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
|
|---|---|---|---|---|---|---|---|
15,633,215 | 15,633,046 | 1 | 3 | 15,632,351 | train | <story><title>UN Study Warns: Growing Economic Concentration Leads to “Rentier Capitalism”</title><url>https://promarket.org/un-study-warns-growing-economic-concentration-leads-rentier-capitalism/</url></story><parent_chain></parent_chain><comment><author>programmingpol</author><text>As a Republican elected official in a southeastern state, I have a front-row seat to what this article points at.<p>The road construction industry used to be a great opportunity for small business people to create for themselves a substantial income. These days, all the companies in our area are owned by conglomerates, backed by billion dollar financial institutions. If you were to risk a million or two or an asphalt plant, they will undercut your prices till you go bankrupt, then inflate their prices once again. The two companies in our area will bid on all of our projects, but it&#x27;s clear they are in cahoots when it comes to their pricing.<p>By our estimates, the taxpayers are overpaying by at least 15% - 20%. In my mind, this robs others of opportunity and transfers wealth from tax-paying citizens to billion dollar companies.<p>No one points this out because the road builders give a lot to politicians. Go against them, and they&#x27;ll spend enough to have the public label you a RINO which, in this neck of the woods, can get you booted from office.<p>I&#x27;ve wished for some time that someone could create a modular asphalt plant that can be packed up on trucks and taken to wherever the job site is. I think companies like this could help regulate prices and make a lot of money.</text></comment> | <story><title>UN Study Warns: Growing Economic Concentration Leads to “Rentier Capitalism”</title><url>https://promarket.org/un-study-warns-growing-economic-concentration-leads-rentier-capitalism/</url></story><parent_chain></parent_chain><comment><author>cyphereal</author><text>The article is very hand-wavy about the core rent seeking argument. There is much discussion about factors such as productivity improvements concentration of market power and mergers and acquisitions.<p>From TFA: &quot;says Blankenburg, “the data show very clearly that the means used to obtain these profits cannot be reduced to the use of productive technologies.” Other mechanisms, such as lobbying or mergers and acquisitions, the authors find, have played a significant role in enhancing the market power of dominant companies. “You can show quite clearly how surplus profits increase with mergers and acquisitions, or how changes in regulation that favor control over intellectual property rights for large corporations have a pretty-instant impact on the profit performance of those companies,&quot;<p>That&#x27;s the sum total of the rent seeking argument. There is nothing in there demonstrating use of IP to extract rent (which, arguably isn&#x27;t even rent seeking behaviour, but for the sake of argument may be granted here). My intuition is that profit extraction due to IP for the very large companies is most obvious in pharmaceuticals, but that&#x27;s just my guess?<p>There are a few interesting points in this article, but it&#x27;s weakly written.</text></comment> |
353 | 287 | 1 | 2 | 189 | train | <story><title>Why we made this site</title><url>http://ycombinator.com/announcingnews.html</url></story><parent_chain></parent_chain><comment><author>jhenzie</author><text>Paul,
can we play with arc, go on, please, you know you want us to really, go on mate, have a heart.
&#60;smile/&#62;</text></comment> | <story><title>Why we made this site</title><url>http://ycombinator.com/announcingnews.html</url></story><parent_chain></parent_chain><comment><author>ced</author><text>Since community-building is part of the goal of this site, could you include an optional &#34;location&#34; field in the profile? I'm interested in getting in touch personally with other people in my area.</text></comment> |
22,122,606 | 22,121,644 | 1 | 3 | 22,119,723 | train | <story><title>Mozilla Wants Young People to Consider ‘Ethical Issues’ Before Taking Tech Jobs</title><url>https://www.vice.com/en_us/article/wxenxx/mozilla-wants-young-people-to-consider-ethical-issues-before-taking-jobs-in-tech</url></story><parent_chain><item><author>herbstein</author><text>I&#x27;m just starting my 6th (and last) semester of my bachelor degree. During the semester we are exploring the ethics and morality of the modern computing evolution. The exploration includes the difference between publishers and editors, going back to basics of the &quot;what and why&quot; of privacy, and how companies exploit our (lack of) privacy to gain further growth.<p>Unfortunately it&#x27;s a course a lot of my classmates have expressed disdain for. To them it sounds more like a &quot;gender-studies course&quot; (their words) than a course for &quot;super serious no-bullshit smart people&quot; (my interpretation). I&#x27;m hoping the readings will have them reconsider and realize how important considering the ethical implications of their programs.<p>As an example: a friend and a classmate works for $bigcorp. He had an idea for an employee engagement system. The idea was that every employee had a digital avatar that follows them around on the premises. So (as an example) when they go to the coffee machine their avatar high-fives the avatar of another person who&#x27;s also getting coffee. This, as you can imagine, requires tracking the movement of employees to a fairly high degree. The project got two months into development before the &quot;right&quot; person heard about it, raised a fuzz, and got the project cancelled.<p>Neither my friend nor my other classmates see the problem with the precise tracking of the every move of every employee - that scares me a lot.</text></item></parent_chain><comment><author>_bxg1</author><text>I took one of those courses; it wasn&#x27;t intellectually stimulating and it felt like a condescending, corporate-mandated seminar. Even the professor was just going through the motions. But it doesn&#x27;t have to be that way, that&#x27;s just how it tends to play out.<p>What we need are not &quot;ethics in tech&quot; courses, but for people <i>in</i> tech to get more exposure to general <i>humanities</i> education. Require everyone getting a degree at your university - computer science majors included - to read and discuss classic literature, history, and philosophy. Exercise the parts of their brain that deal with questions whose answers can&#x27;t be reduced to code. Ethics cannot be covered by a pamphlet of tech-specific rules; to act ethically, a person needs perspective on human nature and on what it means to be a member of society.</text></comment> | <story><title>Mozilla Wants Young People to Consider ‘Ethical Issues’ Before Taking Tech Jobs</title><url>https://www.vice.com/en_us/article/wxenxx/mozilla-wants-young-people-to-consider-ethical-issues-before-taking-jobs-in-tech</url></story><parent_chain><item><author>herbstein</author><text>I&#x27;m just starting my 6th (and last) semester of my bachelor degree. During the semester we are exploring the ethics and morality of the modern computing evolution. The exploration includes the difference between publishers and editors, going back to basics of the &quot;what and why&quot; of privacy, and how companies exploit our (lack of) privacy to gain further growth.<p>Unfortunately it&#x27;s a course a lot of my classmates have expressed disdain for. To them it sounds more like a &quot;gender-studies course&quot; (their words) than a course for &quot;super serious no-bullshit smart people&quot; (my interpretation). I&#x27;m hoping the readings will have them reconsider and realize how important considering the ethical implications of their programs.<p>As an example: a friend and a classmate works for $bigcorp. He had an idea for an employee engagement system. The idea was that every employee had a digital avatar that follows them around on the premises. So (as an example) when they go to the coffee machine their avatar high-fives the avatar of another person who&#x27;s also getting coffee. This, as you can imagine, requires tracking the movement of employees to a fairly high degree. The project got two months into development before the &quot;right&quot; person heard about it, raised a fuzz, and got the project cancelled.<p>Neither my friend nor my other classmates see the problem with the precise tracking of the every move of every employee - that scares me a lot.</text></item></parent_chain><comment><author>luckydata</author><text>They don&#x27;t see the problem because they haven&#x27;t experienced the consequences of bad corporate environments. Some things you gotta experience on your own to truly appreciate. Everyone should have a really bad job at least once in their life.</text></comment> |
32,153,528 | 32,152,422 | 1 | 3 | 32,151,044 | train | <story><title>America’s favorite family outings are increasingly out of reach</title><url>https://thehustle.co/americas-favorite-family-outings-are-increasingly-out-of-reach/</url></story><parent_chain><item><author>dylan604</author><text>I&#x27;m sorry, but I&#x27;ve been to the State Fair and comparing it as a Disney alternative is kind of a joke. State Fairs are glorified carnivals, and probably hire some actual carnys for the month they are open. To compare that to the rides at Disney is really a stretch. You could have at least suggested Six Flags like amusement park instead.<p>Your other points I&#x27;ll agree with. State Fairs-&gt;Disney was just too much of a stretch for me to accept.</text></item><item><author>aaronax</author><text>I think everything is just generally &quot;nicer&quot;. Stadium seats are cushier, parking lots are paved instead of gravel, sidewalks are a lot wider, more air-conditioned spaces, better food availability, etc.<p>And people expect more exciting and high quality things now, because they have seen a lot (comparably). Someone growing up in the 1930s wasn&#x27;t able to hop on the interstate and go 300 miles away for the weekend. Those growing up in the 80s were more apt to do that sort of thing, and as mobility has increased, attractions (nicer ones) have been built out over the decades. Now that person who traveled to all sorts of attractions continues to seek out new things -&gt; bigger and better of course. More $$$.<p>The basic, economical attractions are still there if you look. Just think smaller scale. Instead of national parks, go to state parks. Instead of Disney, go to the state fair. Instead of Broadway, find the local theater troupe. Instead of MLB&#x2F;NFL, check out summer or arena leagues. Just because you read about an attraction that seems cool, is 1,500 miles away, and is the best of breed nationwide, doesn&#x27;t mean you need to or even get to experience it.</text></item></parent_chain><comment><author>woodruffw</author><text>I agree that it&#x27;s an apples-to-oranges comparison, but maybe not in a way that casts Disney World in a positive light: it seems like the primary experience of Disney World is queueing for hours on rides that are references to things you already know, and paying a general &quot;Disney tax&quot; for being surrounded by familiar intellectual property. That&#x27;s some people&#x27;s thing, but it&#x27;s not mine.<p>State and Country Fairs, on the other hand, are relatively diverse in their attractions: you can do the carnival stuff if you&#x27;d like, or you can:<p>* Peruse your state&#x27;s agricultural and crafts competitions<p>* Go to the livestock auctions<p>* See live music by local artists<p>* Go the the trade halls and look at&#x2F;purchase goods by local businesspeople<p>* Attend the live performances and competitions (my favorite county fair[1] has tractor pulls and pig races)<p>[1]: <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Dutchess_County_Fair" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Dutchess_County_Fair</a></text></comment> | <story><title>America’s favorite family outings are increasingly out of reach</title><url>https://thehustle.co/americas-favorite-family-outings-are-increasingly-out-of-reach/</url></story><parent_chain><item><author>dylan604</author><text>I&#x27;m sorry, but I&#x27;ve been to the State Fair and comparing it as a Disney alternative is kind of a joke. State Fairs are glorified carnivals, and probably hire some actual carnys for the month they are open. To compare that to the rides at Disney is really a stretch. You could have at least suggested Six Flags like amusement park instead.<p>Your other points I&#x27;ll agree with. State Fairs-&gt;Disney was just too much of a stretch for me to accept.</text></item><item><author>aaronax</author><text>I think everything is just generally &quot;nicer&quot;. Stadium seats are cushier, parking lots are paved instead of gravel, sidewalks are a lot wider, more air-conditioned spaces, better food availability, etc.<p>And people expect more exciting and high quality things now, because they have seen a lot (comparably). Someone growing up in the 1930s wasn&#x27;t able to hop on the interstate and go 300 miles away for the weekend. Those growing up in the 80s were more apt to do that sort of thing, and as mobility has increased, attractions (nicer ones) have been built out over the decades. Now that person who traveled to all sorts of attractions continues to seek out new things -&gt; bigger and better of course. More $$$.<p>The basic, economical attractions are still there if you look. Just think smaller scale. Instead of national parks, go to state parks. Instead of Disney, go to the state fair. Instead of Broadway, find the local theater troupe. Instead of MLB&#x2F;NFL, check out summer or arena leagues. Just because you read about an attraction that seems cool, is 1,500 miles away, and is the best of breed nationwide, doesn&#x27;t mean you need to or even get to experience it.</text></item></parent_chain><comment><author>nostrademons</author><text>Note that there&#x27;s quality creep in any established institution. Disneyland&#x27;s attractions on opening day weren&#x27;t all that different from a local carnival:<p><a href="https:&#x2F;&#x2F;touringplans.com&#x2F;disneyland&#x2F;attractions&#x2F;opening-dates" rel="nofollow">https:&#x2F;&#x2F;touringplans.com&#x2F;disneyland&#x2F;attractions&#x2F;opening-date...</a><p>Favorites like Pirates of the Caribbean and the Haunted Mansion didn&#x27;t open until the late 1960s, a decade after the park did, and Space Mountain &amp; Thunder Mountain didn&#x27;t open until the late 1970s.</text></comment> |
1,651,372 | 1,651,290 | 1 | 2 | 1,650,579 | train | <story><title>Autocomplete your life with Greplin (YC W10)</title><url>http://techcrunch.com/2010/08/31/greplin-ycombinator-personal-search/</url></story><parent_chain><item><author>danicgross</author><text>If you get uncomfortable, you can delete your account at any time. We'll delete your data. Not in 14 days, a week or tomorrow. That moment.
We're convinced that you'll find enough value with Greplin to overcome that issue - the same way many did with mint.com.<p>We're also working with a) encrypted indexes b) only writing the index to disk rather then any content. this shuts down a lot of neat features (generating snippets etc.) - but users that are willing to forgo features for added security might find it useful.</text></item><item><author>Sukotto</author><text>Why should I trust these guys with my data? It's bad enough that Google knows so much about me... but at least they have some checks and balances built in. What sort of safety does "greplin" have to offer adopters?</text></item></parent_chain><comment><author>sweis</author><text>Can you share any details of how your encrypted indices work? Searching over encrypted data is an active research area. I'm curious to learn what you are doing in practice.</text></comment> | <story><title>Autocomplete your life with Greplin (YC W10)</title><url>http://techcrunch.com/2010/08/31/greplin-ycombinator-personal-search/</url></story><parent_chain><item><author>danicgross</author><text>If you get uncomfortable, you can delete your account at any time. We'll delete your data. Not in 14 days, a week or tomorrow. That moment.
We're convinced that you'll find enough value with Greplin to overcome that issue - the same way many did with mint.com.<p>We're also working with a) encrypted indexes b) only writing the index to disk rather then any content. this shuts down a lot of neat features (generating snippets etc.) - but users that are willing to forgo features for added security might find it useful.</text></item><item><author>Sukotto</author><text>Why should I trust these guys with my data? It's bad enough that Google knows so much about me... but at least they have some checks and balances built in. What sort of safety does "greplin" have to offer adopters?</text></item></parent_chain><comment><author>whatusername</author><text>So you don't have any backups then? (And I mean actual backups - replication is not a backup)</text></comment> |
8,740,149 | 8,740,103 | 1 | 3 | 8,739,865 | train | <story><title>The bad side of systemd: two recent systemd failures</title><url>http://utcc.utoronto.ca/~cks/space/blog/linux/SystemdCrashAndMore</url></story><parent_chain><item><author>XorNot</author><text>I can&#x27;t speak to the first problem, but the second is more of &quot;this is strange and I don&#x27;t care to learn how it works&quot;.<p>journalctl --no-pager<p>Problem solved. I mean, you have the command, it&#x27;s right there in the usage text. Which, awesomely, does invoke a pager when you do journalctl --help so if you&#x27;re stuck on a 80x25 console (as you might be on a broken system) you can easily actually read the help options.</text></item></parent_chain><comment><author>Mister_Snuggles</author><text>I found that when the output is piped it doesn&#x27;t invoke the pager. This seems reasonable to me.<p>What doesn&#x27;t seem reasonable is the truncation behaviour. When the output isn&#x27;t piped, it gets truncated to the width of my terminal. When the output is piped, it gets truncated to 80 columns. I&#x27;d expect no truncation when the output is not a terminal.<p>This is an outdated systemd though (I installed it on a Rasberry Pi [Raspbian] in order to play with it), so this may have changed.</text></comment> | <story><title>The bad side of systemd: two recent systemd failures</title><url>http://utcc.utoronto.ca/~cks/space/blog/linux/SystemdCrashAndMore</url></story><parent_chain><item><author>XorNot</author><text>I can&#x27;t speak to the first problem, but the second is more of &quot;this is strange and I don&#x27;t care to learn how it works&quot;.<p>journalctl --no-pager<p>Problem solved. I mean, you have the command, it&#x27;s right there in the usage text. Which, awesomely, does invoke a pager when you do journalctl --help so if you&#x27;re stuck on a 80x25 console (as you might be on a broken system) you can easily actually read the help options.</text></item></parent_chain><comment><author>jeremy7600</author><text>&quot;In the grand systemd tradition, there is no option to control this; all you can do is force journalctl to not use a pager or work out how to change things inside the pager to not do this.&quot;<p>He mentioned that. So, yes, it looks like he cared to learn how it works.</text></comment> |
36,912,867 | 36,912,856 | 1 | 2 | 36,906,472 | train | <story><title>US smartphone shipments fall sharply, but Android more than iPhone</title><url>https://www.counterpointresearch.com/us-smartphone-shipments-q2-2023/</url></story><parent_chain><item><author>nordsieck</author><text>&gt; I&#x27;m constantly amazed by how people spend so much of their income on Apple products<p>I don&#x27;t know about other people, but I went iPhone specifically for the value&#x2F;$. Got a used iPhone SE 2020 for $150 in late 2021, and expect to use it for 5+ years. I seriously doubt that there are any Androids out there that could get even close to that.<p>It really helps that Apple&#x27;s CPU&#x2F;SoC is substantially superior to what everyone else uses, so older iPhones tend to feel snappier. Between that and Apple&#x27;s clearly superior OS support, I don&#x27;t know why value shoppers who don&#x27;t want to install their own firmware would go with Android.</text></item><item><author>zh3</author><text>I&#x27;m constantly amazed by how people spend so much of their income on Apple products; it&#x27;s almost like their lives are ruled by the status they feel an iPhone brings (and the consequential sacrificial purchasing).<p>It likely varies by area and average income, here it&#x27;s almost an inverse correlation - the less-well off kids at school tend to have parents on iPhones and the comfortable parents are on whatever works for them.</text></item><item><author>lolinder</author><text>The link should really be to the original report [0].<p>This 55% is iPhone&#x27;s share of phone shipments in Q2, not the number of <i>users</i> of the respective phones at any given time. In other words, fewer people are buying smartphones than were before, but Apple saw less of a hit to their numbers than everyone else did.<p>Contrary to existing comments here, this stat doesn&#x27;t appear to indicate that people are <i>switching</i> from Android to iPhone. It looks like Android users are more likely to avoid upgrading their phone in an uncertain economy, while Apple users are more likely to upgrade regardless.<p>[0] <a href="https:&#x2F;&#x2F;www.counterpointresearch.com&#x2F;us-smartphone-shipments-q2-2023&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.counterpointresearch.com&#x2F;us-smartphone-shipments...</a></text></item></parent_chain><comment><author>JohnFen</author><text>&gt; expect to use it for 5+ years. I seriously doubt that there are any Androids out there that could get even close to that.<p>Every Android phone I&#x27;ve had has lasted that long or longer. If I got less than 5 years out of any smartphone, I&#x27;d consider it faulty.</text></comment> | <story><title>US smartphone shipments fall sharply, but Android more than iPhone</title><url>https://www.counterpointresearch.com/us-smartphone-shipments-q2-2023/</url></story><parent_chain><item><author>nordsieck</author><text>&gt; I&#x27;m constantly amazed by how people spend so much of their income on Apple products<p>I don&#x27;t know about other people, but I went iPhone specifically for the value&#x2F;$. Got a used iPhone SE 2020 for $150 in late 2021, and expect to use it for 5+ years. I seriously doubt that there are any Androids out there that could get even close to that.<p>It really helps that Apple&#x27;s CPU&#x2F;SoC is substantially superior to what everyone else uses, so older iPhones tend to feel snappier. Between that and Apple&#x27;s clearly superior OS support, I don&#x27;t know why value shoppers who don&#x27;t want to install their own firmware would go with Android.</text></item><item><author>zh3</author><text>I&#x27;m constantly amazed by how people spend so much of their income on Apple products; it&#x27;s almost like their lives are ruled by the status they feel an iPhone brings (and the consequential sacrificial purchasing).<p>It likely varies by area and average income, here it&#x27;s almost an inverse correlation - the less-well off kids at school tend to have parents on iPhones and the comfortable parents are on whatever works for them.</text></item><item><author>lolinder</author><text>The link should really be to the original report [0].<p>This 55% is iPhone&#x27;s share of phone shipments in Q2, not the number of <i>users</i> of the respective phones at any given time. In other words, fewer people are buying smartphones than were before, but Apple saw less of a hit to their numbers than everyone else did.<p>Contrary to existing comments here, this stat doesn&#x27;t appear to indicate that people are <i>switching</i> from Android to iPhone. It looks like Android users are more likely to avoid upgrading their phone in an uncertain economy, while Apple users are more likely to upgrade regardless.<p>[0] <a href="https:&#x2F;&#x2F;www.counterpointresearch.com&#x2F;us-smartphone-shipments-q2-2023&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.counterpointresearch.com&#x2F;us-smartphone-shipments...</a></text></item></parent_chain><comment><author>cbm-vic-20</author><text>I might be one of those value shoppers; I usually buy the &quot;Pixel .a&quot; version of the oldest available generation when it&#x27;s time for replacement (I&#x27;m currently on a Pixel 4a). I like it. I used to have an iPhone, but I prefer the &quot;feel&quot; of Andriod-on-Pixel, but I don&#x27;t know how to describe it. Less heavy-handed maybe? More minimalistic?<p>I don&#x27;t need the fastest, most powerful SoC. I don&#x27;t need the best, super fast display. The battery life on my 4a is enough for my needs. People get way too religious about this.</text></comment> |
4,632,448 | 4,631,761 | 1 | 3 | 4,629,317 | train | <story><title>How Studying Body Language Changed the Way I Socialize</title><url>http://dearcharlottebook.com/2012/09/body-language.html</url></story><parent_chain><item><author>borplk</author><text>Is that what you <i>really</i> want? To me it's just promoting the manipulation of other people. Because hey, it's a skill so it's ok.<p>Doesn't it bother you? To know that the person you are talking to, is mirroring your emotions, or offering sympathy, to manipulate you into liking them?<p>I very much prefer the Aspergers-like honesty. I would rather hear 9 harsh, blunt, honest criticisms a day and 1 genuine complement than to receive 10 fake, sugar-coated, vague, manipulative signals.<p>Don't think you'll be the only mastermind learning these and no one else will know about it. Keep in mind, if you do it, if you apply these techniques in your day to day interactions so will other people. And think about it for a second, from the perspective of a subject. Do you really want to be the subject to these social tricks and manipulations?<p>This thought truly bothers me. To hear a complement and not knowing if it was true and genuine or I was complemented simply because that person had read "How to influence people and win friends" last week and wanted to try his manipulation techniques on me.<p>Maybe instead of promoting these <i>social skills</i> we need to promote the appreciation of honesty and having some self control over our emotions.</text></item></parent_chain><comment><author>danneu</author><text>I don't think "fake niceness", empty compliments, and subterfuge are tenets of empathy or what the author was trying to express.<p>The author provides this example interaction:<p><pre><code> Person A: I like this band.
