><pre><code> static UNIT: &amp;&#x27;static &amp;&#x27;static () = &amp;&amp;();
fn foo&lt;&#x27;a, &#x27;b, T&gt;(_: &amp;&#x27;a &amp;&#x27;b (), v: &amp;&#x27;b T) -&gt; &amp;&#x27;a T { v }
</code></pre>
Let&#x27;s say that `&amp;&#x27;a` is from a function `a()`, while `&amp;&#x27;b` is from a function `b()`, which called from the function `a()`.<p>The trick here is that we relabel reference from pool `&#x27;b`, from an inner function, to pool `&#x27;a` from outer function, so when program will exit from function `b()`, compiler will destroy memory pool `&#x27;b`, but will keep reference to data inside until end of the function `a()`.<p>This should not be allowed.</text></item><item><author>dgfitz</author><text>Looking at the syntax in that bug report makes me think I could never learn rust.</text></item><item><author>dralley</author><text>Seems to rely on at least one known compiler bug (admittedly one open since 2015) <a href="https:&#x2F;&#x2F;github.com&#x2F;rust-lang&#x2F;rust&#x2F;issues&#x2F;25860">https:&#x2F;&#x2F;github.com&#x2F;rust-lang&#x2F;rust&#x2F;issues&#x2F;25860</a></text></item></parent_chain><comment><author>steveklabnik</author><text>Rust decided to spend very little budget on syntax. The issue though, is that where it took said syntax from is very wide.<p>&amp; is used for references in a lot of languages.<p>() is a tuple, same syntax as Python<p>&#x27;a isn&#x27;t even novel: it was taken from OCaml, which uses it for generic types. Lifetimes are generic types in Rust, so even though it&#x27;s not for an <i>identical</i> thing, it&#x27;s related enough to be similar.<p>_ to ignore a name for something has a long tradition in programming, sometimes purely as a style thing (like _identifier or __identifier), but sometimes supported by the language.<p>fn name(args) -&gt; {} as function syntax is not SUPER unusual. The overall shape is normal, though the choice between &quot;fn,&quot; &quot;fun,&quot; &quot;func,&quot; or &quot;function&quot; varies between languages. The -&gt; comes from languages like Haskell.<p>&lt;&gt; for generics is hotly debated, but certainly common among a variety of langauges.<p>the &quot;static name: type = value;&quot; (with let instead of static too) syntax is becoming increasingly normalized, thanks to how it plays with type inference, but has a long history before Rust.<p>So this leads to a very interesting thing, where like, it&#x27;s not so much that Rust&#x27;s syntax is entirely alien in the context of programming language syntax, but can feel that way unless you&#x27;ve used a lot of things in various places. And that also doesn&#x27;t necessarily mean that just because it&#x27;s influenced from many places that this means it is coherent. I think it does pretty good, but also, I&#x27;d refine some things if I were making a new language.</text></comment> | <story><title>Cve-rs: Fast memory vulnerabilities, written in safe Rust</title><url>https://github.com/Speykious/cve-rs</url></story><parent_chain><item><author>dgfitz</author><text>Thank you very much for spending time explaining this. It makes more sense with that kind of description. I&#x27;m still not sure how long it would take someone like myself to be comfortable and proficient with the syntax.<p>I guess stated another way, I don&#x27;t generally have issues reading code from a wide swath of languages. If someone plopped me in front of a rust codebase I&#x27;d be at the mercy of the manual for quite a long time.<p>Thank you again, sincerely.</text></item><item><author>oneshtein</author><text>`&amp;` is a reference.<p>`&#x27;a` is a label for a memory area, like goto labels in C but for data. You can read it as (memory) pool A. Roughly, when function entered, memory pool is created, then destroyed at exit.<p>`&#x27;static` is special label for static data (embedded constants).<p>`()` is nothing, like void in C.<p>`&amp;()` is an reference to nothing (an address) like `void const *` in C.<p>`&amp;&amp;()` is an reference to reference to nothing, like `void const * const *` in C.<p>`&amp; &#x27;static &amp; &#x27;static ()` is like void `const * const *` to a built-in data in C.<p>`&amp; &#x27;a &amp; &#x27;b ()` tells compiler that second reference is stored in pool &#x27;a, while data is stored in pool &#x27;b. (First reference is in scope of current function.)<p>`_` is a special prefix for variables to instruct compiler to ignore warning about unused variable. Just `_` is a valid variable name too.<p><pre><code> static UNIT: &amp;&#x27;static &amp;&#x27;static () = &amp;&amp;();
fn foo&lt;&#x27;a, &#x27;b, T&gt;(_: &amp;&#x27;a &amp;&#x27;b (), v: &amp;&#x27;b T) -&gt; &amp;&#x27;a T { v }
</code></pre>
Let&#x27;s say that `&amp;&#x27;a` is from a function `a()`, while `&amp;&#x27;b` is from a function `b()`, which called from the function `a()`.<p>The trick here is that we relabel reference from pool `&#x27;b`, from an inner function, to pool `&#x27;a` from outer function, so when program will exit from function `b()`, compiler will destroy memory pool `&#x27;b`, but will keep reference to data inside until end of the function `a()`.<p>This should not be allowed.</text></item><item><author>dgfitz</author><text>Looking at the syntax in that bug report makes me think I could never learn rust.</text></item><item><author>dralley</author><text>Seems to rely on at least one known compiler bug (admittedly one open since 2015) <a href="https:&#x2F;&#x2F;github.com&#x2F;rust-lang&#x2F;rust&#x2F;issues&#x2F;25860">https:&#x2F;&#x2F;github.com&#x2F;rust-lang&#x2F;rust&#x2F;issues&#x2F;25860</a></text></item></parent_chain><comment><author>jcranmer</author><text>To be fair, even for someone who is comfortable in Rust, the example is definitely on the rather confusing side of the language. (Not entirely surprising--it&#x27;s a bug about a soundness hole in the language, which invariably tends to rely on overuse of less commonly used features in the language).<p>In particular, explicit use of lifetimes tends to be seen as somewhat more of a last resort, although the language requires it more frequently than I like. Furthermore, the soupiest of the syntax requires the use of multiple layers of indirection for references, which itself tends to be a bit of a code smell (just like how in C&#x2F;C++, T * tends to be somewhat rare).</text></comment> |
34,099,546 | 34,097,238 | 1 | 3 | 34,096,988 | train | <story><title>Do simpler machine learning models exist and how can we find them?</title><url>https://statmodeling.stat.columbia.edu/2022/12/22/do-simpler-machine-learning-models-exist-and-how-can-we-find-them/</url></story><parent_chain></parent_chain><comment><author>tbalsam</author><text>I recently released a codebase in beta that modernizes a tiny model that gets really good performance on CIFAR-10 in about 18.1 or so seconds on the right single GPU -- a number of years ago the world record was 10 minutes, down from several days a few years previously.<p>While most of my work was porting and cleaning up certain parts of the code for a different purpose (just-clone-and-hack experimentation workbench), I&#x27;ve spent years optimizing neural networks at a very fine grained level, and many of the lessons learned here in debugging reflected that.<p>I believe that there are fundamentally a few big NP-hard layers (at least two that I can define, and likely several other smaller ones) unfortunately but they are not hard blockers to progress. The model I mentioned above is extremely simple and has little &quot;extra fat&quot; where it is not needed. It also importantly seems to have good gradient and such flow throughout, something that&#x27;s important for a model to be able to learn quickly. There are a few reasonable priors, like initializing and freezing the first convolution to whiten the inputs based upon some statistics from the training data. That does a shocking amount of work in stabilizing and speeding up training.<p>Ultimately, the network is simple, and there are a number of other methods to help it reach near-SOTA, but they are as simple as can be. I think as this project evolves and we get nearer to the goal (&lt;2 seconds in a year or two), we&#x27;ll keep uncovering good puzzle pieces showing exactly what it is that&#x27;s allowing such a tiny network to perform so well. There&#x27;s a kind of exponential value to having ultra-short training times -- you can somewhat open-endedly barrage-test your algorithm, something that&#x27;s already led to a few interesting discoveries that I&#x27;d like to refine before publishing to the repo.<p>If you&#x27;re interested, the code is here. The running code is a single .py with the upsides and downsides that come with that. If you&#x27;re interested or have any questions, let me know! :D :))))<p><a href="https:&#x2F;&#x2F;github.com&#x2F;tysam-code&#x2F;hlb-CIFAR10">https:&#x2F;&#x2F;github.com&#x2F;tysam-code&#x2F;hlb-CIFAR10</a></text></comment> | <story><title>Do simpler machine learning models exist and how can we find them?</title><url>https://statmodeling.stat.columbia.edu/2022/12/22/do-simpler-machine-learning-models-exist-and-how-can-we-find-them/</url></story><parent_chain></parent_chain><comment><author>donkeyboy</author><text>Yes, they exist, and they are called Linear Regression and Decision Tree. Not everything needs to be a neural network.<p>Anyway, residual connections in NNs as well as distillation being only a 1% hit to performance imply our models are way too big.</text></comment> |
32,888,723 | 32,888,704 | 1 | 2 | 32,887,795 | train | <story><title>Trianglify.io – Low Poly Pattern Generator</title><url>https://trianglify.io/</url></story><parent_chain><item><author>qrohlf</author><text>One thing that folks may find interesting about this project on a technical level is that it&#x27;s fully stateless including the backend that&#x27;s responsible for interacting with Stripe Checkout, processing payments, and sending emails with receipts and links to re-download patterns.<p>The thing that makes that possible is that I&#x27;m using a seedable PRNG for the pattern generation and have a custom serialization format for all of the possible pattern parameters. This means that any pattern can be represented by a single short string like `w:1440!h:900!x:random!v:0.63!c:0.06!s:9gjk5s!f:sp!i:0.30` and reproduced with 100% accuracy.<p>That means instead of a database, I can just store the entire purchased pattern directly within the Stripe transaction within the `client_id` field using this compressed representation. Then it&#x27;s just a matter of reading it back from the Stripe API when I get the &quot;purchase completed&quot; webhooks in order to build the correct attachments and send the customer their assets via email. This keeps my own service totally stateless &amp; database-free, and also has the very nice property of allowing me to quickly and easily access the pattern by copy-pasting the client-id from the Stripe dashboard if I ever need to grab it for customer service reasons!</text></item></parent_chain><comment><author>josiahpeters</author><text>I know that people are beating you up over the price, but this is great.<p>1. Someone could generate the same asset for themselves using your open source library. Which is great for someone who has time over budget.<p>2. You are providing value in your packaging of that time savings.<p>3. You created a very cheap way to offer this using server less and stateless. Props to you for making something that is financially sustainable for a long time.<p>Number 3 is the most interesting of the above. That’s no easy feat and I applaud you for it.</text></comment> | <story><title>Trianglify.io – Low Poly Pattern Generator</title><url>https://trianglify.io/</url></story><parent_chain><item><author>qrohlf</author><text>One thing that folks may find interesting about this project on a technical level is that it&#x27;s fully stateless including the backend that&#x27;s responsible for interacting with Stripe Checkout, processing payments, and sending emails with receipts and links to re-download patterns.<p>The thing that makes that possible is that I&#x27;m using a seedable PRNG for the pattern generation and have a custom serialization format for all of the possible pattern parameters. This means that any pattern can be represented by a single short string like `w:1440!h:900!x:random!v:0.63!c:0.06!s:9gjk5s!f:sp!i:0.30` and reproduced with 100% accuracy.<p>That means instead of a database, I can just store the entire purchased pattern directly within the Stripe transaction within the `client_id` field using this compressed representation. Then it&#x27;s just a matter of reading it back from the Stripe API when I get the &quot;purchase completed&quot; webhooks in order to build the correct attachments and send the customer their assets via email. This keeps my own service totally stateless &amp; database-free, and also has the very nice property of allowing me to quickly and easily access the pattern by copy-pasting the client-id from the Stripe dashboard if I ever need to grab it for customer service reasons!</text></item></parent_chain><comment><author>mr-karan</author><text>Quite a cool approach. Although only one downside I see here is that you&#x27;re just relying on Stripe to let you access order history? What if they don&#x27;t let you access this data via APIs for data older than a certain time period? Or is that not much of a concern here?</text></comment> |
7,362,763 | 7,361,996 | 1 | 2 | 7,361,947 | train | <story><title>Show HN: My current App Store Featured Game was written entirely in Scheme</title><url>https://itunes.apple.com/us/app/cloud-breaker/id721767500?mt=8</url></story><parent_chain></parent_chain><comment><author>Shivetya</author><text>After reading the story I just have to recall stories from the guys who flew and serviced F4s, they joked they could fly without either wing simply because it was just a rocket sled.<p>We had one guy knicknamed Major Cablecutter as he &quot;clipped&quot; the guidelines of a radio tower one time. He also had come back more than once with branches stuck to his F4. Being that they were only &quot;Recon&quot; they tended to be aggressive during war games and this game guy over stressed his airframe turning into some F18s trying to tag him.<p>So many military planes have such high thrust to weight ratios I do not doubt that wings merely become the means to stable flight</text></comment> | <story><title>Show HN: My current App Store Featured Game was written entirely in Scheme</title><url>https://itunes.apple.com/us/app/cloud-breaker/id721767500?mt=8</url></story><parent_chain></parent_chain><comment><author>rrradical</author><text>I&#x27;m the author. I wrote the game and engine using the wonderful, and fast, Gambit Scheme (<a href="http://gambitscheme.org/" rel="nofollow">http:&#x2F;&#x2F;gambitscheme.org&#x2F;</a>).<p>I needed a lisp to manipulate the puzzles, because they aren&#x27;t based in a strict grid. It ended up being way more natural to program the block structures as lists rather than traditional matrices.<p>Gambit compiles the Scheme code down to C, which I can then link to Objective-C for iOS, or port to Android or any other platform that Gambit supports.</text></comment> |
24,569,215 | 24,569,558 | 1 | 3 | 24,567,455 | train | <story><title>Typography of Star Trek: The Motion Picture</title><url>https://typesetinthefuture.com/2020/08/17/startrek/</url></story><parent_chain></parent_chain><comment><author>dmreedy</author><text>Man, I feel like the Blaster Beam almost deserves a discussion of its own. That thing is wild (link from the article) <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=cj4f5z6nRhs" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=cj4f5z6nRhs</a></text></comment> | <story><title>Typography of Star Trek: The Motion Picture</title><url>https://typesetinthefuture.com/2020/08/17/startrek/</url></story><parent_chain></parent_chain><comment><author>golem14</author><text>The book is very nice. Coffee table books for true nerds, next to Tufte. But I wish there were more recent updates or a 2nd volume where they look at newer material, like &quot;person of interest&quot;, &quot;Black matter&quot;, &quot;The Expanse&quot;, ...</text></comment> |
25,649,776 | 25,648,613 | 1 | 2 | 25,647,287 | train | <story><title>Space things happening in 2021</title><url>https://arstechnica.com/?p=1730399</url></story><parent_chain><item><author>ackbar03</author><text>I really feel space tech is gonna be the next big thing going forward, but I have zero clue about how to get involved. It seems like one of those things where you really need to either be some government agency or have a PhD in it or something.</text></item></parent_chain><comment><author>Rebelgecko</author><text>Basically all space companies (oldspace, newspace) hire software folks. Some specific jobs might require PhDs, but most don&#x27;t. Flight software sometimes has requirements for certain experience (e.g. Embedded). However, flight software is a surprisingly small sliver of all the space related software that gets written. Even though it&#x27;s <i>outer space</i> they still need GUIs for ground systems, CRUD apps for handling downlinked data, WebGL people to build fancy visualizations, etc</text></comment> | <story><title>Space things happening in 2021</title><url>https://arstechnica.com/?p=1730399</url></story><parent_chain><item><author>ackbar03</author><text>I really feel space tech is gonna be the next big thing going forward, but I have zero clue about how to get involved. It seems like one of those things where you really need to either be some government agency or have a PhD in it or something.</text></item></parent_chain><comment><author>avmich</author><text>It&#x27;s both pretty easy and insanely hard.<p>Insanely hard - from an engineer prospective - because there is a big gap between software disciplines and, ughm, &quot;the real world&quot;. When you&#x27;re pushing bits, today it&#x27;s easy to forget about the times when computers were quite unreliable, from the hardware point of view. Bad contacts? Unreliable memory bits? Overheating parts? Magnetic tape which loses data and paper media which breaks? Today most of this is factored away and engineers largely operate with logic. Try to do hardware projects - even easy Arduino-based designs will give you a glimp of difficulties you&#x27;re going to get with space technology, and if you&#x27;re trying something modestly interesting...<p>Pretty easy is because &quot;rocket science isn&#x27;t rocket science&quot;. It&#x27;s technology invented more than a century ago - converging-diverging nozzle was invented about 150 years ago, about 120 years ago Tsiolkovsky wrote about liquid hydrogen fuel and multistage rockets, more than 90 years ago Goddard flew his first rockets, almost 80 years ago von Braun was already working on V-2, and this year we&#x27;re celebrating 60th anniversary of Spootnik. A great deal of efforts went into perfection of rocketry, and now we know a lot - that&#x27;s a big part of the reason why SpaceX moves so fast - and can do a lot.<p>Now you can have a nano-launcher startup for less than 100 million dollars - may be way less - which just couple of decades ago is unheard of. More, there are competitions - X Prize for flight 100 km up, Northrop Grumman Lunar Lander Challenge, Google Lunar Prize, and now, say, NASA&#x27;s <a href="https:&#x2F;&#x2F;breaktheicechallenge.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;breaktheicechallenge.com&#x2F;</a> - where you can participate with much smaller barrier to entry. The webinar from this last challenge - <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=UXgdEDBTPJE" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=UXgdEDBTPJE</a> - contains references on other competitions NASA is hosting.<p>So, to conclude, if you&#x27;re an engineering mind, especially capable of working outside of applied math of programming, the possibilities are certainly there to try in growing space industry.</text></comment> |
7,242,913 | 7,242,663 | 1 | 2 | 7,242,265 | train | <story><title>Why I Dropped Out Of YC</title><url>http://wikichen.is/writing/why-i-dropped-out-of-yc/</url></story><parent_chain><item><author>birken</author><text>Look, startups suck. Failed startups suck. Successful startups suck. Silicon Valley sucks. But so does working regular jobs, and so do a lot of things. The problem here is probably that you had the wrong expectations, and then when reality hit, it hit really hard.<p>If you want to play the game, you better be mentally prepared for dealing with a lot of shit. Egos are going to clash. Friendships are going to be strained. Stress is going to occur. To use one of my favorite quotes my dad always said to me, &quot;that is life in the big city&quot;. Startups are not romantic -- they are a slog.<p>But... if you are building something you want to build, it can be worth it. Just don&#x27;t expect it to be easy.</text></item></parent_chain><comment><author>hnriot</author><text>Startups don&#x27;t suck! After having worked at plenty over the years I don&#x27;t agree at all. I guess it depends how you respond to change and volatility. Some people find comfort in things staying the same, but I enjoy the high rate of change in startups. I enjoy the pace, sometimes it can be stressful but after a few you don&#x27;t get too worried - investors come and go, products come and go, fortunes comes and go. It&#x27;s not the destination that matters, if all you&#x27;re focused on is the exit then you&#x27;ll miss the fun. For me it&#x27;s about staying current. After being a software dev for 25 years I still absolutely love the latest jquery widget, or that Factorie has just hit 1.0 and I can do Dependency Parsing in Scala, or that Pig can now talk to Spark, etc.. To enjoy startups you have to love technology. It&#x27;s like dating, if all you&#x27;re thinking about is getting the girl into bed it won&#x27;t end well, if instead you enjoy the conversation and are genuinely having a good time then ... who knows.</text></comment> | <story><title>Why I Dropped Out Of YC</title><url>http://wikichen.is/writing/why-i-dropped-out-of-yc/</url></story><parent_chain><item><author>birken</author><text>Look, startups suck. Failed startups suck. Successful startups suck. Silicon Valley sucks. But so does working regular jobs, and so do a lot of things. The problem here is probably that you had the wrong expectations, and then when reality hit, it hit really hard.<p>If you want to play the game, you better be mentally prepared for dealing with a lot of shit. Egos are going to clash. Friendships are going to be strained. Stress is going to occur. To use one of my favorite quotes my dad always said to me, &quot;that is life in the big city&quot;. Startups are not romantic -- they are a slog.<p>But... if you are building something you want to build, it can be worth it. Just don&#x27;t expect it to be easy.</text></item></parent_chain><comment><author>founder4fun</author><text>Indeed this shit is not easy!<p>One day your on a huge blog&#x2F;well known publication and your traffic is going nuts. The next day its all gone.<p>One day your celebrating your investment&#x2F;funding win. The next your struggling to find more money and or accept it&#x27;s not going to happen.<p>One day your invited to demo your latest tech to one of the big tech firms thinking it&#x27;s your big win you&#x27;ve worked years for. The next you realize&#x2F;wonder damn did they just steal our hard work - why did they treat us like garbage?<p>So many ups and downs. Sometimes you just want to give up, but you don&#x27;t because this what you love to do and if you stop&#x2F;give up on one tech idea you&#x27;ll get restless and do another!</text></comment> |
2,311,370 | 2,311,372 | 1 | 3 | 2,311,279 | train | <story><title>OS X Isn't for Developers</title><url>http://zachholman.com/2011/03/osx-isnt-for-developers/</url></story><parent_chain><item><author>petercooper</author><text><i>If I wasn't a dev, I'd be pissed to find out some compiler toolchain IDE gongshow eating up 5-15GB of my disk space</i><p>Yeah, but the essentials that most command line builds require wouldn't even take up 10% of that. Apple already wastes gigabytes on printer drivers and extra languages you don't need.</text></item><item><author>darkhelmetlive</author><text>The few of points I've made about this are:<p>1. The Xcode 4 download compared to Xcode 3 is basically just a different IDE. The gcc version is, for all intents and purposes, identical. There's nothing stopping anybody from just installing that if all they need is the toolchain.<p>2. The other big 2 OS's (Windows and Ubuntu) don't have any build tools installed by default either. Granted they are just an apt-get away on Ubuntu, but it's still something you have to explicitly install.<p>3. If I wasn't a dev, I'd be pissed to find some compiler toolchain IDE gongshow eating up 5-15GB of my disk space, so not having it by default is probably a good thing. Most people aren't devs.<p>I paid the $5, but I'd still like to see just the toolchain available as a free download, though I still don't think it would be a good thing to have it installed by default.</text></item></parent_chain><comment><author>eddieplan9</author><text>Your house is not for developers! It did not come with a free computer when you bought it! Even though a computer would only cost as little as 0.2% of the cost of the house, and the previous owner already wasted tons of money on the useless peach trees in the yard.</text></comment> | <story><title>OS X Isn't for Developers</title><url>http://zachholman.com/2011/03/osx-isnt-for-developers/</url></story><parent_chain><item><author>petercooper</author><text><i>If I wasn't a dev, I'd be pissed to find out some compiler toolchain IDE gongshow eating up 5-15GB of my disk space</i><p>Yeah, but the essentials that most command line builds require wouldn't even take up 10% of that. Apple already wastes gigabytes on printer drivers and extra languages you don't need.</text></item><item><author>darkhelmetlive</author><text>The few of points I've made about this are:<p>1. The Xcode 4 download compared to Xcode 3 is basically just a different IDE. The gcc version is, for all intents and purposes, identical. There's nothing stopping anybody from just installing that if all they need is the toolchain.<p>2. The other big 2 OS's (Windows and Ubuntu) don't have any build tools installed by default either. Granted they are just an apt-get away on Ubuntu, but it's still something you have to explicitly install.<p>3. If I wasn't a dev, I'd be pissed to find some compiler toolchain IDE gongshow eating up 5-15GB of my disk space, so not having it by default is probably a good thing. Most people aren't devs.<p>I paid the $5, but I'd still like to see just the toolchain available as a free download, though I still don't think it would be a good thing to have it installed by default.</text></item></parent_chain><comment><author>suchire</author><text>Actually I think Snow Leopard stripped out a lot of those extra gigabytes; only a few printers have drivers out of the box now.</text></comment> |
28,902,884 | 28,898,617 | 1 | 2 | 28,894,481 | train | <story><title>Obsidian – A knowledge base from a local folder of plain text Markdown files</title><url>https://obsidian.md/</url></story><parent_chain><item><author>kepano</author><text>This is an incredible time for knowledge management tools. Just a couple of years ago I was pulling my hair out trying to get a local wiki to feel like a native app, and now we have a dozen great options to choose from.<p>I started using Obsidian when it came out last year, and it instantly clicked for me. I immediately migrated 20 years of notes to it.<p>What differentiates Obsidian from all of the other tools in this area, is that they have made extensibility a top priority. The sheer breadth of plugins, themes, and other community-driven tools that have been generated in 18 months is spectacular. It makes it easy to recommend Obsidian because you can shape it into whatever you want.<p>There are a handful of plugins like Dataview, QuickAdd, Kanban and Periodic Notes that make Obsidian an incredibly powerful environment for thought.<p>I made a theme for Obsidian called Minimal that attempts to make the app feel more native, especially on Mac:
<a href="https:&#x2F;&#x2F;github.com&#x2F;kepano&#x2F;obsidian-minimal" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;kepano&#x2F;obsidian-minimal</a><p>...and published a couple of my own plugins and a Web Clipper bookmarklet: <a href="https:&#x2F;&#x2F;gist.github.com&#x2F;kepano&#x2F;90c05f162c37cf730abb8ff027987ca3" rel="nofollow">https:&#x2F;&#x2F;gist.github.com&#x2F;kepano&#x2F;90c05f162c37cf730abb8ff027987...</a><p>The Obsidian community is just so fun, friendly, and collaborative, that you can&#x27;t help but get involved and work on making the ecosystem better.</text></item></parent_chain><comment><author>sureglymop</author><text>Obsidian is great but I still prefer VSCode for creating these types of interconnected markdown notes on desktop.
Mainly because of the sheer amount of extensions available for VS Code. For example, I can write Jupyter notebooks in markdown files and let them be part of my notes but also open them as notebooks and execute code right in VS Code.<p>I do love Obsidian mobile though, undefeated on mobile!</text></comment> | <story><title>Obsidian – A knowledge base from a local folder of plain text Markdown files</title><url>https://obsidian.md/</url></story><parent_chain><item><author>kepano</author><text>This is an incredible time for knowledge management tools. Just a couple of years ago I was pulling my hair out trying to get a local wiki to feel like a native app, and now we have a dozen great options to choose from.<p>I started using Obsidian when it came out last year, and it instantly clicked for me. I immediately migrated 20 years of notes to it.<p>What differentiates Obsidian from all of the other tools in this area, is that they have made extensibility a top priority. The sheer breadth of plugins, themes, and other community-driven tools that have been generated in 18 months is spectacular. It makes it easy to recommend Obsidian because you can shape it into whatever you want.<p>There are a handful of plugins like Dataview, QuickAdd, Kanban and Periodic Notes that make Obsidian an incredibly powerful environment for thought.<p>I made a theme for Obsidian called Minimal that attempts to make the app feel more native, especially on Mac:
<a href="https:&#x2F;&#x2F;github.com&#x2F;kepano&#x2F;obsidian-minimal" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;kepano&#x2F;obsidian-minimal</a><p>...and published a couple of my own plugins and a Web Clipper bookmarklet: <a href="https:&#x2F;&#x2F;gist.github.com&#x2F;kepano&#x2F;90c05f162c37cf730abb8ff027987ca3" rel="nofollow">https:&#x2F;&#x2F;gist.github.com&#x2F;kepano&#x2F;90c05f162c37cf730abb8ff027987...</a><p>The Obsidian community is just so fun, friendly, and collaborative, that you can&#x27;t help but get involved and work on making the ecosystem better.</text></item></parent_chain><comment><author>runjake</author><text>Can concur, his Minimal theme is really awesome and looks Mac-native.<p>His theme played a huge part in getting me to make the jump from Bear Notes to Obsidian as I try to move away from Mac-specific apps to cross-platform (macOS and Linux) options.</text></comment> |
3,792,868 | 3,792,908 | 1 | 2 | 3,792,623 | train | <story><title>How to apologise to your customers</title><url>http://blogs.balsamiq.com/product/2012/04/03/sorry/</url></story><parent_chain></parent_chain><comment><author>citricsquid</author><text>It's a sad state of affairs when this sort of apology is a surprise and so wonderful. I've been a customer of companies that openly blamed issues on customers and would fake announcements saying that maintenance was planned weeks in advance to save face. Really great to see someone take responsibility for the problems they caused and explain how it's going to be improved for the future.</text></comment> | <story><title>How to apologise to your customers</title><url>http://blogs.balsamiq.com/product/2012/04/03/sorry/</url></story><parent_chain></parent_chain><comment><author>sunir</author><text>I would like to share the relevant part of my comment here as well.<p>I want to caution that it is still better to update on Tuesday morning in case the update fails. Updating before or on the weekend can lead to your releases spiraling out of control with no staff monitoring or just a skeleton crew.<p>It is better to have your whole team available and awake. I also worry that you might forment resentment by making everyone work every release weekend. Releases will likely become more infrequent, and lead to bigger changes and bigger failures.<p>Please consider that Balsamiq did recover. May be harder to do so on Saturday.</text></comment> |
26,251,604 | 26,251,608 | 1 | 3 | 26,250,854 | train | <story><title>Money Creation: 344% in the Last 12mo (Fed, M1, $)</title><url>https://fred.stlouisfed.org/series/M1NS</url></story><parent_chain><item><author>peregrine</author><text>This should be the link.<p>Sharing a link to a graph with minimal context, might as well be spam&#x2F;misinformation.</text></item><item><author>rootusrootus</author><text>Perhaps worth reading along with this:
<a href="https:&#x2F;&#x2F;fredblog.stlouisfed.org&#x2F;2021&#x2F;01&#x2F;whats-behind-the-recent-surge-in-the-m1-money-supply&#x2F;" rel="nofollow">https:&#x2F;&#x2F;fredblog.stlouisfed.org&#x2F;2021&#x2F;01&#x2F;whats-behind-the-rec...</a></text></item></parent_chain><comment><author>habitmelon</author><text>Definitely. The M2 supply grew by about $4T last year, from $15T to about $19T, it&#x27;s a lot, but it&#x27;s about one annual federal budget in normal years. $4T is like 20% of GDP, not nothing, but not hyper-inflationary.<p>The question is will M2 grow by 20% per year, or is this a one-off?</text></comment> | <story><title>Money Creation: 344% in the Last 12mo (Fed, M1, $)</title><url>https://fred.stlouisfed.org/series/M1NS</url></story><parent_chain><item><author>peregrine</author><text>This should be the link.<p>Sharing a link to a graph with minimal context, might as well be spam&#x2F;misinformation.</text></item><item><author>rootusrootus</author><text>Perhaps worth reading along with this:
<a href="https:&#x2F;&#x2F;fredblog.stlouisfed.org&#x2F;2021&#x2F;01&#x2F;whats-behind-the-recent-surge-in-the-m1-money-supply&#x2F;" rel="nofollow">https:&#x2F;&#x2F;fredblog.stlouisfed.org&#x2F;2021&#x2F;01&#x2F;whats-behind-the-rec...</a></text></item></parent_chain><comment><author>Splendor</author><text>&gt; On the other hand, it’s not immediately clear what advantage there is from the bank’s perspective in relabeling savings accounts as transactions balances.<p>Does anyone have any insight into why banks would relabel their savings accounts?</text></comment> |
17,885,317 | 17,884,961 | 1 | 3 | 17,884,215 | train | <story><title>Can Beethoven send takedown requests?</title><url>https://wikimediafoundation.org/2018/08/27/can-beethoven-send-takedown-requests-a-first-hand-account-of-one-german-professors-experience-with-overly-broad-upload-filters/</url></story><parent_chain><item><author>dotancohen</author><text>Who was sending these notices? Sounds like perjury to me.</text></item><item><author>Jerry2</author><text>I used to have a Youtube channel where I posted videos of me playing the piano. I played mostly Mozart, Beethoven and Rachmaninoff compositions. I had around 40 videos in total. Sometime around 2014, I started getting DMCA takedown notices from various companies claiming copyright. I was getting one or two per week and I contested them and things were ruled into my favor. But then it started getting harder and harder to contest them and I even lost the ability to upload. It got so bad that one day several (3 or 4, don&#x27;t remember anymore) notices were filed and Google didn&#x27;t rule on them fast enough.<p>I had to close the channel because my account was locked for one full day and I couldn&#x27;t do a thing. I had too many emails inside of Gmail and didn&#x27;t want to lose them so I gave up. I&#x27;m still pissed about it and how Youtube and Google run things.<p>I always found it interesting that under YT rules content creators have the &quot;3 strikes and you&#x27;re banned&quot; rule hanging over their heads but those who falsely claim copyright can do so with impunity. I still remember one company that ended up falsely claiming copyright over 10+ of my videos and they did so against one or two videos per week. Nothing was ever done about them.</text></item></parent_chain><comment><author>ObsoleteNerd</author><text>Welcome to the DMCA. It&#x27;s as broken as copyright and causing quite serious stifling of young creators. It sometimes feels like it&#x27;s used more for evil than for its legitimate purpose.</text></comment> | <story><title>Can Beethoven send takedown requests?</title><url>https://wikimediafoundation.org/2018/08/27/can-beethoven-send-takedown-requests-a-first-hand-account-of-one-german-professors-experience-with-overly-broad-upload-filters/</url></story><parent_chain><item><author>dotancohen</author><text>Who was sending these notices? Sounds like perjury to me.</text></item><item><author>Jerry2</author><text>I used to have a Youtube channel where I posted videos of me playing the piano. I played mostly Mozart, Beethoven and Rachmaninoff compositions. I had around 40 videos in total. Sometime around 2014, I started getting DMCA takedown notices from various companies claiming copyright. I was getting one or two per week and I contested them and things were ruled into my favor. But then it started getting harder and harder to contest them and I even lost the ability to upload. It got so bad that one day several (3 or 4, don&#x27;t remember anymore) notices were filed and Google didn&#x27;t rule on them fast enough.<p>I had to close the channel because my account was locked for one full day and I couldn&#x27;t do a thing. I had too many emails inside of Gmail and didn&#x27;t want to lose them so I gave up. I&#x27;m still pissed about it and how Youtube and Google run things.<p>I always found it interesting that under YT rules content creators have the &quot;3 strikes and you&#x27;re banned&quot; rule hanging over their heads but those who falsely claim copyright can do so with impunity. I still remember one company that ended up falsely claiming copyright over 10+ of my videos and they did so against one or two videos per week. Nothing was ever done about them.</text></item></parent_chain><comment><author>Jerry2</author><text>&gt;<i>Who was sending these notices?</i><p>There&#x27;s lots of them. The most notorious one I had to deal with was Adrev. There are reports of people getting notices from AdRev for videos that don&#x27;t even have any music in them. [1]<p>[1] <a href="https:&#x2F;&#x2F;productforums.google.com&#x2F;forum&#x2F;#!topic&#x2F;youtube&#x2F;42xLenp36Co" rel="nofollow">https:&#x2F;&#x2F;productforums.google.com&#x2F;forum&#x2F;#!topic&#x2F;youtube&#x2F;42xLe...</a></text></comment> |
14,999,178 | 14,999,027 | 1 | 2 | 14,998,788 | train | <story><title>Why an eight-hour bus ride from Los Angeles to San Francisco might beat a flight</title><url>https://www.economist.com/blogs/gulliver/2017/08/life-slow-lane?fsrc=scn/fb/te/bl/ed/whyaneighthourbusridefromlosangelestosanfranciscomightbeataflight</url></story><parent_chain><item><author>clamprecht</author><text>&quot;The drivers intentionally go slowly and take back roads so that the trip, normally six hours, lasts eight.&quot;<p>Why not just get there 2 hours early, park, and sit for 2 hours. This would (1) reduce vehicle motion, so you can sleep better, and (2) allow people who aren&#x27;t asleep anyway to get out early if they want. It may also save gas, although once buses are electric, this becomes less of a factor.</text></item></parent_chain><comment><author>cwilson</author><text>I&#x27;ve taken quite a few overnight buses during a 6 month trip through South America. Even when paying for the luxury option (which is literally $10-$15 more, totally worth it) and having fully reclining comfortable seats, it all comes down to one thing, the drivers.<p>If the drivers are maximizing for time you&#x27;re not going to sleep very well because they are driving like a maniac. Sudden halts, near misses, and sharp corners make for a particularly terrifying experience when you&#x27;re attempting to sleep.<p>The fact that this endeavor is focusing on drivers that go slow is 100% a positive for me and I would now consider trying it.<p>This is an issue that really just exists with overnight buses, as trains don&#x27;t make sudden stops and they are not competing with other trains for a lane.</text></comment> | <story><title>Why an eight-hour bus ride from Los Angeles to San Francisco might beat a flight</title><url>https://www.economist.com/blogs/gulliver/2017/08/life-slow-lane?fsrc=scn/fb/te/bl/ed/whyaneighthourbusridefromlosangelestosanfranciscomightbeataflight</url></story><parent_chain><item><author>clamprecht</author><text>&quot;The drivers intentionally go slowly and take back roads so that the trip, normally six hours, lasts eight.&quot;<p>Why not just get there 2 hours early, park, and sit for 2 hours. This would (1) reduce vehicle motion, so you can sleep better, and (2) allow people who aren&#x27;t asleep anyway to get out early if they want. It may also save gas, although once buses are electric, this becomes less of a factor.</text></item></parent_chain><comment><author>LewisJEllis</author><text>I don&#x27;t know about everyone else, but if I&#x27;m sleeping in a moving vehicle and it comes to a stop, I&#x27;ll typically wake up.</text></comment> |
30,939,889 | 30,939,649 | 1 | 3 | 30,938,842 | train | <story><title>FAANG promo committees are killing Kubernetes: A Short Thread</title><url>https://twitter.com/kantrn/status/1511791378497384454</url></story><parent_chain><item><author>paxys</author><text>While it is still a stretch, the title should be &quot;Google&#x27;s promo committee is killing Kubernetes&quot;, since no other FAANG-equivalent is using or contributing to Kubernetes in a meaningful way.<p>The core point:<p>&gt; It&#x27;s too indirect, fixing a bug in kube-apiserver might retain a GCP customer or avoid a costly Apple services outage, but can you put a dollar value on that? How much is CI stability worth? Or community happiness?<p>While correct, the same is true for <i>most</i> projects at these companies. Very little work that a single engineer does can be assigned a provable revenue number. How does someone working on an internal build tool get promoted? Or a new training model? A large-scale refactor of a legacy codebase? (All of these are examples of very senior promos at my own FAANG company).<p>Kubernetes is no different. An engineer has to show how the work they did first and foremost aligns with their team&#x27;s goals. If it doesn&#x27;t, then well they shouldn&#x27;t have been working on it in the first place. While working on open-source projects might be tolerated, even on company time, it makes sense that it won&#x27;t put you on a path to promotion unless there is direct benefit to the company from it.</text></item></parent_chain><comment><author>saagarjha</author><text>&gt; While it is still a stretch, the title should be &quot;Google&#x27;s promo committee is killing Kubernetes&quot;, since no other FAANG-equivalent is using or contributing to Kubernetes in a meaningful way.<p>Apple puts Kubernetes on <a href="https:&#x2F;&#x2F;opensource.apple.com" rel="nofollow">https:&#x2F;&#x2F;opensource.apple.com</a> as a project they &quot;lead and contribute to&quot;…<p>&gt; Very little work that a single engineer does can be assigned a provable revenue number. How does someone working on an internal build tool get promoted?<p>While I generally agree, I&#x27;ve made changes in our internal build tools that I can easily put a number on, although it&#x27;s not a revenue number. Make build process 10s faster, 1000 engineers run this 10x a day, you&#x27;re saving more than an engineer day per day of time. That&#x27;s a definite impact right there, assuming your management is on board with accepting it :)</text></comment> | <story><title>FAANG promo committees are killing Kubernetes: A Short Thread</title><url>https://twitter.com/kantrn/status/1511791378497384454</url></story><parent_chain><item><author>paxys</author><text>While it is still a stretch, the title should be &quot;Google&#x27;s promo committee is killing Kubernetes&quot;, since no other FAANG-equivalent is using or contributing to Kubernetes in a meaningful way.<p>The core point:<p>&gt; It&#x27;s too indirect, fixing a bug in kube-apiserver might retain a GCP customer or avoid a costly Apple services outage, but can you put a dollar value on that? How much is CI stability worth? Or community happiness?<p>While correct, the same is true for <i>most</i> projects at these companies. Very little work that a single engineer does can be assigned a provable revenue number. How does someone working on an internal build tool get promoted? Or a new training model? A large-scale refactor of a legacy codebase? (All of these are examples of very senior promos at my own FAANG company).<p>Kubernetes is no different. An engineer has to show how the work they did first and foremost aligns with their team&#x27;s goals. If it doesn&#x27;t, then well they shouldn&#x27;t have been working on it in the first place. While working on open-source projects might be tolerated, even on company time, it makes sense that it won&#x27;t put you on a path to promotion unless there is direct benefit to the company from it.</text></item></parent_chain><comment><author>coredog64</author><text>Here it’s focused on k8s, but it’s not out of line if we generically apply it to AMZN. How many services look cool, have a great re:Invent kick-off, and then go KTLO a year later? I’m going to lay that at the feet of the AMZN promo process, which prioritizes creating something new over real and needed maintenance.<p>I’m going to further reduce this to lazy management. It’s easier to point to splashy announcements to show impact than it is to put in the work and help your direct reports quantity unglamorous maintenance work.</text></comment> |
24,665,991 | 24,665,840 | 1 | 2 | 24,660,775 | train | <story><title>Japan’s lost generation is still jobless and living with their parents</title><url>https://www.bloomberg.com/features/2020-japan-lost-generation/</url></story><parent_chain><item><author>maerF0x0</author><text>Again. We&#x27;re failing to address the &quot;so what?&quot; What does this scenario represent that is _the actual problem_ of the matter?</text></item><item><author>saagarjha</author><text>That&#x27;s because the scenario you&#x27;ve mentioned does not describe these households. The problem here is that there are adults who are partially or wholly supported by their parents in a house where they are not living with (nor was it designed for them to live with) a spouse or children.</text></item><item><author>maerF0x0</author><text>I feel like the &quot;Jobless and living with parents&quot; pejorative is missing the mark.<p>Jobless -- So what? If a country has figured out how to provide for its people w&#x2F;o jobs, so what? For example if we had perfect AI-robot slaves we&#x27;d all be jobless. Would it be a problem? Maybe we should ask people why they want a job, maybe what they want to do doesnt require one?<p>&quot;Living with their parents&quot; - Again, so what? Much of the world and across much of history this was just how it was. No one denigrates someone 0-20 for living with their parents, why should a 30 yr old be denigrated for the same. Plus, for many of us so lucky the same scenario, with opposite take, will occur-- our parents will move in with us later in their life and we&#x27;ll &quot;live with our parents&quot; again. Plus when you add that median sq foot of homes (at least in USA) is rising, you can comfortably live with more people in &quot;home&quot;. With double master bedrooms more common and more square feet we&#x27;re blurring the lines of what a single home means. Some houses are so big that you could just put a dividing wall and a separate entrance and you&#x27;d have 2 homes...</text></item></parent_chain><comment><author>alxlaz</author><text>&gt; What does this scenario represent that is _the actual problem_ of the matter?<p>Among others:<p>- Crippling depression for many of those who are jobless and living with their parents in a culture that is not exactly friendly to them.<p>- An increased incidence of health issues that are correlated with depression and loneliness.<p>- Decreased quality of life for elderly parents who need to support their children within the confines of a difficult, stressful job market and a pension system that sees increasing pressure from an aging population.<p>- An aging working population that has difficulties filling positions around a particular range of experience, which -- in turn -- can make it harder to sustain the social programs required to help people cope.<p>- Increased pressure on social spending in the long term, since people who are struggling to find jobs in their fourties are unlikely to be in a super well-paid position by the time they&#x27;re sixty.<p>It&#x27;s not like these people are basking in a Russell-esque life of idyllic idleness, like they&#x27;re taking a perpetual sabbatical year. Many of them don&#x27;t <i>want</i> to be in the position they&#x27;re in.</text></comment> | <story><title>Japan’s lost generation is still jobless and living with their parents</title><url>https://www.bloomberg.com/features/2020-japan-lost-generation/</url></story><parent_chain><item><author>maerF0x0</author><text>Again. We&#x27;re failing to address the &quot;so what?&quot; What does this scenario represent that is _the actual problem_ of the matter?</text></item><item><author>saagarjha</author><text>That&#x27;s because the scenario you&#x27;ve mentioned does not describe these households. The problem here is that there are adults who are partially or wholly supported by their parents in a house where they are not living with (nor was it designed for them to live with) a spouse or children.</text></item><item><author>maerF0x0</author><text>I feel like the &quot;Jobless and living with parents&quot; pejorative is missing the mark.<p>Jobless -- So what? If a country has figured out how to provide for its people w&#x2F;o jobs, so what? For example if we had perfect AI-robot slaves we&#x27;d all be jobless. Would it be a problem? Maybe we should ask people why they want a job, maybe what they want to do doesnt require one?<p>&quot;Living with their parents&quot; - Again, so what? Much of the world and across much of history this was just how it was. No one denigrates someone 0-20 for living with their parents, why should a 30 yr old be denigrated for the same. Plus, for many of us so lucky the same scenario, with opposite take, will occur-- our parents will move in with us later in their life and we&#x27;ll &quot;live with our parents&quot; again. Plus when you add that median sq foot of homes (at least in USA) is rising, you can comfortably live with more people in &quot;home&quot;. With double master bedrooms more common and more square feet we&#x27;re blurring the lines of what a single home means. Some houses are so big that you could just put a dividing wall and a separate entrance and you&#x27;d have 2 homes...</text></item></parent_chain><comment><author>function_seven</author><text>I suppose if you polled people in this situation, and just asked them, &quot;Is this the life you want to live?&quot;, that would answer the your question.<p>I don&#x27;t know what the results would be, but I can guess that a large percentage of unemployed 30- and 40-somethings living with their parents would very much rather not be. Is it 10%, 35%, 65%? I&#x27;m guessing over 50% to be sure.<p>You can argue that the society is set up wrong. But there it is, with this large cohort of people isolated and shut in. In an economy that still relies on a younger population to take care of its elders.<p>Robots might one day deal with all productive work, but we&#x27;re nowhere near that yet.</text></comment> |
17,915,798 | 17,904,753 | 1 | 2 | 17,902,533 | train | <story><title>Temperature Anomalies by Country 1880-2017</title><url>https://www.flickr.com/photos/150411108@N06/30562013098/in/photostream/</url></story><parent_chain><item><author>epistasis</author><text>I used to think the same thing, that it was supposedly environmental groups that stopped nuclear.<p>However, after investigating the history more closely, it appears that nuclear construction projects were boondoggles even before Three Mile Island. Economics, not activism, is what killed nuclear in the US.<p>Nuclear has always been marketed under a lie, that its cheap, and perhaps too cheap to meter. In reality, well engineered projects are insanely complex, requiring huge material and labor costs during construction. And then there&#x27;s maintenance.<p>People always talk about regulations driving up costs for nuclear, but they never talk about inappropriate regulations that drive up costs, meaning that the high costs are necessary.<p>And when you think about the design of the things, there&#x27;s no reason to think it should be cheap: the nuclear is merely a heat source, which still requires the massive amount of machinery needed for steam turbines. The only part of the thing that&#x27;s potentially cheaper is fuel, but to handle that fuel you&#x27;ve got to have massively engineering and equipment efforts.<p>This history of nuclear is always glossed over by its boosters. It&#x27;s really expensive, and if we didn&#x27;t have better options now, we should build it anyway. And we <i>should</i> have built a lot during the 80s like France did.<p>But today, grid storage is far cheaper than nuclear, and it makes no sense at all to ever build a new nuclear plant. Let&#x27;s keep existing ones running until they&#x27;re replaced with other carbon free sources, but for new investment, current nuclear tech is dead. New SMR, maybe maybe some day if it&#x27;s cheap, but we shall see in a few decades, it&#x27;s not available today like storage, wind, water, and solar are.</text></item><item><author>njarboe</author><text>It is really a shame that nuclear power was demonized so early in its technological development by the same people and groups that are now advocating drastic reductions in fossil fuel consumption. It&#x27;s not like global warming was not understood in 1980. If society had another 40 years of nuclear tech advancement under its belt, I&#x27;m sure China and India would be installing massive nuclear power infrastructure instead of a coal burning power plant a week (and India is just getting started).</text></item><item><author>kimikelku</author><text>In 20 years the changes are huge.
Seeing the data in this perspective is really scary, I don&#x27;t understand how can there be countries ignoring this.</text></item></parent_chain><comment><author>njarboe</author><text>I would like to read a good book on this issue. Any recommendations? Preferably a book written by an historian.<p>My current understanding is that the economics did not work out because: power company borrows x billion in capital to build a nuclear power plant, interest rates in the 80&#x27;s are in the double digits, activists tie up the startup of the power plant for 5-10 years doubling the cost due to interest, power company finally drops starting the plant altogether and the public eats the loss.<p>Of course there are all sorts of complications to what really happened, like power consumption rates going up like crazy while AC is adopted and power companies thinking that the trend would continue forever, which didn&#x27;t happen.<p>Have something you want to believe and you can find a narrative to fit it. This is a really hard trap to avoid and I&#x27;m sure I fall in it often.</text></comment> | <story><title>Temperature Anomalies by Country 1880-2017</title><url>https://www.flickr.com/photos/150411108@N06/30562013098/in/photostream/</url></story><parent_chain><item><author>epistasis</author><text>I used to think the same thing, that it was supposedly environmental groups that stopped nuclear.<p>However, after investigating the history more closely, it appears that nuclear construction projects were boondoggles even before Three Mile Island. Economics, not activism, is what killed nuclear in the US.<p>Nuclear has always been marketed under a lie, that its cheap, and perhaps too cheap to meter. In reality, well engineered projects are insanely complex, requiring huge material and labor costs during construction. And then there&#x27;s maintenance.<p>People always talk about regulations driving up costs for nuclear, but they never talk about inappropriate regulations that drive up costs, meaning that the high costs are necessary.<p>And when you think about the design of the things, there&#x27;s no reason to think it should be cheap: the nuclear is merely a heat source, which still requires the massive amount of machinery needed for steam turbines. The only part of the thing that&#x27;s potentially cheaper is fuel, but to handle that fuel you&#x27;ve got to have massively engineering and equipment efforts.<p>This history of nuclear is always glossed over by its boosters. It&#x27;s really expensive, and if we didn&#x27;t have better options now, we should build it anyway. And we <i>should</i> have built a lot during the 80s like France did.<p>But today, grid storage is far cheaper than nuclear, and it makes no sense at all to ever build a new nuclear plant. Let&#x27;s keep existing ones running until they&#x27;re replaced with other carbon free sources, but for new investment, current nuclear tech is dead. New SMR, maybe maybe some day if it&#x27;s cheap, but we shall see in a few decades, it&#x27;s not available today like storage, wind, water, and solar are.</text></item><item><author>njarboe</author><text>It is really a shame that nuclear power was demonized so early in its technological development by the same people and groups that are now advocating drastic reductions in fossil fuel consumption. It&#x27;s not like global warming was not understood in 1980. If society had another 40 years of nuclear tech advancement under its belt, I&#x27;m sure China and India would be installing massive nuclear power infrastructure instead of a coal burning power plant a week (and India is just getting started).</text></item><item><author>kimikelku</author><text>In 20 years the changes are huge.
Seeing the data in this perspective is really scary, I don&#x27;t understand how can there be countries ignoring this.</text></item></parent_chain><comment><author>bjourne</author><text>Case in point - the bankruptcy of Westinghouse. Caused by economics not environmentalists.</text></comment> |
25,614,043 | 25,613,321 | 1 | 3 | 25,612,786 | train | <story><title>Facebook's advertising integrity chief leaves company</title><url>https://www.reuters.com/article/us-facebook-executive-idUSKBN2962M6</url></story><parent_chain><item><author>absolutelyrad</author><text>&quot;Chief of Advertising Integrity&quot; does anyone take that title seriously? Forget advertising, Facebook and it&#x27;s CEO himself has no integrity.</text></item></parent_chain><comment><author>wpietri</author><text>I can&#x27;t find it now, but I remember a story from somebody in the Lean Manufacturing world about a place that was having safety problems, so they appointed somebody Safety Director. This signaled to everybody that safety was that one guy&#x27;s problem, not theirs. Accidents went up further and stayed up until they got rid of the Safety Directory position and made everybody responsible for safety.<p>That resonated for me because I&#x27;ve seen that happen in software, that classic pattern where cowboy coders ship garbage to QA. The lowest bug rates I&#x27;ve seen are where everybody cares about quality.<p>With Facebook, I expect that &quot;Chief of Advertising Integrity&quot; is sort of light a lightning rod. The job is not to solve the problem, it&#x27;s to take the hits.</text></comment> | <story><title>Facebook's advertising integrity chief leaves company</title><url>https://www.reuters.com/article/us-facebook-executive-idUSKBN2962M6</url></story><parent_chain><item><author>absolutelyrad</author><text>&quot;Chief of Advertising Integrity&quot; does anyone take that title seriously? Forget advertising, Facebook and it&#x27;s CEO himself has no integrity.</text></item></parent_chain><comment><author>VonGuard</author><text>I mean, &quot;Advertising Integrity&quot; and &quot;Facebook&quot; shouldn&#x27;t appear in the same sentence. Amazon is bad enough with fake reviews and retailers that ship terrible products when advertising them as something better.<p>So it takes a lot to make me think something is worse and meaner to consumers than Amazon. But sure enough, Facebook is it. Their ads are about 60% complete scams, from what I can tell. I get all these ads for $200 Lego sets for $30! And there are hundreds of comments from people who have bought. Guarantee they all got 1 Lego brick in the mail 8 weeks later, and the site that sold it to them is gone.<p>This would be bad if it was an occasional thing, but most Facebook ads I see are EXACTLY like this. Bait and switch. They send you a thing so you can&#x27;t claim they didn&#x27;t send you anything, but Facebook is making bank off of these dishonest scammers and seems not only not to care, but to encourage it. Oh and the thing they send you is from China, so sending it back costs more than you spent.</text></comment> |
26,018,788 | 26,018,355 | 1 | 2 | 26,014,455 | train | <story><title>How The Expanse went from game concept to blockbuster TV series</title><url>https://andrewliptak.substack.com/p/the-expanse-james-sa-corey-syfy-amazon</url></story><parent_chain><item><author>yuters</author><text>Other nitpicky things:<p>- Lights inside helmets to light up a person&#x27;s face is a pretty dumb thing when you think about it, but it makes complete sense in a tv series, as you definitely want to see the actor&#x27;s face.<p>- Transparent&#x2F;Glass tablets &amp; phones is still a complete mystery to me how this could be useful in any way... other than it &quot;looks cool&quot;.</text></item><item><author>bentcorner</author><text>Agree - I love the show but the two nits I have with it are the sounds in space (engines&#x2F;guns most notably, although it makes for a better show) and the fact that they can&#x27;t film in zero-G.<p>The weightless thing is obviously understandable but it&#x27;s the kind of thing where you can&#x27;t unsee the things they do to convince you there is no gravity (magnets everywhere!)</text></item><item><author>sillyquiet</author><text>I don&#x27;t know if I&#x27;d say the get the technical details <i>exactly</i> right, as there are some concessions to story-telling over physics - the (probably) impossibly efficient fusion drives, and the protomolecule is kinda magic sometimes, but it get is right <i>enough</i>, and way more so than any other sci-fi show I&#x27;ve seen.</text></item><item><author>dreamcompiler</author><text>I&#x27;m kind of surprised how many nerdy people I know who have never watched this show. It is by far the best (maybe only?) hard sci-fi TV show ever, and almost every episode is better than any hard sci-fi <i>movie</i> ever made.<p>If AC Clarke and Stanley Kubrick were alive they&#x27;d be heaping praise on this show for getting so many of the technical details exactly right.</text></item></parent_chain><comment><author>outworlder</author><text>&gt; Lights inside helmets to light up a person&#x27;s face is a pretty dumb thing when you think about it<p>Only if you are doing EVA astronomy and need pitch black darkness to see stuff outside. Because you can light up someone&#x27;s face enough and still not interfere with their activities.<p>Otherwise – it would be important to be able to see the other person&#x27;s face, both to interact with them, and to gauge their well-being.<p>Their phones are not exactly transparent, they are &quot;holographic&quot;. They can project images larger than their own size. Same as many screens depicted in the show.</text></comment> | <story><title>How The Expanse went from game concept to blockbuster TV series</title><url>https://andrewliptak.substack.com/p/the-expanse-james-sa-corey-syfy-amazon</url></story><parent_chain><item><author>yuters</author><text>Other nitpicky things:<p>- Lights inside helmets to light up a person&#x27;s face is a pretty dumb thing when you think about it, but it makes complete sense in a tv series, as you definitely want to see the actor&#x27;s face.<p>- Transparent&#x2F;Glass tablets &amp; phones is still a complete mystery to me how this could be useful in any way... other than it &quot;looks cool&quot;.</text></item><item><author>bentcorner</author><text>Agree - I love the show but the two nits I have with it are the sounds in space (engines&#x2F;guns most notably, although it makes for a better show) and the fact that they can&#x27;t film in zero-G.<p>The weightless thing is obviously understandable but it&#x27;s the kind of thing where you can&#x27;t unsee the things they do to convince you there is no gravity (magnets everywhere!)</text></item><item><author>sillyquiet</author><text>I don&#x27;t know if I&#x27;d say the get the technical details <i>exactly</i> right, as there are some concessions to story-telling over physics - the (probably) impossibly efficient fusion drives, and the protomolecule is kinda magic sometimes, but it get is right <i>enough</i>, and way more so than any other sci-fi show I&#x27;ve seen.</text></item><item><author>dreamcompiler</author><text>I&#x27;m kind of surprised how many nerdy people I know who have never watched this show. It is by far the best (maybe only?) hard sci-fi TV show ever, and almost every episode is better than any hard sci-fi <i>movie</i> ever made.<p>If AC Clarke and Stanley Kubrick were alive they&#x27;d be heaping praise on this show for getting so many of the technical details exactly right.</text></item></parent_chain><comment><author>musingsole</author><text>Are lights in a helmet dumb? Being able to see companion&#x27;s facial expressions while not critical would be absolutely useful in day-to-day life in space - TV production reasons aside.<p>On the transparent glass phones: &quot;looks cool&quot; is reason enough for most any consumer product. I haven&#x27;t read the series, so I don&#x27;t know if there is some lore explanation somewhere -- but --- if the technology is lying around as some component of a space habitat AND it looks cool, yeah, that tech is definitely going in a phone.</text></comment> |
18,746,585 | 18,746,595 | 1 | 3 | 18,745,182 | train | <story><title>Binctr: Static, unprivileged, self-contained containers as executable binaries</title><url>https://github.com/genuinetools/binctr</url></story><parent_chain></parent_chain><comment><author>jclarkcom</author><text>I worked on something similar for Windows for nearly 10 years, called Thinstall (acquired by vmware and renamed to Thinapp). I love the idea of something like that for linux.<p>We put a lot of effort into being able to run an application directly from a compressed single-file binary, you have a small executable with a big payload attached to the end of it. The payload essentially contains a mountable filesystem, however because windows doesn&#x27;t support doing anything like that from an unprivileged account we had to emulate many things Windows normally does, including execution of binary images.<p>We did some tricks where executable data was stored on disk in a format it can be directly memory mapped and run without reading anything - this allowed us to launch most applications over a network without extracting anything to disk locally and achieve millisecond launch times. Pages would get pulled into local memory by the OS as needed while the application was running.<p>The end result was that you can create a single EXE file could contain things like python + script, or more complex like photoshop &amp; Word. Just go to a new computer from a guest account, launch the EXE and you instantly start using that app.<p>I haven&#x27;t been involved with it for the last 6 years, but I believe vmware still offers it.</text></comment> | <story><title>Binctr: Static, unprivileged, self-contained containers as executable binaries</title><url>https://github.com/genuinetools/binctr</url></story><parent_chain></parent_chain><comment><author>mroche</author><text>&gt; Well judging by the original GitHub issue about unprivileged runc containers, the largest group of commenters is from the scientific community who are restricted to not run certain programs as root.<p>Which is why we use Singularity[0]. Apologies if I’m missing something, but to me this problem they’re trying to solve, has already been solved. As stated in the README:<p>&gt; Singularity is an open source container platform designed to be simple, fast, and secure. Singularity is optimized for EPC and HPC workloads, allowing untrusted users to run untrusted containers in a trusted way.<p>Singularity ‘requires’ root or elevated privileges to create and modify containers, but running them is done in the user’s namespace with that user’s permission set. And privileges can’t be elevated during the containers runtime as there are kernel level catches that prevent sudo and su from working inside the container.<p>In terms of the ‘static’ part, Singularity uses SquashFS to produce a single binary image, and uses the SIF (Singularity Image File) format to define applications, their dependencies, and runscripts. On top of being able to run anything inside the container with the `exec` subcommand.<p>You can also create sandbox development images that are just a directory on disk for testing things out and installing&#x2F;building tools manually, then convert it into a SIF container after for cluster deployment. Or be nicer and port your process into a recipe&#x2F;definition file.<p>Most scientific&#x2F;HPC related centers have started utilizing Singularity for their container workflow. Tools like
Docker are essentially banned because of their perma-root privileges[1].<p>[0] <a href="https:&#x2F;&#x2F;github.com&#x2F;sylabs&#x2F;singularity" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;sylabs&#x2F;singularity</a>
[1] I’m an admin who reimplemented Singularity on our university’s cluster. With a heavy need on filesystem integration (which Singularity solves with great configuration options), containers which run with root privileges would be a massive security vulnerability.</text></comment> |