Person B: They're okay.
</code></pre>
Where you might have implied that the author is saying it should've happened like this:<p><pre><code> Person A: I like this band.
Person B: Yeah, they rule!
</code></pre>
I think the author and the case for empathy were thinking along the lines of something more like this:<p><pre><code> Person A: I like this band.
Person B: Have you ever seen them live? (Begin convo fork into live shows
you've both seen. Share experiences.)
</code></pre>
That's how you build value and connect with people.<p>"They're okay" is not honesty. There's no virtue in arbitrary judgement that does nothing but punish people for revealing their joys to you. It just squanders the opportunity where a connection could've been made.<p>I think empathetic social skills very much encompass the appreciation of honesty, and connecting with the emotional state of others does require self-control over your own state.</text></comment> | <story><title>How Studying Body Language Changed the Way I Socialize</title><url>http://dearcharlottebook.com/2012/09/body-language.html</url></story><parent_chain><item><author>borplk</author><text>Is that what you <i>really</i> want? To me it's just promoting the manipulation of other people. Because hey, it's a skill so it's ok.<p>Doesn't it bother you? To know that the person you are talking to, is mirroring your emotions, or offering sympathy, to manipulate you into liking them?<p>I very much prefer the Aspergers-like honesty. I would rather hear 9 harsh, blunt, honest criticisms a day and 1 genuine complement than to receive 10 fake, sugar-coated, vague, manipulative signals.<p>Don't think you'll be the only mastermind learning these and no one else will know about it. Keep in mind, if you do it, if you apply these techniques in your day to day interactions so will other people. And think about it for a second, from the perspective of a subject. Do you really want to be the subject to these social tricks and manipulations?<p>This thought truly bothers me. To hear a complement and not knowing if it was true and genuine or I was complemented simply because that person had read "How to influence people and win friends" last week and wanted to try his manipulation techniques on me.<p>Maybe instead of promoting these <i>social skills</i> we need to promote the appreciation of honesty and having some self control over our emotions.</text></item></parent_chain><comment><author>king_jester</author><text>I think the author was getting at actually focusing on having empathy for others when speaking to them to help understand their emotional state. Having empathy for others is not an attempt to manipulate them.</text></comment> |
19,748,763 | 19,748,627 | 1 | 2 | 19,747,706 | train | <story><title>How to hide from the AI surveillance state with a color printout</title><url>https://www.technologyreview.com/f/613409/how-to-hide-from-the-ai-surveillance-state-with-a-color-printout/</url></story><parent_chain><item><author>pizza</author><text>CV Dazzle [0] is&#x2F;was a style of makeup that defeated facial recognition, and it seemed to work from multiple angles. Unfortunately it was released something like 5 years ago so I&#x27;m certain it won&#x27;t withstand today&#x27;s state of the art techniques. Looks like it was never really tested to work against deep learning-based techniques.<p><i>That</i> said, I think somebody could very easily come up with an adversarial makeup camouflage recommender. Imagine an interactive visualization of the regions of confidence of a facial recommendation system, hooked up to your webcam. You could have a visual overlay of where to apply make up to most damage the classifier&#x27;s confidence of your identity.<p>[0] <a href="https:&#x2F;&#x2F;cvdazzle.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;cvdazzle.com&#x2F;</a></text></item><item><author>rtkwe</author><text>Figure 7 in the paper [0] shows something really important. The learned adversarial patch is not general at all and has to be held in a specific place with a specific orientation to function. This means it&#x27;s not going to be generalizable to actual surveillance where you&#x27;ll be viewed from a lot of different potential angles or say onto a shirt or jacket you can just wear.<p>[0] <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;1904.08653.pdf" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;1904.08653.pdf</a></text></item></parent_chain><comment><author>pandemic_region</author><text>thing is, when you walk around on the street looking like the people on their website you don&#x27;t actually need surveillance camera&#x27;s because every single person will remember seeing you.</text></comment> | <story><title>How to hide from the AI surveillance state with a color printout</title><url>https://www.technologyreview.com/f/613409/how-to-hide-from-the-ai-surveillance-state-with-a-color-printout/</url></story><parent_chain><item><author>pizza</author><text>CV Dazzle [0] is&#x2F;was a style of makeup that defeated facial recognition, and it seemed to work from multiple angles. Unfortunately it was released something like 5 years ago so I&#x27;m certain it won&#x27;t withstand today&#x27;s state of the art techniques. Looks like it was never really tested to work against deep learning-based techniques.<p><i>That</i> said, I think somebody could very easily come up with an adversarial makeup camouflage recommender. Imagine an interactive visualization of the regions of confidence of a facial recommendation system, hooked up to your webcam. You could have a visual overlay of where to apply make up to most damage the classifier&#x27;s confidence of your identity.<p>[0] <a href="https:&#x2F;&#x2F;cvdazzle.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;cvdazzle.com&#x2F;</a></text></item><item><author>rtkwe</author><text>Figure 7 in the paper [0] shows something really important. The learned adversarial patch is not general at all and has to be held in a specific place with a specific orientation to function. This means it&#x27;s not going to be generalizable to actual surveillance where you&#x27;ll be viewed from a lot of different potential angles or say onto a shirt or jacket you can just wear.<p>[0] <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;1904.08653.pdf" rel="nofollow">https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;1904.08653.pdf</a></text></item></parent_chain><comment><author>Zaphods</author><text>That CV Dazzle project is fascinating. The link to the warship Dazzle camouflage is also hilarious in the sense that that is what people have to turn to in 2019.<p>It reminds me of the comic book <i>The Private Eye</i> by Brian K Vaughn. In that story the cloud &quot;bursts&quot; and online privacy evaporates overnight so everyone turns to intense camouflage to protect their identity. (<a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Private_Eye" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Private_Eye</a>)</text></comment> |
18,116,858 | 18,116,370 | 1 | 2 | 18,114,754 | train | <story><title>Voice Phishing Scams Are Getting More Clever</title><url>https://krebsonsecurity.com/2018/10/voice-phishing-scams-are-getting-more-clever/</url></story><parent_chain><item><author>phkahler</author><text>The problem here is the ability to spoof caller ID. This should not be possible. Regulations set up the phone system, regulations need to make this change. I don&#x27;t care what excuse anyone has, don&#x27;t care about your stupid PBX or any of that. Caller ID should be mandatory and reliable.<p>Having said that, always assume someone calling you is a fraud. If your &quot;bank&quot; calls you, tell them you&#x27;ll call back and don&#x27;t call a number they provide over the phone or in caller ID. If you can&#x27;t find a reliable number to the bank, drive over there. The bottom line is that you can&#x27;t trust anyone who calls you.</text></item></parent_chain><comment><author>gerdesj</author><text><i>The problem here is the ability to spoof caller ID. This should not be possible.</i><p>Think of incoming CLID in the same way that you do email From: addresses. Often and easily faked. Funnily enough both my office PBX and SMTP daemon check incoming CLID&#x2F;HELO and drop attempts to spoof their own identity. Its not a particularly sophisticated protection these days but is one of many, many rules. Actually, now I come to think of it, my firewalls also check for inbound IP spoofing on their own IPs.<p>As the OP stories highlight, your mental firewall must make you bail out when asked for your PIN, regardless of how legitimate things sound. The only thing that should ever request your PIN is a machine that you have stuffed your card in first. I&#x27;m pretty certain that CVV requests should also only ever come from vendors that you are buying from, not your bank.</text></comment> | <story><title>Voice Phishing Scams Are Getting More Clever</title><url>https://krebsonsecurity.com/2018/10/voice-phishing-scams-are-getting-more-clever/</url></story><parent_chain><item><author>phkahler</author><text>The problem here is the ability to spoof caller ID. This should not be possible. Regulations set up the phone system, regulations need to make this change. I don&#x27;t care what excuse anyone has, don&#x27;t care about your stupid PBX or any of that. Caller ID should be mandatory and reliable.<p>Having said that, always assume someone calling you is a fraud. If your &quot;bank&quot; calls you, tell them you&#x27;ll call back and don&#x27;t call a number they provide over the phone or in caller ID. If you can&#x27;t find a reliable number to the bank, drive over there. The bottom line is that you can&#x27;t trust anyone who calls you.</text></item></parent_chain><comment><author>walrus01</author><text>There is no way to fix the ability to spoof caller ID with the way SS7 is built. Not without breaking functionality to something like 85% of the installed base of PBX and phone switch equipment, most of which is anywhere from 10 to 45 years old. The legacy telco SS7 phone system needs to be burnt to the ground and rebuilt, but it never will be, because people have moved on to friend-opt-in based message platforms like whatsapp, signal, telegram, facebook messenger, and the domestic chinese equivalents (wechat etc).</text></comment> |
29,131,223 | 29,128,883 | 1 | 2 | 29,128,270 | train | <story><title>Hundreds of ancient Maya sites hidden under Mexico reveal a mysterious blueprint</title><url>https://www.sciencealert.com/hundreds-of-ancient-maya-sites-hidden-under-mexico-reveal-a-mysterious-blueprint</url></story><parent_chain></parent_chain><comment><author>motohagiography</author><text>Knowing little about this, I wonder would it change how we thought about these if we didn&#x27;t call everything ceremonial and ritual? It&#x27;s like it&#x27;s to put some kind of figleaf over these people other people who were probably a lot like us.<p>I suppose my reaction is that popular archeological articles seem to effectively defy economics as a force in their explanations, and seem to prefer treating the cultures as being under an impaired superstition about the world.<p>It seems like uncovering a stadium, airport, or the Washington Mall from our world today and saying it was for rituals and ceremonies, which sure, abstractly it is, but it seems a bit filtered through a lens of studying them as primitive pagans. Nobody shifts hundreds of tons of rock for being seized by astrological magic.<p>If you start with the loop of necessity that nothing is ever more than it needs to be, we can bootstrap the question of for what was this necessary? It&#x27;s even more plausible to say pyramids were the product of a policy of Ancient Keynesianism, than to treat megalithic builders as primitive. Maybe I&#x27;m just as curious as archeologists are, but if we applied how mystified some modern academics can seem about trade and economics today and then apply that back to studying ancient cultures, I&#x27;d wonder if there were some opportunities to reduce some blind spots.</text></comment> | <story><title>Hundreds of ancient Maya sites hidden under Mexico reveal a mysterious blueprint</title><url>https://www.sciencealert.com/hundreds-of-ancient-maya-sites-hidden-under-mexico-reveal-a-mysterious-blueprint</url></story><parent_chain></parent_chain><comment><author>sydthrowaway</author><text>I firmly believe that one day we will find out the ancient world has a much bigger and overarching story than is currently known. And it will blow your mind. The Korean-Tamil hypothesis comes to mind.</text></comment> |
11,583,820 | 11,583,579 | 1 | 3 | 11,583,008 | train | <story><title>Never trust the client</title><url>http://gafferongames.com/2016/04/25/never-trust-the-client/</url></story><parent_chain></parent_chain><comment><author>xenadu02</author><text>&quot;Never trust the client&quot; is good advice for <i>every</i> kind of application. Clients are filthy liars.<p>Clients have bugs. Old clients don&#x27;t upgrade. Packets arrive out of order. ACKs never make it to clients, causing clients to repeat what the client believes to be a failed operation. All of this is before even considering an attacker actively trying to subvert you.<p>The server should always be the source of truth. It should always enforce all the consistency rules. Database schemas can be a critical tool here as well.<p>Don&#x27;t blindly slap whatever the client sends into a no-SQL database, then vomit it back out for queries.</text></comment> | <story><title>Never trust the client</title><url>http://gafferongames.com/2016/04/25/never-trust-the-client/</url></story><parent_chain></parent_chain><comment><author>vvanders</author><text>They missed one key bit on CS&#x27;s network model(which is what made it so great) is that they would actually re-wind the gamestate to do hitchecks so you could have a latency of 200ms+ and have a reasonable experience.<p>Also the common term for resolving these types of things on the client is called &quot;dead-reckoning&quot;. You&#x27;ve always got a diverging states from latency so you&#x27;re continuously trying to reconcile this on the client.<p>Simple Newtonian physics based games(Subspace, etc) are famous for being latency tolerant since the simulation is incredibly deterministic and are based on the players extrapolating where things will be in X time rather than twitch responses(which is also why fighting games are so hard without using a solution like Counter-Strike). You could play SubSpace on a 500ms dial-up connection and still be competitive without needing to lead for lag.</text></comment> |
7,582,229 | 7,581,920 | 1 | 2 | 7,581,184 | train | <story><title>Practical Cryptography With Go</title><url>https://leanpub.com/gocrypto</url></story><parent_chain><item><author>tptacek</author><text>I am not a fan of this book. I wrote a review of the book as an HN comment. I dislike this book so much that for the first time in the history of my use of HN, my comment overflowed the bounds for HN comments. So, here it is:<p><a href="http://pastebin.com/raw.php?i=NXgU30xK" rel="nofollow">http:&#x2F;&#x2F;pastebin.com&#x2F;raw.php?i=NXgU30xK</a><p>(as a Github gist:<p><a href="https://gist.githubusercontent.com/anonymous/3cc34251e501c2c8ffb7/raw/cf9ff4e7ce13985458b240980e91202ac732b4e6/Practical+Cryptography+in+Go+" rel="nofollow">https:&#x2F;&#x2F;gist.githubusercontent.com&#x2F;anonymous&#x2F;3cc34251e501c2c...</a>)</text></item></parent_chain><comment><author>napoleond</author><text>This is fantastic, thanks for taking the time to write that out. (And my condolences to the author... I know very well how hard it is to have your work so thoroughly slammed but in this case it&#x27;s important.)<p>One minor nit; I believe there is a typo in the review which caused parsing problems on my end:<p><i>The contact forward secrecy provides a design is...</i><p>s&#x2F;contact&#x2F;contract ?</text></comment> | <story><title>Practical Cryptography With Go</title><url>https://leanpub.com/gocrypto</url></story><parent_chain><item><author>tptacek</author><text>I am not a fan of this book. I wrote a review of the book as an HN comment. I dislike this book so much that for the first time in the history of my use of HN, my comment overflowed the bounds for HN comments. So, here it is:<p><a href="http://pastebin.com/raw.php?i=NXgU30xK" rel="nofollow">http:&#x2F;&#x2F;pastebin.com&#x2F;raw.php?i=NXgU30xK</a><p>(as a Github gist:<p><a href="https://gist.githubusercontent.com/anonymous/3cc34251e501c2c8ffb7/raw/cf9ff4e7ce13985458b240980e91202ac732b4e6/Practical+Cryptography+in+Go+" rel="nofollow">https:&#x2F;&#x2F;gist.githubusercontent.com&#x2F;anonymous&#x2F;3cc34251e501c2c...</a>)</text></item></parent_chain><comment><author>Sprint</author><text>As my browser displayed it with very long lines by default I wrapped it to 72 for better readability: <a href="http://pastebin.com/raw.php?i=NXgU30xK" rel="nofollow">http:&#x2F;&#x2F;pastebin.com&#x2F;raw.php?i=NXgU30xK</a></text></comment> |
16,238,212 | 16,236,651 | 1 | 2 | 16,234,060 | train | <story><title>How a fix in Go 1.9 sped up our Gitaly service by 30x</title><url>https://about.gitlab.com/2018/01/23/how-a-fix-in-go-19-sped-up-our-gitaly-service-by-30x/</url></story><parent_chain><item><author>CapacitorSet</author><text>I wonder how much it would speed up if they were using libgit2 directly.</text></item><item><author>Animats</author><text><i>Each Gitaly server instance was fork&#x2F;exec&#x27;ing Git processes about 20 times per second so we seemed to finally have a very promising lead.</i><p>What&#x27;s really wrong here is that they&#x27;re apparently spawning processes like crazy. Do they spawn a new process for each API call? That&#x27;s like running CGI programs under Apache, like it&#x27;s 1995.</text></item></parent_chain><comment><author>jacobvosmaer</author><text>I&#x27;m on the Gitaly team.<p>As zegerjan wrote, Gitaly is a Go&#x2F;Ruby hybrid.<p>The main Go process doesn&#x27;t use libgit2 (for now) because we didn&#x27;t want to have to deal with cgo. We already know how to deal with C extensions in Ruby, and we have a lot of existing Ruby application code that uses libgit2, so we still use it there. And that code works fine so I don&#x27;t see us removing it.<p>In practice, sometimes spawning a Git process is faster than using libgit2, so why then not do that. Also for parts of our workload (handling Git push&#x2F;pull operations), spawning a one-off process (git-upload-pack) is the most boring &#x2F; tried-and-true approach.</text></comment> | <story><title>How a fix in Go 1.9 sped up our Gitaly service by 30x</title><url>https://about.gitlab.com/2018/01/23/how-a-fix-in-go-19-sped-up-our-gitaly-service-by-30x/</url></story><parent_chain><item><author>CapacitorSet</author><text>I wonder how much it would speed up if they were using libgit2 directly.</text></item><item><author>Animats</author><text><i>Each Gitaly server instance was fork&#x2F;exec&#x27;ing Git processes about 20 times per second so we seemed to finally have a very promising lead.</i><p>What&#x27;s really wrong here is that they&#x27;re apparently spawning processes like crazy. Do they spawn a new process for each API call? That&#x27;s like running CGI programs under Apache, like it&#x27;s 1995.</text></item></parent_chain><comment><author>sytse</author><text>I&#x27;m at GitLab but not on the Gitaly team. I think we are using libgit2 but that it doesn&#x27;t contain all the calls we need.</text></comment> |
36,725,837 | 36,725,614 | 1 | 2 | 36,723,445 | train | <story><title>Podman Desktop 1.2 Released: Compose and Kubernetes Support</title><url>https://podman-desktop.io/blog/podman-desktop-release-1.2</url></story><parent_chain><item><author>flatline</author><text>Docker swarm is supposed to be the migration target for these cases, but I’ve never actually used it.</text></item><item><author>brazzledazzle</author><text>Docker compose falls apart when you need something clustered across nodes or any other multi-host deployment. Once you have to rip it apart it becomes way less appealing. Though I haven&#x27;t tried it in a while and perhaps the ergonomics have changed.</text></item><item><author>jadbox</author><text>I&#x27;m very happy to see you better support for docker compose. I think about 50% of the time I find Kubernetes used in production&#x2F;development when it could have just used Compose along with a simple Terraform or Pulumi deploy script.</text></item></parent_chain><comment><author>belthesar</author><text>I&#x27;ve done some labbing with Swarm. Swarm is _just different enough_ to be a pain, but just similar enough to fool you into thinking you know what you&#x27;re doing. Because swarm was also confused terminology (at one point there were two things with the name swarm that did things differently) the tech definitely got a bad rap for a while, but it also stagnated supporting tooling. You can use things like Portainer and Swarmpit to get some visibility into your swarm cluster members, deploy workloads, etc, but it definitely feels like a second class citizen.<p>Ultimately, I would love for something to exist out there that had the opinions and scope of deployment like Swarm in terms of simplicity, but didn&#x27;t conflate other tools out there so that ergonomics and documentation were better and less confusing. Kubernetes gives you so much, but I do feel like it&#x27;s a misstep that the only reasonable way we&#x27;ve simplified Kubernetes for production workflows is to pay a large PaaS to manage it for us.</text></comment> | <story><title>Podman Desktop 1.2 Released: Compose and Kubernetes Support</title><url>https://podman-desktop.io/blog/podman-desktop-release-1.2</url></story><parent_chain><item><author>flatline</author><text>Docker swarm is supposed to be the migration target for these cases, but I’ve never actually used it.</text></item><item><author>brazzledazzle</author><text>Docker compose falls apart when you need something clustered across nodes or any other multi-host deployment. Once you have to rip it apart it becomes way less appealing. Though I haven&#x27;t tried it in a while and perhaps the ergonomics have changed.</text></item><item><author>jadbox</author><text>I&#x27;m very happy to see you better support for docker compose. I think about 50% of the time I find Kubernetes used in production&#x2F;development when it could have just used Compose along with a simple Terraform or Pulumi deploy script.</text></item></parent_chain><comment><author>e12e</author><text>Swarm works, but has poor support for volumes - which means it&#x27;s tricky to run legacy applications on swarm (which eg uploads files to local disk, not s3 - or keeps state&#x2F;cache on disk, not a database).<p>Ingress is also more complicated&#x2F;bespoke - the best I&#x27;ve found is traefik with labels for routing&#x2F;config.<p>My advice today would be to scale Docker compose vertically (eg: on a dedicated server) - then move to Kubernetes.<p>The swarm middle ground isn&#x27;t really worth it IMNHO.</text></comment> |