30,201,256 | 30,201,252 | 1 | 2 | 30,193,450 | train | <story><title>Mysterious aircraft spotted at Area 51 in satellite image</title><url>https://www.thedrive.com/the-war-zone/44057/mysterious-aircraft-spotted-at-area-51-in-unprecedented-satellite-image</url></story><parent_chain><item><author>sethammons</author><text>Does the image not look like a printed tarp laid over the hangar? I think it is simple deception</text></item></parent_chain><comment><author>MontagFTB</author><text>The shadow cast by the tarp suggests it&#x27;s opaque, not transparent (or even translucent, really.) Combined with the horizontal lines across &quot;plane&quot;, it all suggests a weather-beaten opaque tarp that&#x27;s been painted to conceal its contents and confuse any overhead photographers.</text></comment> | <story><title>Mysterious aircraft spotted at Area 51 in satellite image</title><url>https://www.thedrive.com/the-war-zone/44057/mysterious-aircraft-spotted-at-area-51-in-unprecedented-satellite-image</url></story><parent_chain><item><author>sethammons</author><text>Does the image not look like a printed tarp laid over the hangar? I think it is simple deception</text></item></parent_chain><comment><author>runjake</author><text>Could be, but the shadows and taxiway lines line up perfectly. That would require constant shifting of props to maintain for 3 full days (this is 101 stuff for GEOINT folks).<p>It&#x27;s also important to keep in mind that spy sats get far better resolution than this publicly-released image would lead you to believe.</text></comment> |
28,898,600 | 28,897,985 | 1 | 2 | 28,896,367 | train | <story><title>Python stands to lose its GIL, and gain a lot of speed</title><url>https://www.infoworld.com/article/3637073/python-stands-to-lose-its-gil-and-gain-a-lot-of-speed.html</url></story><parent_chain><item><author>chacham15</author><text>There are certain classes of errors that it prevents. E.g:<p>Thread1:
a = 0xFFFFFFFF00000000<p>Thread2:
a = 0x00000000FFFFFFFF<p>One might think that the two possible values of a if those are run concurrently are 0xFFFFFFFF00000000 and 0x00000000FFFFFFFF. But actually 0x0000000000000000
and 0xFFFFFFFFFFFFFFFF are also possible because the load itself isnt atomic.<p>The GIL (AFAICT) will prevent the latter two possibilities.</text></item><item><author>avianlyric</author><text>I don’t see how the GIL makes writing thread safe software any easier. The GIL might prevent two Python threads executing simultaneously, but it doesn’t change the fact that a Python thread can be preempted, meaning your global state can change at any point during execution without warning.<p>Most of the issues with multi-threading come from concurrency, not parallelism. The GIL allows concurrency, you just don’t get any of the advantages of parallelism, which is normally the reason for putting up with the complexity concurrency creates.</text></item><item><author>dleslie</author><text>I wonder how many folks think they&#x27;re writing thread safe software with ease, and are unaware that they are leaning on the GIL?<p>Could be that the impact of this change is far broader than just a few key libraries.</text></item></parent_chain><comment><author>adrian_b</author><text>Most CPUs guarantee that aligned loads and stores up to the register size, i.e. now usually up to 64-bit, are atomic.<p>The compilers also take care to align most variables.<p>So while your scenario is not impossible, it would take some effort to force &quot;a&quot; to be not aligned, e.g. by being a member in a structure with inefficient layout.<p>Normally in a multithreaded program all shared variables should be aligned, which would guarantee atomic loads and stores.</text></comment> | <story><title>Python stands to lose its GIL, and gain a lot of speed</title><url>https://www.infoworld.com/article/3637073/python-stands-to-lose-its-gil-and-gain-a-lot-of-speed.html</url></story><parent_chain><item><author>chacham15</author><text>There are certain classes of errors that it prevents. E.g:<p>Thread1:
a = 0xFFFFFFFF00000000<p>Thread2:
a = 0x00000000FFFFFFFF<p>One might think that the two possible values of a if those are run concurrently are 0xFFFFFFFF00000000 and 0x00000000FFFFFFFF. But actually 0x0000000000000000
and 0xFFFFFFFFFFFFFFFF are also possible because the load itself isnt atomic.<p>The GIL (AFAICT) will prevent the latter two possibilities.</text></item><item><author>avianlyric</author><text>I don’t see how the GIL makes writing thread safe software any easier. The GIL might prevent two Python threads executing simultaneously, but it doesn’t change the fact that a Python thread can be preempted, meaning your global state can change at any point during execution without warning.<p>Most of the issues with multi-threading come from concurrency, not parallelism. The GIL allows concurrency, you just don’t get any of the advantages of parallelism, which is normally the reason for putting up with the complexity concurrency creates.</text></item><item><author>dleslie</author><text>I wonder how many folks think they&#x27;re writing thread safe software with ease, and are unaware that they are leaning on the GIL?<p>Could be that the impact of this change is far broader than just a few key libraries.</text></item></parent_chain><comment><author>ignoramous</author><text>Related: <i>Symmetric Multi-Processor primer for Android</i>, <a href="https:&#x2F;&#x2F;developer.android.com&#x2F;training&#x2F;articles&#x2F;smp" rel="nofollow">https:&#x2F;&#x2F;developer.android.com&#x2F;training&#x2F;articles&#x2F;smp</a> (although for Android&#x2F;ARM, it makes for a pretty good read on the topic).</text></comment> |
19,405,010 | 19,405,197 | 1 | 2 | 19,403,271 | train | <story><title>V Programming Language</title><url>https://vlang.io/</url></story><parent_chain><item><author>andr</author><text>I love looking at new languages. People invent really creative stuff. However, my exploration usually ends with &quot;this is great, but there are no libraries for it, so I probably won&#x27;t use it&quot;.<p>If you are building a language, starting from scratch is the epitome of Not Invented Here syndrome. Build it on top of an existing ecosystem. Look at Elixir and how it builds on Erlang and interoperates with it just perfectly. Or look Groovy, Scala and Clojure to see what kind of range you can get from a single platform. With the exception of Go, every language that has become popular in the past 10 years, built on something else.</text></item></parent_chain><comment><author>mstade</author><text>&gt; With the exception of Go, every language that has become popular in the past 10 years, built on something else.<p>And Go probably wouldn&#x27;t have half the range it enjoys today without the massive reach and coffers of Google. That&#x27;s not a snark, or a critique even, just a reflection of the difficulty of breaking through in this space and indeed a comment to support your assertion that in order to succeed in this space today you probably have to build on or successfully interoperate with an already established platform.<p>If Go didn&#x27;t have the backing of Google, I doubt it&#x27;d have half the audience it enjoys today; Rob Pike notwithstanding. Case in point: Plan 9.</text></comment> | <story><title>V Programming Language</title><url>https://vlang.io/</url></story><parent_chain><item><author>andr</author><text>I love looking at new languages. People invent really creative stuff. However, my exploration usually ends with &quot;this is great, but there are no libraries for it, so I probably won&#x27;t use it&quot;.<p>If you are building a language, starting from scratch is the epitome of Not Invented Here syndrome. Build it on top of an existing ecosystem. Look at Elixir and how it builds on Erlang and interoperates with it just perfectly. Or look Groovy, Scala and Clojure to see what kind of range you can get from a single platform. With the exception of Go, every language that has become popular in the past 10 years, built on something else.</text></item></parent_chain><comment><author>_hardwaregeek</author><text>Except that&#x27;s your specific attitude towards language adoption. And while it&#x27;s a perfectly reasonable stance, there&#x27;s plenty of people who see a language with no libraries and see an opportunity to build their own. Every language ecosystem has to start somewhere.<p>Also, Rust started in the last 10 years and wasn&#x27;t built on anything. Unless you count LLVM?</text></comment> |
13,276,670 | 13,276,192 | 1 | 2 | 13,273,461 | train | <story><title>From Secretary to Software Developer: The Hard Way</title><url>https://medium.com/code-like-a-girl/from-secretary-to-software-developer-the-hard-way-ddfc60c8b675#.xnhuvooy6</url></story><parent_chain><item><author>kirse</author><text><i>they are often just working a day job.</i><p>I used to be snooty about this too until I had a member join one of my teams who is exactly this type of person... Treats it like a day job, and absolutely rips through well-defined coding tasks as long as I do the general solution-finding and lay the architectural groundwork ahead of time. They don&#x27;t burn out either, because it&#x27;s just work to them and they take regular vacations.<p>They&#x27;re not my go-to for solving architectural-type problems (solution-finding as you call it), but I&#x27;m OK with that because their strengths lie elsewhere in terms of discipline, focus, training JR team members in coding practices, knowledge of SW project process, etc. Every team needs its brick-layers who can work hard and follow blueprints really well, and not all of those brick-layers are going to be architects. One of my biggest work-related lessons out of 2016 really.</text></item><item><author>ChuckMcM</author><text>The thing that struck me is &quot;anyone who is fascinated by computers and spends all their free time playing with them can be a developer.&quot;<p>Back before developers were perceived as &#x27;rich&#x27; and &#x27;pampered&#x27; there were people who were fascinated by computers and spent all their time playing with them and were called &#x27;nerds.&#x27; Then it became &quot;cool&quot; to be a developer or &quot;you can get rich as a developer at a startup!&quot; and then you get people who don&#x27;t care at all about computers and really never have, working as developers.<p>My litmus test is often to ask someone when they show me a solution, &quot;what other solutions did you consider?&quot; If they have wandered around looking at different ways to attack the problem they are more typically &#x27;nerd&#x27; type developers, if their response is &quot;none, this works so I went with it, moving on.&quot; they are often just working a day job. Watching the two types of people from the late 90&#x27;s to today, the people in it for the money burn out much more frequently.</text></item></parent_chain><comment><author>throwaway99187</author><text>I&#x27;ve never seen a good architecture that wasn&#x27;t largely by the single individual who started and initially wrote a project.</text></comment> | <story><title>From Secretary to Software Developer: The Hard Way</title><url>https://medium.com/code-like-a-girl/from-secretary-to-software-developer-the-hard-way-ddfc60c8b675#.xnhuvooy6</url></story><parent_chain><item><author>kirse</author><text><i>they are often just working a day job.</i><p>I used to be snooty about this too until I had a member join one of my teams who is exactly this type of person... Treats it like a day job, and absolutely rips through well-defined coding tasks as long as I do the general solution-finding and lay the architectural groundwork ahead of time. They don&#x27;t burn out either, because it&#x27;s just work to them and they take regular vacations.<p>They&#x27;re not my go-to for solving architectural-type problems (solution-finding as you call it), but I&#x27;m OK with that because their strengths lie elsewhere in terms of discipline, focus, training JR team members in coding practices, knowledge of SW project process, etc. Every team needs its brick-layers who can work hard and follow blueprints really well, and not all of those brick-layers are going to be architects. One of my biggest work-related lessons out of 2016 really.</text></item><item><author>ChuckMcM</author><text>The thing that struck me is &quot;anyone who is fascinated by computers and spends all their free time playing with them can be a developer.&quot;<p>Back before developers were perceived as &#x27;rich&#x27; and &#x27;pampered&#x27; there were people who were fascinated by computers and spent all their time playing with them and were called &#x27;nerds.&#x27; Then it became &quot;cool&quot; to be a developer or &quot;you can get rich as a developer at a startup!&quot; and then you get people who don&#x27;t care at all about computers and really never have, working as developers.<p>My litmus test is often to ask someone when they show me a solution, &quot;what other solutions did you consider?&quot; If they have wandered around looking at different ways to attack the problem they are more typically &#x27;nerd&#x27; type developers, if their response is &quot;none, this works so I went with it, moving on.&quot; they are often just working a day job. Watching the two types of people from the late 90&#x27;s to today, the people in it for the money burn out much more frequently.</text></item></parent_chain><comment><author>joatmon-snoo</author><text>Out of curiosity, how did you get this person on your team, since it doesn&#x27;t sound like you were open to the idea until after the fact.</text></comment> |
30,384,294 | 30,384,412 | 1 | 2 | 30,382,691 | train | <story><title>“The president of MIT told me that tenure was not about research or merit.”</title><url>https://threadreaderapp.com/thread/1494369809538195456.html</url></story><parent_chain><item><author>captainmuon</author><text>I don&#x27;t understand why hiring in academia is so weird. People are strung along for years, and then you are suddenly either out or you have tenure for life. (A friend compared a professorship it to being the pope, which I think is fitting.)<p>You need to have a perfect track record. You have to have worked in a couple of different places, with no gaps, you need a lot of publications and &quot;visibility&quot;. And even then, in my experience about 50% of positions are given on merit, and 50% are given seemingly randomly. Even if you are incredibly self-confident and count yourself among the top 5%, it is still a gamble.<p>Academia works like a guild, or maybe like the military (up or out). But it seems everybody would benefit if hiring was changed to be more like outside academia. No more temporary positions vs unfireable professors, but instead hire everybody on regular open-ended contracts. Don&#x27;t insist on an unbroken career and years of travelling journeymanship, but value broad experiences and career changers. I know a lot of people who are considered academic failures but were welcomed in industry &quot;with kisses&quot;.<p>I don&#x27;t think the cause is just resistance from entrenched people, or ideology. There is a lot of neoliberal pressure to run universities more like companies. And I guess hiring is one of the few areas where this would not be a bad thing. Is it just shortsightedness then? Or lack of funding, and scarcity of jobs?</text></item></parent_chain><comment><author>jltsiren</author><text>Traditional universities were structured like guilds. After you completed your studies in liberal arts, you got the rank of master and the license to teach at any university. The members (masters) of the university made decisions by vote. The idea that universities should have bosses and that the faculty are employees is rather new.<p>These days, the weirdness of academic job markets is mostly limited to research universities. That&#x27;s because universities don&#x27;t do research, but they still hire researchers. They provide office&#x2F;lab space, equipment, and administrative services to researchers in exchange for a large fraction of the funding the researchers are able to obtain. Senior researchers are employees only in a technical sense. If one of them quits, the university most likely won&#x27;t try to hire another person to continue the research. Instead, the researcher probably takes their job to another university and continues there.<p>Research universities hire people who teach, mentor, and serve in administrative duties. They don&#x27;t hire people to do research, because they don&#x27;t do research and have no need for researchers. They hire active researchers and give them the opportunity to do research primarily for the prestige value. Because most universities are funded by taxes and&#x2F;or tuition fees, they can&#x27;t pay competitive salaries. In order to attract top researchers (and thus prestige), they have to offer something else. In most cases, that &quot;something else&quot; is a promise of a permanent position with the option to spend a large fraction of their time on whatever they are interested in.</text></comment> | <story><title>“The president of MIT told me that tenure was not about research or merit.”</title><url>https://threadreaderapp.com/thread/1494369809538195456.html</url></story><parent_chain><item><author>captainmuon</author><text>I don&#x27;t understand why hiring in academia is so weird. People are strung along for years, and then you are suddenly either out or you have tenure for life. (A friend compared a professorship it to being the pope, which I think is fitting.)<p>You need to have a perfect track record. You have to have worked in a couple of different places, with no gaps, you need a lot of publications and &quot;visibility&quot;. And even then, in my experience about 50% of positions are given on merit, and 50% are given seemingly randomly. Even if you are incredibly self-confident and count yourself among the top 5%, it is still a gamble.<p>Academia works like a guild, or maybe like the military (up or out). But it seems everybody would benefit if hiring was changed to be more like outside academia. No more temporary positions vs unfireable professors, but instead hire everybody on regular open-ended contracts. Don&#x27;t insist on an unbroken career and years of travelling journeymanship, but value broad experiences and career changers. I know a lot of people who are considered academic failures but were welcomed in industry &quot;with kisses&quot;.<p>I don&#x27;t think the cause is just resistance from entrenched people, or ideology. There is a lot of neoliberal pressure to run universities more like companies. And I guess hiring is one of the few areas where this would not be a bad thing. Is it just shortsightedness then? Or lack of funding, and scarcity of jobs?</text></item></parent_chain><comment><author>gwd</author><text>&gt; I don&#x27;t understand why hiring in academia is so weird.<p>Well do the math. In a steady-state where the number of academic positions is static, each professor needs to train <i>a single academia-focused PhD student in his entire career</i>. OK, maybe make that 2 to account for attrition. But most professors are churning out <i>far</i> more PhDs looking to enter academia than there can possibly ever be jobs for. Then these highly-skilled and disciplined individuals end up working for peanuts for decades in the hopes of landing a &quot;tenure&quot; job.<p>I have two close friends, one in their 40&#x27;s, one around 50, who are in this situation, and I think it&#x27;s absolutely shameful. Post-doc positions are fixed terms, so every two to three years they have to worry about getting more funding or being without a job. There&#x27;s no reason someone as highly skilled and disciplined as these two should be 1) paid so low, and 2) worrying how they&#x27;re going to support their families every few years. It&#x27;s really like some kind of a cult.<p>At this point I would honestly never advise anyone to enter academia, unless you&#x27;re in a field like Computer Science, where industry does a good job competing with universities for PhDs. If you have the chops to get tenure in STEM, you have the chops to be paid more, with better job security, better work&#x2F;life balance, better career trajectory, better everything, somewhere else.</text></comment> |
25,520,570 | 25,519,626 | 1 | 3 | 25,514,930 | train | <story><title>Xfce 4.16</title><url>https://xfce.org/about/news/?post=1608595200</url></story><parent_chain><item><author>awiesenhofer</author><text>Wow, what a blast from the past. I always wonder though is anyone actually using themes like these as their actual daily driver?<p>Link to the project with Screenshots: <a href="https:&#x2F;&#x2F;github.com&#x2F;grassmunk&#x2F;Chicago95" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;grassmunk&#x2F;Chicago95</a></text></item><item><author>refracture</author><text>Chicago95 can take that a step further if you like. I&#x27;m running KDE lately too (Slackware-current finally got KDE5 recently so I&#x27;m trying it out), but XFCE is the old trusty default for me.</text></item><item><author>cies</author><text>Feels like Win98SE to me (that&#x27;s a compliment). Love it for that, though back to KDE for my daily driver.</text></item><item><author>spaniard89277</author><text>I agree, XFCE is there when you need it. No weird experiments, always consistent.</text></item><item><author>Kototama</author><text>Me too but I can tell you why.<p>- Coherency: the way it works and is presented does not change much over the years. It&#x27;s important for me. I don&#x27;t want to adapt everytime a designer thinks he has a good idea.<p>- Simplicity: it just works and is well configured out of the box<p>- Efficiency: not the lightest Desktop Manager in the market but it is light enough so it won&#x27;t eat resources for nothing<p>- Right level of complexity: there is enough to configure it to adapt it to your needs but not too much to make it a mess. Take the xfce console for example: you can rename tabs, move them and search text in them. Last time I check these features were not available in Gnome Terminal. But at the same time I don&#x27;t want much more than that.<p>Coherency is really important for me: Xfce has been there when Gnome &#x2F; Unity &#x2F; Gnome 3 &#x2F; Mate &#x2F; Cinnamon were confusing me by offering all the same but not really the same.<p>Edit: I wrote &quot;consistency&quot; instead of &quot;coherency&quot; but I guess the right term is coherency in this context.</text></item><item><author>m8s</author><text>This seems like a ton of work and a great achievement. XFCE, for whatever reason, is always my go to desktop environment and really just &quot;feels like home&quot;. Thank you to everyone who contributed.</text></item></parent_chain><comment><author>_lffv</author><text>My grandmother&#x27;s computer is an old Debian box with nothing more than `ly` (as a DM), xfce, Chicago95, and Firefox. She loves it, though I made a ton of tweaks here and there to make it easier for her to use (specifically a ton of website launchers on her desktop). She got lost in regards to how to use her computer back in the XP&gt;8 transition so it was great to be able to bring her back to that style of desktop and have the system be easier to fix than Windows 8 or 10.</text></comment> | <story><title>Xfce 4.16</title><url>https://xfce.org/about/news/?post=1608595200</url></story><parent_chain><item><author>awiesenhofer</author><text>Wow, what a blast from the past. I always wonder though is anyone actually using themes like these as their actual daily driver?<p>Link to the project with Screenshots: <a href="https:&#x2F;&#x2F;github.com&#x2F;grassmunk&#x2F;Chicago95" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;grassmunk&#x2F;Chicago95</a></text></item><item><author>refracture</author><text>Chicago95 can take that a step further if you like. I&#x27;m running KDE lately too (Slackware-current finally got KDE5 recently so I&#x27;m trying it out), but XFCE is the old trusty default for me.</text></item><item><author>cies</author><text>Feels like Win98SE to me (that&#x27;s a compliment). Love it for that, though back to KDE for my daily driver.</text></item><item><author>spaniard89277</author><text>I agree, XFCE is there when you need it. No weird experiments, always consistent.</text></item><item><author>Kototama</author><text>Me too but I can tell you why.<p>- Coherency: the way it works and is presented does not change much over the years. It&#x27;s important for me. I don&#x27;t want to adapt everytime a designer thinks he has a good idea.<p>- Simplicity: it just works and is well configured out of the box<p>- Efficiency: not the lightest Desktop Manager in the market but it is light enough so it won&#x27;t eat resources for nothing<p>- Right level of complexity: there is enough to configure it to adapt it to your needs but not too much to make it a mess. Take the xfce console for example: you can rename tabs, move them and search text in them. Last time I check these features were not available in Gnome Terminal. But at the same time I don&#x27;t want much more than that.<p>Coherency is really important for me: Xfce has been there when Gnome &#x2F; Unity &#x2F; Gnome 3 &#x2F; Mate &#x2F; Cinnamon were confusing me by offering all the same but not really the same.<p>Edit: I wrote &quot;consistency&quot; instead of &quot;coherency&quot; but I guess the right term is coherency in this context.</text></item><item><author>m8s</author><text>This seems like a ton of work and a great achievement. XFCE, for whatever reason, is always my go to desktop environment and really just &quot;feels like home&quot;. Thank you to everyone who contributed.</text></item></parent_chain><comment><author>Snortibartfast</author><text>I&#x27;ve used Memphis98 (similar to Chicago95) since it came out. Although just as a GTK-theme, not the entire desktop. Window manager is FVWM and taskbar&#x2F;panel&#x2F;session-manager is LXQt, so it&#x27;s a bit of a Franken-desktop :)<p>For Qt-apps I use the &quot;Windows&quot; style so they fit together nicely.<p>Comparing Memphis and Chicago, there are some layout-bugs in Memphis, but I feel like it&#x27;s overall a bit better balanced than Chicago.<p>I think all new themes are too bright and flat, Windows 9X was perfect (at least in that regard).</text></comment> |
40,007,127 | 40,006,561 | 1 | 3 | 40,005,005 | train | <story><title>Using ClickHouse to scale an events engine</title><url>https://github.com/getlago/lago/wiki/Using-Clickhouse-to-scale-an-events-engine</url></story><parent_chain><item><author>joshstrange</author><text>It&#x27;s to power all our analytics. We ETL data into it and some data is write-once so we don&#x27;t have updates&#x2F;deletes but a number of our tables have summary data ETL&#x27;d into them which means cleaning up the old rows.<p>I&#x27;m sure CH shines for insert-only workloads but that doesn&#x27;t cover all our needs.</text></item><item><author>nsguy</author><text>What is your use case? If you&#x27;re deleting rows that already feels like maybe it&#x27;s not the intended use case. I think about clickhouse as taking in a firehose of immutable data that you want to aggregate&#x2F;analyze&#x2F;report on. Let&#x27;s say a million records per second. I&#x27;ll make up an example, the orientation, speed and acceleration of every Tesla vehicle in the world in real time every second.</text></item><item><author>joshstrange</author><text>I feel like with all the Clickhouse praise on HN that we &#x2F;must&#x2F; be doing something fundamentally wrong because I hate every interaction I have with Clickhouse.<p>* Timeouts (only 30s???) unless I used the cli client<p>* Cancelling rows - Just kill me, so many bugs and FINAL&#x2F;PREWHERE are massive foot-guns<p>* Cluster just feels annoying and fragile don&#x27;t forget &quot;ON CLUSTER&quot; or you&#x27;ll have a bad time<p>Again, I feel like we must be doing something wrong but we are paying an arm and a leg for that &quot;privilege&quot;.</text></item></parent_chain><comment><author>darthShadow</author><text>You have already gotten excellent options from the other comments, but here&#x27;s another one that&#x27;s not been mentioned yet.<p>You may want to consider adjusting your partition key (if feasible) as a function of datetime so you can just drop a complete partition when required, rather than needing separate delete queries.<p>In my experience, it has proven to be a very quick and clean way to clear out older data.</text></comment> | <story><title>Using ClickHouse to scale an events engine</title><url>https://github.com/getlago/lago/wiki/Using-Clickhouse-to-scale-an-events-engine</url></story><parent_chain><item><author>joshstrange</author><text>It&#x27;s to power all our analytics. We ETL data into it and some data is write-once so we don&#x27;t have updates&#x2F;deletes but a number of our tables have summary data ETL&#x27;d into them which means cleaning up the old rows.<p>I&#x27;m sure CH shines for insert-only workloads but that doesn&#x27;t cover all our needs.</text></item><item><author>nsguy</author><text>What is your use case? If you&#x27;re deleting rows that already feels like maybe it&#x27;s not the intended use case. I think about clickhouse as taking in a firehose of immutable data that you want to aggregate&#x2F;analyze&#x2F;report on. Let&#x27;s say a million records per second. I&#x27;ll make up an example, the orientation, speed and acceleration of every Tesla vehicle in the world in real time every second.</text></item><item><author>joshstrange</author><text>I feel like with all the Clickhouse praise on HN that we &#x2F;must&#x2F; be doing something fundamentally wrong because I hate every interaction I have with Clickhouse.<p>* Timeouts (only 30s???) unless I used the cli client<p>* Cancelling rows - Just kill me, so many bugs and FINAL&#x2F;PREWHERE are massive foot-guns<p>* Cluster just feels annoying and fragile don&#x27;t forget &quot;ON CLUSTER&quot; or you&#x27;ll have a bad time<p>Again, I feel like we must be doing something wrong but we are paying an arm and a leg for that &quot;privilege&quot;.</text></item></parent_chain><comment><author>nsguy</author><text>You can always use different databases for different use cases.<p>There are many applications that require extremely high insertion rates (millions of records per second), very large total number of rows (billions, trillions) and flexible&#x2F;fast querying&#x2F;aggregation with high read rates (100&#x27;s of millions or higher rows&#x2F;s) and that&#x27;s sort of the sweet spot IMO for ClickHouse and where you&#x27;ll be pressed to find alternatives. I&#x27;m sure it can be used in other situations but maybe there are more choices if you&#x27;re in those.</text></comment> |
25,347,425 | 25,346,067 | 1 | 3 | 25,342,792 | train | <story><title>First person receives Pfizer Covid-19 vaccine in UK</title><url>https://www.bbc.com/news/uk-55227325</url></story><parent_chain><item><author>daveed</author><text>&gt; Second in line for the jab at University Hospital in Coventry was 81-year-old William Shakespeare from Warwickshire<p>His high priority must&#x27;ve been on purpose, right?</text></item></parent_chain><comment><author>dizzydot</author><text>Taming of the flu.</text></comment> | <story><title>First person receives Pfizer Covid-19 vaccine in UK</title><url>https://www.bbc.com/news/uk-55227325</url></story><parent_chain><item><author>daveed</author><text>&gt; Second in line for the jab at University Hospital in Coventry was 81-year-old William Shakespeare from Warwickshire<p>His high priority must&#x27;ve been on purpose, right?</text></item></parent_chain><comment><author>sshagent</author><text>I wonder if he was randomly determined to patient 1 for the vaccine, then they thought the conspiracy theorists will go nuts if they find out William Shakespear had the first shot</text></comment> |
20,110,343 | 20,110,126 | 1 | 2 | 20,091,141 | train | <story><title>How do I delete bytes from the beginning of a file? (2010)</title><url>https://devblogs.microsoft.com/oldnewthing/20101201-00/?p=12153</url></story><parent_chain><item><author>derefr</author><text>I&#x27;ve often thought it would be useful (especially for software that manages container or archive file-formats, or for databases) to have exposed to the user a file-system object that operates <i>like</i> a file, but which—instead of being exposed by OS as a seekable byte stream that can be appended&#x2F;truncated on one end—is exposed by syscalls as a <i>vector</i> of arbitrary, non-uniformly-sized extents, where the user is expected to ask the OS to pre-allocate extent buffers (think mmap(2) with anonymous private disk pages), and then, separately, stuff those into this vector object (which would be an operation almost exactly like hard-linking an existing file into a directory, in terms of its time and space complexity.)<p>Of course, for most filesystems (and especially ones with sparse-file support, and <i>especially</i> ones with copy-on-write support), such an on-disk data structure is exactly what&#x27;s already underlying the byte-stream abstraction. So this would just be a passthrough to allow people to directly manipulate that data structure. (In the process probably breaking certain preconditions the filesystem relies on, though, so it would need to track these &quot;low-level extent vectors&quot; as a separate filesystem object type. Programs would still be able to use regular file-abstraction syscalls on them, though.)<p>Interestingly, despite filesystems themselves not exposing the lower-level extent-vector abstractions, in some other systems that have file-stream-like abstractions, you <i>can</i> operate on &quot;files&quot; this way.<p>Postgres&#x27;s BLOBs, for example, are seekable byte-streams, which also (at least theoretically) allow you to insert into the middle of them. (I say theoretically because it&#x27;s not an implemented API, but it&#x27;s not exactly hidden from the user, either. BLOBs just get broken out into records in a table representing their extents; you can rewrite the keys of said records in that table to do whatever low-level operations you like.)<p>Or, for another example, S3 and its competitors let you arbitrarily compose objects as “components” of other virtual objects, which then read back as the concatenation of the objects they contain. (Sadly you don’t get any other vector-manipulation ops than this, but if you keep references to the leaf extents around, that’s often enough to rebuild your extent-vectors any time they change.)<p>Also, of course, back on the real filesystem, you can just manage your &quot;vector of parts of a file&quot; as multiple files in a directory, and then abstract over that directory that by using a FUSE server which exposes a view where the files are one contiguous file.</text></item></parent_chain><comment><author>nine_k</author><text>This, and more, has been tried on mainframes. When you could not afford to install a free RDBMS with a click of a mouse (the mouse being not available yet, too), you could really appreciate record-oriented files you could use as a database, and even have indexed access to the records.</text></comment> | <story><title>How do I delete bytes from the beginning of a file? (2010)</title><url>https://devblogs.microsoft.com/oldnewthing/20101201-00/?p=12153</url></story><parent_chain><item><author>derefr</author><text>I&#x27;ve often thought it would be useful (especially for software that manages container or archive file-formats, or for databases) to have exposed to the user a file-system object that operates <i>like</i> a file, but which—instead of being exposed by OS as a seekable byte stream that can be appended&#x2F;truncated on one end—is exposed by syscalls as a <i>vector</i> of arbitrary, non-uniformly-sized extents, where the user is expected to ask the OS to pre-allocate extent buffers (think mmap(2) with anonymous private disk pages), and then, separately, stuff those into this vector object (which would be an operation almost exactly like hard-linking an existing file into a directory, in terms of its time and space complexity.)<p>Of course, for most filesystems (and especially ones with sparse-file support, and <i>especially</i> ones with copy-on-write support), such an on-disk data structure is exactly what&#x27;s already underlying the byte-stream abstraction. So this would just be a passthrough to allow people to directly manipulate that data structure. (In the process probably breaking certain preconditions the filesystem relies on, though, so it would need to track these &quot;low-level extent vectors&quot; as a separate filesystem object type. Programs would still be able to use regular file-abstraction syscalls on them, though.)<p>Interestingly, despite filesystems themselves not exposing the lower-level extent-vector abstractions, in some other systems that have file-stream-like abstractions, you <i>can</i> operate on &quot;files&quot; this way.<p>Postgres&#x27;s BLOBs, for example, are seekable byte-streams, which also (at least theoretically) allow you to insert into the middle of them. (I say theoretically because it&#x27;s not an implemented API, but it&#x27;s not exactly hidden from the user, either. BLOBs just get broken out into records in a table representing their extents; you can rewrite the keys of said records in that table to do whatever low-level operations you like.)<p>Or, for another example, S3 and its competitors let you arbitrarily compose objects as “components” of other virtual objects, which then read back as the concatenation of the objects they contain. (Sadly you don’t get any other vector-manipulation ops than this, but if you keep references to the leaf extents around, that’s often enough to rebuild your extent-vectors any time they change.)<p>Also, of course, back on the real filesystem, you can just manage your &quot;vector of parts of a file&quot; as multiple files in a directory, and then abstract over that directory that by using a FUSE server which exposes a view where the files are one contiguous file.</text></item></parent_chain><comment><author>JoshTriplett</author><text>Today, though, that filesystem abstraction is block-aligned. So you could delete blocks from the beginning or middle of a file easily, but you couldn&#x27;t delete <i>bytes</i> from the beginning or middle.</text></comment> |
30,449,931 | 30,450,113 | 1 | 3 | 30,449,850 | train | <story><title>Explosions in Kiev and Kharkiv now [CNN]</title><url>https://www.cnn.com/europe/live-news/ukraine-russia-news-02-23-22/index.html</url></story><parent_chain></parent_chain><comment><author>atlasunshrugged</author><text>Crossposting from other active thread (<a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=30449831" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=30449831</a>): This is an unmitigated tragedy. There are reports of explosions even in the capital, Kyiv. I used to work in the region and Ukrainians are some of the brightest, hardest working, and passionate people (at least when it comes to advocating for democracy from the people I met in Kyiv) I&#x27;ve gotten to know. A freelance correspondent on twitter I follow posted a thread on charities to donate to for those so inclined (disclosure, I haven&#x27;t done due diligence on them): <a href="https:&#x2F;&#x2F;twitter.com&#x2F;olgatokariuk&#x2F;status&#x2F;1496486993848643584" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;olgatokariuk&#x2F;status&#x2F;1496486993848643584</a></text></comment> | <story><title>Explosions in Kiev and Kharkiv now [CNN]</title><url>https://www.cnn.com/europe/live-news/ukraine-russia-news-02-23-22/index.html</url></story><parent_chain></parent_chain><comment><author>perihelions</author><text>Here&#x27;s a wide view livestream over Kharkiv, retweeted by Jeffrey Lewis (for your &quot;is this credible?&quot; filter),<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=H7ZbVufqW3s" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=H7ZbVufqW3s</a><p><a href="https:&#x2F;&#x2F;twitter.com&#x2F;ArmsControlWonk&#x2F;status&#x2F;1496692896216457222" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;ArmsControlWonk&#x2F;status&#x2F;14966928962164572...</a><p>edit: Also verified by the NYT -- their screenshot looks identical to the video source above:<p>&gt;<i>&quot;The Times’s Visual Investigations team verified the location of the explosions, which were captured on a webcam just outside Kharkhiv.&quot;</i><p><a href="https:&#x2F;&#x2F;www.nytimes.com&#x2F;live&#x2F;2022&#x2F;02&#x2F;23&#x2F;world&#x2F;russia-ukraine" rel="nofollow">https:&#x2F;&#x2F;www.nytimes.com&#x2F;live&#x2F;2022&#x2F;02&#x2F;23&#x2F;world&#x2F;russia-ukraine</a></text></comment> |
17,817,447 | 17,817,269 | 1 | 2 | 17,807,753 | train | <story><title>Being the editor of a newspaper in Eve Online</title><url>https://www.rockpapershotgun.com/2018/08/20/whats-it-like-being-the-editor-of-a-newspaper-in-eve-online/</url></story><parent_chain><item><author>hrnnnnnn</author><text>It&#x27;s amazing sometimes how much EVE mimics real life. I used to know a guy that ran a bank there.<p>My little brother used to be really into it, eventually leading fleets during fights, and he credits that experience with giving him the skills he needed to manage teams at an IT company.</text></item></parent_chain><comment><author>jarboot</author><text>I had the same leadership training with minecraft, leading factions in RP servers and trading with other cities, complete with alliances, trade deals, and wars. Eventually I became an OP and eventually an admin, with all the responsibilities that entails at the age of 13. But obviously EVE is another level of complexity.<p>An interesting article related to minecraft economics can be read here: <a href="https:&#x2F;&#x2F;www.alicemaz.com&#x2F;writing&#x2F;minecraft.html" rel="nofollow">https:&#x2F;&#x2F;www.alicemaz.com&#x2F;writing&#x2F;minecraft.html</a></text></comment> | <story><title>Being the editor of a newspaper in Eve Online</title><url>https://www.rockpapershotgun.com/2018/08/20/whats-it-like-being-the-editor-of-a-newspaper-in-eve-online/</url></story><parent_chain><item><author>hrnnnnnn</author><text>It&#x27;s amazing sometimes how much EVE mimics real life. I used to know a guy that ran a bank there.<p>My little brother used to be really into it, eventually leading fleets during fights, and he credits that experience with giving him the skills he needed to manage teams at an IT company.</text></item></parent_chain><comment><author>jamesdeer</author><text>I used to lead Counter Strike 1.6 teams in my teens- I often reflect on how that was some of my early leadership &quot;training&quot;.<p>Good memories of motivating my teams of 15&#x2F;16&#x2F;17 year olds to get online at 6&#x2F;7am in the morning to work on our skills before school, and for epic days during the summer.<p>Ah, simpler times.</text></comment> |
6,235,107 | 6,234,916 | 1 | 2 | 6,233,646 | train | <story><title>Detaining my partner: a failed attempt at intimidation</title><url>http://www.theguardian.com/commentisfree/2013/aug/18/david-miranda-detained-uk-nsa</url></story><parent_chain><item><author>vabmit</author><text>&gt; 1) A test to see how the journalist will react and to
&gt; flush out more information. I.e. force him to disclose
&gt; more information so they know what he has.<p>I think they already know through a post event review of MicroSoft&#x27;s built in auditing logs. My understanding is that Snowden was a low level Windows admin that copied stuff that was either 1) in transit through a Microsoft Sharepoint server 2) anything he could find by roaming around the intranet. The NSA disclosed that he started grabbing documents when he was working as a contractor under Dell. They said he was aggressively exploring the limits of his network access and announced that 1) documents on their intranet would from now on be encrypted 2) that they would drastically reduce the number of system and network (as in Microsoft misuse of the term) administrators.<p>Plus, Wikileaks leaked an AES256 encrypted insurance file that presumably is everything that have from Snowden. Wikileaks has some of the shittiest OPSEC ever (as the Manning events showed). So, we know that they probably used openssl for the encryption and that the STK string is probably a sentence, or a few sentences, from a seminal published book about liberty&#x2F;privacy. The NSA has probably already cracked the insurance file key. So, if they don&#x27;t have the Manning portfolio from audit logs, they probably have it from Wikileaks.<p>There&#x27;s an ex-NSA NWC guy that is putting out a lot of excellent information on this whole thing: 20committee<p><a href="https://twitter.com/20committee" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;20committee</a></text></item><item><author>rdtsc</author><text>2 tests perhaps and a warning. I suspect they are a step ahead, and actually did think this through. Whether it will backfire or not is up to the citizens to decide. But I suspect it won&#x27;t backfire enough to cause a dent.<p>1) A test to see how the journalist will react and to flush out more information. I.e. force him to disclose more information so they know what he has.<p>2) Another test is to test public opinion. So far we have seen nothing but defensiveness and accusations from the White House. That bill to de-fund the NSA had some legs but didn&#x27;t get off the ground. If there is no reaction that is a good benchmark, they don&#x27;t have to stop and do anything. They could even push the envelope further and probably not get an real repercussions.<p>3) A warning is a powerful thing. It is message to all other journalists working with NSA sources. &quot;Are you prepared to open your family to harassment, black lists and 9 hour detentions during travel?&quot;. As some mentioned in the comments, even the Mafia has basic engagement rules to leave family members alone. That tells one the level of engagement and the mentality of government actors we are dealing with.</text></item><item><author>jacquesm</author><text>I wonder from how high up this order came. After all, it&#x27;s not like Greenwald is going to take this lying down and that&#x27;s something that they could predict quite accurately ahead of time. To abuse these powers on the partner of the journalist that is reporting the abuses is the worst tactical mistake made by any government to date, short of the diversion of a diplomats plane.<p>Taking into account that the UK law enforcement and Brazil have a bit of a history when it comes to labelling people terrorist wrongly makes it even worse.</text></item><item><author>grey-area</author><text>The salient quote from Greenwald&#x27;s article on this:<p><i>They completely abused their own terrorism law for reasons having nothing whatsoever to do with terrorism: a potent reminder of how often governments lie when they claim that they need powers to stop &quot;the terrorists&quot;, and how dangerous it is to vest unchecked power with political officials in its name.</i> [1]<p>This is a great example of why we should treat terrorism like any other crime, and why the police should never be trusted with exceptional powers simply because we feel under threat. Give them the powers, and they will be misused - in this case they were used on a relative of someone nothing to do with terrorism purely for the purpose of intimidation. The security services even called Greenwald to give him the news that his partner had been detained.<p>[1] <a href="http://www.theguardian.com/commentisfree/2013/aug/18/david-miranda-detained-uk-nsa" rel="nofollow">http:&#x2F;&#x2F;www.theguardian.com&#x2F;commentisfree&#x2F;2013&#x2F;aug&#x2F;18&#x2F;david-m...</a></text></item></parent_chain><comment><author>subsection1h</author><text><p><pre><code> https:&#x2F;&#x2F;twitter.com&#x2F;20committee
</code></pre>
John Schindler is a homophobic and transphobic scumbag who recently joked about Greenwald being trans like Manning.</text></comment> | <story><title>Detaining my partner: a failed attempt at intimidation</title><url>http://www.theguardian.com/commentisfree/2013/aug/18/david-miranda-detained-uk-nsa</url></story><parent_chain><item><author>vabmit</author><text>&gt; 1) A test to see how the journalist will react and to
&gt; flush out more information. I.e. force him to disclose
&gt; more information so they know what he has.<p>I think they already know through a post event review of MicroSoft&#x27;s built in auditing logs. My understanding is that Snowden was a low level Windows admin that copied stuff that was either 1) in transit through a Microsoft Sharepoint server 2) anything he could find by roaming around the intranet. The NSA disclosed that he started grabbing documents when he was working as a contractor under Dell. They said he was aggressively exploring the limits of his network access and announced that 1) documents on their intranet would from now on be encrypted 2) that they would drastically reduce the number of system and network (as in Microsoft misuse of the term) administrators.<p>Plus, Wikileaks leaked an AES256 encrypted insurance file that presumably is everything that have from Snowden. Wikileaks has some of the shittiest OPSEC ever (as the Manning events showed). So, we know that they probably used openssl for the encryption and that the STK string is probably a sentence, or a few sentences, from a seminal published book about liberty&#x2F;privacy. The NSA has probably already cracked the insurance file key. So, if they don&#x27;t have the Manning portfolio from audit logs, they probably have it from Wikileaks.<p>There&#x27;s an ex-NSA NWC guy that is putting out a lot of excellent information on this whole thing: 20committee<p><a href="https://twitter.com/20committee" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;20committee</a></text></item><item><author>rdtsc</author><text>2 tests perhaps and a warning. I suspect they are a step ahead, and actually did think this through. Whether it will backfire or not is up to the citizens to decide. But I suspect it won&#x27;t backfire enough to cause a dent.<p>1) A test to see how the journalist will react and to flush out more information. I.e. force him to disclose more information so they know what he has.<p>2) Another test is to test public opinion. So far we have seen nothing but defensiveness and accusations from the White House. That bill to de-fund the NSA had some legs but didn&#x27;t get off the ground. If there is no reaction that is a good benchmark, they don&#x27;t have to stop and do anything. They could even push the envelope further and probably not get an real repercussions.<p>3) A warning is a powerful thing. It is message to all other journalists working with NSA sources. &quot;Are you prepared to open your family to harassment, black lists and 9 hour detentions during travel?&quot;. As some mentioned in the comments, even the Mafia has basic engagement rules to leave family members alone. That tells one the level of engagement and the mentality of government actors we are dealing with.</text></item><item><author>jacquesm</author><text>I wonder from how high up this order came. After all, it&#x27;s not like Greenwald is going to take this lying down and that&#x27;s something that they could predict quite accurately ahead of time. To abuse these powers on the partner of the journalist that is reporting the abuses is the worst tactical mistake made by any government to date, short of the diversion of a diplomats plane.<p>Taking into account that the UK law enforcement and Brazil have a bit of a history when it comes to labelling people terrorist wrongly makes it even worse.</text></item><item><author>grey-area</author><text>The salient quote from Greenwald&#x27;s article on this:<p><i>They completely abused their own terrorism law for reasons having nothing whatsoever to do with terrorism: a potent reminder of how often governments lie when they claim that they need powers to stop &quot;the terrorists&quot;, and how dangerous it is to vest unchecked power with political officials in its name.</i> [1]<p>This is a great example of why we should treat terrorism like any other crime, and why the police should never be trusted with exceptional powers simply because we feel under threat. Give them the powers, and they will be misused - in this case they were used on a relative of someone nothing to do with terrorism purely for the purpose of intimidation. The security services even called Greenwald to give him the news that his partner had been detained.<p>[1] <a href="http://www.theguardian.com/commentisfree/2013/aug/18/david-miranda-detained-uk-nsa" rel="nofollow">http:&#x2F;&#x2F;www.theguardian.com&#x2F;commentisfree&#x2F;2013&#x2F;aug&#x2F;18&#x2F;david-m...</a></text></item></parent_chain><comment><author>jasonwatkinspdx</author><text>&gt; 20committee<p>Wow that guy is a dick. Tons of FUD and highly partisan cheerleading, and some pretty sad troll responses (though I&#x27;m sure he gets a lot of troll attention, which does wear down a person&#x27;s reasonableness).<p>I can understand that someone may have a different view on the balance between liberty and security, but his view is hyperbolic, not informative.</text></comment> |
28,070,475 | 28,070,476 | 1 | 3 | 28,067,731 | train | <story><title>How a fake network pushes pro-China propaganda</title><url>https://www.bbc.co.uk/news/world-asia-china-58062630</url></story><parent_chain><item><author>yesbut</author><text>I wonder how it stacks up to the fake network pushing anti-China propaganda.</text></item></parent_chain><comment><author>est</author><text>Funny if you think about how Chinese government crackdown anti-China content in China&#x27;s intranet. They used similar technics and analysis, plus raiding people&#x27;s home to in order to take them down.</text></comment> | <story><title>How a fake network pushes pro-China propaganda</title><url>https://www.bbc.co.uk/news/world-asia-china-58062630</url></story><parent_chain><item><author>yesbut</author><text>I wonder how it stacks up to the fake network pushing anti-China propaganda.</text></item></parent_chain><comment><author>jlduan</author><text>How The Epoch Times Created a Giant Influence Machine<p>&quot;Since 2016, the Falun Gong-backed newspaper has used aggressive Facebook tactics and right-wing misinformation to create an anti-China, pro-Trump media empire.&quot;<p><a href="https:&#x2F;&#x2F;www.nytimes.com&#x2F;2020&#x2F;10&#x2F;24&#x2F;technology&#x2F;epoch-times-influence-falun-gong.html" rel="nofollow">https:&#x2F;&#x2F;www.nytimes.com&#x2F;2020&#x2F;10&#x2F;24&#x2F;technology&#x2F;epoch-times-in...</a></text></comment> |
27,074,524 | 27,070,597 | 1 | 2 | 27,048,024 | train | <story><title>The original “Hello World”: B. W. Kernighan's intro to B (1973)</title><url>https://web.archive.org/web/20060225195733/http://cm.bell-labs.com/cm/cs/who/dmr/btut.html</url></story><parent_chain><item><author>I_Byte</author><text>I am currently in the process of learning C and having never seen any B code before I am rather surprised at their striking similarities. What could C do at the time that B couldn’t? Why did C eventually replace B?</text></item></parent_chain><comment><author>mettamage</author><text>You just caught me at a moment where I&#x27;m reading Tanenbaum&#x27;s book on Modern Operating Systems. Tanenbaum simplifies a lot of things, but here is his contribution [1]:<p>&gt; The second development concerned the language in which UNIX was written. By now it was becoming painfully obvious that having to rewrite the entire system for each new machine was no fun at all [0], so Thompson decided to rewrite UNIX in a high-level language of his own design, called B. B was a simplified form of BCPL (which itself was a simplified form of CPL, which, like PL&#x2F;I, never worked). Due to weaknesses in B, primarily lack of structures, this attempt was not successful. Ritchie then designed a successor to B, (naturally) called C, and wrote an excellent compiler for it. Working together, Thompson and Ritchie rewrote UNIX in C. C was the right language at the right time and has dominated system programming ever since.<p>Tanenbaum doesn&#x27;t say it, but it almost seems like B and C were designed for creating UNIX. I wonder to what extent the authors of B and C were designing the languages for creating UNIX.<p>[0] In one of the previous paragraphs, Tanenbaum mentioned that the first version of UNIX was written in assembly.<p>[1] Modern Operating Systems (ed. 4, p. 715)</text></comment> | <story><title>The original “Hello World”: B. W. Kernighan's intro to B (1973)</title><url>https://web.archive.org/web/20060225195733/http://cm.bell-labs.com/cm/cs/who/dmr/btut.html</url></story><parent_chain><item><author>I_Byte</author><text>I am currently in the process of learning C and having never seen any B code before I am rather surprised at their striking similarities. What could C do at the time that B couldn’t? Why did C eventually replace B?</text></item></parent_chain><comment><author>gerdesj</author><text>You could start here: <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;B_(programming_language)" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;B_(programming_language)</a><p>As always on HN there is a certain amount of ... discussion about some of the finer points, generally about typing. I suspect that if you follow the refs in the WP article most of the usual bikeshedding here will resolve itself satisfactorily.<p>For me (50 year old bloke) I dimly recall C always being available <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;C_(programming_language)" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;C_(programming_language)</a> - apparently 1972ish so I was 2 or 3 when C came out and replaced B which probably didn&#x27;t do much ....<p>Oh look at this (wrt B): &quot;However, it continues to see use on GCOS mainframes (as of 2014)&quot;</text></comment> |
30,073,168 | 30,071,450 | 1 | 2 | 30,069,402 | train | <story><title>AlphaFold-Powered Drug Discovery of a Novel CDK20 Inhibitor</title><url>https://arxiv.org/abs/2201.09647</url></story><parent_chain></parent_chain><comment><author>cing</author><text>I agree with the sentiment of this paper (AF can enable drug discovery), but in this specific instance, the authors had a real opportunity contribute a general finding to the scientific community but instead they put in the lowest amount of effort (to a point where they&#x27;re almost saying nothing at all).<p>The target had dozens of related structures in the protein databank, including relatives with ~40% sequence identity. This target family has a very similar structure, and conserved active site residues. It&#x27;s relevant that this target has approved cross-CDK family inhibitors (and thousands of data points of CDK family binders on ChEMBL). The conventional way to enable structure-based design is to build a homology model using a similar structure (see here: <a href="https:&#x2F;&#x2F;swissmodel.expasy.org&#x2F;repository&#x2F;uniprot&#x2F;Q8IZL9?template=1v0o.1.A&amp;range=3-290" rel="nofollow">https:&#x2F;&#x2F;swissmodel.expasy.org&#x2F;repository&#x2F;uniprot&#x2F;Q8IZL9?temp...</a>), and in this case, there is very low deviation from the AF2 model and this &quot;old fashioned&quot; approach.<p>To recap, this target had a decent model that would have likely sufficed for drug discovery. The community already knows that &quot;homology models&quot; can be used for structure-based drug design, so any methodological hypotheses of this paper are not supported by evidence.</text></comment> | <story><title>AlphaFold-Powered Drug Discovery of a Novel CDK20 Inhibitor</title><url>https://arxiv.org/abs/2201.09647</url></story><parent_chain></parent_chain><comment><author>civilized</author><text>Very cool.<p>It&#x27;s hard to read the tea leaves of the author affiliation list, but it sure looks like this work was led by a Hong Kong-based startup founded by Russians, with limited assistance from a couple North America-based researchers.<p>I&#x27;m curious why those Russians may have chosen to found in HK rather than, say, the Bay Area. We may want to contemplate what this means for America&#x27;s competitive stance (not that I have any problem with the rest of the world doing awesome cutting edge research).</text></comment> |
15,581,959 | 15,581,708 | 1 | 2 | 15,581,114 | train | <story><title>Facebook denies 'listening' to conversations</title><url>http://www.bbc.com/news/technology-41776215</url></story><parent_chain><item><author>madeofpalk</author><text>How could they respond to remove all doubt they&#x27;re listening?<p>Edit: <a href="https:&#x2F;&#x2F;www.theverge.com&#x2F;2016&#x2F;6&#x2F;3&#x2F;11854860&#x2F;facebook-smartphone-listening-eavesdrop-microphone-denial" rel="nofollow">https:&#x2F;&#x2F;www.theverge.com&#x2F;2016&#x2F;6&#x2F;3&#x2F;11854860&#x2F;facebook-smartpho...</a><p><pre><code> In a statement issued on June 2nd [2016], Facebook said it &quot;does not use your
phone’s microphone to inform ads or to change what you see in News Feed.&quot;
</code></pre>
That&#x27;s pretty fucking clear to me.<p><i>Original comment:</i><p>If they had said something like &quot;We don&#x27;t use microphones to gather data to drive personalisation on users profiles&quot; there would be comments here on HN complaining about corporate speak and how they didnt just flat out deny using it for advertising.<p>Apps get busted for doing dodgy things all the time. The Facebook app has been decompiled and network traffic inspected and studied so often that if this actually was true then it would have been proven by now. Instead, all we have is this weird &#x27;survivorship bias&#x27; where <i>one time</i> someone said something out loud there was a tangentially related ad on FB.<p>Today I was looking up bars in Budapest and found one on Google. I started looking at images, at the only one that loaded so far on the slow internet was of food. &quot;Wow, Google knows me so well. All I care about right now is food and the first image it loads is of food&quot; I said out loud to my friend. Eventually the internet caught up and the rest of the images that loaded were of food. It only showed me food photos (in a bar thats more known for its decoration and alcohol). Nothing more than a coincidence.</text></item><item><author>denzil_correa</author><text>&gt; &quot;I run ads product at Facebook. We don&#x27;t - and have never - used your microphone for ads. Just not true,&quot; Mr Goldman wrote.<p>Personally, I am so used to corp speak and word play by major companies that it is difficult to take anything at face value. Therefore, I think the nature of the question asked to Facebook should be different. It should be on what they do rather do they do X. So, here&#x27;s my question - &quot;What does Facebook use data gathered from user microphones across any devices for?&quot;</text></item></parent_chain><comment><author>denzil_correa</author><text>My question was NOT &quot;Does Facebook use the phone&#x27;s microphone to inform ads or change what we see in the News Feed?&quot;. It seems you have misunderstood my question. Let me repeat my question again :<p>&quot;What does Facebook use data gathered from user microphones across any devices for?&quot;</text></comment> | <story><title>Facebook denies 'listening' to conversations</title><url>http://www.bbc.com/news/technology-41776215</url></story><parent_chain><item><author>madeofpalk</author><text>How could they respond to remove all doubt they&#x27;re listening?<p>Edit: <a href="https:&#x2F;&#x2F;www.theverge.com&#x2F;2016&#x2F;6&#x2F;3&#x2F;11854860&#x2F;facebook-smartphone-listening-eavesdrop-microphone-denial" rel="nofollow">https:&#x2F;&#x2F;www.theverge.com&#x2F;2016&#x2F;6&#x2F;3&#x2F;11854860&#x2F;facebook-smartpho...</a><p><pre><code> In a statement issued on June 2nd [2016], Facebook said it &quot;does not use your
phone’s microphone to inform ads or to change what you see in News Feed.&quot;
</code></pre>
That&#x27;s pretty fucking clear to me.<p><i>Original comment:</i><p>If they had said something like &quot;We don&#x27;t use microphones to gather data to drive personalisation on users profiles&quot; there would be comments here on HN complaining about corporate speak and how they didnt just flat out deny using it for advertising.<p>Apps get busted for doing dodgy things all the time. The Facebook app has been decompiled and network traffic inspected and studied so often that if this actually was true then it would have been proven by now. Instead, all we have is this weird &#x27;survivorship bias&#x27; where <i>one time</i> someone said something out loud there was a tangentially related ad on FB.<p>Today I was looking up bars in Budapest and found one on Google. I started looking at images, at the only one that loaded so far on the slow internet was of food. &quot;Wow, Google knows me so well. All I care about right now is food and the first image it loads is of food&quot; I said out loud to my friend. Eventually the internet caught up and the rest of the images that loaded were of food. It only showed me food photos (in a bar thats more known for its decoration and alcohol). Nothing more than a coincidence.</text></item><item><author>denzil_correa</author><text>&gt; &quot;I run ads product at Facebook. We don&#x27;t - and have never - used your microphone for ads. Just not true,&quot; Mr Goldman wrote.<p>Personally, I am so used to corp speak and word play by major companies that it is difficult to take anything at face value. Therefore, I think the nature of the question asked to Facebook should be different. It should be on what they do rather do they do X. So, here&#x27;s my question - &quot;What does Facebook use data gathered from user microphones across any devices for?&quot;</text></item></parent_chain><comment><author>keketi</author><text>Modify their apps to not request microphone permission.</text></comment> |
5,302,048 | 5,302,061 | 1 | 2 | 5,301,607 | train | <story><title>Bradley Manning Takes "Full Responsibility" for Giving WikiLeaks Government Data</title><url>http://www.wired.com/threatlevel/2013/02/bradley-manning/</url></story><parent_chain><item><author>slurgfest</author><text>Getting disgruntled and indiscriminately dumping whatever you find on sensitive internal networks, in violation of the military law you agreed to be governed by when you VOLUNTEERED for the US military, is not an honorable self-sacrifice.<p>If we believe that, then we should believe that any employee of any startup has an honorable sacrificial duty to leak that startup's code along with a dump of its databases.</text></item><item><author>bdcravens</author><text>I can't deny that he violated the trust placed in him by the military. That's a scary game, and one that I can't honestly take a position in, as I've never served.<p>However, I feel that service is more than to your branch, commander, or unit. What is a soldier? Someone willing to sacrifice themselves for a greater, to defend those who can't defend themselves, to bring honor to their service. A US soldier serves the people first, the government second. Manning realized the risk he was placing his life in, and like a true soldier, he didn't let that knowledge deter him. In taking responsibility, he's holding his head high, not cowering behind attorneys and HTTP proxies.<p>I can't say if he's right or wrong, but I can say that he showed courage befitting his title.</text></item></parent_chain><comment><author>nuclear_eclipse</author><text>So if a volunteer army is committing mass atrocities in the name of protecting state secrets, nobody should blow the whistle because they volunteered for the position before they knew what they were going to be doing?<p>I'm just wondering where the line is drawn here.</text></comment> | <story><title>Bradley Manning Takes "Full Responsibility" for Giving WikiLeaks Government Data</title><url>http://www.wired.com/threatlevel/2013/02/bradley-manning/</url></story><parent_chain><item><author>slurgfest</author><text>Getting disgruntled and indiscriminately dumping whatever you find on sensitive internal networks, in violation of the military law you agreed to be governed by when you VOLUNTEERED for the US military, is not an honorable self-sacrifice.<p>If we believe that, then we should believe that any employee of any startup has an honorable sacrificial duty to leak that startup's code along with a dump of its databases.</text></item><item><author>bdcravens</author><text>I can't deny that he violated the trust placed in him by the military. That's a scary game, and one that I can't honestly take a position in, as I've never served.<p>However, I feel that service is more than to your branch, commander, or unit. What is a soldier? Someone willing to sacrifice themselves for a greater, to defend those who can't defend themselves, to bring honor to their service. A US soldier serves the people first, the government second. Manning realized the risk he was placing his life in, and like a true soldier, he didn't let that knowledge deter him. In taking responsibility, he's holding his head high, not cowering behind attorneys and HTTP proxies.<p>I can't say if he's right or wrong, but I can say that he showed courage befitting his title.</text></item></parent_chain><comment><author>malbs</author><text>Not really a fair comparison. Unless the start-up was tax payer funded, and was doing objectionable things like selling customers credit card/personal information to third parties, and you knew about it, maybe then you would be lauded for exposing it. However no one would label you a hero for releasing a companies IP for the sake of it.<p>MAYBE if it was some company making bucket loads of money off of GPL code they were deliberately and knowingly abusing the license!</text></comment> |
13,178,428 | 13,178,022 | 1 | 2 | 13,175,531 | train | <story><title>Uber’s self-driving cars start picking up passengers in San Francisco</title><url>https://techcrunch.com/2016/12/14/ubers-self-driving-cars-start-picking-up-passengers-in-san-francisco/</url></story><parent_chain><item><author>autotune</author><text>The problem with this is, as a rider, I personally would not want to have to be constantly expecting a dirty car. If one out of every 3 cars has vomit or syringes in it or feces, I would personally stick with a service that has human drivers at the wheel.</text></item><item><author>amelius</author><text>I imagine that the next user would just tap a button on their smartphone saying that the car is dirty, upon which the car drives back to a service center and the user receives a new car (not the same car).</text></item><item><author>autotune</author><text>How is this going to combat people who make a mess inside the vehicle after going 100 percent without human drivers&#x2F;test engineers? If it picks up a drunk person at 3 AM who then throws up inside the car, is it vomit-aware and knows it needs a cleaning before picking up the next passenger?</text></item></parent_chain><comment><author>linkregister</author><text>This is remedied with a service charge for the responsible person.<p>Unlike a Tenderloin sidewalk, deterrents are easily enforced under a scheme like this.<p>Uber and Lyft currently charge $100 for a cleaning fee to the driver when their passengers soil a car&#x27;s interior with vomit, etc. I don&#x27;t see why Waymo, Tesla, or Uber would be any different.</text></comment> | <story><title>Uber’s self-driving cars start picking up passengers in San Francisco</title><url>https://techcrunch.com/2016/12/14/ubers-self-driving-cars-start-picking-up-passengers-in-san-francisco/</url></story><parent_chain><item><author>autotune</author><text>The problem with this is, as a rider, I personally would not want to have to be constantly expecting a dirty car. If one out of every 3 cars has vomit or syringes in it or feces, I would personally stick with a service that has human drivers at the wheel.</text></item><item><author>amelius</author><text>I imagine that the next user would just tap a button on their smartphone saying that the car is dirty, upon which the car drives back to a service center and the user receives a new car (not the same car).</text></item><item><author>autotune</author><text>How is this going to combat people who make a mess inside the vehicle after going 100 percent without human drivers&#x2F;test engineers? If it picks up a drunk person at 3 AM who then throws up inside the car, is it vomit-aware and knows it needs a cleaning before picking up the next passenger?</text></item></parent_chain><comment><author>jonknee</author><text>Zipcar and Reach Now don&#x27;t seem to have an issue with this, I would be surprised if it&#x27;s any different when you don&#x27;t have to the move the steering wheel yourself. If they can make a car that drives itself they can surely figure out a way to keep it clean.</text></comment> |
7,120,794 | 7,120,735 | 1 | 2 | 7,119,674 | train | <story><title>How Long Have I Got Left?</title><url>http://www.nytimes.com/2014/01/25/opinion/sunday/how-long-have-i-got-left.html?smid=tw-share&_r=0</url></story><parent_chain><item><author>ifktaotc</author><text>A few years ago I got testicular cancer. The information about the disease came in pieces: first all I knew was that there was a lump; then came the ultrasound, the CT scan, then biopsy of the testicle, then a second surgery to sample lymph nodes to which the cancer might have spread. At every step I would obsessively query my doctors for conditional probabilities: given what we&#x27;d just found out, what were the chances of dying? Of relapse? Of chemo? Of sterility? I was always incredibly frustrated at how vague their responses would be - they&#x27;d say, e.g. &quot;we don&#x27;t like to give probabilities because you just never know what will happen!&quot;. And I would think, &quot;That&#x27;s exactly the point of a probability! Please just tell me a number!&quot;<p>One doctor eventually showed me a paper on outcomes for the lymph node surgery I had, with a relapse rate curve going out five years so. I found this incredibly helpful for managing my emotions because it let me track my progress in a very precise way: every monthly checkup that would go by uneventfully, I knew exactly what my chance of relapse had dropped to. The goal was to get to zero. More importantly, having actual numbers gave me something on which I could focus my optimism. It&#x27;s so much worse to hear &quot;you might become sterile&quot; than &quot;there&#x27;s a 5% chance of becoming sterile&quot;. With the 5% number in mind, I&#x27;d do things like imagine myself in a room full of 20 people and think &quot;wow, it would be incredibly unlikely to be randomly chosen from this group&quot;. Having spent a lot of time in a cancer hospital now -- around people who were much worse off than I was -- I believe that almost everyone has incredible reserves of optimism. I think it&#x27;s better when the hopeful possibility is concretely defined - it makes it easier to imagine a path forward while you&#x27;re stuck waiting for more information.<p>Mine is obviously a completely different situation from the terminal cancer described by the author, where the question isn&#x27;t, &quot;when will I be free of this cancer&quot;, but rather &quot;when will I die from it&quot;. Testicular cancer is very treatable, and I never faced a significant chance of death. I&#x27;m sure I would have been in a much different psychological state if I had.<p>Also, PSA: testicular cancer is REALLY common for young males (if you&#x27;re male you have a 1 in 500 chance of getting it between 20 and 34). Given HN user demographics, there are almost certainly some of you reading this who&#x27;ve gotten it already, or who will. You can save yourself a ton of trouble if you do a self-examination every once in a while. That&#x27;s actually how I found out, and is a big reason that I avoided chemotherapy.</text></item></parent_chain><comment><author>ct1</author><text>I have (had?) salivary gland cancer. Diagnosed before 30 at a IVa stage. I had surgery, radio and chemo. After that, the 5-years survival rate is 1 in 10. And if you do make it, your quality if life is significantly impacted and you&#x27;re permanently disfigured - radical neck surgery ain&#x27;t pretty.<p>I have a background in academia and despite the fact that I like to tell myself that I am some unique snowflake and that I&#x27;ll make it, I know where I stand. No doctor told me, but I went to PubMed myself.<p>Am I pleased to know that? Not sure. And it kind of bothers me the fact that all my daily careful efforts will all boil down pretty soon to an event that is as dumb as the outcome of rolling a dice.</text></comment> | <story><title>How Long Have I Got Left?</title><url>http://www.nytimes.com/2014/01/25/opinion/sunday/how-long-have-i-got-left.html?smid=tw-share&_r=0</url></story><parent_chain><item><author>ifktaotc</author><text>A few years ago I got testicular cancer. The information about the disease came in pieces: first all I knew was that there was a lump; then came the ultrasound, the CT scan, then biopsy of the testicle, then a second surgery to sample lymph nodes to which the cancer might have spread. At every step I would obsessively query my doctors for conditional probabilities: given what we&#x27;d just found out, what were the chances of dying? Of relapse? Of chemo? Of sterility? I was always incredibly frustrated at how vague their responses would be - they&#x27;d say, e.g. &quot;we don&#x27;t like to give probabilities because you just never know what will happen!&quot;. And I would think, &quot;That&#x27;s exactly the point of a probability! Please just tell me a number!&quot;<p>One doctor eventually showed me a paper on outcomes for the lymph node surgery I had, with a relapse rate curve going out five years so. I found this incredibly helpful for managing my emotions because it let me track my progress in a very precise way: every monthly checkup that would go by uneventfully, I knew exactly what my chance of relapse had dropped to. The goal was to get to zero. More importantly, having actual numbers gave me something on which I could focus my optimism. It&#x27;s so much worse to hear &quot;you might become sterile&quot; than &quot;there&#x27;s a 5% chance of becoming sterile&quot;. With the 5% number in mind, I&#x27;d do things like imagine myself in a room full of 20 people and think &quot;wow, it would be incredibly unlikely to be randomly chosen from this group&quot;. Having spent a lot of time in a cancer hospital now -- around people who were much worse off than I was -- I believe that almost everyone has incredible reserves of optimism. I think it&#x27;s better when the hopeful possibility is concretely defined - it makes it easier to imagine a path forward while you&#x27;re stuck waiting for more information.<p>Mine is obviously a completely different situation from the terminal cancer described by the author, where the question isn&#x27;t, &quot;when will I be free of this cancer&quot;, but rather &quot;when will I die from it&quot;. Testicular cancer is very treatable, and I never faced a significant chance of death. I&#x27;m sure I would have been in a much different psychological state if I had.<p>Also, PSA: testicular cancer is REALLY common for young males (if you&#x27;re male you have a 1 in 500 chance of getting it between 20 and 34). Given HN user demographics, there are almost certainly some of you reading this who&#x27;ve gotten it already, or who will. You can save yourself a ton of trouble if you do a self-examination every once in a while. That&#x27;s actually how I found out, and is a big reason that I avoided chemotherapy.</text></item></parent_chain><comment><author>zrail</author><text>Thank you. When I was diagnosed (IIa good) my fiancé an I spent three hours with my medical oncologist going through exactly what treatment would be, probabilities of relapse, relative risks, everything. She is a wonderful doctor.<p>Also, just to jump on the train, if something is weird with your testicles, pain or lumps or whatever, <i>go see a doctor</i>. I waited longer than I should have and it probably made my treatment harder than it could have been.</text></comment> |
2,348,323 | 2,348,322 | 1 | 3 | 2,348,137 | train | <story><title>.tel, .xxx and .mobi are all pointless and idiotic</title><url>http://blog.tommorris.org/post/3968125126/tel-xxx-and-mobi-are-all-pointless-and-idiotic</url></story><parent_chain></parent_chain><comment><author>duskwuff</author><text>I'd go a step further and suggest that <i>all</i> of the new gTLDs are pointless and idiotic:<p>- .aero: if IATA airport codes were all registered domains here, it might be useful, but they aren't, so it isn't.<p>- .asia: asia is definitely a country &#60;/sarcasm&#62;<p>- .biz: sufficiently stupid that SpamAssassin has a rule for it<p>- .cat: meow? seriously, I've only seen this used for vanity joke domains<p>- .coop: there isn't a .llc, why is this any different?<p>- .info: happy fun SEO land<p>- .jobs: pity they won't take my registration for Blow, Inc.<p>- .mobi: as noted<p>- .museum: 1138 registered domains in 10 years is a sign of true irrelevance<p>- .name: personal names are hardly unique identifiers<p>- .pro: stupid hierarchy makes this one even more useless than you'd think<p>- .tel: as noted<p>- .travel: because .aero just wasn't enough<p>- .xxx: as noted<p>Perhaps I'm just not seeing the possibilities, but I suspect that there's no future for any of the gTLDs beyond com/net/org, and possibly a few of the up-and-coming IDN gTLDs. The future of domain names is really in better unique names, not a more complex hierarchy.</text></comment> | <story><title>.tel, .xxx and .mobi are all pointless and idiotic</title><url>http://blog.tommorris.org/post/3968125126/tel-xxx-and-mobi-are-all-pointless-and-idiotic</url></story><parent_chain></parent_chain><comment><author>kragen</author><text>&#62; Politically, we should push for an actual democratic version of ICANN, and get a bunch of wise Unix neckbeard types to join and require all TLDs to get a supermajority vote of ICANN or a future counterpart to ICANN.<p>Karl Auerbach was the wise Unix neckbeard type who was on ICANN's board for a while. You can read about his efforts to create ICANN transparency: <a href="http://en.wikipedia.org/wiki/Karl_Auerbach" rel="nofollow">http://en.wikipedia.org/wiki/Karl_Auerbach</a></text></comment> |
12,924,098 | 12,924,152 | 1 | 2 | 12,923,460 | train | <story><title>Work/Life Balance Will Make You a Better Software Engineer</title><url>https://codewithoutrules.com/2016/11/10/work-life-balance-software-engineer/?</url></story><parent_chain><item><author>aetherson</author><text>Yeah, I&#x27;d like to see some actual data. Some kind of scientific study, anything.<p>I don&#x27;t say this because I&#x27;m a proponent of work-at-any-cost culture -- I&#x27;m not. I work about 45 hours a week, no weekends or nights outside of rare emergencies. That&#x27;s certainly good for my mood and my relationship with my family and so forth.<p>But I see all these articles in which they suggest that after 40 hours a week, your productivity crashes or goes negative or whatever, and it strikes me as wishful thinking. The universe does not often line up to give us win-wins like this. My belief is that, probably, for at least a lot of people, if you spend a few years working super hard, you&#x27;ll probably gain a lot of skill and be highly productive. Maybe if you keep that up for decades, accumulated stress will make it a net negative. Maybe some people have really low tolerance for stress and will much more rapidly turn to net negative.<p>But the idea that it is universally or near-universally true that everyone is more productive on a 40 hour week is at best under-argued, and, I&#x27;d guess, probably mostly untrue.</text></item></parent_chain><comment><author>dahart</author><text>Here&#x27;s some data &amp; has a bunch of references to more data.