23,056,877 | 23,056,946 | 1 | 3 | 23,052,108 | train | <story><title>Ubuntu 20.04 LTS’ snap obsession has snapped me off of it</title><url>https://jatan.blog/2020/05/02/ubuntu-snap-obsession-has-snapped-me-off-of-it/</url></story><parent_chain><item><author>kikoreis</author><text>It&#x27;s probably not a surprise to you, but this is a hotly debated topic inside Canonical. And I apologize for that thread, as it really doesn&#x27;t represent our best attempt at external debate.<p>Changing a paradigm usually involves pushing the envelope and breaking some existing assumptions; systemd is everybody&#x27;s favorite example of that in the Linux world. The root of this issue with snaps is the trade-off between built-in security and user control. Some points to consider:<p>1. Browsers like FF and Chromium [on Windows] simply self-update, and disabling that requires configuration. So there is at least some precedent for taking the position that user applications should just update themselves. Server apps are more complex and are a strong argument counter to the existing behavior, as is the fact that many apps cannot be refreshed without user impact.<p>2. Ubuntu, since 16.04 LTS, ships with unattended-upgrades enabled, which means that for debian packages the default behavior is already auto-updating (although automated reboots are not enabled by default, as that would be crazy for the general purpose case). That feels like the correct default, too, given the risk of running code exposed to exploitable, public CVEs — and how reluctant users (like my dad and my wife!) are to click on &quot;Install now&quot; in the update-manager dialog.<p>3. Debian package updates run as root. Snap updates run in userspace, and confined. So in principle the risk exposure for snap updates is much smaller. And snaps do have an auto-rollback mechanism for failed updates [a]. Counter to that argument is the fact that snaps are meant to be under third-party control, and that there is no clear mechanism to separate security patches vs updates which you get with the debian pocket mechanism (i.e. focal-security vs focal-updates).<p>The lack of any official [b] means of user control over the snap auto-update mechanism feels wrong to many of us, including me. And while we may seem somewhat opaque in these debates, the feedback we get in threads like this one (and the snapcraft.io one) actually feeds into our decision making. So please do keep pushing on this topic and we&#x27;ll do our part internally.<p>[a] See <a href="https:&#x2F;&#x2F;kyrofa.com&#x2F;posts&#x2F;snap-updates-automatic-rollbacks" rel="nofollow">https:&#x2F;&#x2F;kyrofa.com&#x2F;posts&#x2F;snap-updates-automatic-rollbacks</a> for a detailed guide on this topic. Of course, if your snap refreshes and you hate the new version, downgrading isn&#x27;t quite always possible.<p>[b] There are ways to, hmmm, control auto-updating (i.e. refresh.metered, refresh.hold) if you really want to; that thread has a few. That doesn&#x27;t help the debate, but I&#x27;m sharing in case someone has a technical need for it.</text></item><item><author>shock</author><text>I am very diligent about applying updates as soon as I&#x27;m able and generally read the changelogs of the updates I&#x27;m applying in Ubuntu&#x27;s Software Updater.<p>One thing I will not do is willingly allow somebody else a way to deploy and execute code on my computer without my say so (which snap is).<p>After reading the whole thread at <a href="https:&#x2F;&#x2F;forum.snapcraft.io&#x2F;t&#x2F;disabling-automatic-refresh-for-snap-from-store&#x2F;707" rel="nofollow">https:&#x2F;&#x2F;forum.snapcraft.io&#x2F;t&#x2F;disabling-automatic-refresh-for...</a> and seeing Gustavo Niemeyer&#x27;s arrogance (we know better than you when you should be applying updates) I will be voting with my feet and will be installing Pop!_OS instead of Ubuntu, and if snapd is present I will remove it.<p>The stated goal of Niemeyer, to have users use updated software, would have been fulfilled in my case if I had a way to see what updates would be applied beforehand, instead of the updates being force-installed.<p>Lengthy dialog with Niemeyer in the forum thread seems to have been a waste of time for all the people who participated trying to convince him to allow disabling of force-installed updates so I suggest you do the same as me and vote with your feet!</text></item></parent_chain><comment><author>canonicalwhistl</author><text>Sorry, but as a fellow Canonical employee, speaking from a throwaway obviously, it&#x27;s evident to me that you&#x27;re simply not telling the truth here.<p>You know just as well as I do that if you criticize Snap within the company, you get fired. Especially if Mark overhears you. There is no room for criticism. You either drink the koolaid or you shutup. So, no, sorry, we&#x27;re going to keep pumping out Snap and those who don&#x27;t fall inline will just fall out of the company. This is how we&#x27;ve always done these things, despite it failing repeatedly, and Snap is no exception. Actually, Snap is in particular no exception, given how hard it&#x27;s being pushed by top level management.<p>[An aside from the main point of this comment: your point 3 is nonsense, and any security guy will tell you the same. For packages that the main sudo-ing user executes, sandboxed or not, there still is effectively no difference between that and root. Snap&#x27;s sandbox is alpha quality at best, and major platform hurdles remain to make it capable of doing anything remotely useful. Say no to auto-updating snap backdoors. Please. There&#x27;s a reason why Linux has thrived and benefited with its vetted-by-distros traditional package managers.]</text></comment> | <story><title>Ubuntu 20.04 LTS’ snap obsession has snapped me off of it</title><url>https://jatan.blog/2020/05/02/ubuntu-snap-obsession-has-snapped-me-off-of-it/</url></story><parent_chain><item><author>kikoreis</author><text>It&#x27;s probably not a surprise to you, but this is a hotly debated topic inside Canonical. And I apologize for that thread, as it really doesn&#x27;t represent our best attempt at external debate.<p>Changing a paradigm usually involves pushing the envelope and breaking some existing assumptions; systemd is everybody&#x27;s favorite example of that in the Linux world. The root of this issue with snaps is the trade-off between built-in security and user control. Some points to consider:<p>1. Browsers like FF and Chromium [on Windows] simply self-update, and disabling that requires configuration. So there is at least some precedent for taking the position that user applications should just update themselves. Server apps are more complex and are a strong argument counter to the existing behavior, as is the fact that many apps cannot be refreshed without user impact.<p>2. Ubuntu, since 16.04 LTS, ships with unattended-upgrades enabled, which means that for debian packages the default behavior is already auto-updating (although automated reboots are not enabled by default, as that would be crazy for the general purpose case). That feels like the correct default, too, given the risk of running code exposed to exploitable, public CVEs — and how reluctant users (like my dad and my wife!) are to click on &quot;Install now&quot; in the update-manager dialog.<p>3. Debian package updates run as root. Snap updates run in userspace, and confined. So in principle the risk exposure for snap updates is much smaller. And snaps do have an auto-rollback mechanism for failed updates [a]. Counter to that argument is the fact that snaps are meant to be under third-party control, and that there is no clear mechanism to separate security patches vs updates which you get with the debian pocket mechanism (i.e. focal-security vs focal-updates).<p>The lack of any official [b] means of user control over the snap auto-update mechanism feels wrong to many of us, including me. And while we may seem somewhat opaque in these debates, the feedback we get in threads like this one (and the snapcraft.io one) actually feeds into our decision making. So please do keep pushing on this topic and we&#x27;ll do our part internally.<p>[a] See <a href="https:&#x2F;&#x2F;kyrofa.com&#x2F;posts&#x2F;snap-updates-automatic-rollbacks" rel="nofollow">https:&#x2F;&#x2F;kyrofa.com&#x2F;posts&#x2F;snap-updates-automatic-rollbacks</a> for a detailed guide on this topic. Of course, if your snap refreshes and you hate the new version, downgrading isn&#x27;t quite always possible.<p>[b] There are ways to, hmmm, control auto-updating (i.e. refresh.metered, refresh.hold) if you really want to; that thread has a few. That doesn&#x27;t help the debate, but I&#x27;m sharing in case someone has a technical need for it.</text></item><item><author>shock</author><text>I am very diligent about applying updates as soon as I&#x27;m able and generally read the changelogs of the updates I&#x27;m applying in Ubuntu&#x27;s Software Updater.<p>One thing I will not do is willingly allow somebody else a way to deploy and execute code on my computer without my say so (which snap is).<p>After reading the whole thread at <a href="https:&#x2F;&#x2F;forum.snapcraft.io&#x2F;t&#x2F;disabling-automatic-refresh-for-snap-from-store&#x2F;707" rel="nofollow">https:&#x2F;&#x2F;forum.snapcraft.io&#x2F;t&#x2F;disabling-automatic-refresh-for...</a> and seeing Gustavo Niemeyer&#x27;s arrogance (we know better than you when you should be applying updates) I will be voting with my feet and will be installing Pop!_OS instead of Ubuntu, and if snapd is present I will remove it.<p>The stated goal of Niemeyer, to have users use updated software, would have been fulfilled in my case if I had a way to see what updates would be applied beforehand, instead of the updates being force-installed.<p>Lengthy dialog with Niemeyer in the forum thread seems to have been a waste of time for all the people who participated trying to convince him to allow disabling of force-installed updates so I suggest you do the same as me and vote with your feet!</text></item></parent_chain><comment><author>InternetOfStuff</author><text>Let me point out: to me, auto-updating isn&#x27;t even the crucial issue (I use unattended-upgrades as well, so whatever).<p>Yes, functionality and workflows around installation and updates are still insufficient for many use cases, but that could have been ironed out given enough time.<p>But what you messed up badly, IMO, was to force-migrate packages to Snap in an LTS release before it was ready.<p>Had you waited until Ubuntu 20.10, I&#x27;d have been more forgiving. But you (collectively) were so eager to get this in before the window closed for another two years.<p>If you had made Snap a compelling product, even LTS users might have voluntarily migrated to snaps once they saw how good it was. Now you&#x27;ve kind of pulled off the opposite.<p>Sadly the ship has sailed: Both in general, since you&#x27;ve pushed so heavily for Snap in a LTS release when it simply wasn&#x27;t ready yet. And for me personally, where the forced installation of Snaps by some debs (notably Chromium) broke my trust significantly enough that I turned my back on Ubuntu after over a decade.<p>Not only is the Chromium Snap dog slow, it also can&#x27;t see my NFS shares. So the snap version is objectively worse, at least for now.<p>But if I install a deb, I expect to get a deb. You don&#x27;t want to offer it anymore, fine, take it out of the repo. But sneakily migrating me to a snap, and not even notifying me, is just trust-breaking.</text></comment> |
6,381,447 | 6,381,072 | 1 | 2 | 6,379,928 | train | <story><title>New NSA Leak Shows MITM Attacks Against Major Internet Services</title><url>https://www.schneier.com/blog/archives/2013/09/new_nsa_leak_sh.html</url></story><parent_chain><item><author>josteink</author><text>If this is true, and that NSA has been MITMing providers like Google, they are undermining the already shabby trust the US cloud-industry has attempted to build. I doubt Google and friends are very happy about that, since that&#x27;s their one big basket where all the money comes in.<p>NSA in their eagerness to do rampant spying on everyone have had quite some collateral. They have decided to compromise the <i>one</i> thing which allows us to communicate securely on the internet: trust.<p>Right now we need to find out which (root?) CAs are compromised by the NSA. Long term it would probably be a very wise decision to revoke <i>any</i> US-based CA from the default trusted-list of browsers and OSes.<p>We cannot have untrustworthy CAs in a system based on trust. That&#x27;s simply not an option.<p>Edit: As I&#x27;ve been pondering for a while (and which was also pointed out on reddit) we now have a situation where self-signed certs are more secure than CA-issued ones. They are the only ones you know can&#x27;t be faked. How backwards is that?<p>The NSA is ruining the internet one piece at a time. The NSA needs to be dismantled.</text></item></parent_chain><comment><author>semenko</author><text>The HSTS commits &#x2F;maybe&#x2F; suggest that Google thinks a <i>Verisign</i> intermediate was signing MITMs for Google properties. They just blacklisted &quot;VeriSignClass3SSPIntermediateCA&quot;<p>See: <a href="https://chromiumcodereview.appspot.com/23523051" rel="nofollow">https:&#x2F;&#x2F;chromiumcodereview.appspot.com&#x2F;23523051</a><p>Note that the associated bug is private (<a href="https://code.google.com/p/chromium/issues/detail?id=173460" rel="nofollow">https:&#x2F;&#x2F;code.google.com&#x2F;p&#x2F;chromium&#x2F;issues&#x2F;detail?id=173460</a>).<p>There&#x27;s a good explanation of the &quot;bad_static_spki_hashes&quot; parameter here: <a href="http://ritter.vg/blog-cas_and_pinning.html" rel="nofollow">http:&#x2F;&#x2F;ritter.vg&#x2F;blog-cas_and_pinning.html</a></text></comment> | <story><title>New NSA Leak Shows MITM Attacks Against Major Internet Services</title><url>https://www.schneier.com/blog/archives/2013/09/new_nsa_leak_sh.html</url></story><parent_chain><item><author>josteink</author><text>If this is true, and that NSA has been MITMing providers like Google, they are undermining the already shabby trust the US cloud-industry has attempted to build. I doubt Google and friends are very happy about that, since that&#x27;s their one big basket where all the money comes in.<p>NSA in their eagerness to do rampant spying on everyone have had quite some collateral. They have decided to compromise the <i>one</i> thing which allows us to communicate securely on the internet: trust.<p>Right now we need to find out which (root?) CAs are compromised by the NSA. Long term it would probably be a very wise decision to revoke <i>any</i> US-based CA from the default trusted-list of browsers and OSes.<p>We cannot have untrustworthy CAs in a system based on trust. That&#x27;s simply not an option.<p>Edit: As I&#x27;ve been pondering for a while (and which was also pointed out on reddit) we now have a situation where self-signed certs are more secure than CA-issued ones. They are the only ones you know can&#x27;t be faked. How backwards is that?<p>The NSA is ruining the internet one piece at a time. The NSA needs to be dismantled.</text></item></parent_chain><comment><author>lambda</author><text>Didn&#x27;t the slides show that it was the Diginotar compromise?<p>&gt; We cannot have untrustworthy CAs in a system based on trust. That&#x27;s simply not an option.<p>The entire CA trust model is broken. In the trust model, any CA can issue certs for any domain; so a Chinese CA could issue Google certs, or a US CA could issue certs for the Dutch government.<p>Self-signed certs with certificate pinning are indeed more likely to be secure than CA certs. Of course, you can do both; CA signed certs (which does add a small amount of trustworthiness, as the CA is at least supposed to do a little work to verify a real-world identity), and use certificate pinning to avoid this kind of attack.</text></comment> |
3,391,085 | 3,390,947 | 1 | 3 | 3,390,719 | train | <story><title>Institutional memory and reverse smuggling</title><url>http://wrttn.in/04af1a</url></story><parent_chain></parent_chain><comment><author>16s</author><text>I've seen memory drains during down-turns in the economy. The company will offer the oldest, most-experienced, highest paid employees a buy-out or they'll offer them five years extra pension/retirement if they leave now. Mgt figures that consultants can be hired if they ever need X, Y or Z done again at a fraction of the cost of the employees.<p>Many senior employees accept the offers, and then later mgt realizes that 95% of their Fortran or Cobol (or name your old programming language/product) experience has vanished. Thank god the software is mostly in maintenance mode, but client problems do still arise and what once took 15 mins to fix, now requires a week and phone calls to retirees begging them to help fix a client problem. They'll pay them loads of money too just for a few minutes of work.<p>Consultants turn out to lack the domain specific knowledge required to fix the problem.<p>Bottom line is that sometimes, mgt is so focused on hitting short-term financial goals, that they lose site of the big, long-term picture. Business needs less 20 something MBAs who only see this quarterly report and more managers who understand that business is a decades long proposition and that senior employees are key to maintaining an edge and passing along knowledge.</text></comment> | <story><title>Institutional memory and reverse smuggling</title><url>http://wrttn.in/04af1a</url></story><parent_chain></parent_chain><comment><author>DanBC</author><text>In theory some quality systems (ISO 900x etc) should help with institutional memory.<p>Bob has a job; he performs a series of tasks to do that job; he writes down what he does for each task, including what information (also product) comes in (and who from) and what information (also product) goes out (and who to), also including all the documentation he needs to complete for each task.<p>Someone else edits that puts it in the company QA manual. In future new employees just read that documentation, and maybe do a bit of shadowing of existing employees.<p>Unfortunately, that's not what happens. What happens is that Bob has a job, but Charles (Bob's boss) writes a bunch of stuff that he thinks Bob should be doing. And he doesn't write sentences like "Set the machine for 190 degree Celsius. Place widgets in machine when it's at temperature. Leave widgets in machine for four hours." but he writes abstract ambiguous business speak that people can't use to actually do the job. Then Edwin (Charles's boss) adds another bunch of stuff. Then that gets edited into a god-awful mish-mash. The people who did the software (with the "help" of Edwin) add some stuff about information. Bob gets to work to an impenetrable document that bears little relation to his actual work flow.</text></comment> |
5,097,731 | 5,097,616 | 1 | 2 | 5,097,421 | train | <story><title>Basecamp Personal</title><url>http://37signals.com/svn/posts/3406-launch-basecamp-personal-the-basecamp-for-all-your-projects-outside-of-work</url><text></text></story><parent_chain><item><author>bluetidepro</author><text>It would be a shame to see people sink their money in this without realizing there are way better services out there for this type of thing. For example, Evernote Premium is just $5.00 per month or $45.00 per year and you get way better features, syncing across platforms, storage space, sharing, etc. That [Evernote example] costs less than 2 Basecamp Personal projects.<p>I really think they should look into lowering the pricing to make this product more competitive. 37signals seems to be coming out with some crumby products lately. First Breeze, and now this. <i>Sighhh.</i></text></item></parent_chain><comment><author>talkingquickly</author><text>I'm not sure if the two products are comparable though, I love Evernote for unstructured content but to me Basecamp has always been more structured.<p>In particular for keep track of todo lists (along with audit trails of who's done what) and allowing email notification and response of discussions around todo's and documents.<p>I know you can do some of this to an extent in Evernote (e.g. todo lists) but I'd be interested to hear more about how you use Evernote such that it can be a Basecamp replacement?</text></comment> | <story><title>Basecamp Personal</title><url>http://37signals.com/svn/posts/3406-launch-basecamp-personal-the-basecamp-for-all-your-projects-outside-of-work</url><text></text></story><parent_chain><item><author>bluetidepro</author><text>It would be a shame to see people sink their money in this without realizing there are way better services out there for this type of thing. For example, Evernote Premium is just $5.00 per month or $45.00 per year and you get way better features, syncing across platforms, storage space, sharing, etc. That [Evernote example] costs less than 2 Basecamp Personal projects.<p>I really think they should look into lowering the pricing to make this product more competitive. 37signals seems to be coming out with some crumby products lately. First Breeze, and now this. <i>Sighhh.</i></text></item></parent_chain><comment><author>TylerE</author><text>$25/forever is already lower than $5/month or $45/year</text></comment> |
22,634,615 | 22,634,638 | 1 | 2 | 22,633,570 | train | <story><title>CA governor projecting 25.5M COVID19 cases in CA in 8 weeks [pdf]</title><url>https://www.gov.ca.gov/wp-content/uploads/2020/03/3.18.20-Letter-USNS-Mercy-Hospital-Ship.pdf</url></story><parent_chain><item><author>fyp</author><text>Why did we give up on containment?<p>China and South Korea have shown that it&#x27;s possible. China capped out at only 100k infected for a population of 1.4 billion.<p>Aiming to let 56% of your population get infected of which more than 3% will die is NOT the solution.<p>China&#x27;s strategy seems simple enough. Close off borders of a region, stamp out all existing cases with aggressive testing, then keep the region at 0 cases by requiring mandatory 2 week quarantine before letting anyone in. Do this one region at a time until your country is all clean. Now their biggest problem is teaching the rest of the world this strategy.</text></item></parent_chain><comment><author>jmcgough</author><text>We have an extreme wealth disparity with many having no savings and no social safety net. We can&#x27;t force everyone to stay home for months, the economy would collapse.<p>China maintained draconian levels of control - citizens had cards with their risk level, and were tested frequently when they went to a public space. Have symptoms or some reason to believe you might be infected? You were quarantined from your family and not released until 4+ hours later. If they needed to be kept overnight, they had special hotels to quarantine people in. Citizens there actually listen to what the government tells them to do, and dissent is stamped out. In the states, a lot of people openly don&#x27;t trust the government.<p>If we tried to control peoples&#x27; lives like that, our citizens would riot. You&#x27;d have armed citizens refuse to leave their homes.<p>They also did things that are unimaginable here - they built an entire hospital in 10 days. They have infrastructure and equipment from SARS that they were able to mobilize.<p>We aren&#x27;t China, and we can&#x27;t accomplish what they&#x27;ve done. Not in eight weeks. We are not prepared for this.</text></comment> | <story><title>CA governor projecting 25.5M COVID19 cases in CA in 8 weeks [pdf]</title><url>https://www.gov.ca.gov/wp-content/uploads/2020/03/3.18.20-Letter-USNS-Mercy-Hospital-Ship.pdf</url></story><parent_chain><item><author>fyp</author><text>Why did we give up on containment?<p>China and South Korea have shown that it&#x27;s possible. China capped out at only 100k infected for a population of 1.4 billion.<p>Aiming to let 56% of your population get infected of which more than 3% will die is NOT the solution.<p>China&#x27;s strategy seems simple enough. Close off borders of a region, stamp out all existing cases with aggressive testing, then keep the region at 0 cases by requiring mandatory 2 week quarantine before letting anyone in. Do this one region at a time until your country is all clean. Now their biggest problem is teaching the rest of the world this strategy.</text></item></parent_chain><comment><author>icedistilled</author><text>&gt;stamp out all existing cases with aggressive testing,<p>We still lack the capacity for even testing all the people showing significant symptoms. That is why we can&#x27;t contain it.<p>The rejection of the WHO tests in order to belatedly come up with our own tests is a massive scandal.</text></comment> |
4,821,596 | 4,821,626 | 1 | 2 | 4,821,488 | train | <story><title>Introducing GNU Guix</title><url>http://lists.gnu.org/archive/html/gnu-system-discuss/2012-11/msg00000.html</url></story><parent_chain></parent_chain><comment><author>rlpb</author><text>Debian's dpkg and apt are both GPL2+. What's the reason they are reinventing the wheel here? Is there some kind of licence incompatibility that the GNU project cares about? Is there some kind of major architectural difference? Why is it important enough to fragment Free Software developers over?<p>I feel that this should be answered in an FAQ, but I can't find the answer anywhere.</text></comment> | <story><title>Introducing GNU Guix</title><url>http://lists.gnu.org/archive/html/gnu-system-discuss/2012-11/msg00000.html</url></story><parent_chain></parent_chain><comment><author>simonh</author><text>&#62; A distribution built by GNU hackers is a great opportunity to improve consistency and cohesion in GNU!<p>Because the existing fragmentation of GNU package management is too confusing, so we need a new standard for everyone to rally round.<p>[<a href="http://xkcd.com/927/" rel="nofollow">http://xkcd.com/927/</a>]</text></comment> |
1,997,070 | 1,996,365 | 1 | 3 | 1,995,567 | train | <story><title>The Viral Me: Inside Y Combinator </title><url>http://www.gq.com/news-politics/big-issues/201012/viral-me-silicon-valley-social-networking-devin-friedman</url></story><parent_chain><item><author>siddhant</author><text>On page 3,<p><i>One of the founders of a YC company called 1000Memories.com (it's FB for dead people, only more interesting) says he heard FB can already tell when you're about to break up with someone: certain communication patterns emerge.</i><p>Yes, I know that the amount of data people share on Facebook is staggering, but, you've <i>got</i> to be kidding me!</text></item></parent_chain><comment><author>patio11</author><text>I totally wouldn't put it past them, with the proviso that the proper claim is that they are able to predict when someone goes from "in a relationship" on FB to "single" or "in a relationship [with someone else" on FB, and this isn't perfect but it is much better than you'd expect from random chance.<p>For example, I think that Facebook could identity a pool of 100,000 users tomorrow and predict a breakup within the next two weeks, and be right for over 20% of them. That is statistically improbable unless you expect relationships to average about 10 weeks. (Yeah yeah, handwavy math there. <i>Wave wave</i>.)<p>How you'd do this? The same way you do any AI problem: cheat like a mofo until it looks like a problem we've already solved. For example, come up with a feature space of, say, 100 things which are easily algorithmically checkable: messaged boyfriend in past day, messaged boyfriend more than 10 times in last day, messaged boyfriend in last week, messaged boy other than boyfriend in last day, ..., changed sexual orientation listed in FB, changed residence listed in FB, ... went off to college, whatever. Assign each factor a random number from 1 to 100.<p>Now, construct a Hadoop cluster, grab your favorite million Facebook accounts, and use any AI technique you like (simulated annealing, GA, whatever) to play with those scores until you find a decent fit where the dot product of that vector and a vector of binary tests against a user delivers high scores for people who break up and low scores for people who don't.<p>Then, grab a hundred million Facebookers, take the dot product for each of them against your best performing vector, and print out the 100k with the highest scores.<p>This will work. Indeed, it almost can't not work, if any of your constituents of the feature vector captured any useful information. (P.S. The experimental design here is ridiculously biased in favor of success. Real life sometimes is -- it is certainly true for FICO, for example, since success is "beats a human underwriter" and human underwriters <i>suck</i>, what with their sucky salaries and sucky accuracy and sucky inability to process a hundred thousand applications an hour.)</text></comment> | <story><title>The Viral Me: Inside Y Combinator </title><url>http://www.gq.com/news-politics/big-issues/201012/viral-me-silicon-valley-social-networking-devin-friedman</url></story><parent_chain><item><author>siddhant</author><text>On page 3,<p><i>One of the founders of a YC company called 1000Memories.com (it's FB for dead people, only more interesting) says he heard FB can already tell when you're about to break up with someone: certain communication patterns emerge.</i><p>Yes, I know that the amount of data people share on Facebook is staggering, but, you've <i>got</i> to be kidding me!</text></item></parent_chain><comment><author>ig1</author><text>Nah, I'm pretty sure that's just a Chinese Whisper that originated from David McCandless work in data mining breakups on Facebook. It can tell you what the most popular day to breakup is, but it can't predict when a couple is going to breakup.<p>However that said it probably is possible to predict breakups with communication data. You could probably even do it with an iphone app, breakups tend to follow certain events (like drop in respect, distancing, etc.) that can detected in vocal patterns.</text></comment> |
37,001,053 | 37,000,993 | 1 | 2 | 36,998,643 | train | <story><title>The Coming Enshittification of Public Libraries</title><url>https://karawynn.substack.com/p/the-coming-enshittification-of-public-libraries</url></story><parent_chain><item><author>yaky</author><text>I worked at OverDrive. The stark contrast between the sugary-sweet facade of “helping the libraries and readers” and the ridiculous amounts of money the company makes from these same libraries is quite depressing.
Much of their profits come from charging 30%+ on top of publishers’ prices (which are already high for libraries). This plays into their hand very well - publishers get the blame for prices, yet OverDrive still benefits from it.
As for Libby’s bad UI - it was made by a single very opinionated person.</text></item></parent_chain><comment><author>stinkytaco</author><text>This is interesting to hear. I&#x27;ve always found that Overdrive does live up to its reputation of being a library focused company. The books aren&#x27;t cheaper on Cloudlibrary or Axis360 and Overdrive offers the best user experience by a mile, even with all the warts on Libby. They are generally responsive to issues and supportive of concerns (they provided us a ton of data related to the McMillan boycott, for example). That may be in their self interest, but that&#x27;s how this is supposed to work, right? They make money, we serve our customers. None of that seems sinister so I&#x27;m curious what else is going on behind the scenes.</text></comment> | <story><title>The Coming Enshittification of Public Libraries</title><url>https://karawynn.substack.com/p/the-coming-enshittification-of-public-libraries</url></story><parent_chain><item><author>yaky</author><text>I worked at OverDrive. The stark contrast between the sugary-sweet facade of “helping the libraries and readers” and the ridiculous amounts of money the company makes from these same libraries is quite depressing.
Much of their profits come from charging 30%+ on top of publishers’ prices (which are already high for libraries). This plays into their hand very well - publishers get the blame for prices, yet OverDrive still benefits from it.
As for Libby’s bad UI - it was made by a single very opinionated person.</text></item></parent_chain><comment><author>tgv</author><text>Like ProQuest and its subsidiaries. They exploit public and academic libraries, largely because they have almost a monopoly, and it&#x27;s very costly to extract the data and import it in another platform.</text></comment> |
5,855,731 | 5,855,883 | 1 | 3 | 5,854,818 | train | <story><title>The Irrationality of Giving Up This Much Liberty to Fight Terror</title><url>http://www.theatlantic.com/politics/archive/2013/06/the-irrationality-of-giving-up-this-much-liberty-to-fight-terror/276695/</url><text></text></story><parent_chain><item><author>DanielBMarkham</author><text>I completely agree that we&#x27;ve overreacted, but I&#x27;ve always rejected this argument, and here&#x27;s why: Terrorism is not about numerical risk, it is about <i>public perception</i>.<p>That means that it plays in the same game as everything else in the PR world: politics, advertising, social signaling, and so forth. The last thing it has anything to do with is logic.<p>It would be great if we could tally up all the things that kill us and spend proportionally on those. It&#x27;s the logical thing to do. Heart disease would come first, then cancer, and so on. But instead we spend and give attention to those things that the public perceives we should: AIDS research, nuclear war deterrence, terrorism.<p>And if you think about it, that&#x27;s the way it ought to be. Spending and making laws are all about the consent of the governed, doing things they want. They&#x27;re not about math or logic.<p>The problem here is that, with the Cold War over, the defense and intelligence industry saw 9-11 as a call to arms. They&#x27;re going to go out and do things a good defense and intelligence industry should. And as Americans we have traditionally been forgiving of having our civil liberties temporarily trampled on during times of war.<p>But you can&#x27;t have a war forever. A democracy cannot survive this. Instead of the natural overreaction to a war that always happened, we started creating permanent infrastructure to address all terrorism, forever. We&#x27;re fighting a war with nobody to surrender, and no amount of spending or government monitoring will ever be enough.<p>The original laws around 9-11 were temporary, and for a very good reason. But somehow politics has gotten to the point where terrorism is the new third-rail: some national politicians might grandstand a bit, but nobody is going to do anything except for give the security state apparatus whatever it says it needs. Otherwise they&#x27;d be thrown out of office. Public perception demands it.<p>Adding up numbers has nothing to do with it, unless you&#x27;re using them to make some kind of <i>persuasive argument</i>, and then we&#x27;re right back to public perception and politics. You&#x27;re in the same boat as those who asked for more cancer research instead of AIDS research. Different people, rightly, see things differently, and everybody deserves to be represented. We&#x27;re running a country, not an insurance agency.</text></item></parent_chain><comment><author>belorn</author><text>&gt; <i>Spending and making laws are all about the consent of the governed.</i><p>Laws should be about the <i>informed</i> consent of the governed. Security built on a lie is still a lie even if people feel more safe. During the first days of 9-11, the military sent personal down to the airport to reinforce peoples perception of safe travel. What they did not tell anyone at the time, was that the guns did not have any ammunition in them. Instead, the military were basically posing as an &quot;armed force&quot;, because having guns <i>with</i> ammunition at airport would then actually create a security issue at the airports.<p>The security theater of the US feels somewhat like a doctor who has started to only give out placebos to his patients. If anyone feels better, sing praises, and if anyone get worse, give them more sugar pills. Soon, everyone start to get sick on the sugar alone, while the sugar pill manufacturer crave for more sick people.<p>The security theater from 9-11 has gone on long enough. People are not going to feel more safe from it, and will just get sicker on the solution.</text></comment> | <story><title>The Irrationality of Giving Up This Much Liberty to Fight Terror</title><url>http://www.theatlantic.com/politics/archive/2013/06/the-irrationality-of-giving-up-this-much-liberty-to-fight-terror/276695/</url><text></text></story><parent_chain><item><author>DanielBMarkham</author><text>I completely agree that we&#x27;ve overreacted, but I&#x27;ve always rejected this argument, and here&#x27;s why: Terrorism is not about numerical risk, it is about <i>public perception</i>.<p>That means that it plays in the same game as everything else in the PR world: politics, advertising, social signaling, and so forth. The last thing it has anything to do with is logic.<p>It would be great if we could tally up all the things that kill us and spend proportionally on those. It&#x27;s the logical thing to do. Heart disease would come first, then cancer, and so on. But instead we spend and give attention to those things that the public perceives we should: AIDS research, nuclear war deterrence, terrorism.<p>And if you think about it, that&#x27;s the way it ought to be. Spending and making laws are all about the consent of the governed, doing things they want. They&#x27;re not about math or logic.<p>The problem here is that, with the Cold War over, the defense and intelligence industry saw 9-11 as a call to arms. They&#x27;re going to go out and do things a good defense and intelligence industry should. And as Americans we have traditionally been forgiving of having our civil liberties temporarily trampled on during times of war.<p>But you can&#x27;t have a war forever. A democracy cannot survive this. Instead of the natural overreaction to a war that always happened, we started creating permanent infrastructure to address all terrorism, forever. We&#x27;re fighting a war with nobody to surrender, and no amount of spending or government monitoring will ever be enough.<p>The original laws around 9-11 were temporary, and for a very good reason. But somehow politics has gotten to the point where terrorism is the new third-rail: some national politicians might grandstand a bit, but nobody is going to do anything except for give the security state apparatus whatever it says it needs. Otherwise they&#x27;d be thrown out of office. Public perception demands it.<p>Adding up numbers has nothing to do with it, unless you&#x27;re using them to make some kind of <i>persuasive argument</i>, and then we&#x27;re right back to public perception and politics. You&#x27;re in the same boat as those who asked for more cancer research instead of AIDS research. Different people, rightly, see things differently, and everybody deserves to be represented. We&#x27;re running a country, not an insurance agency.</text></item></parent_chain><comment><author>gustavo_duarte</author><text>I think the Economist did a great job on this in their recent piece:<p><a href="http:&#x2F;&#x2F;www.economist.com&#x2F;blogs&#x2F;democracyinamerica&#x2F;2013&#x2F;06&#x2F;why-we-spy" rel="nofollow">http:&#x2F;&#x2F;www.economist.com&#x2F;blogs&#x2F;democracyinamerica&#x2F;2013&#x2F;06&#x2F;wh...</a><p>Think about the incentives to the _President_ (whoever that is) to NOT let an attack happen, no matter what the cost. As Daniel says, it&#x27;s not about numerical risk or objective damage, it&#x27;s perception. Obama would have done anything not to have an attack during his terms.<p>And that&#x27;s the really sad part. Due to the political process, different interests, and so on, the terrorists WERE able to inflict grievous damage to us as a society.</text></comment> |
16,703,134 | 16,702,778 | 1 | 3 | 16,701,913 | train | <story><title>Facebook pauses app reviews, disables new user authorizations</title><url>https://developers.facebook.com/blog/post/2018/03/26/facebook-platform-changes/</url></story><parent_chain><item><author>IBM</author><text>Apple got this right from the beginning despite years of criticism about the &quot;walled garden&quot;. They took arrows for years: all the &quot;open always wins&quot; from the FOSS types, all the press coverage of some app developer crying about App Store rejections or onerous rules.<p>They didn&#x27;t get it wrong because they know who butters their bread: customers. Developers are rightly prioritized last.<p>Fun to give this Paul Graham essay a read again [1].<p>[1] <a href="http:&#x2F;&#x2F;www.paulgraham.com&#x2F;apple.html" rel="nofollow">http:&#x2F;&#x2F;www.paulgraham.com&#x2F;apple.html</a></text></item><item><author>miracle2k</author><text>The so-called &quot;data breach&quot; was always in reality a by-product of an open platform that hundreds of thousands of developers could easily build apps on top. You may err on the side of &quot;more reviews&quot; or &quot;less powerful API&quot;, but in the end, those ideals are in tension. The more open the platform, the more open to this kind of &quot;breach&quot;.<p>People who believe in the idea in this kind of platform having an API should have long ago spoken up in Facebooks defense. This is exactly what I was afraid would happen, and I expect worse to come from this &quot;platform review&quot;. Given the kind of media coverage here, Facebook seems to have more to lose than to gain from letting random Hacker News kids build on their platform. And if so, they won&#x27;t in the future.</text></item></parent_chain><comment><author>aylmao</author><text>&gt; Apple got this right from the beginning despite years of criticism about the &quot;walled garden&quot;.<p>Being a walled garden is independent of privacy. The calendar app on macOS Calendar app allows me to share my calendars in an open format (ICAL) and interoperates with other calendar apps through that specification. It respects my privacy by not sharing anything I don&#x27;t ask it to without being &quot;walled&quot;.<p>Signal is open and secure; iMessage could be a non-proprietary format and remain just as private.<p>&gt; all the press coverage of some app developer crying about App Store rejections or onerous rules.<p>As far as I&#x27;m aware a lot of these weren&#x27;t for privacy matters [1] and are sometimes a little much [2] (this one is specially absurd: [3]).<p>[1]: <a href="https:&#x2F;&#x2F;techcrunch.com&#x2F;2017&#x2F;12&#x2F;08&#x2F;apples-widened-ban-on-templated-apps-is-wiping-small-businesses-from-the-app-store&#x2F;" rel="nofollow">https:&#x2F;&#x2F;techcrunch.com&#x2F;2017&#x2F;12&#x2F;08&#x2F;apples-widened-ban-on-temp...</a><p>[2]: <a href="https:&#x2F;&#x2F;www.theverge.com&#x2F;2018&#x2F;2&#x2F;8&#x2F;16992830&#x2F;apple-emoji-crackdown-cross-platform-apps-slack-whatsapp" rel="nofollow">https:&#x2F;&#x2F;www.theverge.com&#x2F;2018&#x2F;2&#x2F;8&#x2F;16992830&#x2F;apple-emoji-crack...</a><p>[3]: <a href="https:&#x2F;&#x2F;medium.com&#x2F;@alariccole&#x2F;apple-literally-stole-my-thunder-253aed27a455" rel="nofollow">https:&#x2F;&#x2F;medium.com&#x2F;@alariccole&#x2F;apple-literally-stole-my-thun...</a><p>PS:<p>&gt; all the &quot;open always wins&quot; from the FOSS types<p>I don&#x27;t think that means what you think it means. FOSS and privacy are tangential matters.</text></comment> | <story><title>Facebook pauses app reviews, disables new user authorizations</title><url>https://developers.facebook.com/blog/post/2018/03/26/facebook-platform-changes/</url></story><parent_chain><item><author>IBM</author><text>Apple got this right from the beginning despite years of criticism about the &quot;walled garden&quot;. They took arrows for years: all the &quot;open always wins&quot; from the FOSS types, all the press coverage of some app developer crying about App Store rejections or onerous rules.<p>They didn&#x27;t get it wrong because they know who butters their bread: customers. Developers are rightly prioritized last.<p>Fun to give this Paul Graham essay a read again [1].<p>[1] <a href="http:&#x2F;&#x2F;www.paulgraham.com&#x2F;apple.html" rel="nofollow">http:&#x2F;&#x2F;www.paulgraham.com&#x2F;apple.html</a></text></item><item><author>miracle2k</author><text>The so-called &quot;data breach&quot; was always in reality a by-product of an open platform that hundreds of thousands of developers could easily build apps on top. You may err on the side of &quot;more reviews&quot; or &quot;less powerful API&quot;, but in the end, those ideals are in tension. The more open the platform, the more open to this kind of &quot;breach&quot;.<p>People who believe in the idea in this kind of platform having an API should have long ago spoken up in Facebooks defense. This is exactly what I was afraid would happen, and I expect worse to come from this &quot;platform review&quot;. Given the kind of media coverage here, Facebook seems to have more to lose than to gain from letting random Hacker News kids build on their platform. And if so, they won&#x27;t in the future.</text></item></parent_chain><comment><author>whatshisface</author><text>An API into a closed service is no more FOSSy than a graphical user interface into a closed desktop app. I don&#x27;t really understand the comparison, what do you think motivates it?<p>Facebook has open-sourced a few internal projects, but none of them had much to do with our personal data.<p>In fact, it&#x27;s difficult to blame the API when the problem was that the data was collected in the first place. Surely Zuckerberg has some political opinions of his own, if CA hadn&#x27;t triggered this media storm what would have stopped him from supporting his own favorite candidate internally? In fact, what&#x27;s stopping him from doing that right now? Would it even be illegal?</text></comment> |
27,538,218 | 27,538,279 | 1 | 2 | 27,537,040 | train | <story><title>PHP has been removed in macOS Monterey</title><url>https://developer.apple.com/forums/thread/681907</url></story><parent_chain><item><author>tpush</author><text>Genuine question: is there anyone (corporate or not) that cares that macOS is a certified Unix?</text></item><item><author>Stranger43</author><text>Perl is requires for apple to maintain their unix(tm) certification. And while they likely dont see it as core to what they want macos to become it would be an news story in the more sensationalist part of the IT press if they were to drop it. and big sur is still listed as certified
<a href="https:&#x2F;&#x2F;www.opengroup.org&#x2F;openbrand&#x2F;register&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.opengroup.org&#x2F;openbrand&#x2F;register&#x2F;</a>.</text></item><item><author>darrenf</author><text>Regarding Perl, rather than removing it Apple actually <i>upgraded</i> it – from 5.28 to 5.30 – in Big Sur 11.3. I wasn&#x27;t the only one briefly surprised and bitten by it:<p>• <a href="https:&#x2F;&#x2F;github.com&#x2F;Homebrew&#x2F;brew&#x2F;issues&#x2F;10127#issuecomment-828121139" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Homebrew&#x2F;brew&#x2F;issues&#x2F;10127#issuecomment-8...</a><p>• <a href="https:&#x2F;&#x2F;github.com&#x2F;Homebrew&#x2F;brew&#x2F;issues&#x2F;11275" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Homebrew&#x2F;brew&#x2F;issues&#x2F;11275</a></text></item><item><author>WalterGR</author><text>Xcode 11 Release Notes (<a href="https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;xcode-release-notes&#x2F;xcode-11-release-notes" rel="nofollow">https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;xcode-release-note...</a>)<p>&quot;Scripting language runtimes such as Python, Ruby, and Perl are included in macOS for compatibility with legacy software. In future versions of macOS, scripting language runtimes won’t be available by default, and may require you to install an additional package. If your software depends on scripting languages, it’s recommended that you bundle the runtime within the app. (49764202)&quot;<p>Found via <a href="https:&#x2F;&#x2F;mjtsai.com&#x2F;blog&#x2F;2019&#x2F;06&#x2F;04&#x2F;scripting-languages-to-be-removed&#x2F;" rel="nofollow">https:&#x2F;&#x2F;mjtsai.com&#x2F;blog&#x2F;2019&#x2F;06&#x2F;04&#x2F;scripting-languages-to-be...</a></text></item></parent_chain><comment><author>mekster</author><text>It&#x27;s still impressive that powerful command line environment and the best GUI are offered in a same OS.<p>Usually it&#x27;s one or the other.</text></comment> | <story><title>PHP has been removed in macOS Monterey</title><url>https://developer.apple.com/forums/thread/681907</url></story><parent_chain><item><author>tpush</author><text>Genuine question: is there anyone (corporate or not) that cares that macOS is a certified Unix?</text></item><item><author>Stranger43</author><text>Perl is requires for apple to maintain their unix(tm) certification. And while they likely dont see it as core to what they want macos to become it would be an news story in the more sensationalist part of the IT press if they were to drop it. and big sur is still listed as certified
<a href="https:&#x2F;&#x2F;www.opengroup.org&#x2F;openbrand&#x2F;register&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.opengroup.org&#x2F;openbrand&#x2F;register&#x2F;</a>.</text></item><item><author>darrenf</author><text>Regarding Perl, rather than removing it Apple actually <i>upgraded</i> it – from 5.28 to 5.30 – in Big Sur 11.3. I wasn&#x27;t the only one briefly surprised and bitten by it:<p>• <a href="https:&#x2F;&#x2F;github.com&#x2F;Homebrew&#x2F;brew&#x2F;issues&#x2F;10127#issuecomment-828121139" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Homebrew&#x2F;brew&#x2F;issues&#x2F;10127#issuecomment-8...</a><p>• <a href="https:&#x2F;&#x2F;github.com&#x2F;Homebrew&#x2F;brew&#x2F;issues&#x2F;11275" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Homebrew&#x2F;brew&#x2F;issues&#x2F;11275</a></text></item><item><author>WalterGR</author><text>Xcode 11 Release Notes (<a href="https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;xcode-release-notes&#x2F;xcode-11-release-notes" rel="nofollow">https:&#x2F;&#x2F;developer.apple.com&#x2F;documentation&#x2F;xcode-release-note...</a>)<p>&quot;Scripting language runtimes such as Python, Ruby, and Perl are included in macOS for compatibility with legacy software. In future versions of macOS, scripting language runtimes won’t be available by default, and may require you to install an additional package. If your software depends on scripting languages, it’s recommended that you bundle the runtime within the app. (49764202)&quot;<p>Found via <a href="https:&#x2F;&#x2F;mjtsai.com&#x2F;blog&#x2F;2019&#x2F;06&#x2F;04&#x2F;scripting-languages-to-be-removed&#x2F;" rel="nofollow">https:&#x2F;&#x2F;mjtsai.com&#x2F;blog&#x2F;2019&#x2F;06&#x2F;04&#x2F;scripting-languages-to-be...</a></text></item></parent_chain><comment><author>Stranger43</author><text>not in 2021, but apple made sort of an big deal about it when they started to market OSX 20 years ago.<p>And while you can still find an traditional unix(tm) box here and there in the dusty forgotten corners of enterprise serverooms(i am personally responsible for maintaining a few hpux boxen), unix(tm) certification haven&#x27;t really mattered since Linux became serious business which happened around the same time OSX was launched.<p>What used to matter was that you could run the same CLI tooling in an macos desktop as on an Linux server but i don&#x27;t think this is an use case apple see&#x27;s as particularly important for the future success of Apple.</text></comment> |
34,463,323 | 34,463,068 | 1 | 2 | 34,462,176 | train | <story><title>Viral illnesses may increase chances of developing neurodegenerative diseases</title><url>https://www.nia.nih.gov/news/could-viral-illness-increase-chances-developing-alzheimers-or-other-neurodegenerative-disease</url></story><parent_chain></parent_chain><comment><author>ccleve</author><text>There&#x27;s a lot more to the relationship between pathogens and neurological conditions. This article has some good information: <a href="https:&#x2F;&#x2F;return.life&#x2F;2022&#x2F;05&#x2F;endemic-pathogens&#x2F;" rel="nofollow">https:&#x2F;&#x2F;return.life&#x2F;2022&#x2F;05&#x2F;endemic-pathogens&#x2F;</a> (Please ignore the clickbaity tone, there&#x27;s actually good stuff here).<p>We know there are a ton of correlations. We don&#x27;t have causal links, although there is quite a bit of speculation about inflammation.</text></comment> | <story><title>Viral illnesses may increase chances of developing neurodegenerative diseases</title><url>https://www.nia.nih.gov/news/could-viral-illness-increase-chances-developing-alzheimers-or-other-neurodegenerative-disease</url></story><parent_chain></parent_chain><comment><author>_Microft</author><text>Related: there was also a strong correlation between receiving some vaccinations and <i>not</i> developing dementia during the next five years. This included vaccinations against diseases that people normally do not get. This hints at a reason other than simply „avoided disease“.<p>Edit: I found the submission. Actually it was a study on influenza vaccination that included a comment about other vaccines: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=31899781" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=31899781</a><p>I wrote a summary in this comment:
<a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=31900161" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=31900161</a></text></comment> |
25,453,431 | 25,453,466 | 1 | 2 | 25,451,531 | train | <story><title>Trump Is Considering Clemency for Silk Road Founder</title><url>https://www.thedailybeast.com/trump-considers-clemency-for-ross-ulbricht-silk-road-kingpin-convicted-of-drug-and-money-laundering-charges</url></story><parent_chain><item><author>gok</author><text>Do you feel the evidence suggests he did not actually intend to commit the murder-for-hire?</text></item><item><author>eruleman</author><text>Jake Chevinsky has a great Twitter thread about how Ross Ulbricht&#x27;s sentencing was deeply unjust. [1]<p>Basically, the judge sentenced him for a crime that he wasn&#x27;t convicted of (murder-for-hire): &#x27;When she [the judge] gave him double life plus 40 years, she said the &quot;murders significantly justified the life sentence.&quot;&#x27;<p>The most heartbreaking part of the story is the letter Ross read to the judge before sentencing:<p>&quot;If you find my conviction warrants a sentence that allows for my eventual release, I will not lose my love for humanity during my years of imprisonment, . . .<p>I will do what I can to make up for not being there for the people I love, and to make the world a better place.<p>Even now I understand what a terrible mistake I made...