<a href="http:&#x2F;&#x2F;lunar.lostgarden.com&#x2F;Rules%20of%20Productivity.pdf" rel="nofollow">http:&#x2F;&#x2F;lunar.lostgarden.com&#x2F;Rules%20of%20Productivity.pdf</a><p>The claim is not that 40 is some kind of hard threshold, and if you work any more than that you&#x27;ll be instantly less productive. The claim is that a steady-state of, say, 60 hours per week is less productive long term. It&#x27;s actually more productive for a little while, like a month, but then people get tired and less productive than rested 40-hour workers after that.<p>I have experience doing long periods of 80 hour weeks, when I was working in game development. I think it&#x27;s hard to say definitively that productivity goes negative, that&#x27;s not what it felt like when we were crunching. OTOH, I did watch as tired crews would make bad decisions during crunch that ended up costing time in the long run, and I can definitely say that 80 hour weeks are not twice as productive as 40 hour weeks.</text></comment> | <story><title>Work/Life Balance Will Make You a Better Software Engineer</title><url>https://codewithoutrules.com/2016/11/10/work-life-balance-software-engineer/?</url></story><parent_chain><item><author>aetherson</author><text>Yeah, I&#x27;d like to see some actual data. Some kind of scientific study, anything.<p>I don&#x27;t say this because I&#x27;m a proponent of work-at-any-cost culture -- I&#x27;m not. I work about 45 hours a week, no weekends or nights outside of rare emergencies. That&#x27;s certainly good for my mood and my relationship with my family and so forth.<p>But I see all these articles in which they suggest that after 40 hours a week, your productivity crashes or goes negative or whatever, and it strikes me as wishful thinking. The universe does not often line up to give us win-wins like this. My belief is that, probably, for at least a lot of people, if you spend a few years working super hard, you&#x27;ll probably gain a lot of skill and be highly productive. Maybe if you keep that up for decades, accumulated stress will make it a net negative. Maybe some people have really low tolerance for stress and will much more rapidly turn to net negative.<p>But the idea that it is universally or near-universally true that everyone is more productive on a 40 hour week is at best under-argued, and, I&#x27;d guess, probably mostly untrue.</text></item></parent_chain><comment><author>ThrustVectoring</author><text>It&#x27;s comments like this that really make me sad about the state of labor solidarity among tech professionals. Like, please, stop torpedoing our negotiation position, especially on a public forum that many technical employers and managers read.<p>On the object level, I have a suspicion that being productive past 40 hr&#x2F;wk or so has reverse causation for me. It&#x27;s bad for me to work over 40 hours a week, so that magically translates into being bad at it. Social negotiation is one of those things that your non-verbal and emotional parts is really good at, and Thomas Schelling style &quot;don&#x27;t have the ability to do things you don&#x27;t want others to pressure you into doing&quot; strategies work.</text></comment> |
22,042,643 | 22,042,647 | 1 | 2 | 22,018,946 | train | <story><title>Ask HN: What has your work taught you that other people don't realize?</title><text>Inspired by PG&#x27;s tweet - <a href="https:&#x2F;&#x2F;twitter.com&#x2F;paulg&#x2F;status&#x2F;1215673204125073408?s=19" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;paulg&#x2F;status&#x2F;1215673204125073408?s=19</a></text></story><parent_chain><item><author>jl6</author><text>The taxonomy of jobs that most people have in their minds is extremely simple (doctor, lawyer, teacher, builder, engineer, window cleaner, garbage collector, astronaut, ...) and is mostly based on a grade-school understanding of what kind of jobs people do.<p>But the reality is that there are <i>millions</i> of <i>types</i> of jobs, with incredible variety and specialisms, and the real content of a job is rarely captured in a job title.</text></item></parent_chain><comment><author>badtuple</author><text>Not only that, but the incredible depth of pretty much every field. Not every practitioner dives deep, but the masters of any job leave me speechless.</text></comment> | <story><title>Ask HN: What has your work taught you that other people don't realize?</title><text>Inspired by PG&#x27;s tweet - <a href="https:&#x2F;&#x2F;twitter.com&#x2F;paulg&#x2F;status&#x2F;1215673204125073408?s=19" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;paulg&#x2F;status&#x2F;1215673204125073408?s=19</a></text></story><parent_chain><item><author>jl6</author><text>The taxonomy of jobs that most people have in their minds is extremely simple (doctor, lawyer, teacher, builder, engineer, window cleaner, garbage collector, astronaut, ...) and is mostly based on a grade-school understanding of what kind of jobs people do.<p>But the reality is that there are <i>millions</i> of <i>types</i> of jobs, with incredible variety and specialisms, and the real content of a job is rarely captured in a job title.</text></item></parent_chain><comment><author>Nursie</author><text>I fixed my mum&#x27;s computer a few years back (cleaned up some adware and other stuff that was making it awful to use) and did a bunch of virus scans and cleanup etc. After a while she asked &quot;Is this what you do for a job?&quot;<p>The conception of what happens inside our industry just isn&#x27;t present in the wider population, and I imagine we&#x27;re not unique in that.</text></comment> |
34,236,340 | 34,236,518 | 1 | 3 | 34,211,110 | train | <story><title>Disagreeable personalities do not have an advantage in power at work (2020)</title><url>https://pubmed.ncbi.nlm.nih.gov/32868412/</url></story><parent_chain><item><author>talentedcoin</author><text>Strong disagree. It is possible to disagree without being disagreeable, and I personally find it frustrating when people excuse their behaviour in the manner you are doing. Yes work sucks, but being unpleasant, cynical and snarky just makes it even worse. Roll up your sleeves and help or please get out of the way.</text></item><item><author>kyleyeats</author><text>We&#x27;re not jerks. We&#x27;re people who notice problems. You&#x27;re shooting the messenger.<p>Every problem that tech has comes from treating disagreeable people as pariahs. Organizational bloat and tech debt are still issues even when we&#x27;re not there. Avoid hiring disagreeable people and you&#x27;ll arrive at the stereotypical tech org that can&#x27;t get anything done. If you don&#x27;t have disagreeable people to solve your issues, you have to use the other tool: Layoffs.<p>Discriminating against people because they&#x27;re disagreeable is <i>insane</i>. It&#x27;s a Big Five personality trait. You hate <i>half of humanity</i>. Evolution produced the best problem-solving thing ever, humanity, and you decided a lot of the work done there was just pointless.<p>The real reason disagreeable people are valuable and can attain power in the workplace is because you&#x27;ve made it so with this completely unreasonable bias you have. They&#x27;re not supposed to be extremely rare! That only happens in the tech workplace.<p>Would you similarly discriminate against anxious people? What about people who aren&#x27;t open to new experiences? Do you shut them out too? How does your ideology square with black people being <i>way</i> more disagreeable on average? Let me guess: You don&#x27;t hire any and then mumble something about culture fit.<p>Working with disagreeable people doesn&#x27;t suck. Working sucks. The disagreeable people just point it out. How do you ever improve without that? Working at an all-agreeable-people tech firm is a Kafkaesque nightmare of everything being perfect and nothing getting done. And you all deserve it because you decided that when people tend to be one way or the other, the ones who are like you are <i>just better</i>.</text></item><item><author>derbOac</author><text>This is interesting because it counters the idea that someone has to be a jerk to get ahead. However I&#x27;m also not sure the study really examined the idea too well, and ended up feeling like it&#x27;s the sort of thing that could be misinterpreted and overleveraged.<p>In my personal experience (which is limited) there&#x27;s a certain constellation of organizational characteristics that leads to disagreeable individuals attaining power, and organizational &quot;combativeness&quot; isn&#x27;t really it. I think &quot;corruption&quot; is closer, and good luck measuring that with a self report survey.<p>Then again, maybe the relevant issue isn&#x27;t whether or not people who are jerks are more likely to attain power, it&#x27;s than once they&#x27;re there they&#x27;re more likely to cause problems, and they&#x27;re not <i>less likely</i> to attain power. So then them being in power is salient.<p>But then I think you have to ask, why aren&#x27;t they less likely to attain power? Is this a case where a zero correlation is actually masking some mixture of processes, one positive in direction and the other negative? If so you&#x27;d think that certain settings would inhibit one or the other of those processes.<p>I guess I feel like this is a case where studying normative organizational dynamics in a cursory way could end up being really misleading.</text></item></parent_chain><comment><author>Name_Chawps</author><text>This study, and the person you&#x27;re replying to, are using the term disagreeable in the Big Five psychology sense. They don&#x27;t mean unpleasant, cynical, or snarky. Sometimes disagreeable people are snarky, but they don&#x27;t have to be.<p>You do, actually, have to be disagreeable to disagree. Agreeable people don&#x27;t like to cause a fuss and just go along with stuff even if they disagree internally. Disagreeable people are the people who tend to disagree. That&#x27;s all it means. Some of them are snarky assholes (you right now?), and others are just people who disagree.<p>&quot;Disagreeable&quot; in common parlance means difficult, overly-critical, and aggressive, but that&#x27;s not what &#x27;s being said here.</text></comment> | <story><title>Disagreeable personalities do not have an advantage in power at work (2020)</title><url>https://pubmed.ncbi.nlm.nih.gov/32868412/</url></story><parent_chain><item><author>talentedcoin</author><text>Strong disagree. It is possible to disagree without being disagreeable, and I personally find it frustrating when people excuse their behaviour in the manner you are doing. Yes work sucks, but being unpleasant, cynical and snarky just makes it even worse. Roll up your sleeves and help or please get out of the way.</text></item><item><author>kyleyeats</author><text>We&#x27;re not jerks. We&#x27;re people who notice problems. You&#x27;re shooting the messenger.<p>Every problem that tech has comes from treating disagreeable people as pariahs. Organizational bloat and tech debt are still issues even when we&#x27;re not there. Avoid hiring disagreeable people and you&#x27;ll arrive at the stereotypical tech org that can&#x27;t get anything done. If you don&#x27;t have disagreeable people to solve your issues, you have to use the other tool: Layoffs.<p>Discriminating against people because they&#x27;re disagreeable is <i>insane</i>. It&#x27;s a Big Five personality trait. You hate <i>half of humanity</i>. Evolution produced the best problem-solving thing ever, humanity, and you decided a lot of the work done there was just pointless.<p>The real reason disagreeable people are valuable and can attain power in the workplace is because you&#x27;ve made it so with this completely unreasonable bias you have. They&#x27;re not supposed to be extremely rare! That only happens in the tech workplace.<p>Would you similarly discriminate against anxious people? What about people who aren&#x27;t open to new experiences? Do you shut them out too? How does your ideology square with black people being <i>way</i> more disagreeable on average? Let me guess: You don&#x27;t hire any and then mumble something about culture fit.<p>Working with disagreeable people doesn&#x27;t suck. Working sucks. The disagreeable people just point it out. How do you ever improve without that? Working at an all-agreeable-people tech firm is a Kafkaesque nightmare of everything being perfect and nothing getting done. And you all deserve it because you decided that when people tend to be one way or the other, the ones who are like you are <i>just better</i>.</text></item><item><author>derbOac</author><text>This is interesting because it counters the idea that someone has to be a jerk to get ahead. However I&#x27;m also not sure the study really examined the idea too well, and ended up feeling like it&#x27;s the sort of thing that could be misinterpreted and overleveraged.<p>In my personal experience (which is limited) there&#x27;s a certain constellation of organizational characteristics that leads to disagreeable individuals attaining power, and organizational &quot;combativeness&quot; isn&#x27;t really it. I think &quot;corruption&quot; is closer, and good luck measuring that with a self report survey.<p>Then again, maybe the relevant issue isn&#x27;t whether or not people who are jerks are more likely to attain power, it&#x27;s than once they&#x27;re there they&#x27;re more likely to cause problems, and they&#x27;re not <i>less likely</i> to attain power. So then them being in power is salient.<p>But then I think you have to ask, why aren&#x27;t they less likely to attain power? Is this a case where a zero correlation is actually masking some mixture of processes, one positive in direction and the other negative? If so you&#x27;d think that certain settings would inhibit one or the other of those processes.<p>I guess I feel like this is a case where studying normative organizational dynamics in a cursory way could end up being really misleading.</text></item></parent_chain><comment><author>kyleyeats</author><text>No, it&#x27;s not possible, if you&#x27;re disagreeable. Being disagreeable is a matter of personality, not a matter of personal choice. It would be like me disagreeing while not being tall. I can&#x27;t do it because I am tall all the time.<p>Obviously disagreeable can agree or disagree, and they can do either well or badly (I happen to be very good at both, thanks). It doesn&#x27;t change who they are while doing it. Just like someone who isn&#x27;t open to new experiences doesn&#x27;t experience a personality change while trying a new restaurant.<p>Disagreeable people do, as a group, have more unpleasant, cynical and snarky people. But that doesn&#x27;t mean that all people in that group are that way. It&#x27;s not fair for you to assign me these qualities and then argue against them when I&#x27;m talking about disagreeable people at large. Again, it&#x27;s half the population so there&#x27;s a wide spectrum of outcomes.</text></comment> |
4,144,914 | 4,144,945 | 1 | 2 | 4,144,621 | train | <story><title>I Just Gave Up $4000 Per Month to Keep My Freedom of Speech</title><url>http://www.mrmoneymustache.com/2012/06/21/i-just-gave-up-4000-per-month-to-keep-my-freedom-of-speech/?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+MrMoneyMustache+%28Mr.+Money+Mustache%29</url></story><parent_chain><item><author>crazygringo</author><text>It's certainly an interesting attitude.<p>But what if he had decided to change the banner, and give the money away to a charity instead?<p>Money is a tool you can use for good. If you are blessed with the kind of extra money he was suddenly given, you can use it to do good with.<p>Obviously it's all his choice, but making a big show of "freedom of speech" feels a little disingenuous. No government is trying to censor him; nobody is taking away his freedom; this is just a business negotiation. At no point was his freedom of speech ever threatened in the slightest.</text></item></parent_chain><comment><author>Smerity</author><text>Freedom of speech has many facets. I don't see this as being disingenuous at all as it literally did impinge on his choice of speech if he wanted to remain in the business relationship.
This situation would be similar in nature to Microsoft forcing businesses to disavow Linux to remain in partnership with them.
Censorship can be legal and doesn't have to come from a government for it to still be censorship.<p>The charity argument is unfair -- most people and businesses could give more money to charity if they live "comfortably". The manner in which he gives back to the community is purely for him to decide. In this situation it's not a free trade either as he needs to give up something quite important to him (censorship) to receive the money. He'd be endorsing a product or service that he doesn't believe in and changing the content of his product or site to fit with it.</text></comment> | <story><title>I Just Gave Up $4000 Per Month to Keep My Freedom of Speech</title><url>http://www.mrmoneymustache.com/2012/06/21/i-just-gave-up-4000-per-month-to-keep-my-freedom-of-speech/?utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+MrMoneyMustache+%28Mr.+Money+Mustache%29</url></story><parent_chain><item><author>crazygringo</author><text>It's certainly an interesting attitude.<p>But what if he had decided to change the banner, and give the money away to a charity instead?<p>Money is a tool you can use for good. If you are blessed with the kind of extra money he was suddenly given, you can use it to do good with.<p>Obviously it's all his choice, but making a big show of "freedom of speech" feels a little disingenuous. No government is trying to censor him; nobody is taking away his freedom; this is just a business negotiation. At no point was his freedom of speech ever threatened in the slightest.</text></item></parent_chain><comment><author>FreakLegion</author><text><i>&#62; making a big show of "freedom of speech" feels a little disingenuous</i><p>Maybe not disingenuous (which implies some degree of pretense), but certainly inaccurate. People like to use the phrase "freedom of speech" because it has propaganda value in most Western cultures. To paraphrase one legal scholar, the first lawyer to yell "freedom of speech!" in a crowded courtroom wins.</text></comment> |
6,531,569 | 6,531,313 | 1 | 3 | 6,530,924 | train | <story><title>Full archives of Game Developer magazine</title><url>http://gdcvault.com/gdmag</url></story><parent_chain><item><author>meritt</author><text>If you want to download all the PDFs to your current working directory:<p><pre><code> wget -rH -nd -Dubm-us.net -Apdf http:&#x2F;&#x2F;gdcvault.com&#x2F;gdmag
</code></pre>
Edit: for the curious, the flags are:<p><pre><code> -r recursively retrieve all the links on the page
-H span hosts (default would stay with gdcvault.com only)
-nd don&#x27;t replicate directory hierarchy, just download the files to cwd
-D only download from ubm-us.net
-A pdf extensions only</code></pre></text></item></parent_chain><comment><author>candydance</author><text>Consider grabbing the torrent[0] instead so as not to peg the gdcvault server.<p>[0]: <a href="http://thepiratebay.sx/torrent/8940823/Game_Developer_Magazine_Complete_1994-2013_Archives" rel="nofollow">http:&#x2F;&#x2F;thepiratebay.sx&#x2F;torrent&#x2F;8940823&#x2F;Game_Developer_Magazi...</a></text></comment> | <story><title>Full archives of Game Developer magazine</title><url>http://gdcvault.com/gdmag</url></story><parent_chain><item><author>meritt</author><text>If you want to download all the PDFs to your current working directory:<p><pre><code> wget -rH -nd -Dubm-us.net -Apdf http:&#x2F;&#x2F;gdcvault.com&#x2F;gdmag
</code></pre>
Edit: for the curious, the flags are:<p><pre><code> -r recursively retrieve all the links on the page
-H span hosts (default would stay with gdcvault.com only)
-nd don&#x27;t replicate directory hierarchy, just download the files to cwd
-D only download from ubm-us.net
-A pdf extensions only</code></pre></text></item></parent_chain><comment><author>blinkingled</author><text>DownThemAll works with Firefox cross platform. Right Click on the page and dta OneClick. Fast Filter <i>.pdf, </i>.zip covers all downloads.</text></comment> |
35,492,258 | 35,488,020 | 1 | 3 | 35,484,594 | train | <story><title>Ask Wirecutter: Can you recommend a not-smart TV for me?</title><url>https://www.nytimes.com/wirecutter/blog/ask-wirecutter-dumb-tvs/</url></story><parent_chain><item><author>lbotos</author><text>Search: &lt;brand name&gt; digital information display<p>Samsung 4k <a href="https:&#x2F;&#x2F;www.samsung.com&#x2F;us&#x2F;business&#x2F;displays&#x2F;4k-uhd&#x2F;qb-series&#x2F;qbb-n-series-65-lh65qbbnbgcxgo&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.samsung.com&#x2F;us&#x2F;business&#x2F;displays&#x2F;4k-uhd&#x2F;qb-serie...</a><p>It&#x27;s more expensive then the subsidized ones, but right in the description:<p>QB65B--N * Direct-Lit 4K Crystal UHD LED Display for Business Without Embedded Wi-Fi or Bluetooth<p>As others have suggested as well, possibly a monitor, but I&#x27;m not aware of many 65&quot; 4k monitors (But they may exist)</text></item></parent_chain><comment><author>thih9</author><text>Keep in mind that digital signage is a different use case and products may focus on that, offering different materials and performance (brightness, viewing angles, refresh rate, etc).</text></comment> | <story><title>Ask Wirecutter: Can you recommend a not-smart TV for me?</title><url>https://www.nytimes.com/wirecutter/blog/ask-wirecutter-dumb-tvs/</url></story><parent_chain><item><author>lbotos</author><text>Search: &lt;brand name&gt; digital information display<p>Samsung 4k <a href="https:&#x2F;&#x2F;www.samsung.com&#x2F;us&#x2F;business&#x2F;displays&#x2F;4k-uhd&#x2F;qb-series&#x2F;qbb-n-series-65-lh65qbbnbgcxgo&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.samsung.com&#x2F;us&#x2F;business&#x2F;displays&#x2F;4k-uhd&#x2F;qb-serie...</a><p>It&#x27;s more expensive then the subsidized ones, but right in the description:<p>QB65B--N * Direct-Lit 4K Crystal UHD LED Display for Business Without Embedded Wi-Fi or Bluetooth<p>As others have suggested as well, possibly a monitor, but I&#x27;m not aware of many 65&quot; 4k monitors (But they may exist)</text></item></parent_chain><comment><author>nrvn</author><text>DIDs are great but there are two main problems with them:<p>1. They appear to be more expensive than consumer TV’s<p>2. They might be more difficult to find through usual channels because they are targeted at businesses (but it probably depends on where you are located)</text></comment> |
37,943,803 | 37,941,967 | 1 | 3 | 37,930,634 | train | <story><title>The fake browser update scam gets a makeover</title><url>https://krebsonsecurity.com/2023/10/the-fake-browser-update-scam-gets-a-makeover/</url></story><parent_chain><item><author>fturst</author><text>Preserving privacy, reliable transactions with no, i repeat, no bank or govmnt involvement, no kyc. No&#x2F;low fees (on some currencies), public immutable databases...</text></item><item><author>d11z</author><text>Could you give some other concrete, practical examples of use cases for cryptocurrencies instead of the passive-aggressive snark?</text></item><item><author>staplers</author><text>The suffocating irony of this forum being called &quot;Hacker News&quot; when it is filled with comments like this never fails to amaze me. A truly unimaginative bunch.</text></item><item><author>d11z</author><text>It’s been great for gambling, cybercrime, and enabling the drug trade practically since its inception.</text></item><item><author>andybak</author><text>I&#x27;m just happy to finally see a practical use case for Blockchain technology.</text></item></parent_chain><comment><author>LetsGetTechnicl</author><text>How is having every transaction on the blockchain considered private? If someone knows your wallet address they can see everything you&#x27;ve done</text></comment> | <story><title>The fake browser update scam gets a makeover</title><url>https://krebsonsecurity.com/2023/10/the-fake-browser-update-scam-gets-a-makeover/</url></story><parent_chain><item><author>fturst</author><text>Preserving privacy, reliable transactions with no, i repeat, no bank or govmnt involvement, no kyc. No&#x2F;low fees (on some currencies), public immutable databases...</text></item><item><author>d11z</author><text>Could you give some other concrete, practical examples of use cases for cryptocurrencies instead of the passive-aggressive snark?</text></item><item><author>staplers</author><text>The suffocating irony of this forum being called &quot;Hacker News&quot; when it is filled with comments like this never fails to amaze me. A truly unimaginative bunch.</text></item><item><author>d11z</author><text>It’s been great for gambling, cybercrime, and enabling the drug trade practically since its inception.</text></item><item><author>andybak</author><text>I&#x27;m just happy to finally see a practical use case for Blockchain technology.</text></item></parent_chain><comment><author>michaelcampbell</author><text>These feel more like theoretical selling points, not documented uses of.</text></comment> |
27,279,184 | 27,278,810 | 1 | 2 | 27,275,906 | train | <story><title>Data portability, the forgotten right of GDPR</title><url>https://www.alias.dev/report</url></story><parent_chain><item><author>somethingAlex</author><text>What are consumers intuitively expecting compliance with this law to look like?<p>Data from one service may be in an entirely different schema than the service you want to import it too - let alone format. Service A may summarize your data and throw away the granular stuff, but service B runs on the granular data.<p>Are consumers going to implement ETL pipelines to achieve portability? Are they expecting to hook up streaming mechanisms for enormous swathes of data?<p>Just as an example, if I wanted to get a list of every song I liked on Spotify and import it into Apple Music, how would that even work? The songId of Spotify is undoubtedly different than the one Apple uses. Are Apple and Spotify supposed to agree on a common file format?<p>I agree with the intent of the law but I&#x27;m not surprised most services do not offer an automated way to take out data. It&#x27;s a rare case, often a heavy workload, and there&#x27;s really no way to guarantee the data you receive is actually portable.</text></item></parent_chain><comment><author>izacus</author><text>&gt; Just as an example, if I wanted to get a list of every song I liked on Spotify and import it into Apple Music, how would that even work? The songId of Spotify is undoubtedly different than the one Apple uses. Are Apple and Spotify supposed to agree on a common file format?<p>Why wouldn&#x27;t it work? Desktop apps had m3u playlist formats which could be read by multiple players - from Winamp on desktop, iTunes on a Mac or even car headunits. It&#x27;s now kinda wierd to say that rockstar engineers of Apple&#x2F;Spotify can&#x27;t find a way to export playlists and liked songs (a global singletons essentially) they got from the SAME publishers and probably ingest from the SAME content owner data sources.</text></comment> | <story><title>Data portability, the forgotten right of GDPR</title><url>https://www.alias.dev/report</url></story><parent_chain><item><author>somethingAlex</author><text>What are consumers intuitively expecting compliance with this law to look like?<p>Data from one service may be in an entirely different schema than the service you want to import it too - let alone format. Service A may summarize your data and throw away the granular stuff, but service B runs on the granular data.<p>Are consumers going to implement ETL pipelines to achieve portability? Are they expecting to hook up streaming mechanisms for enormous swathes of data?<p>Just as an example, if I wanted to get a list of every song I liked on Spotify and import it into Apple Music, how would that even work? The songId of Spotify is undoubtedly different than the one Apple uses. Are Apple and Spotify supposed to agree on a common file format?<p>I agree with the intent of the law but I&#x27;m not surprised most services do not offer an automated way to take out data. It&#x27;s a rare case, often a heavy workload, and there&#x27;s really no way to guarantee the data you receive is actually portable.</text></item></parent_chain><comment><author>dsr_</author><text>There are incentives for, say, Mastodon to be able to ingest your tweeting history, or for Linked-In to eat your Facebook social graph.<p>There&#x27;s no incentive other than the law for Twitter or Facebook to make that data exportable.</text></comment> |
6,557,952 | 6,557,982 | 1 | 2 | 6,557,794 | train | <story><title>Cockroach farms multiplying in China</title><url>http://www.latimes.com/world/la-fg-c1-china-cockroach-20131015-dto,2669,4433405.htmlstory</url></story><parent_chain></parent_chain><comment><author>spodek</author><text>Capitalism is stronger than customs.<p>If growing them feeds people efficiently, we&#x27;ll see it here soon enough.<p>Potatoes didn&#x27;t exist outside the Americas until after 1492. Then many cultures viewed them as lowly and not worth eating. But you can feed more people per area than any other food and they grow in more types of land than many other edible plants. Cultures would reject them until a famine struck. Then the ruler would eat them out of necessity. Then everyone would eat them. Now potatoes are in more cuisines of the world than any other food.<p>If cockroaches are efficient, I would expect a few shocks in some commodity markets to put them on a few cultures&#x27; dinner plates, then to spread. Like roaches, if you&#x27;ll pardon the pun.</text></comment> | <story><title>Cockroach farms multiplying in China</title><url>http://www.latimes.com/world/la-fg-c1-china-cockroach-20131015-dto,2669,4433405.htmlstory</url></story><parent_chain></parent_chain><comment><author>pkfrank</author><text>I&#x27;m more excited by cricket farming for protein flour (here in the US).<p>There&#x27;s a Brooklyn company called Exo (Exo.co) which is doing just that after a kickstarter campaign + media blitz. Cricket flour is super high in protein, and also very sustainable. Could see it becoming the next acai, chia seed, quinoa, etc.</text></comment> |
37,220,359 | 37,220,395 | 1 | 2 | 37,219,779 | train | <story><title>Arm Announces Public Filing for Proposed Initial Public Offering</title><url>https://www.arm.com/company/news/2023/08/arm-announces-public-filing-of-registration-statement-for-proposed-initial-public-offering</url></story><parent_chain><item><author>masklinn</author><text>Sounds like English banking has not changed much from 20 years ago, when I needed to spend 3 months in the UK, had to have a uk bank account to rent a flat, but needed an English residence to open a bank account.</text></item><item><author>ricardobayes</author><text>The business enviroment is a lot better in the US, a friend just started a company there, got an unsecured 80k line of credit at 1.5% on a fresh LLC. This kind of thing doesn&#x27;t exist in the UK. I know people who couldn&#x27;t even get a 5k overdraft after 2 years in business (and profitable).</text></item><item><author>Thev00d00</author><text>Bit of a downer for the UK to see them list in the US, I do understand they just want access to the most capital, but I find a shame LSE is not competitive for this kind of thing.</text></item></parent_chain><comment><author>noelwelsh</author><text>Consumer banking has radically changed. I can&#x27;t comment on needing a residence to open a bank account to get a residence, because although I ran into the same issue when I first came here it&#x27;s been a long time since that was a problem for me. In other aspect personal banking is much much easier. Many banks allow you to open accounts online, for example.</text></comment> | <story><title>Arm Announces Public Filing for Proposed Initial Public Offering</title><url>https://www.arm.com/company/news/2023/08/arm-announces-public-filing-of-registration-statement-for-proposed-initial-public-offering</url></story><parent_chain><item><author>masklinn</author><text>Sounds like English banking has not changed much from 20 years ago, when I needed to spend 3 months in the UK, had to have a uk bank account to rent a flat, but needed an English residence to open a bank account.</text></item><item><author>ricardobayes</author><text>The business enviroment is a lot better in the US, a friend just started a company there, got an unsecured 80k line of credit at 1.5% on a fresh LLC. This kind of thing doesn&#x27;t exist in the UK. I know people who couldn&#x27;t even get a 5k overdraft after 2 years in business (and profitable).</text></item><item><author>Thev00d00</author><text>Bit of a downer for the UK to see them list in the US, I do understand they just want access to the most capital, but I find a shame LSE is not competitive for this kind of thing.</text></item></parent_chain><comment><author>googamooga</author><text>Yeah, and to prove your English residence you have to provide a paper bill from a utility company (water or electricity) with your name and address on it. Which adds another 3 month as those utility bills are on a quarterly basis. Crazy stuff...</text></comment> |
17,335,941 | 17,335,543 | 1 | 3 | 17,330,734 | train | <story><title>Netflix Is Why AT&T bought Time Warner, and Comcast and Disney want Fox</title><url>https://www.cnbc.com/2018/06/13/netflix-why-att-bought-time-warner-and-comcast-and-disney-want-fox.html</url></story><parent_chain><item><author>JimmyAustin</author><text>The on-demand nexus already works on Apple TV. Say &quot;I want to watch Billions&quot; into the remote and it shows you all the services you can watch it on, then tap through to actually watching it.<p>Now if only it existed on other platforms.</text></item><item><author>lgregg</author><text>&gt; We want an on-demand nexus. A single hub.<p>That is close to existing, it&#x27;d be nice if the top players agreed to open their APIs so you could integrate it into a unified TV external like Chromecast or Firestick. Or, to go further, a unified platform that can process subscriptions and PPV across each library.<p>&gt; $100&#x2F;month for a dozen streaming &quot;channels&quot; with one or two good shows and a the same crap the rest of the other &quot;channels&quot; have.<p>Amen, we cut the cord officially on Friday. We went to $67 (including modem rental) per month plus about $25 dollars in streaming services and $40 for YT TV per month. That&#x27;s still $35 dollars cheaper than what we were paying for Comcast TV and once we buy a compatible modem then we&#x27;ll drop our internet to about $55 per month. We also have renters, so we loop them into YTTV for them to watch to their heart&#x27;s desire for an extra $5 on their rent per month.<p>&gt; Ghost in the Shell<p>Respect just got done rewatching an episode of the TV show.</text></item><item><author>MisterTea</author><text>These companies are obsessed with fragmenting the market for the sake of owning content from production to delivery. I have bad news for them: you&#x27;re going to lose. People don&#x27;t want to go back to paying $100&#x2F;month for a dozen streaming &quot;channels&quot; with one or two good shows and a the same crap the rest of the other &quot;channels&quot; have.<p>We want an on-demand nexus. A single hub. Just the other day I had the urge to watch ghost in the shell. Not available on any of the major streaming sites (Netflix, Hulu, Prime) but available on stars via prime. So I have to pay an addition $7&#x2F;month to watch a single show? No thanks. Off to a torrent site or asking around to see if someone has rips or a box set. I have better things to do with $7 like buy dinner.</text></item></parent_chain><comment><author>Sargos</author><text>Like most features this has existed on other platforms like Android TV way before Apple TV.<p>The parent comment was actually talking about paying for one service that has everything I think not just a shortcut to each disparate service.</text></comment> | <story><title>Netflix Is Why AT&T bought Time Warner, and Comcast and Disney want Fox</title><url>https://www.cnbc.com/2018/06/13/netflix-why-att-bought-time-warner-and-comcast-and-disney-want-fox.html</url></story><parent_chain><item><author>JimmyAustin</author><text>The on-demand nexus already works on Apple TV. Say &quot;I want to watch Billions&quot; into the remote and it shows you all the services you can watch it on, then tap through to actually watching it.<p>Now if only it existed on other platforms.</text></item><item><author>lgregg</author><text>&gt; We want an on-demand nexus. A single hub.<p>That is close to existing, it&#x27;d be nice if the top players agreed to open their APIs so you could integrate it into a unified TV external like Chromecast or Firestick. Or, to go further, a unified platform that can process subscriptions and PPV across each library.<p>&gt; $100&#x2F;month for a dozen streaming &quot;channels&quot; with one or two good shows and a the same crap the rest of the other &quot;channels&quot; have.<p>Amen, we cut the cord officially on Friday. We went to $67 (including modem rental) per month plus about $25 dollars in streaming services and $40 for YT TV per month. That&#x27;s still $35 dollars cheaper than what we were paying for Comcast TV and once we buy a compatible modem then we&#x27;ll drop our internet to about $55 per month. We also have renters, so we loop them into YTTV for them to watch to their heart&#x27;s desire for an extra $5 on their rent per month.<p>&gt; Ghost in the Shell<p>Respect just got done rewatching an episode of the TV show.</text></item><item><author>MisterTea</author><text>These companies are obsessed with fragmenting the market for the sake of owning content from production to delivery. I have bad news for them: you&#x27;re going to lose. People don&#x27;t want to go back to paying $100&#x2F;month for a dozen streaming &quot;channels&quot; with one or two good shows and a the same crap the rest of the other &quot;channels&quot; have.<p>We want an on-demand nexus. A single hub. Just the other day I had the urge to watch ghost in the shell. Not available on any of the major streaming sites (Netflix, Hulu, Prime) but available on stars via prime. So I have to pay an addition $7&#x2F;month to watch a single show? No thanks. Off to a torrent site or asking around to see if someone has rips or a box set. I have better things to do with $7 like buy dinner.</text></item></parent_chain><comment><author>toast0</author><text>Roku has a pretty large list of providers and the ability to search across them. It does feel like I&#x27;m being nickle and dined to death though when back catalog stuff I want to watch costs the same as recent shows :(</text></comment> |
7,308,008 | 7,306,611 | 1 | 2 | 7,306,319 | train | <story><title>Texas Appeals Court Rules Phone Search After Arrest Violates 4th Amendment [pdf]</title><url>http://www.cca.courts.state.tx.us/opinions/pdfOpinion.asp?OpinionID=25167</url></story><parent_chain></parent_chain><comment><author>tptacek</author><text>Footnote 30, on Page 13, is very very important to understanding the limitations of this ruling; the ruling concerns <i>inventory searches</i> and not the more common <i>searches incident to arrest</i>. If you are arrested, in most locales in the US, it is very likely that evidence taken from your phone <i>at the time of your arrest</i> will stand up in court. Keep your phones secure.</text></comment> | <story><title>Texas Appeals Court Rules Phone Search After Arrest Violates 4th Amendment [pdf]</title><url>http://www.cca.courts.state.tx.us/opinions/pdfOpinion.asp?OpinionID=25167</url></story><parent_chain></parent_chain><comment><author>dmix</author><text>In Canada, if the phone has a password police need a search warrant to go through it.<p>Whats more alarming is he was a high school student who got arrested for a disturbance on a bus:<p>&gt; One morning, Anthony Granville was arrested for the Class C offense of causing adisturbance on the school bus. His cell phone was taken from him during the bookingprocedure and placed in the jail property room.</text></comment> |
39,081,010 | 39,077,949 | 1 | 3 | 39,077,535 | train | <story><title>Boehm-Demers-Weiser conservative C/C++ Garbage Collector</title><url>https://hboehm.info/gc/</url></story><parent_chain></parent_chain><comment><author>Jeaye</author><text>I have been using the Boehm-Demers-Weiser GC for jank [1], the native Clojure dialect on LLVM with C++ interop. Since jank is a Clojure dialect, and Clojure is built primarily on persistent, immutable data structures, there are potentially a lot of references to objects, potentially cyclical, across many threads, and there&#x27;s a lot of garbage being churned. I originally started with reference counting and RAII, using boost::intrusive_ptr and an atomic count. The GC was actually 2x faster, in the sequence benchmark I was trying to optimize.<p>At this point, jank is generally several times faster than the equivalent Clojure JVM code. I&#x27;m sure there are better GCs out there, in terms of performance, and I have my eye on MMTK [2] for a future upgrade, but the fact that remains is this: the Boehm GC is stupid simple to integrate and it&#x27;s surprisingly fast. Compare it to MPS, MMTK, and others and both the documentation and the actual dev work required are worlds apart.<p>For a project which needs a GC but doesn&#x27;t need to pick the absolute fastest one first, it seems like the best option, based on my research and my experience.<p>1: <a href="https:&#x2F;&#x2F;jank-lang.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;jank-lang.org&#x2F;</a><p>2: <a href="https:&#x2F;&#x2F;www.mmtk.io&#x2F;code" rel="nofollow">https:&#x2F;&#x2F;www.mmtk.io&#x2F;code</a></text></comment> | <story><title>Boehm-Demers-Weiser conservative C/C++ Garbage Collector</title><url>https://hboehm.info/gc/</url></story><parent_chain></parent_chain><comment><author>torginus</author><text>Ah the spectre of the 80s, most famously used by the ancient fork of Mono that Unity uses, leading to GC-pause induced stutters that have plagued gaming for over a decade.<p>I&#x27;d estimate that the bad rap GC languages get can be traced back to this piece of code.</text></comment> |
12,873,965 | 12,873,550 | 1 | 2 | 12,870,811 | train | <story><title>“Ultrasonic cross-device tracking” embeds inaudible tones in advertisements</title><url>http://arstechnica.com/security/2016/11/how-to-block-the-ultrasonic-signals-you-didnt-know-were-tracking-you/</url></story><parent_chain><item><author>danbruc</author><text>This is reaching the point where the only sensible policy is to flat-out prohibit all forms of adverting on any medium. Paying a company to lie to you is already a pretty bizarre idea but the invasion of privacy - online or offline - makes advertising increasingly intolerable.</text></item></parent_chain><comment><author>ogig</author><text>Child oriented ads are especially awful. We let some greedy people massively influence our kids just so they profit. I would ban every kind of marketing oriented to kids and youngs.<p>If you have something really useful and good for the kids, sell it to their fathers. If you want to scam their money then get out.</text></comment> | <story><title>“Ultrasonic cross-device tracking” embeds inaudible tones in advertisements</title><url>http://arstechnica.com/security/2016/11/how-to-block-the-ultrasonic-signals-you-didnt-know-were-tracking-you/</url></story><parent_chain><item><author>danbruc</author><text>This is reaching the point where the only sensible policy is to flat-out prohibit all forms of adverting on any medium. Paying a company to lie to you is already a pretty bizarre idea but the invasion of privacy - online or offline - makes advertising increasingly intolerable.</text></item></parent_chain><comment><author>rocky1138</author><text>I found it interesting that the FCC&#x27;s recommendation was to build an opt-out system, since this is so obviously anti-human and pro-corporation. It shows where their interests lie.<p>This kind of system should be opt-in only, with hand-signed agreements.</text></comment> |
24,909,651 | 24,909,961 | 1 | 2 | 24,908,729 | train | <story><title>Next.js 10</title><url>https://nextjs.org/blog/next-10</url></story><parent_chain><item><author>pbowyer</author><text>&gt; Nowadays users browse the web using their phones, tablets, and laptops, yet images are still as a one size fits all. For example: sites load a 2000 by 2000 pixel image, but phones are only displaying it as 100 by 100 pixels.<p>That&#x27;s what srcset &amp; &lt;source&gt; were invented for.<p>&gt; Furthermore, 30% of images on web pages are outside of the initial viewport, meaning the browser loads images that a user does not see until they scroll further down the page.<p>That&#x27;s why we now have a loading=lazy HTML attribute<p>&gt; When using the next&#x2F;image component, images are automatically lazy-loaded, meaning they&#x27;re only rendered when the user is close to seeing the image. This prevents loading that 30% of images outside of the initial viewport.<p>This has been done many times before. For images outside the viewport it&#x27;s great; for images which are in the viewport, the browser isn&#x27;t able to discover the image until the JS has loaded and decided which image size to fetch. In my experience this slows down the overall rendering of the page.<p>I see the Google Chrome team was involved in creating this component so I&#x27;d like to know what&#x27;s different this time, because they have the data.<p>&gt; Developers can mark images that are in the initial viewport, allowing Next.js to automatically preload these images. Preloading images in the initial viewport has shown improvements to the Largest Contentful Paint by up to 50%.<p>How can smart preloading work when the image size isn&#x27;t known until the JS component runs? If we&#x27;re back to loading the 2000px image then we&#x27;re losing a lot of optimization.<p>If they&#x27;re relying on client hints [1] then we can get as far as an image as wide as the browser window width, but no more - at the price of poor browser compatibility.<p>Preloading also has its own costs, as it messes with the browser&#x27;s prioritization of page content. I&#x27;ve found it easy to prioritize something you know is essential and unintentionally increase load time metrics.<p>1. <a href="https:&#x2F;&#x2F;caniuse.com&#x2F;client-hints-dpr-width-viewport" rel="nofollow">https:&#x2F;&#x2F;caniuse.com&#x2F;client-hints-dpr-width-viewport</a></text></item></parent_chain><comment><author>mulholio</author><text>&gt; That&#x27;s what srcset &amp; &lt;source&gt; were invented for.<p>Next.js is going to be using srcset under the hood, I&#x27;m sure. The whole point of Next.js is to make best practices like this defaults, not to do anything groundbreaking and new.</text></comment> | <story><title>Next.js 10</title><url>https://nextjs.org/blog/next-10</url></story><parent_chain><item><author>pbowyer</author><text>&gt; Nowadays users browse the web using their phones, tablets, and laptops, yet images are still as a one size fits all. For example: sites load a 2000 by 2000 pixel image, but phones are only displaying it as 100 by 100 pixels.<p>That&#x27;s what srcset &amp; &lt;source&gt; were invented for.<p>&gt; Furthermore, 30% of images on web pages are outside of the initial viewport, meaning the browser loads images that a user does not see until they scroll further down the page.<p>That&#x27;s why we now have a loading=lazy HTML attribute<p>&gt; When using the next&#x2F;image component, images are automatically lazy-loaded, meaning they&#x27;re only rendered when the user is close to seeing the image. This prevents loading that 30% of images outside of the initial viewport.<p>This has been done many times before. For images outside the viewport it&#x27;s great; for images which are in the viewport, the browser isn&#x27;t able to discover the image until the JS has loaded and decided which image size to fetch. In my experience this slows down the overall rendering of the page.<p>I see the Google Chrome team was involved in creating this component so I&#x27;d like to know what&#x27;s different this time, because they have the data.<p>&gt; Developers can mark images that are in the initial viewport, allowing Next.js to automatically preload these images. Preloading images in the initial viewport has shown improvements to the Largest Contentful Paint by up to 50%.<p>How can smart preloading work when the image size isn&#x27;t known until the JS component runs? If we&#x27;re back to loading the 2000px image then we&#x27;re losing a lot of optimization.<p>If they&#x27;re relying on client hints [1] then we can get as far as an image as wide as the browser window width, but no more - at the price of poor browser compatibility.<p>Preloading also has its own costs, as it messes with the browser&#x27;s prioritization of page content. I&#x27;ve found it easy to prioritize something you know is essential and unintentionally increase load time metrics.<p>1. <a href="https:&#x2F;&#x2F;caniuse.com&#x2F;client-hints-dpr-width-viewport" rel="nofollow">https:&#x2F;&#x2F;caniuse.com&#x2F;client-hints-dpr-width-viewport</a></text></item></parent_chain><comment><author>jaredklewis</author><text>&gt; That&#x27;s what srcset &amp; &lt;source&gt; were invented for.<p>next&#x2F;image makes use of srcset.<p>&gt; This has been done many times before. For images outside the viewport it&#x27;s great; for images which are in the viewport, the browser isn&#x27;t able to discover the image until the JS has loaded and decided which image size to fetch. In my experience this slows down the overall rendering of the page.