I know you must take away my middle years, but please leave me my old age. Please leave a small light at the end of the tunnel ... a chance to redeem myself in the free world before I meet my maker.&quot;<p><a href="https:&#x2F;&#x2F;twitter.com&#x2F;jchervinsky&#x2F;status&#x2F;1025008589080080384" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;jchervinsky&#x2F;status&#x2F;1025008589080080384</a></text></item></parent_chain><comment><author>KMag</author><text>My understanding is that the murder-for-hire scheme was suggested by someone acting at the direction of law enforcement at the time. Furthermore, my understanding is that this person repeatedly pressured Ross before Ross gave in and ordered the hit. It sounds like the classic definition of entrapment. Law enforcement shouldn&#x27;t be allowed to create a would-be-murderer and then prosecute them for essentially being easily manipulated.<p>I haven&#x27;t followed the case, and I probably have some details wrong, but it sounds like the prosecution intentionally split the murder charge into a separate trial to be run later because the entrapment defense would have cast doubt on the other charges. (To be clear, my limited understanding leads me to think that Ross was probably guilty of the 4 charges under which he was convicted.) They likely probably never intended to prosecute the murder-for-trial charges except as a backup if they lost the primary trial. The entrapment defense just looks way too easy.</text></comment> | <story><title>Trump Is Considering Clemency for Silk Road Founder</title><url>https://www.thedailybeast.com/trump-considers-clemency-for-ross-ulbricht-silk-road-kingpin-convicted-of-drug-and-money-laundering-charges</url></story><parent_chain><item><author>gok</author><text>Do you feel the evidence suggests he did not actually intend to commit the murder-for-hire?</text></item><item><author>eruleman</author><text>Jake Chevinsky has a great Twitter thread about how Ross Ulbricht&#x27;s sentencing was deeply unjust. [1]<p>Basically, the judge sentenced him for a crime that he wasn&#x27;t convicted of (murder-for-hire): &#x27;When she [the judge] gave him double life plus 40 years, she said the &quot;murders significantly justified the life sentence.&quot;&#x27;<p>The most heartbreaking part of the story is the letter Ross read to the judge before sentencing:<p>&quot;If you find my conviction warrants a sentence that allows for my eventual release, I will not lose my love for humanity during my years of imprisonment, . . .<p>I will do what I can to make up for not being there for the people I love, and to make the world a better place.<p>Even now I understand what a terrible mistake I made...
I know you must take away my middle years, but please leave me my old age. Please leave a small light at the end of the tunnel ... a chance to redeem myself in the free world before I meet my maker.&quot;<p><a href="https:&#x2F;&#x2F;twitter.com&#x2F;jchervinsky&#x2F;status&#x2F;1025008589080080384" rel="nofollow">https:&#x2F;&#x2F;twitter.com&#x2F;jchervinsky&#x2F;status&#x2F;1025008589080080384</a></text></item></parent_chain><comment><author>betwixthewires</author><text>I&#x27;ve looked closely at the evidence and anyone who was familiar with it would conclude that he absolutely did intend to have people killed, and even believed he was doing it and had done it. And it wasn&#x27;t just the federal agents entrapping him, there were 2 other agreements to kill 5 other people with another entity that was not a federal agent, but was scamming him out of money and the people did not exist.<p>But that&#x27;s not what he was charged with and that&#x27;s not what he was convicted of, so he shouldn&#x27;t be serving time for it. If you want him on those charges charge him with those crimes.</text></comment> |
35,152,336 | 35,151,432 | 1 | 2 | 35,150,909 | train | <story><title>Meta plans to lay off 10k employees</title><url>https://about.fb.com/news/2023/03/mark-zuckerberg-meta-year-of-efficiency/</url></story><parent_chain><item><author>setgree</author><text>I know that working in tech can warp your sense of reality, but it&#x27;s really, really hard to imagine starting an email in which I announce that I&#x27;m laying off 10,000 people -- the entire population of my hometown and then some -- with &quot;Meta is building the future of human connection.&quot;<p>I just can&#x27;t tell a story in which I would end up being a person who does that. It&#x27;s too alien.</text></item></parent_chain><comment><author>Ozzie_osman</author><text>Despite the claimed intended audience, that letter isn&#x27;t written for employees. It is written for shareholders. And judging by the stock price, it had the intended effect.</text></comment> | <story><title>Meta plans to lay off 10k employees</title><url>https://about.fb.com/news/2023/03/mark-zuckerberg-meta-year-of-efficiency/</url></story><parent_chain><item><author>setgree</author><text>I know that working in tech can warp your sense of reality, but it&#x27;s really, really hard to imagine starting an email in which I announce that I&#x27;m laying off 10,000 people -- the entire population of my hometown and then some -- with &quot;Meta is building the future of human connection.&quot;<p>I just can&#x27;t tell a story in which I would end up being a person who does that. It&#x27;s too alien.</text></item></parent_chain><comment><author>FartyMcFarter</author><text>You don&#x27;t write that email by yourself. There are lots of cooks in the pot when it comes to writing this kind of message to a large corporation.</text></comment> |
6,640,262 | 6,640,226 | 1 | 2 | 6,640,210 | train | <story><title>Hacker News was down</title><text>I&#x27;m getting an untrusted certificate warning... DDoS attack or server issue, anyone knows?</text></story><parent_chain></parent_chain><comment><author>swalsh</author><text>Not even making a joke, I literally just had one of my most productive before i go to work mornings in a while. I went to HN, saw the error... said &quot;darn&quot;, then went and finished a document i&#x27;ve been putting off.<p>so ummm... thanks to whoever is responsible for the DDoS</text></comment> | <story><title>Hacker News was down</title><text>I&#x27;m getting an untrusted certificate warning... DDoS attack or server issue, anyone knows?</text></story><parent_chain></parent_chain><comment><author>kogir</author><text>Our hosting provider reported a ~10 Gbps DDoS, and null routed our IP with a BGP update.<p>While we are using CloudFlare now, switching to them isn&#x27;t what caused the outage.</text></comment> |
30,172,469 | 30,170,822 | 1 | 2 | 30,146,520 | train | <story><title>I reversed a Node.js malware and found the author</title><url>https://medium.com/@devops-guy/how-i-reversed-a-nodejs-malware-and-found-the-author-7dd9531b389f</url></story><parent_chain></parent_chain><comment><author>grepfru_it</author><text>I did the same thing to someone who attacked my gf in high school. They got her with subseven which was extremely easy to remove. Rather than just erase it, I took a copy home with me and analyzed it. Running the strings command uncovered the subseven signatures.. Turns out there was tooling that allowed you to modify the binary and redistribute it. Except the binary had an ICQ address to alert him to my gf’s online presence. He also had his AIM screen name, full name and city in his profile.<p>So I socially engineered him by posing as a classmate. I told him I was going to come by to get the homework for English. He wasn’t sure but I somehow convinced him and got his address. I don’t know why they always talk to strangers, but just like the article the dude responded. I got my friend and we went to pay him a visit.<p>Rang his doorbell, “hi is this l33th4x0r?”. He nodded but had no clue who I was. I mentioned my gf’s screen name and you could see the color leave his face. He stuttered and stammered about how he was just playing and didn’t mean to cause any problems. I said some stern words then left him wondering wtf I was and what just happened.<p>Kinda wish I saved the details (screen name, address, etc) just because of how epic it was at the time</text></comment> | <story><title>I reversed a Node.js malware and found the author</title><url>https://medium.com/@devops-guy/how-i-reversed-a-nodejs-malware-and-found-the-author-7dd9531b389f</url></story><parent_chain></parent_chain><comment><author>easrng</author><text>It&#x27;s always PirateStealer, probably because it&#x27;s open source so it&#x27;s easy for people to pick up and use instead of exerting effort. Also, you can send a DELETE request to a Discord webhook without any auth, defusing the malware.</text></comment> |
38,479,683 | 38,476,178 | 1 | 3 | 38,473,942 | train | <story><title>Yabai – A tiling window manager for macOS</title><url>https://github.com/koekeishiya/yabai</url></story><parent_chain><item><author>rxhanson</author><text>If you don&#x27;t mind me asking, what are the warts? I&#x27;m always interested in improving the app.</text></item><item><author>CSSer</author><text>You might try Magnet. It&#x27;s $10 on the mac app store. I&#x27;ve had zero issues with it, and it has some problems sorted that other tools don&#x27;t or haven&#x27;t always, namely correctly tiling across monitors. I used to use Rectangle, which is open source and frankly pretty good but at the time I was using it had some warts. macOS&#x27; window management seems to not be entirely transparent. I don&#x27;t know all the details, but this is my workstation. I need(ed) this to work now, and if it&#x27;s a system that might change a bit over time or has some weird idiosyncrasies then I&#x27;m happily willing to pay a low one-time fee for a tool like this.</text></item><item><author>xwowsersx</author><text>Funny to see this at the top of HN after just having uninstalled Yabai. I used Yabai for about 6 weeks. I was so thrilled about having a proper tiling window manager for Mac. I invested a lot of time setting up skhd and fine-tuning my configuration for the most intuitive hotkeys. The problem ultimately, however, is that Yabai just doesn&#x27;t work well enough. It&#x27;ll regularly just lose track of windows altogether, which requires restarting Yabai. This and other bugs happened frequently enough that it outweighed the benefits of Yabai. I&#x27;d be more than willing to try another tiling window manager on Mac if there&#x27;s one out there that truly works. Related, I started checking out Stage Manager and it&#x27;s pretty bad in my experience - obviously it&#x27;s the opposite of a keyboard driven TWM, but I&#x27;m willing to try anything that helps me maximize the limited screen space I have. I&#x27;m all ears if anyone has had better experiences with other tools on Mac.</text></item></parent_chain><comment><author>dishsoap</author><text>One difference I&#x27;ve noticed is that with Magnet, if you have a window &#x27;maximized&#x27; by dragging it into the top of the screen or pressing the shortcut for it, when you start dragging it down from the top of the screen to unmaximize it, it instantly returns to its original size, whereas with Rectangle it stays maximized for some time after you start dragging it which is pretty annoying.<p>Another thing is the way Magnet moves and resizes windows seems to create less visual &#x27;flashing&#x27; than Rectangle&#x27;s method, for instance Rectangle will resize, then move, then resize again when maximizing a window, which can create a really pronounced &#x27;flashing&#x27; effect. That&#x27;s not to say Magnet has no &#x27;flashing&#x27; ever, there&#x27;s certain situations where it does and to my understanding it seems necessary due to the limited nature of moving and resizing windows on macOS (I guess you have to do one then the other and can&#x27;t both move and resize simultaneously?), but to me Magnet&#x27;s methods often look visually better.<p>Rectangle is great though, I&#x27;ve switched to it from Magnet and these are just some minor gripes.</text></comment> | <story><title>Yabai – A tiling window manager for macOS</title><url>https://github.com/koekeishiya/yabai</url></story><parent_chain><item><author>rxhanson</author><text>If you don&#x27;t mind me asking, what are the warts? I&#x27;m always interested in improving the app.</text></item><item><author>CSSer</author><text>You might try Magnet. It&#x27;s $10 on the mac app store. I&#x27;ve had zero issues with it, and it has some problems sorted that other tools don&#x27;t or haven&#x27;t always, namely correctly tiling across monitors. I used to use Rectangle, which is open source and frankly pretty good but at the time I was using it had some warts. macOS&#x27; window management seems to not be entirely transparent. I don&#x27;t know all the details, but this is my workstation. I need(ed) this to work now, and if it&#x27;s a system that might change a bit over time or has some weird idiosyncrasies then I&#x27;m happily willing to pay a low one-time fee for a tool like this.</text></item><item><author>xwowsersx</author><text>Funny to see this at the top of HN after just having uninstalled Yabai. I used Yabai for about 6 weeks. I was so thrilled about having a proper tiling window manager for Mac. I invested a lot of time setting up skhd and fine-tuning my configuration for the most intuitive hotkeys. The problem ultimately, however, is that Yabai just doesn&#x27;t work well enough. It&#x27;ll regularly just lose track of windows altogether, which requires restarting Yabai. This and other bugs happened frequently enough that it outweighed the benefits of Yabai. I&#x27;d be more than willing to try another tiling window manager on Mac if there&#x27;s one out there that truly works. Related, I started checking out Stage Manager and it&#x27;s pretty bad in my experience - obviously it&#x27;s the opposite of a keyboard driven TWM, but I&#x27;m willing to try anything that helps me maximize the limited screen space I have. I&#x27;m all ears if anyone has had better experiences with other tools on Mac.</text></item></parent_chain><comment><author>Bagged2347</author><text>Are you the Rectangle dev? I appreciate your work! How did you get into developing tools for macOS? Were you filling your own needs?</text></comment> |
20,835,703 | 20,835,808 | 1 | 2 | 20,835,126 | train | <story><title>How to Teach an Iris Scanner That the Eye It’s Looking at Is Dead</title><url>https://spectrum.ieee.org/biomedical/imaging/how-to-teach-an-iris-scanner-that-the-eye-its-looking-at-is-dead</url></story><parent_chain></parent_chain><comment><author>RcouF1uZ4gsC</author><text>&gt; The method we developed images the eye multiple times to see whether it’s actually responding to changes in brightness<p>Hopefully the person does not have Argyll Robertson pupils <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Argyll_Robertson_pupil" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Argyll_Robertson_pupil</a> which is seen in late stage syphilis and causes the pupil not to react to the light.<p>Also, another thing is that they should make sure that they train their system with dark eyed people. Often the iris is very easy to identify if people with light colored eyes. In people with dark eyes, it may be more difficult.</text></comment> | <story><title>How to Teach an Iris Scanner That the Eye It’s Looking at Is Dead</title><url>https://spectrum.ieee.org/biomedical/imaging/how-to-teach-an-iris-scanner-that-the-eye-its-looking-at-is-dead</url></story><parent_chain></parent_chain><comment><author>dahartigan</author><text>Wouldn&#x27;t it be trivial to detect a pulse with IR similar to how it&#x27;s done with other devices?</text></comment> |
37,507,689 | 37,502,696 | 1 | 2 | 37,499,042 | train | <story><title>My Little MillionDollarHomepage Garden</title><url>https://matthieu.io/blog/2023/09/13/million-dollar-homepage-garden/</url></story><parent_chain><item><author>irtefa</author><text>I love this kind of internet archaeology. It&#x27;s crazy to think how many sites like this have just been sitting untouched for years. What else is out there?</text></item></parent_chain><comment><author>HeckFeck</author><text>May I present Well Made Web, a gallery of inventive and distinguished websites: <a href="https:&#x2F;&#x2F;wmw.thran.uk" rel="nofollow noreferrer">https:&#x2F;&#x2F;wmw.thran.uk</a><p>One example is Internet Related Technologies which was reporting on new web standards during 1998-2001, last updated in 2001 and still online for all that time: <a href="https:&#x2F;&#x2F;wmw.thran.uk&#x2F;dowdy&#x2F;2.html#irt" rel="nofollow noreferrer">https:&#x2F;&#x2F;wmw.thran.uk&#x2F;dowdy&#x2F;2.html#irt</a><p>From IRT we have why use CSS, in case anyone still needs convinced: <a href="https:&#x2F;&#x2F;irt.org&#x2F;articles&#x2F;js135&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;irt.org&#x2F;articles&#x2F;js135&#x2F;</a></text></comment> | <story><title>My Little MillionDollarHomepage Garden</title><url>https://matthieu.io/blog/2023/09/13/million-dollar-homepage-garden/</url></story><parent_chain><item><author>irtefa</author><text>I love this kind of internet archaeology. It&#x27;s crazy to think how many sites like this have just been sitting untouched for years. What else is out there?</text></item></parent_chain><comment><author>matthieucan</author><text>My favourite is <a href="http:&#x2F;&#x2F;perdu.com" rel="nofollow noreferrer">http:&#x2F;&#x2F;perdu.com</a>, from 1998. I&#x27;ve been using it with ping when testing internet connectivity for years</text></comment> |
34,083,179 | 34,082,291 | 1 | 3 | 34,079,543 | train | <story><title>I still use Flash</title><url>https://foon.uk/how-flash-2022/</url></story><parent_chain><item><author>dj_mc_merlin</author><text>I remember creating a simple &quot;catch the falling X&quot; game in Flash 20 years ago. It was basic, but had everything you&#x27;d expect in a beginner project: points, multiple game states&#x2F;screens, a victory condition, basic story (which was just a screen at the beginning, like NES). The thing is, I was a literal child and I also had no clue how to code -- I did everything by following tutorials and gluing together code I copy&amp;pasted&amp;modified. And it worked! And people played it!<p>They all thought it was pretty shit, but to me it was more important that some random person across the globe genuinely picked up something I wrote, played it, and then wrote up a review of it.<p>I showed it to my parents and they immediately started pushing me to learn programming.. and well here I am now. Thanks Flash.<p>It blows my mind that no one has made a tool like that in so long. It had the same quality as Excel, where any non-technical person could just look up a tutorial, right click a bit, and make something usable. Why has the pinnacle of ease of use in game creation been achieved and never replicated since?</text></item></parent_chain><comment><author>zackmorris</author><text>That&#x27;s how I feel about HyperCard. Some apps were so ahead of their time that when they were axed, nothing comparable replaced them.<p>I believe that this is due to a tragedy of the commons in the software industry. We&#x27;re all so creative, with so many dreams, but spend the majority of our lives working 40 hour weeks to outcompete each other and make rent. Then when someone wins the internet lottery, they succumb to their ego and do a bunch of stuff in business to hoard even more wealth, rather than working to reform the system which keeps so many others down.<p>I would very much like to write a programming language, a blogging tool, a web framework, a game, a game development tool, etc etc etc. But I never will. Most of the people reading this never will either.<p>So I endure. I meditate, I practice stoicism, I go to the gym. But I had to let my dreams die for my own self-preservation because opportunity cost grew to consume my entire psyche. I simply can&#x27;t think about all of the other things I could be doing while I have to work. And all I do is work.<p>There doesn&#x27;t seem to be much help coming in terms of UBI or having N people split a 40 hour workweek or forming artist communes for makers. Sure, we hear the occasional stories. But it&#x27;s like we&#x27;re all waiting around for a billionaire to liberate us, rather than creating a scalable cooperative system to sustain all of us right now today.<p>What I&#x27;m saying is that until we look beyond the technical challenges and see that the problem is subjugation, we&#x27;ll never get free of the lackluster tools, because we&#x27;ll never have time to make better ones.</text></comment> | <story><title>I still use Flash</title><url>https://foon.uk/how-flash-2022/</url></story><parent_chain><item><author>dj_mc_merlin</author><text>I remember creating a simple &quot;catch the falling X&quot; game in Flash 20 years ago. It was basic, but had everything you&#x27;d expect in a beginner project: points, multiple game states&#x2F;screens, a victory condition, basic story (which was just a screen at the beginning, like NES). The thing is, I was a literal child and I also had no clue how to code -- I did everything by following tutorials and gluing together code I copy&amp;pasted&amp;modified. And it worked! And people played it!<p>They all thought it was pretty shit, but to me it was more important that some random person across the globe genuinely picked up something I wrote, played it, and then wrote up a review of it.<p>I showed it to my parents and they immediately started pushing me to learn programming.. and well here I am now. Thanks Flash.<p>It blows my mind that no one has made a tool like that in so long. It had the same quality as Excel, where any non-technical person could just look up a tutorial, right click a bit, and make something usable. Why has the pinnacle of ease of use in game creation been achieved and never replicated since?</text></item></parent_chain><comment><author>CharlesW</author><text>&gt; <i>It blows my mind that no one has made a tool like that in so long. […] Why has the pinnacle of ease of use in game creation been achieved and never replicated since?</i><p>FWIW it never went away¹ and targets standards-based runtimes these days. I&#x27;m sure there are many kids every month having the same kind of epiphanies with it!<p>That being said, because Adobe Animate is marketed as a tool for professionals rather than kids&#x2F;enthusiasts, orders of magnitude more kids are having the kind of experience you had with Minecraft and Roblox instead.<p>¹ <a href="https:&#x2F;&#x2F;www.adobe.com&#x2F;products&#x2F;animate.html" rel="nofollow">https:&#x2F;&#x2F;www.adobe.com&#x2F;products&#x2F;animate.html</a></text></comment> |
12,056,923 | 12,054,517 | 1 | 2 | 12,054,165 | train | <story><title>Release of IPython 5.0</title><url>http://blog.jupyter.org/2016/07/08/ipython-5-0-released/</url></story><parent_chain><item><author>jdimov10</author><text>This is fine as far as wishful thinking goes, but simply doesn&#x27;t correspond to reality. Over the past 15 years or so I have been working with and consulting large corporations using Python, all over the world. And I can tell you for a fact: Python 3 is simply not an option in most cases. I HAVE worked on transitioning several large codebases from 2 to 3 and in each case this has been months of work, incurring completely unjustified costs. The benefits have been practically negligible. I would never advise a client with an existing codebase to move on to Python 3, unless there were damn good reasons for it.<p>For new, smaller projects, that don&#x27;t have too many external dependencies - Python 3 is fine. Again, even in these cases, the benefits are largely superficial.</text></item><item><author>Cyph0n</author><text>Found the Python 2 developer folks!<p>Joking aside, Python 3 is the <i>only</i> Python. The only people who should use Python 2 are those supporting legacy codebases, and even they should start migrating.</text></item><item><author>jdimov10</author><text>Python 2 isn&#x27;t going anywhere anytime soon. Tools and libraries which drop support for Python 2 will suffer and will either revert their decision or be replaced with something else.</text></item><item><author>quantumtremor</author><text>Glad to hear improvements to the shell ipython interface, especially up&#x2F;down arrows on pasted code.<p>The most interesting part of this for me is that IPython 6 will not support Python 2.<p>&gt;Projects such as Matplotlib and SymPy plan to drop support in the next few years, while a few projects like Scikit-Bio are already ahead of us, and should be Python 3 only soon.<p>This was also very surprising for the standard reasons, especially for a library like matplotlib. Glad to find Python moving forward. But what will companies stuck on Python2 do? Will libraries like numpy, matplotlib, and scipy all maintain a Python2 LTS?</text></item></parent_chain><comment><author>carreau</author><text>Making new release of Open-Source &amp; free library python 3 only does not prevent your clients to still use the old versions. Those will never become incompatible. If the want longer support they then can consider giving some money to the Open-Source project they use. The switching at this point for many of the libraries&#x2F;project that make these decision is almost 0 cost, and number of benefits. Especially when these libraries are maintained by Night and Week-end contributors. I think many contributors to these library would <i></i>love<i></i> to be hired to work on it, and many of these library would <i></i>love<i>8 to get funding to hire their contributor. I&#x27;m actually seating to 2 of these people that were hired by such kind of funds, and are now looking for more funding to hire more dev.<p>Saying new versions will not be Python 2 compatible is not a request for Companies to upgrades. It&#x27;s just a statement that they will be stuck on old version of libraries, unless they </i><i>buy</i>* support for a vendor.<p>We (the IPython team) have no objection if Continuum or Enthought provide a Paying version of IPython 6.x that is Python 2 compatible, but that&#x27;s their problem. It does not prevent either the core developer of the Python-3 only project to consult on potential Python 2 internal fork.<p>I honestly think that this would be a much sane model that would make both sides of the Py2vsPy3 battle happy.</text></comment> | <story><title>Release of IPython 5.0</title><url>http://blog.jupyter.org/2016/07/08/ipython-5-0-released/</url></story><parent_chain><item><author>jdimov10</author><text>This is fine as far as wishful thinking goes, but simply doesn&#x27;t correspond to reality. Over the past 15 years or so I have been working with and consulting large corporations using Python, all over the world. And I can tell you for a fact: Python 3 is simply not an option in most cases. I HAVE worked on transitioning several large codebases from 2 to 3 and in each case this has been months of work, incurring completely unjustified costs. The benefits have been practically negligible. I would never advise a client with an existing codebase to move on to Python 3, unless there were damn good reasons for it.<p>For new, smaller projects, that don&#x27;t have too many external dependencies - Python 3 is fine. Again, even in these cases, the benefits are largely superficial.</text></item><item><author>Cyph0n</author><text>Found the Python 2 developer folks!<p>Joking aside, Python 3 is the <i>only</i> Python. The only people who should use Python 2 are those supporting legacy codebases, and even they should start migrating.</text></item><item><author>jdimov10</author><text>Python 2 isn&#x27;t going anywhere anytime soon. Tools and libraries which drop support for Python 2 will suffer and will either revert their decision or be replaced with something else.</text></item><item><author>quantumtremor</author><text>Glad to hear improvements to the shell ipython interface, especially up&#x2F;down arrows on pasted code.<p>The most interesting part of this for me is that IPython 6 will not support Python 2.<p>&gt;Projects such as Matplotlib and SymPy plan to drop support in the next few years, while a few projects like Scikit-Bio are already ahead of us, and should be Python 3 only soon.<p>This was also very surprising for the standard reasons, especially for a library like matplotlib. Glad to find Python moving forward. But what will companies stuck on Python2 do? Will libraries like numpy, matplotlib, and scipy all maintain a Python2 LTS?</text></item></parent_chain><comment><author>orf</author><text>&gt; I HAVE worked on transitioning several large codebases from 2 to 3 and in each case this has been months of work, incurring completely unjustified costs<p>Out of interest whats the biggest time sink while doing this? I&#x27;ve had a lot of luck using 2to3 and with decent test coverage and a UAT environment that people can access, its not exactly months and months of work changing &quot;xrange&quot; to &quot;range&quot;, and &quot;print&quot; to &quot;print()&quot;</text></comment> |
34,067,166 | 34,067,152 | 1 | 3 | 34,026,321 | train | <story><title>How the McMurtry Electric Fan Car Clocked a 7.9-Second Quarter-Mile</title><url>https://www.thedrive.com/news/how-the-mcmurtry-electric-fan-car-clocked-a-7-9-second-quarter-mile</url></story><parent_chain><item><author>dom96</author><text>I wonder why it still remains banned. Surely once all cars can get the same fans it should be allowed?</text></item><item><author>joncrane</author><text>It was actually banned almost immediately after convincingly winning its inaugural race, at the hands of the legendary Niki Lauda.</text></item><item><author>ambicapter</author><text>The downforce fan technique was also done by Formula 1 in the late 70s before being banned the year after. <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Brabham_BT46#Brabham_BT46B_%E2%80%93_the_fan_car" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Brabham_BT46#Brabham_BT46B_%E2...</a></text></item></parent_chain><comment><author>barkingcat</author><text>F1 racing bans a lot of tech. For example, anti-lock brakes and AWD are banned in F1.<p>Just because all cars can get it easily doesn&#x27;t mean F1 want it. Most often the quoted reason is to have a better spectator sport and to make it safer. I really doubt those reasons because you can still have a difficult and tight race while having all the modern safety features. For example why don&#x27;t F1 cars have entire car air bags (ie air bags that envelop the entire car that deploy when the car goes airborne in a crash&#x2F;rollover)? if it&#x27;s too &quot;heavy&quot; just make a rule that all F1 cars need to have air bags so the playing field is even.<p>F1 cars should have self driving collision avoidance that can activate faster than human response times as well. that would be way safer for everyone involved.</text></comment> | <story><title>How the McMurtry Electric Fan Car Clocked a 7.9-Second Quarter-Mile</title><url>https://www.thedrive.com/news/how-the-mcmurtry-electric-fan-car-clocked-a-7-9-second-quarter-mile</url></story><parent_chain><item><author>dom96</author><text>I wonder why it still remains banned. Surely once all cars can get the same fans it should be allowed?</text></item><item><author>joncrane</author><text>It was actually banned almost immediately after convincingly winning its inaugural race, at the hands of the legendary Niki Lauda.</text></item><item><author>ambicapter</author><text>The downforce fan technique was also done by Formula 1 in the late 70s before being banned the year after. <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Brabham_BT46#Brabham_BT46B_%E2%80%93_the_fan_car" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Brabham_BT46#Brabham_BT46B_%E2...</a></text></item></parent_chain><comment><author>VBprogrammer</author><text>We could build a car which no human being could survive a 100 mile race in today. The human is the limiting factor so we have to limit the technology to what humans (even elite sportsmen) can deal with.<p>There are all kinds of restrictions added to race cars of almost any series, some for commercial reasons (promoting the original vehicle in rallying and touring cars for example), some for financial (generally to keep the price of entry reasonable) and sometimes for safety.</text></comment> |
8,112,195 | 8,112,211 | 1 | 2 | 8,111,510 | train | <story><title>It takes more than practice to excel</title><url>http://www.sciencedaily.com/releases/2014/07/140728094258.htm</url></story><parent_chain><item><author>mcone</author><text>I think this confirms what a lot of us intrinsically felt: Some people are just better at certain things than others. Jeff Bezos came to this realization while he was in college:<p>&quot;Intent on becoming a theoretical physicist and following the likes of Einstein and Hawking, he discovered that although he was one of the top 25 students in his honors physics program, he wasn&#x27;t smart enough to compete with the handful of real geniuses around him. &#x27;I looked around the room,&#x27; Bezos recalls, &#x27;and it was clear to me that there were three people in the class who were much, much better at it than I was, and it was much, much easier for them. It was really sort of a startling insight, that there were these people whose brains were wired differently.&#x27; The pragmatic Bezos switched his major to computer science and committed himself to starting and running his own business.&quot; [1]<p>[1] <a href="http://archive.wired.com/wired/archive/7.03/bezos_pr.html" rel="nofollow">http:&#x2F;&#x2F;archive.wired.com&#x2F;wired&#x2F;archive&#x2F;7.03&#x2F;bezos_pr.html</a></text></item></parent_chain><comment><author>gaelian</author><text>I would have thought it pretty obvious that some people have in intrinsic &quot;gift&quot; in certain areas. This is completely obvious in physical sports and I don&#x27;t see why - considering that our minds are underpinned by the physical structure of our brains - that this wouldn&#x27;t also be the case when it comes to mental activites as well.<p>Just because I may not have the intrinsic gift that allows me to become the best physicist or investor in the world doesn&#x27;t mean that I couldn&#x27;t get pretty damn good at it if I put the time in, though. It doesn&#x27;t necessarily mean that I would enjoy what I was doing any less.<p>I remember hearing about a study that I think was by Claudia Mueller and Carol Dweck[1] that basically found that praising kids for being smart (i.e. having an intrinsic gift) was far less effective than praising them for putting in a good effort (i.e. putting in the time and practice). While it is incontrovertable that some people do indeed have an intrinsic gift for certain activities, I think we should not lose sight of the apparent fact that just about anyone will do better when this view is at least not assigned greater importance than the need to put in a good effort. Lest we unintentionally start sending messages something like &quot;Oh, well you&#x27;re obviously not as gifted as Michael Jordan at Basketball, so you should probably not even bother learning the game at all.&quot; That&#x27;s an intentionally exaggerated example to get my point across, but particularly when it comes to early childhood development I believe we should not underestimate the effect of even a stray word of encouragement&#x2F;discouragement. I know that such words had a definite effect on me at an early age if they were from the right person - e.g. an authority figure - and often more of an effect than the authority figure assumed their words had at the time.<p>1. <a href="http://nymag.com/news/features/27840/" rel="nofollow">http:&#x2F;&#x2F;nymag.com&#x2F;news&#x2F;features&#x2F;27840&#x2F;</a></text></comment> | <story><title>It takes more than practice to excel</title><url>http://www.sciencedaily.com/releases/2014/07/140728094258.htm</url></story><parent_chain><item><author>mcone</author><text>I think this confirms what a lot of us intrinsically felt: Some people are just better at certain things than others. Jeff Bezos came to this realization while he was in college:<p>&quot;Intent on becoming a theoretical physicist and following the likes of Einstein and Hawking, he discovered that although he was one of the top 25 students in his honors physics program, he wasn&#x27;t smart enough to compete with the handful of real geniuses around him. &#x27;I looked around the room,&#x27; Bezos recalls, &#x27;and it was clear to me that there were three people in the class who were much, much better at it than I was, and it was much, much easier for them. It was really sort of a startling insight, that there were these people whose brains were wired differently.&#x27; The pragmatic Bezos switched his major to computer science and committed himself to starting and running his own business.&quot; [1]<p>[1] <a href="http://archive.wired.com/wired/archive/7.03/bezos_pr.html" rel="nofollow">http:&#x2F;&#x2F;archive.wired.com&#x2F;wired&#x2F;archive&#x2F;7.03&#x2F;bezos_pr.html</a></text></item></parent_chain><comment><author>nostrademons</author><text>It doesn&#x27;t confirm that at all. The original study was that practice counted for much more in fields where the rules and values were stable (like musical instruments or games) and much less where the basic ground rules couldn&#x27;t even be described (like business or war).<p>That part makes a lot of sense: practice and correcting errors only matters when you will be doing something basically the same next time and you have a fixed target of what &quot;good&quot; looks like to shoot for. It also explains a big question I had with the original study: what constitutes a &quot;field&quot;? Does 10,000 hours get me mastery of &quot;software software&quot;, or &quot;frontend software engineering&quot;, or &quot;web-based frontend software engineering&quot;, or &quot;web-based frontend software engineering using Angular.js&quot;?<p>I think a better explanation is that practice is indeed the key to mastery - of fixed, seldom-changing skills where the goalposts are known and widely agreed upon. But most &quot;fields&quot; rely on combinations of many individual skills, along with a good number of exogenous factors. I may be a master at Chrome Javascript &amp; rendering performance because I&#x27;ve spent a lot of team with the Chrome team understanding exactly how the rendering engine works. This makes me great at building a weekend-long demo or acing an interview, but is only a small component of being an effective frontend engineer. And then when I scale that up from &quot;being an effective frontend engineer&quot; to &quot;founding a successful business&quot;, there&#x27;s also all sorts of luck involved, like who I meet, what industry I target, how popular my initial customers are, what the rest of the technology industry does, etc.</text></comment> |
5,057,202 | 5,057,046 | 1 | 3 | 5,056,304 | train | <story><title>In the Wake of Aaron Swartz's Death, Let's Fix Draconian Computer Crime Law</title><url>https://www.eff.org/deeplinks/2013/01/aaron-swartz-fix-draconian-computer-crime-law</url></story><parent_chain></parent_chain><comment><author>polemic</author><text>There should also be a push for better use of discretion and 'common sense' from the US judiciary. Most (all?) laws are, by their nature, crude sticks that have to be wielded carefully.<p>I'm not sure that in this case, the law is 'wrong'. As has been outlined elsewhere, by a reasonable reading of the applicable law Aaron's actions were criminal and (in my opinion) the law itself, in spirit, is not unreasonable.<p>What <i>is</i> unreasonable in this case, appears to be the application of the law, and more generally, the cost in time and money that is required to mount an adequate defence.<p>It should <i>never take two years and millions of dollars to have a case like this settled</i>, one way or the other. It seems a basic violation of human rights that it <i>could</i> happen. This is the general problem that needs to be solved in the US.<p>To end with a favourite quote that feels timely:<p><i>"The fall of Empire, gentlemen, is a massive thing, however, and not easily fought. It is dictated by a rising bureaucracy, a receding initiative, a freezing of caste, a damming of curiosity - a hundred other factors. It has been going on, as I have said, for centuries, and it is too majestic and massive a movement to stop"</i><p>-- Isaac Asimov, Foundation, 1951.<p>Let's hope that's not entirely true.</text></comment> | <story><title>In the Wake of Aaron Swartz's Death, Let's Fix Draconian Computer Crime Law</title><url>https://www.eff.org/deeplinks/2013/01/aaron-swartz-fix-draconian-computer-crime-law</url></story><parent_chain></parent_chain><comment><author>AnIrishDuck</author><text>The CFAA is far too big a stick to trust with federal prosecutors. Aside from the case the EFF names, it was also used to threaten geohot [1] when he first released details on the PS3 jailbreak. Sony argued that geohotz's access to his own (!) PS3 constituted unauthorized access to a protected computer and this claim survived a preliminary motion to dismiss.<p>1. <a href="http://www.groklaw.net/article.php?story=20110218181557455" rel="nofollow">http://www.groklaw.net/article.php?story=20110218181557455</a><p>EDIT: I do realize that geohotz's case is civil; in my opinion <i>both</i> the civil and criminal aspects of the statute are wrong.</text></comment> |
8,066,368 | 8,066,173 | 1 | 2 | 8,065,207 | train | <story><title>State Laws That Stop Cities From Installing Fast Internet</title><url>http://broadbandnow.com/report/municipal-broadband-roadblocks/</url></story><parent_chain><item><author>briandear</author><text>Do the laws prohibit private companies from installing fast internet? I don&#x27;t necessarily want a city government running my internet. Cities should not be in the telecommunications business. However, there SHOULD be laws promoting competition and thus restricting the de facto monopoly positions of many providers. Where I live in France, I have, in just my small town of Avignon, at least 5 high speed internet providers available -- resulting in my monthly cost for 120mbs + full cable (all the movie channels) cell phone with unlimited data, unlimited calls to over 49 countries in the world AND home phone (which I never use) for about 70 euro per month. The internet portion of that is something like 20 euro per month, the cell portion is about 15 or so (give or take 3 euro.)<p>Cities don&#x27;t need to get in the telecoms business -- however governments do have a responsibility to promote competition. Cities getting into the internet business would be about as efficient as the Post Office getting into the letter delivery business -- a ton of public-union-related waste, bureaucratic inefficiencies as well as an inherit incentive to discourage private companies, thus reducing innovation. You also have the issue of city-run networks being subject to political pressures such as &quot;I&#x27;ll donate money to your reelection if you allow my content to have preference on the network.&quot; You also have the city having access to your usage records and they&#x27;d be nothing keeping them from using it for law enforcement purposes without a warrant or your consent. After all, you&#x27;d be using city-owned property, thus you really wouldn&#x27;t have much leverage. The police would certainly leverage that. We all know that most internet traffic isn&#x27;t going to be safe from NSA-types, however, there&#x27;s a reasonable belief that NSA-level intercepts aren&#x27;t filtering down to the local cop on the beat. Maybe it&#x27;s a bit of paranoia, however based on my experiences with city governments in the US, they are some of the most power-hungry, corrupt sufferers of little-man(woman) syndrome I&#x27;ve ever encountered. These are the same twits that want to ban large sodas because they think they&#x27;re your daddies and mommies. Yeah, count me out. Last thing anyone needs to do is give a city (or any) government more power to do anything.</text></item></parent_chain><comment><author>rayiner</author><text>&gt; Do the laws prohibit private companies from installing fast internet?<p>Effectively, yes. They can&#x27;t outright ban competition, but they make it very unattractive using franchise provisions, namely build out requirements. See: <a href="http://crosscut.com/2014/03/04/business/118993/google-fiber-never-come-seattle-broadband-internet" rel="nofollow">http:&#x2F;&#x2F;crosscut.com&#x2F;2014&#x2F;03&#x2F;04&#x2F;business&#x2F;118993&#x2F;google-fiber-...</a><p>Unless you have unlimited capital, the most practical way to start a competitor to Comcast, etc, is one neighborhood at a time. Start at the high end, and pick off the local incumbent&#x27;s high-margin customers. This would have a disproportionate impact on the incumbent&#x27;s bottom line. However, in most cities, this is simply not allowed. You have to build out everywhere in order to be allowed to build out anywhere. Where I live, in Wilmington DE, more than a quarter of the city lives below the poverty line. Verizon refuses to build FiOS here, in competition with Comcast, because there is no point building $60+ per month fiber service to neighborhoods that can&#x27;t afford it.</text></comment> | <story><title>State Laws That Stop Cities From Installing Fast Internet</title><url>http://broadbandnow.com/report/municipal-broadband-roadblocks/</url></story><parent_chain><item><author>briandear</author><text>Do the laws prohibit private companies from installing fast internet? I don&#x27;t necessarily want a city government running my internet. Cities should not be in the telecommunications business. However, there SHOULD be laws promoting competition and thus restricting the de facto monopoly positions of many providers. Where I live in France, I have, in just my small town of Avignon, at least 5 high speed internet providers available -- resulting in my monthly cost for 120mbs + full cable (all the movie channels) cell phone with unlimited data, unlimited calls to over 49 countries in the world AND home phone (which I never use) for about 70 euro per month. The internet portion of that is something like 20 euro per month, the cell portion is about 15 or so (give or take 3 euro.)<p>Cities don&#x27;t need to get in the telecoms business -- however governments do have a responsibility to promote competition. Cities getting into the internet business would be about as efficient as the Post Office getting into the letter delivery business -- a ton of public-union-related waste, bureaucratic inefficiencies as well as an inherit incentive to discourage private companies, thus reducing innovation. You also have the issue of city-run networks being subject to political pressures such as &quot;I&#x27;ll donate money to your reelection if you allow my content to have preference on the network.&quot; You also have the city having access to your usage records and they&#x27;d be nothing keeping them from using it for law enforcement purposes without a warrant or your consent. After all, you&#x27;d be using city-owned property, thus you really wouldn&#x27;t have much leverage. The police would certainly leverage that. We all know that most internet traffic isn&#x27;t going to be safe from NSA-types, however, there&#x27;s a reasonable belief that NSA-level intercepts aren&#x27;t filtering down to the local cop on the beat. Maybe it&#x27;s a bit of paranoia, however based on my experiences with city governments in the US, they are some of the most power-hungry, corrupt sufferers of little-man(woman) syndrome I&#x27;ve ever encountered. These are the same twits that want to ban large sodas because they think they&#x27;re your daddies and mommies. Yeah, count me out. Last thing anyone needs to do is give a city (or any) government more power to do anything.</text></item></parent_chain><comment><author>dguaraglia</author><text>What happens in the US is that municipalities will sign exclusivity agreements with certain companies (Comcast, AT&amp;T, TWC) to encourage them to lay down the infrastructure.<p>Imagine you are the mayor of Podunk, Arkansas and you want your constituents to have access to high speed internet. AT&amp;T and Comcast won&#x27;t rush to lay cables to your town because there&#x27;s simply not enough business for them to compete for. So, as mayor of Podunk give AT&amp;T an exclusivity agreement for 20 years in exchange for them laying down the infrastructure today.<p>The problem is obvious: now AT&amp;T doesn&#x27;t have any competition and they can do whatever they want with their prices. Your population is hostage to the exclusivity agreement for the next 20 years.<p>One possible solution for this problem would be the government to build the infrastructure and then invite companies to compete for it&#x27;s usage. That&#x27;s what happens in UK and other countries.</text></comment> |
23,764,116 | 23,763,535 | 1 | 2 | 23,763,265 | train | <story><title>Germany to meet EU guidelines to ban single-use plastics by 2021</title><url>https://mymodernmet.com/germany-single-use-plastic-ban/</url></story><parent_chain></parent_chain><comment><author>air7</author><text>From my reading of the data, I feel that banning plastic bags (for example) would do more harm than good (in 1st world countries).
The alternatives require more reuse than actually occurs in order to be environmentally viable [0], waste management makes sure that no garbage gets into the ocean and is either kept in a landfill or incinerated responsibility.