&gt;I see the Google Chrome team was involved in creating this component so I&#x27;d like to know what&#x27;s different this time, because they have the data.<p>No knowledge of what Google contributed to this, but my experience of running Google PageSpeed Insights on many sites is that this sort of optimization does improve the metrics Google measures.<p>Also, while I agree in part with most of your points, I still think we should give credit to nextjs for making this easy.<p>Sure, maybe you don&#x27;t need a library to use srcset. If you are going to run our own custom build processes (or server endpoints) that generate images in a range of appropriate sizes and write the corresponding front-end code, good for you. Next.js has done nothing to stop any of this.<p>But many (most?) websites don&#x27;t bother with any of that and just load one giant image for everyone. If there is a tool that makes using optimized images as easy loading one giant image for everyone, I think that&#x27;s great.</text></comment> |
29,027,492 | 29,026,800 | 1 | 3 | 29,025,401 | train | <story><title>I was rejected by Codecademy three times, so I built my own</title><url>https://codeamigo.dev?ref=HN</url></story><parent_chain><item><author>mtc010170</author><text>Way to be! It&#x27;s silly how often employers overlook the &quot;I just really want to be part of&#x2F;build this&quot; factor. People with that make for excellent teammates.</text></item></parent_chain><comment><author>PragmaticPulp</author><text>&gt; It&#x27;s silly how often employers overlook the &quot;I just really want to be part of&#x2F;build this&quot; factor. People with that make for excellent teammates.<p>Every startup I&#x27;ve been a part of has picked up a few extremely passionate but not necessarily fully qualified people along the way. It&#x27;s <i>hard</i> to turn down an enthusiastic candidate who really, really likes your company, so they&#x27;re often given a chance.<p>Some of them turned out to be excellent teammates who did everything necessary to grow into the role.<p>But sadly, many of them just wanted to be startup people without doing the startup grunt work. Worst case, someone with a lot of passion that goes in a different direction than the founders can become a drag on the company or create a lot of conflict. (NOTE: I&#x27;m speaking generally, not implying this is the case with the linked author)<p>Passionate people are <i>generally</i> good when their skills and wants align with the company, but if they&#x27;re not well-aligned then the passion just amplifies every conflict.</text></comment> | <story><title>I was rejected by Codecademy three times, so I built my own</title><url>https://codeamigo.dev?ref=HN</url></story><parent_chain><item><author>mtc010170</author><text>Way to be! It&#x27;s silly how often employers overlook the &quot;I just really want to be part of&#x2F;build this&quot; factor. People with that make for excellent teammates.</text></item></parent_chain><comment><author>WesolyKubeczek</author><text>&gt; &quot;I just really want to be part of&#x2F;build this&quot; factor. People with that make for excellent teammates.<p>Not always. You want to be a part of something&#x2F;build something, and then you want to build it YOUR way. Or you see an obvious hole and then an ugly battle between your ego and that of the chief architect ensues.<p>Also, there may be cases when you want to be a part of something, meet your heroes, and then it all goes pear-shaped. Because you shouldn&#x27;t meet your heroes.<p>And sometimes it&#x27;s better to have mercenaries who don&#x27;t necessary believe in the same thing as you but care a lot about their own reputation and take pride in having done a good job.</text></comment> |
24,856,200 | 24,856,116 | 1 | 3 | 24,855,183 | train | <story><title>Debian donation for Peertube development</title><url>https://bits.debian.org/2020/10/debian-donation-peertube.html</url></story><parent_chain></parent_chain><comment><author>roenxi</author><text>10,000 euros isn&#x27;t a lot of money. I&#x27;m going to interpret the enthusiastic upvoting of this post as being more about what it implies when steady and serious collectives like the Debian project start signalling that something is important. There needs to be better software infrastructure and it needs to be open source (and, indeed, free).<p>It is hard not to like Debian. It is wonderful to see that focused, principled, good-for-everyone organisations can still carry on even in 2020. Maybe not everyone believes in freedom but Debian has standards.</text></comment> | <story><title>Debian donation for Peertube development</title><url>https://bits.debian.org/2020/10/debian-donation-peertube.html</url></story><parent_chain></parent_chain><comment><author>kome</author><text>That&#x27;s SO cool! While everybody is busy wasting their life on a super centralized internet, it&#x27;s heartwarming to know that there are still ideas, people and money that goes towards interesting, free and perhaps even a bit idealistic projects.<p>And we are talking about tiny numbers: 10,000 €. But they can go a long way.<p>Support free software, people!</text></comment> |
23,390,981 | 23,387,475 | 1 | 3 | 23,387,211 | train | <story><title>Stitch Fix to Lay off About 1,400 Employees in California</title><url>https://www.wsj.com/articles/stitch-fix-to-lay-off-about-1-400-employees-in-california-11591053525</url></story><parent_chain><item><author>nostromo</author><text>This is more interesting than all the other layoff stories in that they&#x27;re axing 1,400 California jobs but adding 2,000 in lower-cost locations like Dallas, Pittsburgh, Cleveland, Minneapolis and Austin.<p>It&#x27;s like offshoring -- but off-Californiaing.</text></item></parent_chain><comment><author>Spooky23</author><text>It makes sense. If you&#x27;re not looking for super high-end tech talent, there is no magical advantage to paying California salaries so that people can spend every dime on housing.<p>I skeptical of most of the tech stuff too -- fewer tech roles require the skillsets&#x2F;social connections only found a big tech hub than in the past. For many years, IBM was able to run successful tech operations in places like Minneapolis, Austin, Binghamton NY, Hudson Valley NY, North Carolina, Tampa, etc.<p>The median home price is Pittsburgh is literally 90% less than many California locales. Even with a 40% pay cut, in many professions moving to one of these places will be a neutral in terms of money and probably a positive impact on the employee&#x27;s quality of life.</text></comment> | <story><title>Stitch Fix to Lay off About 1,400 Employees in California</title><url>https://www.wsj.com/articles/stitch-fix-to-lay-off-about-1-400-employees-in-california-11591053525</url></story><parent_chain><item><author>nostromo</author><text>This is more interesting than all the other layoff stories in that they&#x27;re axing 1,400 California jobs but adding 2,000 in lower-cost locations like Dallas, Pittsburgh, Cleveland, Minneapolis and Austin.<p>It&#x27;s like offshoring -- but off-Californiaing.</text></item></parent_chain><comment><author>onemoresoop</author><text>I wonder if they gave the employees the option to relocate with out of calofornia salary. Not sure if that’s legal but it would have been worth giving them an option, some might as well take it, everything’s too expensive in cali, one cannot easily start a family there</text></comment> |
12,086,284 | 12,086,305 | 1 | 2 | 12,085,044 | train | <story><title>Critical Behavior from Deep Dynamics: A Hidden Dimension in Natural Language</title><url>http://arxiv.org/abs/1606.06737v2</url></story><parent_chain><item><author>BenoitP</author><text>&gt; [...] A Hidden Dimension in Natural Language<p>Mmmh<p>&gt; [...] We show that in many data sequences — from texts in different languages to melodies and genomes<p>Hum, ehrm<p>&gt; [...] natural languages are poorly approximated by Markov processes.<p>Alright, alright<p>&gt; [...] This model class captures the essence of probabilistic context-free grammars<p>Ok, ok<p>&gt; [...] and cosmological inflation<p>Wat.<p>Out of nowhere, Creation of the Univerve.<p>-------------<p>I&#x27;m always baffled by the ability to draw parallels. Did a colleague take at peek at the screen and said, hey I have the same equations?</text></item></parent_chain><comment><author>Gargoyle</author><text>Worth noting the authors, Henry Lin and Max Tegmark, are both astrophysicists. Among other things.</text></comment> | <story><title>Critical Behavior from Deep Dynamics: A Hidden Dimension in Natural Language</title><url>http://arxiv.org/abs/1606.06737v2</url></story><parent_chain><item><author>BenoitP</author><text>&gt; [...] A Hidden Dimension in Natural Language<p>Mmmh<p>&gt; [...] We show that in many data sequences — from texts in different languages to melodies and genomes<p>Hum, ehrm<p>&gt; [...] natural languages are poorly approximated by Markov processes.<p>Alright, alright<p>&gt; [...] This model class captures the essence of probabilistic context-free grammars<p>Ok, ok<p>&gt; [...] and cosmological inflation<p>Wat.<p>Out of nowhere, Creation of the Univerve.<p>-------------<p>I&#x27;m always baffled by the ability to draw parallels. Did a colleague take at peek at the screen and said, hey I have the same equations?</text></item></parent_chain><comment><author>jakub_h</author><text>&gt; Did a colleague take at peek at the screen and said, hey I have the same equations?<p>This would an interesting thing to try - a computer system that would scan all the papers for math and find parallels. I think we already have something like term indexing for deductive systems?</text></comment> |
14,344,449 | 14,344,458 | 1 | 3 | 14,342,521 | train | <story><title>Two years of Rust</title><url>https://blog.rust-lang.org/2017/05/15/rust-at-two-years.html</url></story><parent_chain><item><author>brandur</author><text>I&#x27;m consistently blown away by just how good the project management for this language is. It&#x27;s not just the forward progress that the language is making (which is considerable), but also just how well they package the information up into a form that the rest of us who are not involved day to day can digest, like has been done here.<p>Another example is the &quot;This Week in Rust&quot; newsletter which takes progress that would&#x27;ve taken you hours to read about yourself, and puts it into a succinct format that you can get through in minutes [1].<p>The Rust 2017 roadmap which targeted forward movement on all the language&#x27;s weakest features was admirable in itself, but even moreso is how much progress has already been made. In particular, I&#x27;m really excited about incremental compilation, which is showing as much as 5x speedups in early results [2].<p>I was also very happy to hear that the Rust team acknowledges that regardless of how performant they are, futures are <i>not</i> a particularly ergonomic or maintainable way to write code, and are considering what new constructs might look like over the longer term:<p>&gt; <i>Over the rest of this year, we expect all of the above libraries to significantly mature; for a middleware ecosystem to sprout up; for the selection of supported protocols and services to grow; and, quite possibly, to tie all this all together with an async&#x2F;await notation that works natively with Rust’s futures.</i><p>I&#x27;m still on dabbling in Rust, but I&#x27;m fairly convinced that in another few years after this Tokio churn has gotten a chance to settle down and the async patterns are more broadly refined, there won&#x27;t be many justifiable reasons to <i>not</i> write new projects in it, whether they&#x27;re as low level as a Postgres extension, or as high level as a DB-backed HTTP application. It seems to have an almost perfect compromise between performance, safety, productivity, and ecosystem.<p>[1] <a href="https:&#x2F;&#x2F;this-week-in-rust.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;this-week-in-rust.org&#x2F;</a><p>[2] <a href="https:&#x2F;&#x2F;blog.rust-lang.org&#x2F;2017&#x2F;05&#x2F;15&#x2F;rust-at-two-years.html#rust-should-have-a-pleasant-edit-compile-debug-cycle" rel="nofollow">https:&#x2F;&#x2F;blog.rust-lang.org&#x2F;2017&#x2F;05&#x2F;15&#x2F;rust-at-two-years.html...</a></text></item></parent_chain><comment><author>FlyingSnake</author><text>Agreed.<p>Rust is like a fresh breath of air, and the community around the language is a great example how an OpenSource project can work without being hostile to newcomers. Kudos to the Rust team!</text></comment> | <story><title>Two years of Rust</title><url>https://blog.rust-lang.org/2017/05/15/rust-at-two-years.html</url></story><parent_chain><item><author>brandur</author><text>I&#x27;m consistently blown away by just how good the project management for this language is. It&#x27;s not just the forward progress that the language is making (which is considerable), but also just how well they package the information up into a form that the rest of us who are not involved day to day can digest, like has been done here.<p>Another example is the &quot;This Week in Rust&quot; newsletter which takes progress that would&#x27;ve taken you hours to read about yourself, and puts it into a succinct format that you can get through in minutes [1].<p>The Rust 2017 roadmap which targeted forward movement on all the language&#x27;s weakest features was admirable in itself, but even moreso is how much progress has already been made. In particular, I&#x27;m really excited about incremental compilation, which is showing as much as 5x speedups in early results [2].<p>I was also very happy to hear that the Rust team acknowledges that regardless of how performant they are, futures are <i>not</i> a particularly ergonomic or maintainable way to write code, and are considering what new constructs might look like over the longer term:<p>&gt; <i>Over the rest of this year, we expect all of the above libraries to significantly mature; for a middleware ecosystem to sprout up; for the selection of supported protocols and services to grow; and, quite possibly, to tie all this all together with an async&#x2F;await notation that works natively with Rust’s futures.</i><p>I&#x27;m still on dabbling in Rust, but I&#x27;m fairly convinced that in another few years after this Tokio churn has gotten a chance to settle down and the async patterns are more broadly refined, there won&#x27;t be many justifiable reasons to <i>not</i> write new projects in it, whether they&#x27;re as low level as a Postgres extension, or as high level as a DB-backed HTTP application. It seems to have an almost perfect compromise between performance, safety, productivity, and ecosystem.<p>[1] <a href="https:&#x2F;&#x2F;this-week-in-rust.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;this-week-in-rust.org&#x2F;</a><p>[2] <a href="https:&#x2F;&#x2F;blog.rust-lang.org&#x2F;2017&#x2F;05&#x2F;15&#x2F;rust-at-two-years.html#rust-should-have-a-pleasant-edit-compile-debug-cycle" rel="nofollow">https:&#x2F;&#x2F;blog.rust-lang.org&#x2F;2017&#x2F;05&#x2F;15&#x2F;rust-at-two-years.html...</a></text></item></parent_chain><comment><author>sillysaurus3</author><text><i>I&#x27;m still on dabbling in Rust, but I&#x27;m fairly convinced that in another few years after this Tokio churn has gotten a chance to settle down and the async patterns are more broadly refined, there won&#x27;t be many justifiable reasons to not write new projects in it, whether they&#x27;re as low level as a Postgres extension or as high level as a DB-backed HTTP application.</i><p>Not being hindered by the compiler telling you what you can and can&#x27;t do; freeing yourself from the write-compile-debug cycle, reducing it to repl-done; etc.</text></comment> |
36,265,363 | 36,264,991 | 1 | 2 | 36,264,232 | train | <story><title>Reddit CEO doubles down on attack on Apollo developer in drama-filled AMA</title><url>https://techcrunch.com/2023/06/09/reddit-ceo-doubles-down-on-attack-on-apollo-developer-in-drama-filled-ama/</url></story><parent_chain><item><author>hiccuphippo</author><text>I think a place like reddit should be a non-profit foundation rather than a business. The Archive Of Our Own community was able to do it, the reddit community can do it too.</text></item><item><author>mduggles</author><text>Reddit cannot go public. Its product is volunteer work by moderators and users to produce value. There’s no way to take that work and guarantee its delivery on a quarterly cycle.<p>This is all a ridiculous self-delusion that Reddit management has engaged in that the platform is really the “value add”. It’s not. Reddit has become the shorthand for cut through ML spam and that’s based on users constantly posting up to the minute accurate data. There’s almost no historical value to that data.</text></item></parent_chain><comment><author>jeffparsons</author><text>I&#x27;d feel a lot more comfortable giving my time to &quot;the community&quot; under an arrangement like that, too. The fediverse has its place, for sure, but I think a centralised platform run by a non-profit has the best chance of unseating Reddit in the short term.<p>It could even connect to the fediverse, but with its own moderation hierarchy etc. so it has its own culture and doesn&#x27;t _rely_ on the fediverse.</text></comment> | <story><title>Reddit CEO doubles down on attack on Apollo developer in drama-filled AMA</title><url>https://techcrunch.com/2023/06/09/reddit-ceo-doubles-down-on-attack-on-apollo-developer-in-drama-filled-ama/</url></story><parent_chain><item><author>hiccuphippo</author><text>I think a place like reddit should be a non-profit foundation rather than a business. The Archive Of Our Own community was able to do it, the reddit community can do it too.</text></item><item><author>mduggles</author><text>Reddit cannot go public. Its product is volunteer work by moderators and users to produce value. There’s no way to take that work and guarantee its delivery on a quarterly cycle.<p>This is all a ridiculous self-delusion that Reddit management has engaged in that the platform is really the “value add”. It’s not. Reddit has become the shorthand for cut through ML spam and that’s based on users constantly posting up to the minute accurate data. There’s almost no historical value to that data.</text></item></parent_chain><comment><author>bradleyjg</author><text>We had something like that. It was called USENET. With the right reader and a decent ISP, it was great.</text></comment> |
13,024,254 | 13,024,488 | 1 | 3 | 13,023,683 | train | <story><title>GuriVR – Describe your VR experience and the editor will do the rest</title><url>https://gurivr.com/</url></story><parent_chain></parent_chain><comment><author>danzajdband</author><text>Hi, GuriVR author here. Let me know if you have any questions :)</text></comment> | <story><title>GuriVR – Describe your VR experience and the editor will do the rest</title><url>https://gurivr.com/</url></story><parent_chain></parent_chain><comment><author>eridius</author><text>Clever idea. But scrolling the little VR scene on the right with my mouse is backwards. When I click and drag to the right, the camera pans to the right. But since I&#x27;m clicking on the content and dragging, it feels like the content should pan to the right, meaning the camera should pan to the left.</text></comment> |
15,529,131 | 15,529,138 | 1 | 2 | 15,528,824 | train | <story><title>Fact Checks</title><url>https://developers.google.com/search/docs/data-types/factcheck</url></story><parent_chain><item><author>patrickaljord</author><text>I wonder how far they are willing to go with this. How about these kinds of claims:<p>&quot;Increasing the minimum wage helps improve the economy&quot;<p>* Fact check by Conservative-example: false<p>* Fact check by Progressive-example: true<p>Another good one:<p>&quot;God exists&quot;:<p>* Fact check by Conservative-example: true<p>* Fact check by Progressive-example: false<p>This is going to be fun. This is typical of Google, providing a technical solution to a human problem that can&#x27;t be solved easily. Not everything can be tweaked with an algorithm.</text></item></parent_chain><comment><author>dvdhnt</author><text>&gt; “God exists
...