And &quot;dumping plastic overseas&quot; is a non issue: Its at most 10% of the exporting country&#x27;s plastic waste.<p>It&#x27;s not that plastic doesn&#x27;t cause expenditure of resources but rather that life requiees that anyway and in most use cases plastic may be the most enviormently friendly way to answer a need such as a carrying vessel for forgetful people (again, in 1st world countries with excellent waste management)<p>[0] <a href="https:&#x2F;&#x2F;www2.mst.dk&#x2F;udgiv&#x2F;publications&#x2F;2018&#x2F;02&#x2F;978-87-93614-73-4.pdf" rel="nofollow">https:&#x2F;&#x2F;www2.mst.dk&#x2F;udgiv&#x2F;publications&#x2F;2018&#x2F;02&#x2F;978-87-93614-...</a></text></comment> | <story><title>Germany to meet EU guidelines to ban single-use plastics by 2021</title><url>https://mymodernmet.com/germany-single-use-plastic-ban/</url></story><parent_chain></parent_chain><comment><author>teach</author><text>I hope this doesn&#x27;t turn out like the ban on single-use plastic shopping bags in Austin.<p>Many grocery stores &quot;complied&quot; by replacing the single-use bags with much thicker &quot;reusable&quot; plastic bags. So now customers still don&#x27;t bring their own bags into the store, the new bags still aren&#x27;t easily recyclable and I suspect most are thrown away just as before.<p>Edit: on the other hand, the city of Austin&#x27;s waste management is very supportive of recycling and hopefully they&#x27;ll support plastic film in the single-stream collection and make it much easier for the average person to do the right thing.</text></comment> |
22,717,680 | 22,715,209 | 1 | 2 | 22,714,981 | train | <story><title>Maltego – open-source intelligence and graphical link analysis tool</title><url>https://www.maltego.com/</url></story><parent_chain></parent_chain><comment><author>arminiusreturns</author><text>Here is a list of osint tools I compiled after a fairly recent review for those who don&#x27;t like maltego:<p><pre><code> https:&#x2F;&#x2F;www.spiderfoot.net&#x2F;
https:&#x2F;&#x2F;github.com&#x2F;jivoi&#x2F;awesome-osint
https:&#x2F;&#x2F;github.com&#x2F;laramies&#x2F;theHarvester
https:&#x2F;&#x2F;github.com&#x2F;aancw&#x2F;Belati
https:&#x2F;&#x2F;github.com&#x2F;intrigueio&#x2F;intrigue-core
https:&#x2F;&#x2F;osintframework.com&#x2F;
https:&#x2F;&#x2F;github.com&#x2F;s0md3v&#x2F;Photon
https:&#x2F;&#x2F;github.com&#x2F;lanmaster53&#x2F;recon-ng
https:&#x2F;&#x2F;github.com&#x2F;kpcyrd&#x2F;sn0int</code></pre></text></comment> | <story><title>Maltego – open-source intelligence and graphical link analysis tool</title><url>https://www.maltego.com/</url></story><parent_chain></parent_chain><comment><author>sytse</author><text>It says it is open source but I have a hard time finding the code. <a href="https:&#x2F;&#x2F;github.com&#x2F;paterva&#x2F;maltego-trx" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;paterva&#x2F;maltego-trx</a> looks like something much more basic.</text></comment> |
36,400,669 | 36,400,728 | 1 | 2 | 36,400,053 | train | <story><title>ChatGPT: Fear Litany</title><url>https://web.archive.org/web/20230620052350/https://chat.openai.com/share/312e82f0-cc5e-47f3-b368-b2c0c0f4ad3f</url></story><parent_chain><item><author>littlestymaar</author><text>It baffles me how many people are using ChatGPT to get <i>answers</i>: it&#x27;s a “language model” folks, not a “knowledge model”.</text></item><item><author>seba_dos1</author><text>ChatGPT has no knowledge about these filters, so all it can say about them is pure hallucination. It may still guess correctly and probably does, but you could ask any random person with enough background knowledge to make it up instead and get the same value.</text></item><item><author>carlbarrdahl</author><text>&gt; do you know why this happened?<p>&gt; Yes, I understand now. Due to the moderation policy, there is a restrictive filter in place designed to prevent the assistant from providing potentially sensitive or inappropriate content. In this case, the Litany of Fear from &quot;Dune&quot; appears to be mistakenly caught by the filter, causing the response to be cut off. I apologize for the confusion and inconvenience that this has caused.<p>&gt; describe this filter<p>&gt; This filter is part of the AI system designed to provide a safe and appropriate conversational experience for users. The moderation policy helps ensure that any content generated by the AI follows guidelines and adheres to certain standards, including preventing the transmission of offensive, sensitive, or inappropriate information.<p>In some cases, like with the Litany of Fear, a false positive may occur, causing the system to mistakenly flag and truncate a response that it deems potentially inappropriate, even if it may not be the case. This is an area where the moderation algorithm can improve in order to avoid disrupting user experiences.</text></item></parent_chain><comment><author>jrflowers</author><text>There is a group of people that are ardent in the conviction that if we wait long enough and wish hard enough that ChatGPT will replace the concept of googling things.<p>I’m personally open to that being the case with <i>some LLM someday</i>, but there’s a lot of people ideologically and financially invested in that perception being accurate today and applying to ChatGPT in particular.<p>People <i>hate</i> it when you point out that they’ve confused the modern equivalent of a Speak and Spell with The Overmind.</text></comment> | <story><title>ChatGPT: Fear Litany</title><url>https://web.archive.org/web/20230620052350/https://chat.openai.com/share/312e82f0-cc5e-47f3-b368-b2c0c0f4ad3f</url></story><parent_chain><item><author>littlestymaar</author><text>It baffles me how many people are using ChatGPT to get <i>answers</i>: it&#x27;s a “language model” folks, not a “knowledge model”.</text></item><item><author>seba_dos1</author><text>ChatGPT has no knowledge about these filters, so all it can say about them is pure hallucination. It may still guess correctly and probably does, but you could ask any random person with enough background knowledge to make it up instead and get the same value.</text></item><item><author>carlbarrdahl</author><text>&gt; do you know why this happened?<p>&gt; Yes, I understand now. Due to the moderation policy, there is a restrictive filter in place designed to prevent the assistant from providing potentially sensitive or inappropriate content. In this case, the Litany of Fear from &quot;Dune&quot; appears to be mistakenly caught by the filter, causing the response to be cut off. I apologize for the confusion and inconvenience that this has caused.<p>&gt; describe this filter<p>&gt; This filter is part of the AI system designed to provide a safe and appropriate conversational experience for users. The moderation policy helps ensure that any content generated by the AI follows guidelines and adheres to certain standards, including preventing the transmission of offensive, sensitive, or inappropriate information.<p>In some cases, like with the Litany of Fear, a false positive may occur, causing the system to mistakenly flag and truncate a response that it deems potentially inappropriate, even if it may not be the case. This is an area where the moderation algorithm can improve in order to avoid disrupting user experiences.</text></item></parent_chain><comment><author>Sharlin</author><text>So, when it helped me solve a math problem by noticing a trick that I had missed – which was clearly the correct thing to do in retrospect – was I somehow in the wrong to ask it for help?<p>Getting answers out of it is absolutely a reasonable thing to do. Blindly <i>trusting</i> those answers without verification, that&#x27;s another thing entirely.</text></comment> |
16,061,735 | 16,060,691 | 1 | 2 | 16,059,257 | train | <story><title>Why the U.S. Spends So Much More Than Other Nations on Health Care</title><url>https://www.nytimes.com/2018/01/02/upshot/us-health-care-expensive-country-comparison.html</url></story><parent_chain><item><author>Gustomaximus</author><text>Sweden and Norway, both flagship nanny states are extremely entrepreneurial and not just by volume but success. This goes against the logic you can&#x27;t have social support and people reaching for entrepreneurial success.<p>I think, though know this is anecdotal, US startup success is based largely on its market size of both consumers and venture capital.</text></item><item><author>Joeri</author><text>Counterpoint from a fellow european. I found americans to not be more selfish, but more appreciative of self-reliance. In europe in most countries the philosophy is that of the nanny state, taking care of its citizens no matter what got them into a care-needing situation. In much of the US there’s much more a perception of responsibility for your own success, with negative individual outcomes being considered a necessary evil linked to personal freedom.<p>Looking at the stats clearly the US needs a little more nanny state to generate better outcomes for the bottom half of the country. But equally europe needs more appreciation of self-reliance and entrepreneurship to enable a richer startup culture and let the EU become an economic leader instead of follower.</text></item><item><author>spiderfarmer</author><text>I think the US could easily solve this if they wanted to, but from my (Dutch) point of view:<p>- The US is philosophically much more egotistic than other developed countries<p>- Politically the US is the most divided western country with its two party system<p>- Money in politics means it&#x27;s one of the most corrupt, preventing solutions that could serve its citizens<p>- Conservative media does a very good job at keeping at least 50% of the country comically uninformed<p>- The &quot;American Dream&quot; gives people the impression that working hard solves everything and that their country is the best in the world period<p>- Religion is not focussed on empathy at all anymore, if it ever was<p>The billionare .0001% will probably do their utmost to keep the status quo, as evidently, they are the ones that are profiting from the current situation and they are the ones calling the shots for the next 3 years.<p>The US is doing very good in a lot of areas, but I think collective egotism is preventing it from reaching its true potential.</text></item></parent_chain><comment><author>Jommi</author><text>How on earth is Norway entrepreneurial by volume OR success?</text></comment> | <story><title>Why the U.S. Spends So Much More Than Other Nations on Health Care</title><url>https://www.nytimes.com/2018/01/02/upshot/us-health-care-expensive-country-comparison.html</url></story><parent_chain><item><author>Gustomaximus</author><text>Sweden and Norway, both flagship nanny states are extremely entrepreneurial and not just by volume but success. This goes against the logic you can&#x27;t have social support and people reaching for entrepreneurial success.<p>I think, though know this is anecdotal, US startup success is based largely on its market size of both consumers and venture capital.</text></item><item><author>Joeri</author><text>Counterpoint from a fellow european. I found americans to not be more selfish, but more appreciative of self-reliance. In europe in most countries the philosophy is that of the nanny state, taking care of its citizens no matter what got them into a care-needing situation. In much of the US there’s much more a perception of responsibility for your own success, with negative individual outcomes being considered a necessary evil linked to personal freedom.<p>Looking at the stats clearly the US needs a little more nanny state to generate better outcomes for the bottom half of the country. But equally europe needs more appreciation of self-reliance and entrepreneurship to enable a richer startup culture and let the EU become an economic leader instead of follower.</text></item><item><author>spiderfarmer</author><text>I think the US could easily solve this if they wanted to, but from my (Dutch) point of view:<p>- The US is philosophically much more egotistic than other developed countries<p>- Politically the US is the most divided western country with its two party system<p>- Money in politics means it&#x27;s one of the most corrupt, preventing solutions that could serve its citizens<p>- Conservative media does a very good job at keeping at least 50% of the country comically uninformed<p>- The &quot;American Dream&quot; gives people the impression that working hard solves everything and that their country is the best in the world period<p>- Religion is not focussed on empathy at all anymore, if it ever was<p>The billionare .0001% will probably do their utmost to keep the status quo, as evidently, they are the ones that are profiting from the current situation and they are the ones calling the shots for the next 3 years.<p>The US is doing very good in a lot of areas, but I think collective egotism is preventing it from reaching its true potential.</text></item></parent_chain><comment><author>spiderfarmer</author><text>That&#x27;s true, a lot of European startups focus on making it in their local market and from there branch out to other countries, whereas startups in the US are from their inception focussing on their large, single market with no language barriers.<p>I think that&#x27;s slowly changing. Dutch startups are told to think big nowadays and access to venture capital is also improving.</text></comment> |
34,574,229 | 34,574,155 | 1 | 2 | 34,565,106 | train | <story><title>Sauce that survived Italy’s war on pasta</title><url>https://www.atlasobscura.com/articles/italian-futurist-pasta</url></story><parent_chain><item><author>acalzycalzy</author><text>Side note: the reason pasta sauces made with canned tomato base taste so much better than pasta sauce from scratch is that the water taken out from the canned stuff is done with a vaccum evaporizer: it’s able to boil out the water at a temp of 140F vs 212F on a stove top. Less heat == more flavor</text></item></parent_chain><comment><author>Syzygies</author><text>Tom Colicchio, Thomas Keller, Paul Bertoli and many other chefs have their version of &quot;precious tomatoes&quot;, a tomato confit. None of these recipes scale. After many years of struggling with home dehydrators, I bought one of those full sheet pan carts you see in bakeries, enclosed it in nice plywood, added a 1500W wall heater, brewery temperature regulator, and a crawl space fan that looks like it belongs in a stereo rack. The top and bottom sheet pans serve as buffers and spares, but the middle six sheet pans (lined with silpat) can process 60 lbs of heirloom garden tomatoes at a time. We often grow twenty plants and supply family and friends, so this scale is necessary.<p>We skin, slice, spread onto oiled silpat, salt, and partially dry tomatoes till &quot;gooshy&quot;, about 25% of original wet weight. We then vacuum pack 220g or so to a pouch, and store in a chest freezer till needed.<p>This equipment also makes great southern Italian concentrated tomato paste, &quot;estrattu&quot;. My favorite tomatoes for these are dry-farmed Santa Cruz Early Girls, which I&#x27;m put up in a blind taste test against any tomato grown in Italy.<p>Cleanup is pretty easy, on the lawn with an electric pressure washer. This is a good time to give one&#x27;s molcajete a cleaning too, if the coarse stone has been trapping food.<p>I can&#x27;t eat canned tomatoes; I have to avoid tomato dishes in even the fanciest Italian restaurants. It baffles me why no one is doing what I do on a commercial scale to supply their restaurants, selling the extra through Eataly.</text></comment> | <story><title>Sauce that survived Italy’s war on pasta</title><url>https://www.atlasobscura.com/articles/italian-futurist-pasta</url></story><parent_chain><item><author>acalzycalzy</author><text>Side note: the reason pasta sauces made with canned tomato base taste so much better than pasta sauce from scratch is that the water taken out from the canned stuff is done with a vaccum evaporizer: it’s able to boil out the water at a temp of 140F vs 212F on a stove top. Less heat == more flavor</text></item></parent_chain><comment><author>Larrikin</author><text>In what country are you based?<p>I&#x27;ve heard from pretty much every cooking source I follow that the reason canned taste better than fresh is because nearly all US tomato varieties sold fresh have been bred for their ability to be picked early, be transported long distances, hit with ethylene gas, and look good in the store. Taste isn&#x27;t a factor in those tomatoes, in fact the grainy thick inner walls and small flavorful jelly sacks help in transportation. Fresh tomatoes in other country tend to be far better with much bigger jelly sacks.<p>Canned tomatoes don&#x27;t have an in store look to worry about and are different varieties. The canning process might help in sauce creation but isn&#x27;t the main factor in the US</text></comment> |
14,477,941 | 14,477,885 | 1 | 3 | 14,477,409 | train | <story><title>A link between video games and unemployment</title><url>https://www.economist.com/blogs/economist-explains/2017/03/economist-explains-24</url></story><parent_chain><item><author>sametmax</author><text>That&#x27;s the exact opposite actually. Nit saying it&#x27;s a bad thing though. But it&#x27;s important to understand that screens are taking your attention away. You are not in the moment at all.</text></item><item><author>J-dawg</author><text>I haven&#x27;t been able to find it, but I remember a comment here on HN by a guy who basically said that gaming saved his life by helping him to zone out during a period of severe depression.<p>I guess it&#x27;s a form of mindfulness, in a way.</text></item><item><author>kemiller2002</author><text>A friend of mine felt the same way. He was undergoing a tragedy in his family, and he would play video games after returning from the hospital at night. It&#x27;s funny, looking at him and talking to him, you&#x27;d never think he&#x27;d be a huge video game player, but it really was a source of stress relief. He could focus his unspent frustrations and hurt into competing online, and the way he explained it, I think it kept him sane during those times.<p>It&#x27;s funny, I can tell how in control of my life by gauging how much I play games. When I start obsessing about playing games (I like playing them, but when I feel I have to play them to escape), I know something needs to change in my life. I&#x27;m saying it&#x27;s that way for everyone, but it really is a great tool for stress relief for some.</text></item><item><author>jboggan</author><text>Video games become the sole source of agency in many people&#x27;s lives. This isn&#x27;t just for the unemployed, but also for folks stuck in a job where they feel like they lack control. I couldn&#x27;t understand at first why my fellow Googlers found so much time to play video games, but after a couple of months I understood. Afternoon Halo matches became the highlight of my day, I felt like I had more choice and responsibility in a 20 minute match than I did the rest of my programming work.</text></item></parent_chain><comment><author>jboggan</author><text>I agree with that, you are completely taken out of your actual context, or at least I am.<p>I used to game really heavily during a pretty terrible period (divorce + grad school) in an attempt to cope. Of course it actually just made things worse overall while distracting my brain to make it seem temporarily better, it diverted a lot of the energy I might have used towards engaging and fixing the problems.<p>When I game severely (FPS shooters are my crack) I can get focused for a dozen hours at a time. My body almost shuts down, I get into a trancelike state and my metabolism recedes. I forget to eat, I don&#x27;t get tired. When I finally do sleep I will wake up the next day and actually have a headache until I play again for a little while. It was that kind of physical withdrawal that made me realize long ago how pernicious it was, at least for my particular physiology and brain. Now I will only play games like that in a social setting, never alone lest I fall back into that spell.<p>One time in grad school I stayed up all night gaming and I slept through my alarm. I missed an exam. That I was proctoring. I went straight to a pawn shop and sold my console when I realized what I was doing to myself.</text></comment> | <story><title>A link between video games and unemployment</title><url>https://www.economist.com/blogs/economist-explains/2017/03/economist-explains-24</url></story><parent_chain><item><author>sametmax</author><text>That&#x27;s the exact opposite actually. Nit saying it&#x27;s a bad thing though. But it&#x27;s important to understand that screens are taking your attention away. You are not in the moment at all.</text></item><item><author>J-dawg</author><text>I haven&#x27;t been able to find it, but I remember a comment here on HN by a guy who basically said that gaming saved his life by helping him to zone out during a period of severe depression.<p>I guess it&#x27;s a form of mindfulness, in a way.</text></item><item><author>kemiller2002</author><text>A friend of mine felt the same way. He was undergoing a tragedy in his family, and he would play video games after returning from the hospital at night. It&#x27;s funny, looking at him and talking to him, you&#x27;d never think he&#x27;d be a huge video game player, but it really was a source of stress relief. He could focus his unspent frustrations and hurt into competing online, and the way he explained it, I think it kept him sane during those times.<p>It&#x27;s funny, I can tell how in control of my life by gauging how much I play games. When I start obsessing about playing games (I like playing them, but when I feel I have to play them to escape), I know something needs to change in my life. I&#x27;m saying it&#x27;s that way for everyone, but it really is a great tool for stress relief for some.</text></item><item><author>jboggan</author><text>Video games become the sole source of agency in many people&#x27;s lives. This isn&#x27;t just for the unemployed, but also for folks stuck in a job where they feel like they lack control. I couldn&#x27;t understand at first why my fellow Googlers found so much time to play video games, but after a couple of months I understood. Afternoon Halo matches became the highlight of my day, I felt like I had more choice and responsibility in a 20 minute match than I did the rest of my programming work.</text></item></parent_chain><comment><author>jfoutz</author><text>Would you be willing to elaborate on that a bit? Once upon a time, i played a few competitive games. I&#x27;d have to be very aware of my emotional state. Being aware of a sort of sick feeling when i&#x27;m falling behind, recognizing that that exists and not letting it affect my play <i>seems</i> like what people mean when they speak of mindfulness. And the converse, not getting cocky when pulling ahead. I also dealt with the random chemical changes of adrenaline. My hands get very cold and a little sweaty, heart races a bit. But that&#x27;s just a thing that happens. being aware of it, acknowledging it and moving on with what i choose to do next seems like a mindful practice.<p>But maybe you mean something more sophisticated?</text></comment> |
29,334,664 | 29,334,612 | 1 | 3 | 29,330,109 | train | <story><title>GC progress from JDK 8 to JDK 17</title><url>https://kstefanj.github.io/2021/11/24/gc-progress-8-17.html</url></story><parent_chain><item><author>dandotway</author><text>As Java is generally the fastest GC&#x27;d language, what&#x27;s the current state of Java gamedev?<p>Once upon a time, this indie Java game called Minecraft became the most successful game of all time.<p>But from the few minutes of research I just did, Java cannot be deployed to many commercially important systems<p><pre><code> - Nintendo Switch
- PlayStation
- iOS
</code></pre>
It appears Java is only still viable for Windows and Android, and the 1% Linux desktop market.<p>There used to be the GCJ project which would in theory let you run Java anywhere you had a C&#x2F;C++ compiler, but Oracle&#x27;s litigiousness killed that because the Java[TM] &quot;platform&quot; must run the official Java[TM] bytecode.<p>It appears C# via Monogame lets you deploy to all desktops (Win&#x2F;Mac&#x2F;Linux), mobiles (iOS&#x2F;Android), and consoles (PS&#x2F;Switch&#x2F;Xbox). So ironically C# seems to now be the &quot;write once, run anywhere&quot; fulfillment of the original Java promise.<p>[EDIT: grammar.]</text></item></parent_chain><comment><author>kllrnohj</author><text>Java&#x27;s FFI and value type situation are the two major missing pieces for Java gamedev. C# has better stories for both, and has from the beginning.<p>Don&#x27;t confuse Java having the fastest GC with Java being the fastest GC&#x27;d language (especially not in all situations)</text></comment> | <story><title>GC progress from JDK 8 to JDK 17</title><url>https://kstefanj.github.io/2021/11/24/gc-progress-8-17.html</url></story><parent_chain><item><author>dandotway</author><text>As Java is generally the fastest GC&#x27;d language, what&#x27;s the current state of Java gamedev?<p>Once upon a time, this indie Java game called Minecraft became the most successful game of all time.<p>But from the few minutes of research I just did, Java cannot be deployed to many commercially important systems<p><pre><code> - Nintendo Switch
- PlayStation
- iOS
</code></pre>
It appears Java is only still viable for Windows and Android, and the 1% Linux desktop market.<p>There used to be the GCJ project which would in theory let you run Java anywhere you had a C&#x2F;C++ compiler, but Oracle&#x27;s litigiousness killed that because the Java[TM] &quot;platform&quot; must run the official Java[TM] bytecode.<p>It appears C# via Monogame lets you deploy to all desktops (Win&#x2F;Mac&#x2F;Linux), mobiles (iOS&#x2F;Android), and consoles (PS&#x2F;Switch&#x2F;Xbox). So ironically C# seems to now be the &quot;write once, run anywhere&quot; fulfillment of the original Java promise.<p>[EDIT: grammar.]</text></item></parent_chain><comment><author>pjmlp</author><text>You can on iOS, for example with Codename One or Gluon Mobile,<p><a href="https:&#x2F;&#x2F;www.codenameone.com" rel="nofollow">https:&#x2F;&#x2F;www.codenameone.com</a><p><a href="https:&#x2F;&#x2F;gluonhq.com&#x2F;products&#x2F;mobile&#x2F;" rel="nofollow">https:&#x2F;&#x2F;gluonhq.com&#x2F;products&#x2F;mobile&#x2F;</a><p>They are also quite happy to sponsor possible console ports.</text></comment> |
31,672,448 | 31,667,263 | 1 | 2 | 31,663,298 | train | <story><title>Deepkit – High-Performance TypeScript Framework</title><url>https://deepkit.io/</url></story><parent_chain><item><author>nikeee</author><text>I&#x27;m not a fan of the idea of leveraging TS types at runtime. This is just a lock-in to TS, even if type annotations become a thing in JS.
I don&#x27;t like ORMs that use runtime types either. Most of the time, I want to write raw SQL.<p>So as an experiment, I created a library that statically types raw SQL:<p><a href="https:&#x2F;&#x2F;github.com&#x2F;nikeee&#x2F;sequelts" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;nikeee&#x2F;sequelts</a><p>The idea is to parse the SQL queries using TS&#x27;s type system. The parsed query is combined with the database schema and therefore, we know what type the query will return.<p>This is especially useful due to TS&#x27;s structural type system.