&gt; Fact check by Progressive-example: false<p>I know you’re making an observation so this isn’t directed at you, but to those who got us to this segregation - so no offense intended towards you friend.<p>It makes me so sad that this is the assumption. Yes, the traditional definition of God is not one many of us subscribe to, but to generally group progressives and atheists together, conservatives and religion together is just as much the problem as “fake news”.<p>Reference, myself, a progressive who found his spirituality in his late twenties while working at a startup and finding the church of consumerism unacceptable. Yet, look at that, still progressive.</text></comment> | <story><title>Fact Checks</title><url>https://developers.google.com/search/docs/data-types/factcheck</url></story><parent_chain><item><author>patrickaljord</author><text>I wonder how far they are willing to go with this. How about these kinds of claims:<p>&quot;Increasing the minimum wage helps improve the economy&quot;<p>* Fact check by Conservative-example: false<p>* Fact check by Progressive-example: true<p>Another good one:<p>&quot;God exists&quot;:<p>* Fact check by Conservative-example: true<p>* Fact check by Progressive-example: false<p>This is going to be fun. This is typical of Google, providing a technical solution to a human problem that can&#x27;t be solved easily. Not everything can be tweaked with an algorithm.</text></item></parent_chain><comment><author>smsm42</author><text>That is the best case scenario. The worst case scenario is when one of those is prohibited from publishing &quot;fact checks&quot; because they &quot;don&#x27;t meet our high standards&quot; (which Google is free to set as they see fit) and the other is free to declare &quot;false&quot; anything opposing tribe says because everybody knows they&#x27;re the bunch of damn liars anyway.<p>Also, &quot;fact checkers&quot; are free to misinterpret the content of the article, i.e.:<p>&quot;Increasing the minimum wage helps improve the economy&quot;<p>* Fact check by Conservative-example:<p><i></i> Claim: &quot;we should take all the money away from successful people and give it free to drug addicts and moochers&quot;<p><i></i> Verdict: false<p>* Fact check by Progressive-example:<p><i></i> Claim: &quot;we should let poor people to just die from hunger&quot;<p><i></i> Verdict: false<p>etc. Neither of that contributes to the discussion much, in fact, it makes it harder by caricaturising positions of opposing sides and making it harder to discuss arguments on the manner, while wearing the veil of &quot;objective fact checking&quot;. The expression &quot;fact checking&quot;, which once meant verifying objective facts, has already been hijacked by propagandists to make their propaganda more plausibly sounding. I predict more such abuse is going to happen and the term would be further eroded until it&#x27;s completely meaningless.</text></comment> |
23,638,239 | 23,636,514 | 1 | 2 | 23,633,850 | train | <story><title>Those who exercise free speech should also defend it even when it’s offensive</title><url>https://www.latimes.com/opinion/story/2020-06-19/protests-free-speech-first-amendment</url></story><parent_chain><item><author>bosswipe</author><text>There&#x27;s a disconnect that keeps running through a lot of the arguments from the conservative side which I don&#x27;t understand. The examples given in this piece are a) the right of street protesters to be heard without being attacked by government officers vs b) the right of people to not get fired for what they say by private organizations like the New York Times.<p>This disconnect keeps coming up, and it&#x27;s extra weird because conservatives have traditionally been the bigger proponents of corporate freedom to fire whoever they want. But now many conservatives seem to want some kind of new labor protection laws.<p>Maybe what is going on is not really about free speech but more about quickly changing cultural norms. It used to be OK to make blatant racist and sexist jokes in an office setting but at some point that changed and now you can easily get fired over it. That&#x27;s not a change in free speech restrictions, it&#x27;s a change in what is considered culturally acceptable behavior between private actors. But changing cultural norms aren&#x27;t something that should be somehow regulated by the government.</text></item></parent_chain><comment><author>belorn</author><text>The disconnect goes away if we see person opinions as something people are rather than something which people say.<p>This happens also to be a common thread in the disagreement between left and right. When something becomes a voluntary chosen action it can be controlled, limited and stopped by the government. When something is a personal trait it should be protected and given status as a right.<p>To take the example of a street protestor. Should companies be allowed to fire political activists? When we see it as a personal trait a lot of people find the answer as no. Should companies be allowed to fire people who choosed to say bad things? Many say yes. The issue becomes how people frame the question and what values get attached to it.</text></comment> | <story><title>Those who exercise free speech should also defend it even when it’s offensive</title><url>https://www.latimes.com/opinion/story/2020-06-19/protests-free-speech-first-amendment</url></story><parent_chain><item><author>bosswipe</author><text>There&#x27;s a disconnect that keeps running through a lot of the arguments from the conservative side which I don&#x27;t understand. The examples given in this piece are a) the right of street protesters to be heard without being attacked by government officers vs b) the right of people to not get fired for what they say by private organizations like the New York Times.<p>This disconnect keeps coming up, and it&#x27;s extra weird because conservatives have traditionally been the bigger proponents of corporate freedom to fire whoever they want. But now many conservatives seem to want some kind of new labor protection laws.<p>Maybe what is going on is not really about free speech but more about quickly changing cultural norms. It used to be OK to make blatant racist and sexist jokes in an office setting but at some point that changed and now you can easily get fired over it. That&#x27;s not a change in free speech restrictions, it&#x27;s a change in what is considered culturally acceptable behavior between private actors. But changing cultural norms aren&#x27;t something that should be somehow regulated by the government.</text></item></parent_chain><comment><author>nmfisher</author><text>True, but by the same token, there is a clear distinction between these two opinions:<p>1) I believe the government should outlaw firing people based on what they say in the office<p>2) I believe that companies should not fire people based on what they say in the office.<p>Believing in small government doesn&#x27;t mean you have no opinion on cultural norms. It just means you don&#x27;t think the government should enforce them.<p>But you&#x27;re also right that many modern &quot;conservatives&quot; don&#x27;t grasp the distinction.</text></comment> |
25,045,921 | 25,044,733 | 1 | 3 | 25,044,016 | train | <story><title>Valve Is Working on Another Extension to Help in Direct3D-over-Vulkan</title><url>https://www.phoronix.com/scan.php?page=news_item&px=VK_VALVE_mutable_descriptor</url></story><parent_chain><item><author>Jnr</author><text>If I remember correctly, Valve started doing this some time ago as an &quot;insurance policy&quot;, when Microsoft spoke about locking down Windows (before they introduced Windows Store).<p>It is amazing to see how far Linux gaming has come since then. 10 years ago almost none of the big games worked, 5 years ago lots of games worked after fiddling with wine config, and now most of the games I have tried work out of the box after enabling Proton.<p>Imagine what will come in the next 5 to 10 years.</text></item><item><author>mosselman</author><text>Valve is doing god’s work when it comes to Linux gaming. I have played over 40 hours of GTA V without many troubles. The game looks great and performs great. So glad I could get rid of my windows install.</text></item></parent_chain><comment><author>WhyNotHugo</author><text>Yeah, Steam continuously investing on Linux is what keeps MS in check.<p>Microsoft knows they can&#x27;t lock down the OS while gaming on Linux [at least] works.<p>It&#x27;s truly an insurance policy, and they have to pay it each month -- if they let Linux gaming lag behind long enough, they lose their ground on MS.</text></comment> | <story><title>Valve Is Working on Another Extension to Help in Direct3D-over-Vulkan</title><url>https://www.phoronix.com/scan.php?page=news_item&px=VK_VALVE_mutable_descriptor</url></story><parent_chain><item><author>Jnr</author><text>If I remember correctly, Valve started doing this some time ago as an &quot;insurance policy&quot;, when Microsoft spoke about locking down Windows (before they introduced Windows Store).<p>It is amazing to see how far Linux gaming has come since then. 10 years ago almost none of the big games worked, 5 years ago lots of games worked after fiddling with wine config, and now most of the games I have tried work out of the box after enabling Proton.<p>Imagine what will come in the next 5 to 10 years.</text></item><item><author>mosselman</author><text>Valve is doing god’s work when it comes to Linux gaming. I have played over 40 hours of GTA V without many troubles. The game looks great and performs great. So glad I could get rid of my windows install.</text></item></parent_chain><comment><author>jorvi</author><text>All that is needed now is working with the most-used anti-cheat companies. It sucks when a game works perfectly but you get booted (and possibly banned) for running Linux.</text></comment> |
17,182,544 | 17,182,575 | 1 | 2 | 17,181,130 | train | <story><title>People using Venmo to spy on cheating spouses</title><url>https://www.marketwatch.com/story/venmo-stalkers-or-amateur-sleuths-they-out-cheating-boyfriends-spy-on-exes-and-see-who-buys-drugs-2018-05-11</url></story><parent_chain><item><author>rconti</author><text>I&#x27;m utterly perplexed that Venmo is even a thing.<p>When I first started hearing about it maybe 5-6 years ago, I just figured, I already have PayPal and Square Cash, I&#x27;m too old, nobody I know uses Venmo, why bother.<p>I&#x27;ve mostly ignored that it existed except occasionally hearing (usually younger) folks talking about it.<p>A couple of months ago I was telling some people at work that I&#x27;m too old for it, and Square Cash works well enough for me, and commented that I can&#x27;t see how a newcomer could be any easier than just having the money go directly into my bank account.<p>When a coworker informed me that Venmo payments stay in your account, my exasperated reply was &quot;wait, it&#x27;s WORSE than Square Cash? It&#x27;s like going back to PayPal?&quot; Well, you can imagine how incredulous I was when I found out that Venmo <i>IS</i> PayPal, just with different branding.<p>For the past 5 years I&#x27;ve been assuming Venmo is something new and cool that &quot;the kids&quot; are using, but I&#x27;m too out of touch to bother, and suddenly I find out it&#x27;s a rebranding of PayPal with all of the drawbacks of it. It blows my mind that something caught traction that is functionally worse than the competitor of the product it&#x27;s a rebranding of!</text></item><item><author>gnicholas</author><text>When I first created a Venmo account, I was shocked to see users&#x27; payments flowing through my feed and immediately found a way to make my payments private.<p>But I could never find a way to effectively unlink the social media account (FB) that I had used to find my first friend&#x2F;payee. I think I unlinked the account, but I still see payments from all the people that Venmo made me follow as a result of linking the now-unlinked FB account.<p>I haven&#x27;t used the app in a long time, and I wonder if this mass-unfollow feature has been added. I know they think that people open Venmo to check their feed, but some people find the public feed creepy, and it makes me use the app less in favor of alternatives.</text></item></parent_chain><comment><author>ajkjk</author><text>I imagine my feelings about Venmo reflect a lot of peoples&#x27;:<p>Basically it was the first way to send money on mobile phones that wasn&#x27;t miserable or charged fees so everyone started using it. By the time PayPal owned it it was already popular.<p>Everyone wanted to easily send money for at least, like, 10 years before that. It was the first mainstream option and it still felt really late. (PayPal already existed but was... disliked. I think because of lots of horror stories about customer service, and maybe not having a convenient app interface, or requiring a bank account connection?)<p>The competitors are all equivalent now (FB, Google, whatever), but I would never embrace using a FB or Google product exclusively so Venmo feels like a &#x27;neutral third-party option&#x27; , at least to an extent, which we can use as the &#x27;default&#x27; payments app.<p>The Bank&#x27;s versions (Zelle, etc) are way too coupled to banks and too big-corporation to be excited about.<p>If there was, say, a startup that did exactly the same thing as Venmo but wasn&#x27;t affiliated with a big company (PayPal), I think everyone would happily use it. If it was, like, a B-corp or non-profit that gives proceeds to charity, I think everyone would jump ship instantly.<p>Basically I don&#x27;t care at all about Venmo&#x27;s social features, I just want to send money and prefer not to support a big corporation or give more data to FB or Google. I bet lots of people are of similar mind.</text></comment> | <story><title>People using Venmo to spy on cheating spouses</title><url>https://www.marketwatch.com/story/venmo-stalkers-or-amateur-sleuths-they-out-cheating-boyfriends-spy-on-exes-and-see-who-buys-drugs-2018-05-11</url></story><parent_chain><item><author>rconti</author><text>I&#x27;m utterly perplexed that Venmo is even a thing.<p>When I first started hearing about it maybe 5-6 years ago, I just figured, I already have PayPal and Square Cash, I&#x27;m too old, nobody I know uses Venmo, why bother.<p>I&#x27;ve mostly ignored that it existed except occasionally hearing (usually younger) folks talking about it.<p>A couple of months ago I was telling some people at work that I&#x27;m too old for it, and Square Cash works well enough for me, and commented that I can&#x27;t see how a newcomer could be any easier than just having the money go directly into my bank account.<p>When a coworker informed me that Venmo payments stay in your account, my exasperated reply was &quot;wait, it&#x27;s WORSE than Square Cash? It&#x27;s like going back to PayPal?&quot; Well, you can imagine how incredulous I was when I found out that Venmo <i>IS</i> PayPal, just with different branding.<p>For the past 5 years I&#x27;ve been assuming Venmo is something new and cool that &quot;the kids&quot; are using, but I&#x27;m too out of touch to bother, and suddenly I find out it&#x27;s a rebranding of PayPal with all of the drawbacks of it. It blows my mind that something caught traction that is functionally worse than the competitor of the product it&#x27;s a rebranding of!</text></item><item><author>gnicholas</author><text>When I first created a Venmo account, I was shocked to see users&#x27; payments flowing through my feed and immediately found a way to make my payments private.<p>But I could never find a way to effectively unlink the social media account (FB) that I had used to find my first friend&#x2F;payee. I think I unlinked the account, but I still see payments from all the people that Venmo made me follow as a result of linking the now-unlinked FB account.<p>I haven&#x27;t used the app in a long time, and I wonder if this mass-unfollow feature has been added. I know they think that people open Venmo to check their feed, but some people find the public feed creepy, and it makes me use the app less in favor of alternatives.</text></item></parent_chain><comment><author>tgb</author><text>I use it for the fact that it&#x27;s popular, of course. Worse than the fact that your balance stays in Venmo is that if you make a transaction larger than your balance, it gets paid exclusively from your bank account and doesn&#x27;t clear out your balance first.<p>Moreover, Venmo is garbage at the simplest thing of letting me find the person I&#x27;m paying. The only way to distinguish between all the many people of the same name (profile pictures being far too small to see in the selection list) is to have the person actually tell you their exact ID. The fact that I have previously done transactions with them or that they are a once-removed transaction friend from me isn&#x27;t displayed.</text></comment> |
8,807,574 | 8,807,520 | 1 | 2 | 8,806,835 | train | <story><title>Neat Algorithms: Paxos</title><url>http://harry.me/blog/2014/12/27/neat-algorithms-paxos/?hn=1</url></story><parent_chain><item><author>krat0sprakhar</author><text>This is up for debate but this[0], IMHO, is pretty much the gold standard of explaining distributed algorithms.<p>[0] - <a href="http://thesecretlivesofdata.com/raft/" rel="nofollow">http:&#x2F;&#x2F;thesecretlivesofdata.com&#x2F;raft&#x2F;</a></text></item></parent_chain><comment><author>nacs</author><text>Thanks the presentation, helps a lot.<p>Quick question though. On this slide ( <a href="http://i.imgur.com/m02CMxx.png" rel="nofollow">http:&#x2F;&#x2F;i.imgur.com&#x2F;m02CMxx.png</a> ) it shows a network split condition and shows how the 2 split networks will eventually negotiate and the 3 node split wins because it had a majority while the 2 node side&#x27;s uncommitted changes are thrown out.<p>What happens if the split happens right down the middle (3 active nodes on each side instead of the 2 and 3)? Wouldn&#x27;t both sides elect leaders that both have majorities with committed data?</text></comment> | <story><title>Neat Algorithms: Paxos</title><url>http://harry.me/blog/2014/12/27/neat-algorithms-paxos/?hn=1</url></story><parent_chain><item><author>krat0sprakhar</author><text>This is up for debate but this[0], IMHO, is pretty much the gold standard of explaining distributed algorithms.<p>[0] - <a href="http://thesecretlivesofdata.com/raft/" rel="nofollow">http:&#x2F;&#x2F;thesecretlivesofdata.com&#x2F;raft&#x2F;</a></text></item></parent_chain><comment><author>DAddYE</author><text>I agree, I would also add that Paxos seems exceptionally hard to get it right or at least this was what I saw so far in popular projects (i.e. Cassandra) that use it.</text></comment> |
41,406,614 | 41,402,730 | 1 | 2 | 41,400,723 | train | <story><title>Experience the Apollo 11 Lunar Landing</title><url>https://www.firstmenonthemoon.com</url></story><parent_chain><item><author>faizshah</author><text>Do yourself a favor and look up moon landing 4k on youtube. There’s some amazing immersive stuff now: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;boFZ3cAws20" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;boFZ3cAws20</a><p>There’s also a few amazing first person videos from space walks on the ISS: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;AmrrSfiMxGA" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;AmrrSfiMxGA</a><p>The footage from Artemis is gonna be incredible.<p>Also highly recommend this “are we going?” Talk on engineering issues in Artemis: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;OoJsPvmFixU" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;OoJsPvmFixU</a>
Which is where I learned about this report from NASA called “What Made Apollo a Success”: <a href="https:&#x2F;&#x2F;ntrs.nasa.gov&#x2F;api&#x2F;citations&#x2F;19720005243&#x2F;downloads&#x2F;19720005243.pdf" rel="nofollow">https:&#x2F;&#x2F;ntrs.nasa.gov&#x2F;api&#x2F;citations&#x2F;19720005243&#x2F;downloads&#x2F;19...</a></text></item></parent_chain><comment><author>tuetnsuppe</author><text><a href="http:&#x2F;&#x2F;apolloinrealtime.org" rel="nofollow">http:&#x2F;&#x2F;apolloinrealtime.org</a> also quite good.<p>&quot;Failure is not an Option&quot; is a fascinating read to get a lot of background from a first hand perspective. E.g. Go&#x2F;No-Go became Stay&#x2F;No-Stay after the landing to avoid confusion (<a href="https:&#x2F;&#x2F;www.goodreads.com&#x2F;book&#x2F;show&#x2F;141499.Failure_is_Not_an_Option" rel="nofollow">https:&#x2F;&#x2F;www.goodreads.com&#x2F;book&#x2F;show&#x2F;141499.Failure_is_Not_an...</a>)</text></comment> | <story><title>Experience the Apollo 11 Lunar Landing</title><url>https://www.firstmenonthemoon.com</url></story><parent_chain><item><author>faizshah</author><text>Do yourself a favor and look up moon landing 4k on youtube. There’s some amazing immersive stuff now: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;boFZ3cAws20" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;boFZ3cAws20</a><p>There’s also a few amazing first person videos from space walks on the ISS: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;AmrrSfiMxGA" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;AmrrSfiMxGA</a><p>The footage from Artemis is gonna be incredible.<p>Also highly recommend this “are we going?” Talk on engineering issues in Artemis: <a href="https:&#x2F;&#x2F;youtu.be&#x2F;OoJsPvmFixU" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;OoJsPvmFixU</a>
Which is where I learned about this report from NASA called “What Made Apollo a Success”: <a href="https:&#x2F;&#x2F;ntrs.nasa.gov&#x2F;api&#x2F;citations&#x2F;19720005243&#x2F;downloads&#x2F;19720005243.pdf" rel="nofollow">https:&#x2F;&#x2F;ntrs.nasa.gov&#x2F;api&#x2F;citations&#x2F;19720005243&#x2F;downloads&#x2F;19...</a></text></item></parent_chain><comment><author>albert_e</author><text>Thanks!<p>I liked reading this extensive accunt of all apollo missions and what each accomplished --<p>A Man on the Moon: The Voyages of the Apollo Astronauts
Andrew Chaikin
<a href="https:&#x2F;&#x2F;www.amazon.in&#x2F;Man-Moon-Voyages-Apollo-Astronauts&#x2F;dp&#x2F;014311235X" rel="nofollow">https:&#x2F;&#x2F;www.amazon.in&#x2F;Man-Moon-Voyages-Apollo-Astronauts&#x2F;dp&#x2F;...</a><p>I wish there was an &quot;annotated verison&quot; or enthusiast discussion forum that corss-linked footage like this to the corresponding passages in the book so we can live it more fully</text></comment> |
38,550,004 | 38,546,096 | 1 | 3 | 38,543,155 | train | <story><title>Governments spying on Apple, Google users through push notifications</title><url>https://www.reuters.com/technology/cybersecurity/governments-spying-apple-google-users-through-push-notifications-us-senator-2023-12-06/</url></story><parent_chain><item><author>robbiet480</author><text>We at the Home Assistant Companion for iOS team have been wanting to implement end to end encryption for our push notifications for a while now but Apple has denied our request for the com.apple.developer.usernotifications.filtering [0] entitlement multiple times. Wondering if with today&#x27;s news we could apply again and get it.<p>For context, we are sending ~35 million push notifications per month on iOS and ~67 million on Android, see more at [1]<p>[0]: <a href="https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;bundleresources&#x2F;entitlements&#x2F;com_apple_developer_usernotifications_filtering" rel="nofollow noreferrer">https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;bundleresources&#x2F;en...</a><p>[1]: <a href="https:&#x2F;&#x2F;threadreaderapp.com&#x2F;thread&#x2F;1721717002946191480.html" rel="nofollow noreferrer">https:&#x2F;&#x2F;threadreaderapp.com&#x2F;thread&#x2F;1721717002946191480.html</a></text></item></parent_chain><comment><author>st3fan</author><text>We implemented APNS encryption for Firefox iOS without much trouble. Keys are negotiated out of band and message decryption is done in a Notification extension that allows you to pre process incoming notifications. Did not need any special entitlements.<p>Source code on GitHub.com&#x2F;mozilla-mobile</text></comment> | <story><title>Governments spying on Apple, Google users through push notifications</title><url>https://www.reuters.com/technology/cybersecurity/governments-spying-apple-google-users-through-push-notifications-us-senator-2023-12-06/</url></story><parent_chain><item><author>robbiet480</author><text>We at the Home Assistant Companion for iOS team have been wanting to implement end to end encryption for our push notifications for a while now but Apple has denied our request for the com.apple.developer.usernotifications.filtering [0] entitlement multiple times. Wondering if with today&#x27;s news we could apply again and get it.<p>For context, we are sending ~35 million push notifications per month on iOS and ~67 million on Android, see more at [1]<p>[0]: <a href="https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;bundleresources&#x2F;entitlements&#x2F;com_apple_developer_usernotifications_filtering" rel="nofollow noreferrer">https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;bundleresources&#x2F;en...</a><p>[1]: <a href="https:&#x2F;&#x2F;threadreaderapp.com&#x2F;thread&#x2F;1721717002946191480.html" rel="nofollow noreferrer">https:&#x2F;&#x2F;threadreaderapp.com&#x2F;thread&#x2F;1721717002946191480.html</a></text></item></parent_chain><comment><author>michh</author><text>for my understanding, you need that entitlement so you can send an encrypted invisible notification which you can then decrypt locally in your app and push out again as a local notification that doesn&#x27;t go over the network (i.e. not use apns)? Or is doing this kind of stuff just weirdly tied to that specific entitlement?</text></comment> |
24,039,360 | 24,038,571 | 1 | 3 | 24,035,203 | train | <story><title>The Truth Is Paywalled but the Lies Are Free</title><url>https://www.currentaffairs.org/2020/08/the-truth-is-paywalled-but-the-lies-are-free/</url></story><parent_chain><item><author>giancarlostoro</author><text>Another fun one I ask when someone brings up Snopes: Who snopes the snopes? In other words how do we know they are not being biased or thorough enough?<p>I am not saying everything there is wrong but I have ran into weird biased articles before.</text></item><item><author>marcus_holmes</author><text>As always, who judges whether something is true?</text></item><item><author>Dotnaught</author><text>The linked article concludes:<p>&quot;Creators must be compensated well. But at the same time we have to try to keep things that are important and profound from getting locked away where few people will see them. The truth needs to be free and universal.&quot;<p>Let&#x27;s also consider whether lies should be made more expensive. Free costs more than it&#x27;s worth.</text></item></parent_chain><comment><author>beerandt</author><text>The bigger issues with Snopes are:<p>1) Complete lack of transparency. No versioning or history of how answers have changed. They even opt-out of archive.org history tracking. They usually only disclose one author, when oftentimes there are many.<p>2) They editorialize many <i>questions</i>, changing them in such a way that they can give the answer they want to. This is done often by inserting modifiers like &quot;always&quot; or &quot;never&quot; or something similar.</text></comment> | <story><title>The Truth Is Paywalled but the Lies Are Free</title><url>https://www.currentaffairs.org/2020/08/the-truth-is-paywalled-but-the-lies-are-free/</url></story><parent_chain><item><author>giancarlostoro</author><text>Another fun one I ask when someone brings up Snopes: Who snopes the snopes? In other words how do we know they are not being biased or thorough enough?<p>I am not saying everything there is wrong but I have ran into weird biased articles before.</text></item><item><author>marcus_holmes</author><text>As always, who judges whether something is true?</text></item><item><author>Dotnaught</author><text>The linked article concludes:<p>&quot;Creators must be compensated well. But at the same time we have to try to keep things that are important and profound from getting locked away where few people will see them. The truth needs to be free and universal.&quot;<p>Let&#x27;s also consider whether lies should be made more expensive. Free costs more than it&#x27;s worth.</text></item></parent_chain><comment><author>stjohnswarts</author><text>You can, follow their sources. Even if they&#x27;re only 90-95 correct that is orders of magnitude better than what&#x27;s on facebook and twitter where people go just because someone put up a picture with words on it.</text></comment> |
9,852,714 | 9,852,742 | 1 | 2 | 9,851,512 | train | <story><title>Microsoft Now OpenBSD Foundation Gold Contributor</title><url>http://undeadly.org/cgi?action=article&sid=20150708134520</url></story><parent_chain><item><author>hackuser</author><text><p><pre><code> Gold: $25,000 to $50,000
Microsoft Corporation
Silver: $10,000 to $25,000
Facebook Inc.
Google Inc.
</code></pre>
Arguably these are small amounts for all three companies, but what is the best way to calculate a fair share - not just for large companies but for anyone? For example,<p>* How much does OpenBSD need?<p>* How much does each company benefit from OpenBSD&#x27;s work?<p>* How much would it cost to license the software if it were proprietary? How much would it cost to build and maintain it in-house?</text></item><item><author>Systemic33</author><text>Worth noting that Facebook and Google are both silver contributors.<p>=== <a href="http:&#x2F;&#x2F;www.openbsdfoundation.org&#x2F;contributors.html" rel="nofollow">http:&#x2F;&#x2F;www.openbsdfoundation.org&#x2F;contributors.html</a> ===<p>For 2015 The OpenBSD Foundation will recognize donors in the following categories based on contribution amount.<p>On request we will provide a link to your website for donations of $5000 or more, and display your logo for donations of $10,000 or more.<p><pre><code> Iridium: $100,000 to $250,000
Platinum: $50,000 to $100,000
Gold: $25,000 to $50,000
Microsoft Corporation
Silver: $10,000 to $25,000
Facebook Inc.
Google Inc.
Bronze: $5,000 to $10,000
2Keys Security Solutions
Mandrill
genua mbh </code></pre>
=============================================</text></item></parent_chain><comment><author>seiji</author><text>Those are hilariously small numbers. The accounting departments of those companies probably wouldn&#x27;t even blink if one extra zero were added to the end.<p>If you&#x27;re funding open source products like this, companies should fund at least 3-5 full time senior engineer salaries per year. We should praise &quot;donating&quot; $3 million to $10 million per year. Anything less is a joke seeing these amounts are from multi-billion dollar companies <i>built on</i> free software.<p>Imagine you lived next to a free buffet that only accepted donations. You ate there every day of the year, saved thousands of dollars over buying and making your own food, then thought you were being &quot;generous&quot; by dropping them a tenner at Christmas. Also, you&#x27;re a full time tech employee who cashed out millions in stock and have several million dollar apartments in cities around the world. But, sure, you&#x27;re generous by dropping them $10.</text></comment> | <story><title>Microsoft Now OpenBSD Foundation Gold Contributor</title><url>http://undeadly.org/cgi?action=article&sid=20150708134520</url></story><parent_chain><item><author>hackuser</author><text><p><pre><code> Gold: $25,000 to $50,000
Microsoft Corporation
Silver: $10,000 to $25,000
Facebook Inc.
Google Inc.
</code></pre>
Arguably these are small amounts for all three companies, but what is the best way to calculate a fair share - not just for large companies but for anyone? For example,<p>* How much does OpenBSD need?<p>* How much does each company benefit from OpenBSD&#x27;s work?<p>* How much would it cost to license the software if it were proprietary? How much would it cost to build and maintain it in-house?</text></item><item><author>Systemic33</author><text>Worth noting that Facebook and Google are both silver contributors.<p>=== <a href="http:&#x2F;&#x2F;www.openbsdfoundation.org&#x2F;contributors.html" rel="nofollow">http:&#x2F;&#x2F;www.openbsdfoundation.org&#x2F;contributors.html</a> ===<p>For 2015 The OpenBSD Foundation will recognize donors in the following categories based on contribution amount.<p>On request we will provide a link to your website for donations of $5000 or more, and display your logo for donations of $10,000 or more.<p><pre><code> Iridium: $100,000 to $250,000
Platinum: $50,000 to $100,000
Gold: $25,000 to $50,000
Microsoft Corporation
Silver: $10,000 to $25,000
Facebook Inc.
Google Inc.
Bronze: $5,000 to $10,000
2Keys Security Solutions
Mandrill
genua mbh </code></pre>
=============================================</text></item></parent_chain><comment><author>alecco</author><text>Tiny amounts. The OpenBSD folks contribute a lot of code those corporations use, like OpenSSH and plenty of security bugs fixed for many projects not their own.<p>OpenBSD still is at a financial crisis and not enough people care. Not even the ones reaping benefits out of it.</text></comment> |
7,657,090 | 7,657,188 | 1 | 3 | 7,656,282 | train | <story><title>Software of the Apollo guidance computer was hand-woven into rope core memory</title><url>https://www.youtube.com/watch?v=P12r8DKHsak&t=20s</url></story><parent_chain></parent_chain><comment><author>ErsatzVerkehr</author><text>I thought this was interesting (both that the space shuttle still used core memory, and that the challenger memory was retrieved and its contents recovered):<p>&gt; Core memory is non-volatile storage—it can retain its contents indefinitely without power. It is also relatively unaffected by EMP and radiation. ... For example, the Space Shuttle flight computers initially used core memory, which preserved the contents of memory even through the Challenger&#x27;s disintegration and subsequent plunge into the sea in 1986.<p>(From <a href="http://en.wikipedia.org/wiki/Magnetic-core_memory#Physical_characteristics" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Magnetic-core_memory#Physical_c...</a> )<p>Note that this core memory is a little different than the rope core memory described in the linked article.</text></comment> | <story><title>Software of the Apollo guidance computer was hand-woven into rope core memory</title><url>https://www.youtube.com/watch?v=P12r8DKHsak&t=20s</url></story><parent_chain></parent_chain><comment><author>mx12</author><text>Here&#x27;s a link to the full video:<p><a href="http://www.dailymotion.com/video/xxxiij_moon-machines-2008-part-3-the-navigation-computer_tech" rel="nofollow">http:&#x2F;&#x2F;www.dailymotion.com&#x2F;video&#x2F;xxxiij_moon-machines-2008-p...</a><p>Around 37 minutes they talk about the alarms on approach and how the dealt with them.</text></comment> |
5,435,785 | 5,435,768 | 1 | 3 | 5,435,611 | train | <story><title>Nasty Gal, an Online Start-Up, Is a Fast-Growing Retailer</title><url>http://www.nytimes.com/2013/03/25/technology/nasty-gal-an-online-start-up-is-a-fast-growing-retailer.html?pagewanted=all&_r=1&</url></story><parent_chain></parent_chain><comment><author>jval</author><text>I don't know anything about fashion but I spoke to some friends who are lifelong fashion addicts. Apparently in the fashion blogosphere they're more well known for copying small designers than they are for the quality of their clothing:<p><a href="http://la.racked.com/archives/2013/01/09/nasty_gal_engages_in_some_supernasty_instagram_bickering.php" rel="nofollow">http://la.racked.com/archives/2013/01/09/nasty_gal_engages_i...</a></text></comment> | <story><title>Nasty Gal, an Online Start-Up, Is a Fast-Growing Retailer</title><url>http://www.nytimes.com/2013/03/25/technology/nasty-gal-an-online-start-up-is-a-fast-growing-retailer.html?pagewanted=all&_r=1&</url></story><parent_chain></parent_chain><comment><author>DanielRibeiro</author><text>Sophia gave a very good, albeit a bit long, interview recently: <a href="http://www.youtube.com/watch?v=y04gnM57Sow" rel="nofollow">http://www.youtube.com/watch?v=y04gnM57Sow</a><p>This has a lot more insights into how she built Nasty Gal, and how she raised her series A.</text></comment> |
17,228,087 | 17,228,065 | 1 | 2 | 17,227,307 | train | <story><title>Chris, Nat and Satya's Calldeck Regarding Microsoft and GitHub</title><url>https://view.officeapps.live.com/op/view.aspx?src=https://c.s-microsoft.com/en-us/CMSFiles/calldeck.pptx?version=f3eef72b-35d3-95b2-4fda-73a47f805c7f</url></story><parent_chain><item><author>ekianjo</author><text>&gt; Slide 10: Microsoft &lt;hearts&gt; Open Source.<p>you do realize that&#x27;s just PR talk right? Most of their money-making products and services are far from being open source, so let&#x27;s tone down the grandiloquent claims a little.</text></item><item><author>ckastner</author><text>Slide 10: Microsoft &lt;hearts&gt; Open Source.<p>It&#x27;s really amazing how much Microsoft has changed (to the positive) since Ballmer stepped down as CEO.</text></item></parent_chain><comment><author>sandGorgon</author><text>Microsoft is the largest contributor to open source on Github already...much higher than even Google.<p><a href="https:&#x2F;&#x2F;medium.freecodecamp.org&#x2F;the-top-contributors-to-github-2017-be98ab854e87" rel="nofollow">https:&#x2F;&#x2F;medium.freecodecamp.org&#x2F;the-top-contributors-to-gith...</a></text></comment> | <story><title>Chris, Nat and Satya's Calldeck Regarding Microsoft and GitHub</title><url>https://view.officeapps.live.com/op/view.aspx?src=https://c.s-microsoft.com/en-us/CMSFiles/calldeck.pptx?version=f3eef72b-35d3-95b2-4fda-73a47f805c7f</url></story><parent_chain><item><author>ekianjo</author><text>&gt; Slide 10: Microsoft &lt;hearts&gt; Open Source.<p>you do realize that&#x27;s just PR talk right? Most of their money-making products and services are far from being open source, so let&#x27;s tone down the grandiloquent claims a little.</text></item><item><author>ckastner</author><text>Slide 10: Microsoft &lt;hearts&gt; Open Source.<p>It&#x27;s really amazing how much Microsoft has changed (to the positive) since Ballmer stepped down as CEO.</text></item></parent_chain><comment><author>ckastner</author><text>The point I was trying to make was that there was a time, not too long ago, when Microsoft was <i>actively hostile</i> towards open source (and <i>all</i> of their money-making products where closed source).<p>As to your point, it is possible for an entity to favor and support open source, even without the entity itself following this policy. These issues aren&#x27;t one-dimensional.</text></comment> |
5,101,494 | 5,101,461 | 1 | 2 | 5,101,318 | train | <story><title>Megafail</title><url>http://fail0verflow.com/blog/2013/megafail.html</url></story><parent_chain><item><author>PhrosTT</author><text>When I started the article I thought, "Oh great another speculative Mega bashing."<p>Then you actually wrote the proof of concept and proved it to be a very real problem.<p>Nice work. Also the mouseover on your site title is sexy.</text></item></parent_chain><comment><author>dlitz</author><text>I'm not surprised. These are the same guys who thoroughly ripped apart the PS3 security system and presented it for a more-or-less general developer audience: <a href="http://www.youtube.com/watch?v=LuIlbmn-4A4" rel="nofollow">http://www.youtube.com/watch?v=LuIlbmn-4A4</a></text></comment> | <story><title>Megafail</title><url>http://fail0verflow.com/blog/2013/megafail.html</url></story><parent_chain><item><author>PhrosTT</author><text>When I started the article I thought, "Oh great another speculative Mega bashing."<p>Then you actually wrote the proof of concept and proved it to be a very real problem.<p>Nice work. Also the mouseover on your site title is sexy.</text></item></parent_chain><comment><author>tedunangst</author><text>"You do not understand cryptography" should never be dismissed as speculative bashing.</text></comment> |
20,185,431 | 20,185,488 | 1 | 3 | 20,184,373 | train | <story><title>OCaml 4.08</title><url>https://inbox.ocaml.org/caml-list/[email protected]/</url></story><parent_chain><item><author>threwawasy1228</author><text>It doesn&#x27;t get said very much but the ML ecosystem is full, complete, and very much production quality. It is a shame that there are not many projects or companies that make use of all that it has to offer.</text></item></parent_chain><comment><author>neilv</author><text>Agreed, OCaml has looked good for a long time.<p>And I have a similar feeling of sadness that Racket (or one of the other Scheme variants) isn&#x27;t used more.<p>I&#x27;ve wondered whether one of the barriers is still that students&#x27; only exposure to these is usually using it in school for some contrived homework assignments, and dismissing the tools for &quot;real work&quot; before they&#x27;ve tried applying them. (And at least some schools are emphasizing having students ready for internship&#x2F;interview with popular languages now, so innovative languages can get even less attention.)</text></comment> | <story><title>OCaml 4.08</title><url>https://inbox.ocaml.org/caml-list/[email protected]/</url></story><parent_chain><item><author>threwawasy1228</author><text>It doesn&#x27;t get said very much but the ML ecosystem is full, complete, and very much production quality. It is a shame that there are not many projects or companies that make use of all that it has to offer.</text></item></parent_chain><comment><author>scriptkiddy</author><text>I really want to use Ocaml for web application back-ends, but last time I checked the ecosystem around that in Ocaml is less than extensive compared to languages like Python, JS, java, etc. It really is a shame. I need to set aside some time to really dive deep into Ocaml and make a simple micro framework or something.<p>From my small amount of exposure, I can say that I love Ocaml&#x27;s expressiveness and flexibility.</text></comment> |
23,770,103 | 23,770,336 | 1 | 3 | 23,769,558 | train | <story><title>MIT and Harvard file suit against new ICE regulations</title><url>http://news.mit.edu/2020/mit-and-harvard-file-suit-against-new-ice-regulations-0708</url></story><parent_chain><item><author>ben7799</author><text>It&#x27;s incredibly unfair for the the administration to target international students like this.<p>However Harvard and MIT aren&#x27;t all about caring about their international students here. They are also thinking heavily about the money they might be losing. International students usually pay a much higher effective tuition rate. The higher the % of international students the school takes in the more money they take in. If these schools had to replace international students with domestic ones (even if they could) they wouldn&#x27;t be able to get away with selecting only the highest paying students.<p>I&#x27;m from Boston, we have an incredibly high number of international students, and a lot of the interest in keeping them is about getting their money.<p>The Boston Globe estimates they are worth $3.6 billion dollars to the area... lots of money, lots of tuition, lots of apartment rentals, lots of bar &amp; restaurant revenue.</text></item></parent_chain><comment><author>PragmaticPulp</author><text>&gt; However Harvard and MIT aren&#x27;t all about caring about their international students here. They are also thinking heavily about the money they might be losing.<p>It’s okay to have multiple motivations.<p>The fact that they have a monetary incentive doesn’t detract from the good of what they’re doing. In fact, that’s partially what enables these expensive lawsuits.<p>We shouldn’t try to downplay good actions just because money is also involved.</text></comment> | <story><title>MIT and Harvard file suit against new ICE regulations</title><url>http://news.mit.edu/2020/mit-and-harvard-file-suit-against-new-ice-regulations-0708</url></story><parent_chain><item><author>ben7799</author><text>It&#x27;s incredibly unfair for the the administration to target international students like this.<p>However Harvard and MIT aren&#x27;t all about caring about their international students here. They are also thinking heavily about the money they might be losing. International students usually pay a much higher effective tuition rate. The higher the % of international students the school takes in the more money they take in. If these schools had to replace international students with domestic ones (even if they could) they wouldn&#x27;t be able to get away with selecting only the highest paying students.<p>I&#x27;m from Boston, we have an incredibly high number of international students, and a lot of the interest in keeping them is about getting their money.<p>The Boston Globe estimates they are worth $3.6 billion dollars to the area... lots of money, lots of tuition, lots of apartment rentals, lots of bar &amp; restaurant revenue.</text></item></parent_chain><comment><author>tsotnet</author><text>&gt; However Harvard and MIT aren&#x27;t all about caring about their international students here. They are also thinking heavily about the money they might be losing. International students usually pay a much higher effective tuition rate<p>As an international MIT alumni, I can confidently say that this is completely wrong. MIT and Harvard have need-based scholarships, meaning that students pay tuition depending on their financial circumstances. Most of the international students come from poorer countries &amp; families compared to an average domestic student and therefore end up paying a lot less in tuition.<p>Also, MIT&#x27;s international undergraduate students are usually around 10% of the whole class. Even if you were right, they don&#x27;t represent a big enough chunk of the whole class to have a significant impact on the money they&#x27;re making.</text></comment> |
19,784,666 | 19,784,711 | 1 | 3 | 19,756,230 | train | <story><title>The Treaty That Forced the Cherokee People from Their Homelands Goes on View</title><url>https://www.smithsonianmag.com/blogs/national-museum-american-indian/2019/04/24/treaty-new-echota/</url></story><parent_chain><item><author>RickJWagner</author><text>I wonder what things would be like if the European settlers hadn&#x27;t displaced the indigenous Americans. (If the American Indian way of life evolved and was still predominant today.)<p>It&#x27;s an interesting mental exercise.</text></item></parent_chain><comment><author>williamstein</author><text>There are still millions of native Americans today, some full blood. Go visit the rez. Their culture is beautiful.</text></comment> | <story><title>The Treaty That Forced the Cherokee People from Their Homelands Goes on View</title><url>https://www.smithsonianmag.com/blogs/national-museum-american-indian/2019/04/24/treaty-new-echota/</url></story><parent_chain><item><author>RickJWagner</author><text>I wonder what things would be like if the European settlers hadn&#x27;t displaced the indigenous Americans. (If the American Indian way of life evolved and was still predominant today.)<p>It&#x27;s an interesting mental exercise.</text></item></parent_chain><comment><author>protomyth</author><text>That would require the Columbian Exchange of diseases to have been a non-event. That massive population loss opened up the continent.<p>Also, American Indian tribes are not a monolith so the contrast would be interesting. Given the migration of some tribes, I would expect a lot more tribal wars.</text></comment> |
27,072,546 | 27,071,401 | 1 | 2 | 27,068,466 | train | <story><title>Tip Jar</title><url>https://blog.twitter.com/en_us/topics/product/2021/introducing-tip-jar.html</url></story><parent_chain><item><author>anonytrary</author><text>I remember in 2017 in &#x2F;r&#x2F;dogecoin, we would tip each other thousands of doge (back then, it was 1&#x2F;10th of a penny) for &quot;such many random and much wow comment in forum&quot;. This was achieved with a DOGE tipping bot.<p>This idea <i>will</i> most likely work if Twitter starts supporting it as a first class feature. And maybe it will encourage people to speak about things that are valuable. Or maybe it will continue to encourage the Twitter mob to just tear the other side apart. I don&#x27;t know.</text></item></parent_chain><comment><author>pcthrowaway</author><text>Not sure if you remember what happened with that. The creator of dogetipbot held the money that wasn&#x27;t withdrawn, then eventually froze withdrawals and absconded with a possible fortune (they claimed they were burning it to pay for ridiculous server costs, but I can&#x27;t imagine running it would cost more than $20&#x2F;week unless it was horrendously misconfigured)</text></comment> | <story><title>Tip Jar</title><url>https://blog.twitter.com/en_us/topics/product/2021/introducing-tip-jar.html</url></story><parent_chain><item><author>anonytrary</author><text>I remember in 2017 in &#x2F;r&#x2F;dogecoin, we would tip each other thousands of doge (back then, it was 1&#x2F;10th of a penny) for &quot;such many random and much wow comment in forum&quot;. This was achieved with a DOGE tipping bot.<p>This idea <i>will</i> most likely work if Twitter starts supporting it as a first class feature. And maybe it will encourage people to speak about things that are valuable. Or maybe it will continue to encourage the Twitter mob to just tear the other side apart. I don&#x27;t know.</text></item></parent_chain><comment><author>rawtxapp</author><text>On the other hand &#x2F;r&#x2F;cryptocurrency introduced &quot;moons&quot; as tipping mechanism and the quality of the discussions went downhill <i>really</i> quick. Nowadays, there&#x27;s lots of sob stories or random posts about how a person just bought in to some random coin, personal anecdotes, etc.<p>I think whatever tipping is implemented needs to be pretty much worthless (aka mostly symbolic), otherwise, people will just spend a lot of their time just trying to game it. In many parts of the world, even making a couple dollars a day is more than they would make in their local economy.</text></comment> |
13,118,055 | 13,117,373 | 1 | 3 | 13,114,803 | train | <story><title>Google says it will run entirely on renewable energy in 2017</title><url>http://www.nytimes.com/2016/12/06/technology/google-says-it-will-run-entirely-on-renewable-energy-in-2017.html?_r=0</url></story><parent_chain><item><author>tylercubell</author><text>&gt; “In my mind it’s a P.R. gimmick,” said Chris Warren, vice president of communications at the Institute for Energy Research, a think tank in Washington supported largely by donations from individuals and companies in the fossil fuel industry. “If they think they can actually support themselves with wind and solar panels, they should connect them directly to their data centers.”<p>I love how the author throws in a disclaimed quotation from a big oil Luddite to help reinforce the message of the article. It&#x27;s a two-fold sales tactic.<p>1. Discredit the opposition.<p>2. Tell the buyer what the opposition will say, after already convincing them of the benefits, so they&#x27;re prepared to defend what they&#x27;re buying thereby reinforcing their beliefs.<p>I&#x27;m not implying that the article is wrong, but it&#x27;s something we should be aware of.</text></item></parent_chain><comment><author>rocketraman</author><text>Unfortunately, there is indeed a lot of truth to the statement that it is a PR gimmick.<p>The problem with wind and solar is that they are intermittent. Therefore, Google&#x27;s consumption <i>at any particular moment in time</i> cannot be supplied solely by these intermittent sources because their energy output never matches current demand (at least until some big honking batteries are built to level this out, for which the tech currently does not exist AFAIK -- no, Tesla&#x27;s battery tech isn&#x27;t even close to operating at this scale, though its a small step in that direction).<p>Therefore, Google <i>must</i> take power from the grid from non-intermittent sources that <i>can</i> ramp up and down based on demand, such as coal, gas, and nuclear. And this fact will remain true, even if Google had purchased wind and solar contracts for total energy many times greater than their total energy use.<p>So even though they may be purchasing contracts for wind&#x2F;solar energy that exceed their own total energy use, they still cannot even <i>approach</i> viable operation without access to non-wind and solar sources, so its definitely misleading by Google to suggest they are running entirely on wind&#x2F;solar.<p>Furthermore, the excess energy produced that Google purchased, but did not use because of the intermittency issue, actually reduces the efficiency of fossil and nuclear sources. Because the wind&#x2F;solar energy is loaded onto the grid intermittently, it forces fossil and nuclear to cycle up and down to compensate. Just like city vs. highway driving, this is vastly less efficient.</text></comment> | <story><title>Google says it will run entirely on renewable energy in 2017</title><url>http://www.nytimes.com/2016/12/06/technology/google-says-it-will-run-entirely-on-renewable-energy-in-2017.html?_r=0</url></story><parent_chain><item><author>tylercubell</author><text>&gt; “In my mind it’s a P.R. gimmick,” said Chris Warren, vice president of communications at the Institute for Energy Research, a think tank in Washington supported largely by donations from individuals and companies in the fossil fuel industry. “If they think they can actually support themselves with wind and solar panels, they should connect them directly to their data centers.”<p>I love how the author throws in a disclaimed quotation from a big oil Luddite to help reinforce the message of the article. It&#x27;s a two-fold sales tactic.<p>1. Discredit the opposition.<p>2. Tell the buyer what the opposition will say, after already convincing them of the benefits, so they&#x27;re prepared to defend what they&#x27;re buying thereby reinforcing their beliefs.<p>I&#x27;m not implying that the article is wrong, but it&#x27;s something we should be aware of.</text></item></parent_chain><comment><author>aperetto</author><text>It&#x27;s such a ridiculous statement, too. With his logic this guy would have to buy the cow that makes the milk he drinks in his coffee...</text></comment> |
40,248,002 | 40,245,336 | 1 | 3 | 40,243,014 | train | <story><title>Dressmaking CAD</title><url>https://xn--6xw240d.net/</url></story><parent_chain></parent_chain><comment><author>zenkalia</author><text>All these OSS projects are cool but it&#x27;s worth noting that the industry standard for this is Gerber:<p><a href="https:&#x2F;&#x2F;www.lectra.com&#x2F;en&#x2F;products&#x2F;gerber-accumark-accunest-fashion" rel="nofollow">https:&#x2F;&#x2F;www.lectra.com&#x2F;en&#x2F;products&#x2F;gerber-accumark-accunest-...</a><p>My mother was a &quot;grader&quot; and her workflow was actually very similar to software engineering. A designer would give her sketches of a garment. She would figure out how to build it - break it down to individual pieces of cloth and construction steps that then get fanned out to cutters and seamstresses to build.<p>When I got into software I found the parallels fascinating.</text></comment> | <story><title>Dressmaking CAD</title><url>https://xn--6xw240d.net/</url></story><parent_chain></parent_chain><comment><author>kelsolaar</author><text>Marvelous Designer has been used in the VFX and Game industries for quite a few years now: <a href="https:&#x2F;&#x2F;www.marvelousdesigner.com" rel="nofollow">https:&#x2F;&#x2F;www.marvelousdesigner.com</a><p>Wētā FX used it on The Hobbit for example: <a href="https:&#x2F;&#x2F;www.facebook.com&#x2F;marvelousdesigner&#x2F;photos&#x2F;james-moore-senior-modeller-at-weta-digital-describes-how-marvelous-designer-2-w&#x2F;464799476927913&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.facebook.com&#x2F;marvelousdesigner&#x2F;photos&#x2F;james-moor...</a></text></comment> |
33,699,647 | 33,699,696 | 1 | 2 | 33,698,094 | train | <story><title>Is wine fake?</title><url>https://asteriskmag.com/issues/1/is-wine-fake</url></story><parent_chain><item><author>hn_throwaway_99</author><text>Two scientific points to bring up about this article:<p>1. When the author talks about Coke vs. Pepsi, he comes to the conclusion that the reason people prefer Pepsi in blind taste tests but Coke in unblinded ones is &quot;Think of it as the brain combining two sources of input to make a final taste perception: the actual taste of the two sodas and a preconceived notion (probably based on great marketing) that Coke should taste better.&quot; I&#x27;ve read elsewhere, though, that the reason for this difference is actually because of the difference between &quot;sip tests&quot; vs. &quot;drinking tests&quot;. Pepsi is objectively sweeter than Coke, so if you&#x27;re just taking a few quick sips (as most taste tests are set up), you may prefer the sweeter taste of Pepsi because it stands out more, but if you&#x27;re drinking a whole bunch, the sweeter taste of Pepsi can feel cloying.<p>2. The article includes this quote, &quot;the correlation between price and overall rating is small and negative, suggesting that individuals on average enjoy more expensive wines slightly less.&quot; I wonder if this could be due to Berkon&#x27;s paradox, a statistical paradox that was on the HN front page yesterday, <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=33677781" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=33677781</a>. After all, I&#x27;m guessing most truly bad wines may not be rated at all.</text></item></parent_chain><comment><author>chrisseaton</author><text>A joke in the UK is that the unofficial slogan of Pepsi is &#x27;yeah fine whatever mate&#x27; because when you order Coca-Cola in a pub and they (for some reason) stock Pepsi instead they always have to ask &#x27;is Pepsi ok?&#x27;.</text></comment> | <story><title>Is wine fake?</title><url>https://asteriskmag.com/issues/1/is-wine-fake</url></story><parent_chain><item><author>hn_throwaway_99</author><text>Two scientific points to bring up about this article:<p>1. When the author talks about Coke vs. Pepsi, he comes to the conclusion that the reason people prefer Pepsi in blind taste tests but Coke in unblinded ones is &quot;Think of it as the brain combining two sources of input to make a final taste perception: the actual taste of the two sodas and a preconceived notion (probably based on great marketing) that Coke should taste better.&quot; I&#x27;ve read elsewhere, though, that the reason for this difference is actually because of the difference between &quot;sip tests&quot; vs. &quot;drinking tests&quot;. Pepsi is objectively sweeter than Coke, so if you&#x27;re just taking a few quick sips (as most taste tests are set up), you may prefer the sweeter taste of Pepsi because it stands out more, but if you&#x27;re drinking a whole bunch, the sweeter taste of Pepsi can feel cloying.<p>2. The article includes this quote, &quot;the correlation between price and overall rating is small and negative, suggesting that individuals on average enjoy more expensive wines slightly less.&quot; I wonder if this could be due to Berkon&#x27;s paradox, a statistical paradox that was on the HN front page yesterday, <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=33677781" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=33677781</a>. After all, I&#x27;m guessing most truly bad wines may not be rated at all.</text></item></parent_chain><comment><author>googlryas</author><text>My cousin who was one of the people giving the challenge also said they were always supposed to give Pepsi second, because after the bitterness of the coke first, the relative sweetness of Pepsi would be slightly refreshing, even if the drinker liked the bitter taste</text></comment> |
30,108,974 | 30,108,940 | 1 | 3 | 30,107,687 | train | <story><title>Masterclass on mathematical thinking</title><url>https://terrytao.wordpress.com/2022/01/27/masterclass-on-mathematical-thinking/</url></story><parent_chain><item><author>Graffur</author><text>My first reaction to this blog post was kind of negative because Master Class is not free. I watched the teaser video and it&#x27;s actually pretty inspiring. As someone who has done undergraduate Computer Science level Math, but completely forgotten most things about Math except for simple Algebra, I am going to try this.<p>The cost is €16&#x2F;month which is cheaper than Netflix. I just cancelled my Spotify recently so this is affordable for me right now.<p>EDIT: The problem I see with Master Class as a subcription service is... if you watch Master classes on everything you are getting a broad education rather than a deep dive. I guess it&#x27;s more for entertainment though.</text></item></parent_chain><comment><author>dfdz</author><text>In case anyone missed the response to a similar comment on the blog:<p>&gt; Terence Tao on 27 January, 2022 at 10:31 am
The production values of the lecture series given by Masterclass would not be possible for me to replicate by myself. (For instance, the film shoot alone involved well over a dozen people, including makeup, prop design, camera and lighting crew, director, editing, etc., in a custom studio with professional-quality recording equipment. The professional scriptwriting services were also very valuable, improving the selection and arrangement of material in ways I would not have thought of.)</text></comment> | <story><title>Masterclass on mathematical thinking</title><url>https://terrytao.wordpress.com/2022/01/27/masterclass-on-mathematical-thinking/</url></story><parent_chain><item><author>Graffur</author><text>My first reaction to this blog post was kind of negative because Master Class is not free. I watched the teaser video and it&#x27;s actually pretty inspiring. As someone who has done undergraduate Computer Science level Math, but completely forgotten most things about Math except for simple Algebra, I am going to try this.<p>The cost is €16&#x2F;month which is cheaper than Netflix. I just cancelled my Spotify recently so this is affordable for me right now.<p>EDIT: The problem I see with Master Class as a subcription service is... if you watch Master classes on everything you are getting a broad education rather than a deep dive. I guess it&#x27;s more for entertainment though.</text></item></parent_chain><comment><author>zwieback</author><text>We&#x27;ve had Masterclass for a bit over a year now. It&#x27;s not deep, for sure, not going to replace any kind of study or exercise.<p>However, the production value is not only visually high, it is generally well done so I find myself watching something I might otherwise not be interested in. It&#x27;s not like TED talks, which I often find too showy, too heavy on the presentation.<p>I think Masterclass is a good platform for this kind of thing: get experts to introduce people to watch something they otherwise wouldn&#x27;t.</text></comment> |
31,736,625 | 31,733,932 | 1 | 2 | 31,733,513 | train | <story><title>Writing is a single-player game</title><url>https://www.otherlife.co/singleplayer/</url></story><parent_chain></parent_chain><comment><author>cs137</author><text>I don&#x27;t disagree with the general sentiment, but as someone who has faced literal attempts on his life for revealing unpleasant truths about powerful people and has PTSD, I find myself cautious in fully accepting the optimism. And I&#x27;m someone who had a pretty big platform in the 2010s.<p>The problem with &quot;speaking truth to power&quot; is that the shitbags in power already know the truth (that they&#x27;re shitbags, and that in a just world they would be torn down and humiliated, if not destroyed). What you do by &quot;speaking truth&quot; is reveal to them that you also know this. By doing so, you make yourself dangerous to them. Sometimes, this is what you want. Sometimes, it is not. It is not an easy, one-size-fits-all decision. Your enemies, but also your friends, start to see you as an instrument of war.<p>Also, with regard to &quot;algorithmic demons&quot;... it&#x27;s not &quot;algorithms&quot; that are the problem. It&#x27;s (a) the complete lack of transparency, (b) that the algorithms are often tailored toward objectives other than content quality (which leads to gaming, hence the perceived need for opacity), and (c) that the data now available about us is invariably used against us by bad actors (and that a lack of influence &#x2F; platform will also be used against us, so I don&#x27;t know if there&#x27;s a way to win).<p>The algorithms themselves aren&#x27;t so bad; what&#x27;s worse is that these companies often slip shit into the algorithms that punishes people or ideas they dislike, and of course (a) this is completely unregulated, (b) it&#x27;s impossible to prove, and (c) you&#x27;ll often damage your reputation if you point it out (since you sound identical to a crazy person who failed organically and is lashing out at &quot;the algorithm&quot; with unprovable assertions).</text></comment> | <story><title>Writing is a single-player game</title><url>https://www.otherlife.co/singleplayer/</url></story><parent_chain></parent_chain><comment><author>antux</author><text>As someone who is written over 300 articles on my blog I can relate to the feeling of wondering if my words even matter or make difference. Feeling like they don&#x27;t matter is the easiest way to quit.<p>Some articles have made a splash, but only for the momentary period it was first published. I always wonder if the next generation of people will ever see it, or will it just get lost in the void.<p>I&#x27;ve come to terms that it doesn&#x27;t matter if it helps people or not. What keeps me writing is all the interesting thoughts and ideas I want to share. It&#x27;s a way to express what&#x27;s inside of me to the few people that want to listen.<p>If you can make writing so engaging to you to where you want to play it like a video game, you&#x27;ve cracked the code to being a writer.</text></comment> |
21,637,340 | 21,637,284 | 1 | 2 | 21,636,708 | train | <story><title>Scala.js 1.0.0-RC1</title><url>https://www.scala-js.org/news/2019/11/26/announcing-scalajs-1.0.0-RC1/</url></story><parent_chain></parent_chain><comment><author>threeseed</author><text>Would highly recommend pairing this with Slinky (React for Scala.js).<p><a href="https:&#x2F;&#x2F;slinky.dev" rel="nofollow">https:&#x2F;&#x2F;slinky.dev</a></text></comment> | <story><title>Scala.js 1.0.0-RC1</title><url>https://www.scala-js.org/news/2019/11/26/announcing-scalajs-1.0.0-RC1/</url></story><parent_chain></parent_chain><comment><author>utkarshkukreti</author><text>Anyone know what&#x27;s the minimum size of the compiled JS now? Is there any way Scala.js can produce code as compact as BuckleScript&#x2F;ReasonML in the future?<p>I like Scala&#x27;s syntax but the last time I tried Scala.js, the output was several hundred kb for something slightly more than a Hello World -- it used some List and Seq functions. I&#x27;d bet the comparable ReasonML output would likely be in tens of kb (including List and Array functions from Belt).</text></comment> |
14,374,604 | 14,374,531 | 1 | 3 | 14,374,307 | train | <story><title>Kotlin is the hero Android needs</title><url>https://10clouds.com/blog/kotlin-android/</url></story><parent_chain><item><author>eng_monkey</author><text>WTF? Some people are spending serious money on a PR campaign to promote Kotlin this week!</text></item></parent_chain><comment><author>StevePerkins</author><text>1. Android is the largest mobile platform on the planet.<p>2. It&#x27;s been around for a decade now, but has only supported development with Java and C++.<p>3. The most recent version of Java supported comes from 2011. And full C++ support is only recent.<p>4. Few people (if any) really like these options.<p>5. This week Google announced that Kotlin is the next &quot;official&quot; language with first-class support.<p>6. A temporary wave of stories appear on HN.<p>Are you new here? I&#x27;m sure that next week it&#x27;ll go back to the usual threads about Rust or Haskell, or someone will start a retro fad around Algol-68 or something.</text></comment> | <story><title>Kotlin is the hero Android needs</title><url>https://10clouds.com/blog/kotlin-android/</url></story><parent_chain><item><author>eng_monkey</author><text>WTF? Some people are spending serious money on a PR campaign to promote Kotlin this week!</text></item></parent_chain><comment><author>Lewton</author><text>I wouldn&#x27;t be surprised if money wasn&#x27;t involved, HN has always worked like this.<p>Some tech post about some technology gets a ton of votes, some people get excited about the tech, they investigate and find articles about that tech, they share it, and all the excited people upvote it.<p>Has happened several times with Rust, Go, Ember, Meteor, Angular, TypeScript, etc etc<p>This time android support and that steve yegge blog post set it off (it probably wasn&#x27;t an accident that these two coincided though?)<p>It&#x27;s like an echo-chamber with ADHD</text></comment> |
20,013,724 | 20,013,603 | 1 | 2 | 20,011,521 | train | <story><title>SpaceX Raptor: Methane fueled full-flow staged combustion cycle engine</title><url>https://everydayastronaut.com/raptor-engine/</url></story><parent_chain></parent_chain><comment><author>_ph_</author><text>While the article was focused on the Raptor engine, it shows how great an engine the RS-25 of the space shuttle was. It was crazy expensive, but as the shuttle was reused, one could justify the cost. The sad thing is, this engine will be used in the SLS - with no reuse what so ever. If anything describes the insanity of the SLS system, then this. They are flying the most expensive rocket engine ever in fully disposable mode. Even worse. After ending the shuttle program, the engines were of course preserved, so at least the first SLS flights are going to waste the origininal shuttle engines.</text></comment> | <story><title>SpaceX Raptor: Methane fueled full-flow staged combustion cycle engine</title><url>https://everydayastronaut.com/raptor-engine/</url></story><parent_chain></parent_chain><comment><author>ncmncm</author><text>Seems like with as many F1s as were used on each Apollo mission, he should count more than 17 flights. Also, I know at least one F1 was shut down before reaching orbit.<p>But, wow, what a great presentation! None of the other explanations I read of the full-flow design were anywhere near as clear and comprehensible. My understanding of rocket design principles has taken a great leap.</text></comment> |
9,372,112 | 9,371,258 | 1 | 2 | 9,370,979 | train | <story><title>The J1 Forth CPU</title><url>http://www.excamera.com/sphinx/fpga-j1.html</url></story><parent_chain></parent_chain><comment><author>avodonosov</author><text>Another Forth CPU by the Forth creator Chuck Moore and colleagues: <a href="http:&#x2F;&#x2F;www.greenarraychips.com&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.greenarraychips.com&#x2F;</a>. It&#x27;s has 144 cores on a square centimeter chip.<p>Each core is equipped with its own little data and control Forth stacks, making it a fully fledged independent computer (that&#x27;s why the more precise term is &quot;multi-computer chips&quot; rather than &quot;multi-core&quot;).<p>The cores talk to each other via communication ports. Writing to a port suspends the core until
the peer reads the value. And vice-versa.
(similar to channels in Go language).<p>Some other interesting properties (quoting the docs):<p>A computer can read from multiple ports [corresponds to Go&#x27;s select] and can execute instructions directly from those ports.<p>FINE GRAINED ENERGY CONTROL: ... The read or write instruction is automatically suspended in mid-operation if the address [one or more of communication ports and I&#x2F;O pin] is inactive, consuming energy only due to transistor leakage currents, resuming when the address becomes active.<p>NO CLOCKS: Most computing devices have one or more clocks that synchronize all operations. When a conventional computer is powered up and waiting to respond quickly to stimuli, clock generation and distribution are consuming energy at a huge rate by our standards, yet accomplishing nothing. This is why “starting” and “stopping” the clock is a big deal and takes much time and energy for other architectures. Our architecture explicitly omits a clock, saving energy and time among other benefits.<p><a href="http:&#x2F;&#x2F;www.greenarraychips.com&#x2F;home&#x2F;documents&#x2F;greg&#x2F;PB002-100822-GA-Arch.pdf" rel="nofollow">http:&#x2F;&#x2F;www.greenarraychips.com&#x2F;home&#x2F;documents&#x2F;greg&#x2F;PB002-100...</a></text></comment> | <story><title>The J1 Forth CPU</title><url>http://www.excamera.com/sphinx/fpga-j1.html</url></story><parent_chain></parent_chain><comment><author>MCRed</author><text>I loved Forth as a kid, I thought it was a great language to learn on.<p>I think that it&#x27;s much better than BASIC for small projects and I would love to see someone make an arduino or BASIC STAMP type product (maybe kickstarter it?) with a little bit of an ecosystem.<p>I think a lot of people who are hardware focused but need to do some software would benefit, and software people who want to get into hardware would benefit too.</text></comment> |
1,722,213 | 1,722,209 | 1 | 3 | 1,722,126 | train | <story><title>Details on today's Facebook outage</title><url>http://www.facebook.com/notes/facebook-engineering/more-details-on-todays-outage/431441338919</url></story><parent_chain></parent_chain><comment><author>davidu</author><text>This is known generally as the "Thundering Herd" problem:<p>The thundering herd problem occurs when a large number of processes waiting for an event are awoken when that event occurs, but only one process is able to proceed at a time. After the processes wake up, they all demand the resource and a decision must be made as to which process can continue. After the decision is made the remaining processes are put back to sleep, only to wake up again to request access to the resource.<p>This occurs repeatedly, until there are no more processes to be woken up. Because all the processes use system resources upon waking, it is more efficient if only one process is woken up at a time.<p>This may render the computer unusable, but it can also be used as a technique if there is no other way to decide which process should continue (for example when programming with semaphores).<p>Though the phrase is mostly used in computer science, it could be an abstraction of the observation seen when cattle are released from a shed or when wildebeest are crossing the Mara River. In both instances, the movement is suboptimal.<p>From: <a href="http://en.wikipedia.org/wiki/Thundering_herd_problem" rel="nofollow">http://en.wikipedia.org/wiki/Thundering_herd_problem</a></text></comment> | <story><title>Details on today's Facebook outage</title><url>http://www.facebook.com/notes/facebook-engineering/more-details-on-todays-outage/431441338919</url></story><parent_chain></parent_chain><comment><author>sethwartak</author><text>My favorite comments on fb page:<p><pre><code> Stick with Mysql
* * * * If it aint broke, dont fix it!
Me too Melissa, and it's out there in the media that a group of hackers caused the problem, is this true, Mr Robert Johnson?
PLEASE !!!! WHAT CAN YOU DO TO HELP THIS FROM EVER HAPPENING AGAIN???????????????? PLEASE!!!!!!!!!!!!!!! CANDY
Kip da updates comin'
Did anyone get a message like I did about someone trying to access your account from another state?</code></pre></text></comment> |
13,729,914 | 13,729,924 | 1 | 2 | 13,729,517 | train | <story><title>Cloudflare data still in Bing caches</title><url>https://news.ycombinator.com/item?id=13727279</url></story><parent_chain><item><author>MichaelGG</author><text>I&#x27;ve had a fairly high opinion of CF, apart from their Tor handling and bad defaults (Trump&#x27;s website requires a captcha to view static content.) Yeah I&#x27;m uncomfortable with them having so much power, but they seemed like a decent company.<p>But their response here is embarassingly bad. They&#x27;re blaming Google? And totally downplaying the issue. I really didn&#x27;t expect this from them. Zero self awareness- or they believe they can just pretend it&#x27;s not real and it&#x27;ll go away.</text></item></parent_chain><comment><author>kyledrake</author><text>I&#x27;ll just use their own logic they use against us when we ask them to take down the DDoS attack-for-hire sites they host while they are attacking our servers:<p>Why does Cloudflare think Google needs to do anything here? It&#x27;s not illegal. Google shouldn&#x27;t do anything unless they receive a court order to do so! Why does everyone expect Google to do enforcement here? Google has the right to post this information, it&#x27;s not illegal to do so, therefore they shouldn&#x27;t do anything at all about this. Don&#x27;t you care about freedom of speech? If Google removes this, it creates a slippery slope that will lead to the entire internet being censored.</text></comment> | <story><title>Cloudflare data still in Bing caches</title><url>https://news.ycombinator.com/item?id=13727279</url></story><parent_chain><item><author>MichaelGG</author><text>I&#x27;ve had a fairly high opinion of CF, apart from their Tor handling and bad defaults (Trump&#x27;s website requires a captcha to view static content.) Yeah I&#x27;m uncomfortable with them having so much power, but they seemed like a decent company.<p>But their response here is embarassingly bad. They&#x27;re blaming Google? And totally downplaying the issue. I really didn&#x27;t expect this from them. Zero self awareness- or they believe they can just pretend it&#x27;s not real and it&#x27;ll go away.</text></item></parent_chain><comment><author>dcosson</author><text>Agree that it&#x27;s a shame that it doesn&#x27;t really feel like they&#x27;re owning up to how bad it was.<p>But I wonder if it will just mostly go away. Luckily for cloudflare this is a pretty random sampling of people around the country and world. Unless someone has put together a big data set from the caches and decides to leak it or inform the victims, it seems like most people whose accounts do get taken over from this will have no way to trace it back to this bug.</text></comment> |
11,265,540 | 11,265,136 | 1 | 2 | 11,264,469 | train | <story><title>How OpenGL works: software renderer in 500 lines of code</title><url>https://github.com/ssloy/tinyrenderer/wiki</url></story><parent_chain></parent_chain><comment><author>sclangdon</author><text>This is great and so concise, but I&#x27;m surprised that the author didn&#x27;t implement OpenGL&#x27;s interface (obviously not all of it), if the goal is to show how OpenGL works.<p>Another good example of this is Trenki&#x27;s software renderer for the GPX2[1], which implements a shader architecture if memory serves. I haven&#x27;t looked at it for many years, but I remember it being a useful resource when learning this stuff.<p>Other useful resources are, of course, Michael Abrash&#x27;s Graphics Programming Black Book[2] (despite it&#x27;s age, is still a great read filled with useful information), and for a really deep dive into the graphic&#x27;s pipeline, ryg&#x27;s (of Farbrausch fame) A Trip Through the Graphics Pipeline[3].<p>[1] <a href="http:&#x2F;&#x2F;www.trenki.net&#x2F;content&#x2F;view&#x2F;18&#x2F;38&#x2F;" rel="nofollow">http:&#x2F;&#x2F;www.trenki.net&#x2F;content&#x2F;view&#x2F;18&#x2F;38&#x2F;</a><p>[2] <a href="https:&#x2F;&#x2F;github.com&#x2F;jagregory&#x2F;abrash-black-book" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;jagregory&#x2F;abrash-black-book</a><p>[3] <a href="https:&#x2F;&#x2F;fgiesen.wordpress.com&#x2F;2011&#x2F;07&#x2F;09&#x2F;a-trip-through-the-graphics-pipeline-2011-index&#x2F;" rel="nofollow">https:&#x2F;&#x2F;fgiesen.wordpress.com&#x2F;2011&#x2F;07&#x2F;09&#x2F;a-trip-through-the-...</a></text></comment> | <story><title>How OpenGL works: software renderer in 500 lines of code</title><url>https://github.com/ssloy/tinyrenderer/wiki</url></story><parent_chain></parent_chain><comment><author>8bitpimp</author><text>I wrote a software implementation of OpenGL with the only goal of being able to play Quake3 using it. I can vouch that it is an amazing learning experience. The tutorial here doesnt seem to aproach the issues of performance however, which really are another learning experience entirely.</text></comment> |
28,955,466 | 28,954,001 | 1 | 3 | 28,953,167 | train | <story><title>The 'impossible' crane shot from Soy Cuba (1964) [video]</title><url>https://twitter.com/nickdale/status/1450617359375343617</url></story><parent_chain><item><author>coolandsmartrr</author><text>Soy Cuba contains lush and gorgeous B&amp;W cinematography. The film opens up with the camera flying over the waters of Cuba; the reflection of the water is glistening in a way unlike other films. I believe they used an X-ray film strip to achieve this shot.<p>Mikhail Kalatozov has included another impressive shot at the end of his previous work, &quot;The Cranes Are Flying.&quot; (Palme d&#x27;Or at Cannes 1958) The camera follows the protagonist, then gets seamlessly lifted up by a crane to depict the entire street parading.<p>While Soviet-era films does not have much exposure in the English-speaking world, there are so many gems, critically and technically. The filmmakers were acutely aware of great filming techniques.<p>Also check out:<p>Walking the Streets of Moscow (1964)
- B-roll scenery contains another lush reflection of the Moscow waters<p>Ivan the Terrible (1944&#x2F;1958)
- Eisenstein is an ardent practitioner of the montage, and prefers to static camera shots. However, his compositions are very imaginative, and there is no shot you want to miss. His film also briefly experiments with color, and he exploits colored lighting to emphasize the characters&#x27; psyche.<p>Anything by Andrei Tarkovsky
- Tarkovsky is indisputably a master of Russian cinema after Eisenstein. He often shoots in nature, but no director shoots with such rich texture of the mud. His long shots emphasizes the bleakness inherent in the Russian psyche.<p>The Ascent (1977)
- Set in WWII, the film shows the resistance escaping the Nazis covered in snow and panting in the cold. Great snow photography.<p>Hard to Be a God (2013)
- A sci-fi story on the immigration of humans to a different planet, the colonizers inhabit the inhospitable environment. Like Tarkovsky, the slow dragging in the mud conveys the dreary lives.<p>These are recommendations I came up off the top of my head relating to cinematography, but there are definitely many more to appreciate.</text></item></parent_chain><comment><author>skhr0680</author><text>The shot from OP looks like IR film, it’s what makes it look “HDR” with plenty of detail in the shadows and sky. If it were shot on normal film then exposing for the sky would make the areas in shadow look black.</text></comment> | <story><title>The 'impossible' crane shot from Soy Cuba (1964) [video]</title><url>https://twitter.com/nickdale/status/1450617359375343617</url></story><parent_chain><item><author>coolandsmartrr</author><text>Soy Cuba contains lush and gorgeous B&amp;W cinematography. The film opens up with the camera flying over the waters of Cuba; the reflection of the water is glistening in a way unlike other films. I believe they used an X-ray film strip to achieve this shot.<p>Mikhail Kalatozov has included another impressive shot at the end of his previous work, &quot;The Cranes Are Flying.&quot; (Palme d&#x27;Or at Cannes 1958) The camera follows the protagonist, then gets seamlessly lifted up by a crane to depict the entire street parading.<p>While Soviet-era films does not have much exposure in the English-speaking world, there are so many gems, critically and technically. The filmmakers were acutely aware of great filming techniques.<p>Also check out:<p>Walking the Streets of Moscow (1964)
- B-roll scenery contains another lush reflection of the Moscow waters<p>Ivan the Terrible (1944&#x2F;1958)
- Eisenstein is an ardent practitioner of the montage, and prefers to static camera shots. However, his compositions are very imaginative, and there is no shot you want to miss. His film also briefly experiments with color, and he exploits colored lighting to emphasize the characters&#x27; psyche.<p>Anything by Andrei Tarkovsky
- Tarkovsky is indisputably a master of Russian cinema after Eisenstein. He often shoots in nature, but no director shoots with such rich texture of the mud. His long shots emphasizes the bleakness inherent in the Russian psyche.<p>The Ascent (1977)
- Set in WWII, the film shows the resistance escaping the Nazis covered in snow and panting in the cold. Great snow photography.<p>Hard to Be a God (2013)
- A sci-fi story on the immigration of humans to a different planet, the colonizers inhabit the inhospitable environment. Like Tarkovsky, the slow dragging in the mud conveys the dreary lives.<p>These are recommendations I came up off the top of my head relating to cinematography, but there are definitely many more to appreciate.</text></item></parent_chain><comment><author>blancNoir</author><text>For long, unbroken, takes I would additionally recommend Bi Gan&#x27;s 2018 film Long Day&#x27;s Journey into Night whose second part features an hour long take over various open terrain and enclosures. I would recommend it in any case, as it&#x27;s a beautiful film by a highly creative young director who was inspired by Tarkovsky to become a filmmaker.</text></comment> |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.