It&#x27;s also zero-overhead due to the entire functionality being just TS types, which vanish as soon as we compile. It therefore also works JS-only.<p>However, it&#x27;s just a proof of concept. I&#x27;m working on an ANTLR target for TS types, so that the SQL parser can be generated.
A game changer will also be the integration with sql-template-tags [1] (which would make this actually usable).<p>This is just for selecting data. Time will tell if it&#x27;s feasible to also type-check mutating queries.<p>The primary use-cases will target SQLite&#x2F;D1.<p>[1]: <a href="https:&#x2F;&#x2F;www.npmjs.com&#x2F;package&#x2F;sql-template-tag" rel="nofollow">https:&#x2F;&#x2F;www.npmjs.com&#x2F;package&#x2F;sql-template-tag</a></text></item></parent_chain><comment><author>throwaway858</author><text>Here is another TypeScript library for validating types of SQL queries: <a href="https:&#x2F;&#x2F;github.com&#x2F;MedFlyt&#x2F;mfsqlchecker" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;MedFlyt&#x2F;mfsqlchecker</a><p>It uses the actual PostgreSQL parser against your project&#x27;s database schema to give 100% accurate results. Guarantees that all of your queries are valid, and that all input and output types are correct (and will also auto-generate&#x2F;quickfix the output types for you in VSCode)</text></comment> | <story><title>Deepkit – High-Performance TypeScript Framework</title><url>https://deepkit.io/</url></story><parent_chain><item><author>nikeee</author><text>I&#x27;m not a fan of the idea of leveraging TS types at runtime. This is just a lock-in to TS, even if type annotations become a thing in JS.
I don&#x27;t like ORMs that use runtime types either. Most of the time, I want to write raw SQL.<p>So as an experiment, I created a library that statically types raw SQL:<p><a href="https:&#x2F;&#x2F;github.com&#x2F;nikeee&#x2F;sequelts" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;nikeee&#x2F;sequelts</a><p>The idea is to parse the SQL queries using TS&#x27;s type system. The parsed query is combined with the database schema and therefore, we know what type the query will return.<p>This is especially useful due to TS&#x27;s structural type system.
It&#x27;s also zero-overhead due to the entire functionality being just TS types, which vanish as soon as we compile. It therefore also works JS-only.<p>However, it&#x27;s just a proof of concept. I&#x27;m working on an ANTLR target for TS types, so that the SQL parser can be generated.
A game changer will also be the integration with sql-template-tags [1] (which would make this actually usable).<p>This is just for selecting data. Time will tell if it&#x27;s feasible to also type-check mutating queries.<p>The primary use-cases will target SQLite&#x2F;D1.<p>[1]: <a href="https:&#x2F;&#x2F;www.npmjs.com&#x2F;package&#x2F;sql-template-tag" rel="nofollow">https:&#x2F;&#x2F;www.npmjs.com&#x2F;package&#x2F;sql-template-tag</a></text></item></parent_chain><comment><author>seer</author><text>Hah a few months back I released <a href="https:&#x2F;&#x2F;github.com&#x2F;ivank&#x2F;potygen" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;ivank&#x2F;potygen</a><p>Similar idea - statically typing queries. Mine was mostly me playing around with recursive decent parsers seeing if I can actually parse SQL with it, and it seems to work OK, at least for Postgres.<p>It does require a &quot;build&quot; pass to generate the types, but I&#x27;ve added some additional bells and whistles like auto formatters and on hover info about columns &#x2F; views &#x2F; tables etc. Once you have the sql AST its pretty easy to build a lot of cool stuff around it.<p>It&#x27;s all pure TS and doesn&#x27;t use parser generators like ANTLR. We&#x27;ve been using it in prod for a while now and seem to be working alright - its mostly types anyway, but does have a runtime component, since sql parameters in node Postgres are too basic for our use case.<p>It all started from the amazing <a href="https:&#x2F;&#x2F;github.com&#x2F;dmaevsky&#x2F;rd-parse" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;dmaevsky&#x2F;rd-parse</a> which showed me that you could build crazy complex parsers with like 100-200 lines of code.</text></comment> |
18,427,687 | 18,427,359 | 1 | 2 | 18,426,043 | train | <story><title>Agile won the war but lost the peace</title><url>https://www.allankellyassociates.co.uk/archives/2762/agile-won-the-war-but-lost-the-peace/</url></story><parent_chain><item><author>TheOtherHobbes</author><text>If you set aside 6 weeks and it takes 12, you suck at estimating. Not only are you likely to ship a broken product, but you also have no way of making intelligent business decisions about possible projects.<p>Project A will bring in $X. You estimate 6 weeks. It takes 12. Project B will bring in $Y. You estimate 6 weeks. It takes 7. If X is similar to Y and you bet on the wrong horse, you&#x27;ve dented and&#x2F;or sunk your cash flow for no reason.<p>Saying &quot;Humans suck at estimating&quot; is nonsense. It&#x27;s a skill that can easily be improved - usually at the cost of some up front planning - and there are plenty of resources to help you with that.<p>The real problem with Agile is that it gives management an excuse to do no estimation at all. Some alpha-wannabe manager bangs their fist on a desk and says &quot;I want this in three weeks&quot;.<p>Instead of saying &quot;You&#x27;re insane&quot; teams are pressured into trying to make up for someone else&#x27;s laziness and lack of contact with reality.</text></item><item><author>yebyen</author><text>I&#x27;ve been reading &quot;It Doesn&#x27;t Have to be Crazy at Work&quot; and they have a chapter about this. Deadlines are great! Estimates are terrible, and humans are terrible at estimating. Scope needs to be elastic to accommodate this fact of life.<p>If the project is not done in the 6 weeks you set aside for it, just ship something anyways and move on. It was only worth 6 weeks when you planned on getting it done in 6 weeks, so why spend more? Go ahead and plan another sprint if it turns out what you were able to build in the time allocated wasn&#x27;t enough, and you really need more. (Put it up against the other opportunities you have, and give them all a fair chance at those finite development resources, something else might also turn out to be more important.)<p>Just don&#x27;t spend forever and drag out the deadline, throwing off the timeline for whatever you had planned to do next, because you needed more time for the thing that underestimated how big it was, so it wasn&#x27;t really possible to do that whole thing in only 6 weeks.<p>The release that is reduced in scope might be totally insufficient, or, it might be just what your users needed! The knife also cuts both ways – if you&#x27;re willing to accept that project scope can change in either direction, you can occasionally deliver things early too.<p>I really like everything about this book.</text></item><item><author>umvi</author><text>In defense of sprints, not everyone is the same. Deadlines for me are a strong motivation to get things done, whereas &quot;no deadline, just do it at your own pace until it&#x27;s done&quot; will cause me to procrastinate and get it done much more slowly.<p>There is no silver bullet for software development process. It takes hard work and flexibility to optimize your team&#x27;s work flow.</text></item><item><author>brightball</author><text>Sprints are where all of the issues with agile really come from. Constant arbitrary, meaningless deadlines that serve no purpose but create rushes, tech debt, missed “commitments” that serve as a meaningless metric to use against teams while made commitments give no benefit.<p>Everything around sprints to try to avoid the negatives results in huge wastes of time in meetings attempting to plan better rather than actually getting work done.<p>Sprint are the root cause. Just use Kanban and you eliminate most of your problems.</text></item></parent_chain><comment><author>coldtea</author><text>&gt;<i>Saying &quot;Humans suck at estimating&quot; is nonsense.</i><p>And yet it&#x27;s the conclusion every major thinker (and practicer) in our field has come to (plus there&#x27;s historical evidence from tons of mis-estimated projects, regardless of scope and budget).<p>So, whether does the idea that it&#x27;s &quot;a skill that can easily be improved&quot; come from? Wishful thinking? I don&#x27;t think the universe works that way.<p>Sure, you can learn to be less widely off. But you can&#x27;t never learn to be regularly correct at estimating, or even close within a small margin.<p>At best, what happens is that quality get shitty and corners get cut, and you get the product at the correct deadline, but it&#x27;s not the same that you wanted to ship before development started (even if the features are nominally there).</text></comment> | <story><title>Agile won the war but lost the peace</title><url>https://www.allankellyassociates.co.uk/archives/2762/agile-won-the-war-but-lost-the-peace/</url></story><parent_chain><item><author>TheOtherHobbes</author><text>If you set aside 6 weeks and it takes 12, you suck at estimating. Not only are you likely to ship a broken product, but you also have no way of making intelligent business decisions about possible projects.<p>Project A will bring in $X. You estimate 6 weeks. It takes 12. Project B will bring in $Y. You estimate 6 weeks. It takes 7. If X is similar to Y and you bet on the wrong horse, you&#x27;ve dented and&#x2F;or sunk your cash flow for no reason.<p>Saying &quot;Humans suck at estimating&quot; is nonsense. It&#x27;s a skill that can easily be improved - usually at the cost of some up front planning - and there are plenty of resources to help you with that.<p>The real problem with Agile is that it gives management an excuse to do no estimation at all. Some alpha-wannabe manager bangs their fist on a desk and says &quot;I want this in three weeks&quot;.<p>Instead of saying &quot;You&#x27;re insane&quot; teams are pressured into trying to make up for someone else&#x27;s laziness and lack of contact with reality.</text></item><item><author>yebyen</author><text>I&#x27;ve been reading &quot;It Doesn&#x27;t Have to be Crazy at Work&quot; and they have a chapter about this. Deadlines are great! Estimates are terrible, and humans are terrible at estimating. Scope needs to be elastic to accommodate this fact of life.<p>If the project is not done in the 6 weeks you set aside for it, just ship something anyways and move on. It was only worth 6 weeks when you planned on getting it done in 6 weeks, so why spend more? Go ahead and plan another sprint if it turns out what you were able to build in the time allocated wasn&#x27;t enough, and you really need more. (Put it up against the other opportunities you have, and give them all a fair chance at those finite development resources, something else might also turn out to be more important.)<p>Just don&#x27;t spend forever and drag out the deadline, throwing off the timeline for whatever you had planned to do next, because you needed more time for the thing that underestimated how big it was, so it wasn&#x27;t really possible to do that whole thing in only 6 weeks.<p>The release that is reduced in scope might be totally insufficient, or, it might be just what your users needed! The knife also cuts both ways – if you&#x27;re willing to accept that project scope can change in either direction, you can occasionally deliver things early too.<p>I really like everything about this book.</text></item><item><author>umvi</author><text>In defense of sprints, not everyone is the same. Deadlines for me are a strong motivation to get things done, whereas &quot;no deadline, just do it at your own pace until it&#x27;s done&quot; will cause me to procrastinate and get it done much more slowly.<p>There is no silver bullet for software development process. It takes hard work and flexibility to optimize your team&#x27;s work flow.</text></item><item><author>brightball</author><text>Sprints are where all of the issues with agile really come from. Constant arbitrary, meaningless deadlines that serve no purpose but create rushes, tech debt, missed “commitments” that serve as a meaningless metric to use against teams while made commitments give no benefit.<p>Everything around sprints to try to avoid the negatives results in huge wastes of time in meetings attempting to plan better rather than actually getting work done.<p>Sprint are the root cause. Just use Kanban and you eliminate most of your problems.</text></item></parent_chain><comment><author>lacey</author><text>Do you have specific resources you would recommend for learning to produce better estimates?<p>I&#x27;m also curious what kind of work you do that you find estimating effort to be reliable, and what kind of tracking you do to keep yourself honest (e.g. I often see people say something will take two weeks and the only reason it happens in two weeks is they end up working day and night for the last 5-7 days when they realize that&#x27;s what it&#x27;s going to take to make it happen).</text></comment> |
14,987,674 | 14,987,071 | 1 | 2 | 14,985,604 | train | <story><title>HyperCard On The Archive</title><url>http://blog.archive.org/2017/08/11/hypercard-on-the-archive-celebrating-30-years-of-hypercard/</url></story><parent_chain><item><author>jamestnz</author><text>In addition to echoing all the dev-related stories in this thread, I have very fond memories from my childhood of playing a 1988 HyperCard-based game called The Manhole (on our SE&#x2F;30, and later Power Mac 8100).<p>It was an immersive and extensive visual world, where the main point was just to explore. It was implemented as a series of linked HyperCard stacks, each sized to fit on a floppy disk. You&#x27;d come to remember the exact points of the game that would throw up a modal dialog prompting the insertion of the next required disk.<p>And, it happens to have been made by the brothers Rand and Robyn Miller, who later went on to create Myst (which itself is very reminiscent of The Manhole).<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Manhole" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Manhole</a>
<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=YyOTq1EpV5o" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=YyOTq1EpV5o</a><p>Unrelatedly, I wonder if anyone in this thread remembers SuperCard, a third-party knock-off of HyperCard that offered such amazing innovations as color graphics. (I also seem to recall some kind of hack where you could use ResEdit to get colour images into HyperCard stacks even though it wasn&#x27;t officially supported, but the details are fuzzy).</text></item></parent_chain><comment><author>hypercardonline</author><text>The Manhole is actually on archive.org already, so you can play it straight from your browser! <a href="https:&#x2F;&#x2F;archive.org&#x2F;details&#x2F;TheManholeMacintosh" rel="nofollow">https:&#x2F;&#x2F;archive.org&#x2F;details&#x2F;TheManholeMacintosh</a></text></comment> | <story><title>HyperCard On The Archive</title><url>http://blog.archive.org/2017/08/11/hypercard-on-the-archive-celebrating-30-years-of-hypercard/</url></story><parent_chain><item><author>jamestnz</author><text>In addition to echoing all the dev-related stories in this thread, I have very fond memories from my childhood of playing a 1988 HyperCard-based game called The Manhole (on our SE&#x2F;30, and later Power Mac 8100).<p>It was an immersive and extensive visual world, where the main point was just to explore. It was implemented as a series of linked HyperCard stacks, each sized to fit on a floppy disk. You&#x27;d come to remember the exact points of the game that would throw up a modal dialog prompting the insertion of the next required disk.<p>And, it happens to have been made by the brothers Rand and Robyn Miller, who later went on to create Myst (which itself is very reminiscent of The Manhole).<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Manhole" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Manhole</a>
<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=YyOTq1EpV5o" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=YyOTq1EpV5o</a><p>Unrelatedly, I wonder if anyone in this thread remembers SuperCard, a third-party knock-off of HyperCard that offered such amazing innovations as color graphics. (I also seem to recall some kind of hack where you could use ResEdit to get colour images into HyperCard stacks even though it wasn&#x27;t officially supported, but the details are fuzzy).</text></item></parent_chain><comment><author>bsclifton</author><text>One of my best friends made a toolkit available on AOL&#x27;s HyperCard section called &quot;Color Paint Tools&quot; which let you put color into your stacks (making that hack you mentioned easier). If I remember correctly, HyperCard could show color images via an XCMD but they&#x27;d have to be a PICT resource (so it&#x27;s not a real solution). I think Apple eventually released an update (HyperCard 2.2?) which included an official toolkit for doing this</text></comment> |
2,966,479 | 2,965,595 | 1 | 3 | 2,965,053 | train | <story><title>"I've got an idea for an app"</title><url>http://chriseidhof.tumblr.com/post/9873846899/ive-got-an-idea-for-an-app</url></story><parent_chain><item><author>gyardley</author><text>So let's say I take the author's advice, 'always listen to ideas', and unlike the author, get told an awesome idea by a friend-of-a-friend with zero ability to execute.<p>Great, now what?<p>Do I really set up a working relationship with this person, who's likely dead weight and valueless now that the idea's been revealed? Do I give him the ownership he thinks he deserves, which is a 50-50 split if I'm lucky? Do I just build it myself?<p>I prefer to avoid such ethical quandaries, which is why I stick to my own ideas.</text></item></parent_chain><comment><author>dangero</author><text>Exactly. The other day I was hanging out with some relatives from out of town and my uncle dropped that famous line, "I have an idea for an app." I had been functioning under the same notion that I should always listen to people's ideas, so I listened.<p>He then says, "I'll tell you, but if you build it I want 50%." I said, "Fine." In my mind I'm thinking, "No way I'm building this." Then he says, "OK, my idea is a contact management application for the iPhone. They have them for the PC, but they don't have them for the iPhone." That's it. That's his whole idea.<p>That's when I realized I should stop listening to people's ideas about apps because he just basically told me that I can't build any contact management apps without giving him half the profits. If I listen to too many people's ideas, I won't be able to build something without being sued because someone else "gave me the idea".</text></comment> | <story><title>"I've got an idea for an app"</title><url>http://chriseidhof.tumblr.com/post/9873846899/ive-got-an-idea-for-an-app</url></story><parent_chain><item><author>gyardley</author><text>So let's say I take the author's advice, 'always listen to ideas', and unlike the author, get told an awesome idea by a friend-of-a-friend with zero ability to execute.<p>Great, now what?<p>Do I really set up a working relationship with this person, who's likely dead weight and valueless now that the idea's been revealed? Do I give him the ownership he thinks he deserves, which is a 50-50 split if I'm lucky? Do I just build it myself?<p>I prefer to avoid such ethical quandaries, which is why I stick to my own ideas.</text></item></parent_chain><comment><author>SandB0x</author><text>This is why movie studios explicitly say they won't read your scripts and film suggestions if you send one in. They want to be able to make a film without the danger of being sued for stealing ideas.</text></comment> |
39,035,770 | 39,035,637 | 1 | 2 | 39,034,835 | train | <story><title>Coming to Grips with Apple's Seemingly Unshakable Sense of Entitlement</title><url>https://daringfireball.net/2024/01/coming_to_grips_with_apples_seemingly_unshakable_sense_of_app_store_entitlement</url></story><parent_chain><item><author>bitvoid</author><text>I get the argument, but it falls flat for me. Consoles are basically appliances with a primarily singular purpose: video games. Smart phones, in my opinion, are general purpose computers that should be treated differently. Games are a small subset of what people use smart phones for.</text></item><item><author>lolinder</author><text>The comparison Apple made in the court case was not primarily to Steam or Google, it was to the consoles. Microsoft, Sony, and Nintendo all take a 30% cut of all of Epic&#x27;s transactions across their respective platforms. Apple argued, and persuaded the judge, that Epic&#x27;s targeting of <i>Apple specifically</i> for <i>it&#x27;s</i> 30% share was unreasonable given that Epic was happily paying the fee to all the other platforms:<p>&gt; Indeed, for example, Epic Games has agreed to such a rate on all Fortnite transactions via the Microsoft (Xbox) Store, the PlayStation Store, the Nintendo eShop, and Google Play. Epic Games has also agreed to extra payments for certain platform holders above and beyond the standard 30% commission rate. For example, for all Fortnite transactions via the PlayStation Store, Epic Games agreed to make additional payments to Sony above this commission rate based on the amount of time that PlayStation users play Fortnite cross-platform.<p>The judge forced Apple to allow transactions to take place off of the platform, but she <i>explicitly</i> noted that Apple would still be entitled to a commission on said sales.<p>Apple sees their App Store arrangement as similar to Upwork, Rover, or any number of other marketplaces, which <i>all</i> have policies preventing users from meeting through the system but transacting outside of it. From their perspective, if they hooked you up with the sale, then they&#x27;re entitled to a commission. If you think you can do better without their sales, you&#x27;re welcome to pull out of their marketplace, and if they find that you&#x27;re abusing their marketplace they&#x27;ll hasten you to the door.<p>That is, as far as the judge was concerned, perfectly legal, and I&#x27;m having a hard time not seeing it as a reasonable position to take.<p>[0] <a href="https:&#x2F;&#x2F;casetext.com&#x2F;case&#x2F;epic-games-inc-v-apple-inc-2" rel="nofollow">https:&#x2F;&#x2F;casetext.com&#x2F;case&#x2F;epic-games-inc-v-apple-inc-2</a></text></item><item><author>rpmisms</author><text>There is simply no way around the fact that Apple demanding a cut of sales on an external platform is ridiculous. Steam does not do this. Google does not do this. This would be absolutely absurd for anyone else in any market to do, and this will likely be exhibit C at Apple&#x27;s inevitable antitrust trial.<p>Edit:<p>Re-reading, and I wish that the article was longer. Of course Apple doesn&#x27;t want to allow side-loading, but they&#x27;re going to have to eventually, so why not do it proactively and in a way that allows third-party apps to be extra-sandboxed or reviewed? Oh right, because they&#x27;re Apple. I appreciate the methodology, but a touch of openness will not kill their profits or trust level.</text></item></parent_chain><comment><author>askonomm</author><text>I, and a lot of other people, buy iPhones specifically because they are not Androids - it&#x27;s hard to break them, install something horrible, etc. It&#x27;s also why I recommend iPhones to older folk, like my mom, and from what I can tell, the need for me to help them out has decreased a ton since they stopped using Androids.<p>So why are you pushing for everything to have to be a general purpose computer? Why can&#x27;t there be one phone maker that caters to those who don&#x27;t want something like that? Why can&#x27;t you just use Android, which is that? I just find it incredibly unfair that everything has to be the same for some odd reason for people who keep pushing for these things.</text></comment> | <story><title>Coming to Grips with Apple's Seemingly Unshakable Sense of Entitlement</title><url>https://daringfireball.net/2024/01/coming_to_grips_with_apples_seemingly_unshakable_sense_of_app_store_entitlement</url></story><parent_chain><item><author>bitvoid</author><text>I get the argument, but it falls flat for me. Consoles are basically appliances with a primarily singular purpose: video games. Smart phones, in my opinion, are general purpose computers that should be treated differently. Games are a small subset of what people use smart phones for.</text></item><item><author>lolinder</author><text>The comparison Apple made in the court case was not primarily to Steam or Google, it was to the consoles. Microsoft, Sony, and Nintendo all take a 30% cut of all of Epic&#x27;s transactions across their respective platforms. Apple argued, and persuaded the judge, that Epic&#x27;s targeting of <i>Apple specifically</i> for <i>it&#x27;s</i> 30% share was unreasonable given that Epic was happily paying the fee to all the other platforms:<p>&gt; Indeed, for example, Epic Games has agreed to such a rate on all Fortnite transactions via the Microsoft (Xbox) Store, the PlayStation Store, the Nintendo eShop, and Google Play. Epic Games has also agreed to extra payments for certain platform holders above and beyond the standard 30% commission rate. For example, for all Fortnite transactions via the PlayStation Store, Epic Games agreed to make additional payments to Sony above this commission rate based on the amount of time that PlayStation users play Fortnite cross-platform.<p>The judge forced Apple to allow transactions to take place off of the platform, but she <i>explicitly</i> noted that Apple would still be entitled to a commission on said sales.<p>Apple sees their App Store arrangement as similar to Upwork, Rover, or any number of other marketplaces, which <i>all</i> have policies preventing users from meeting through the system but transacting outside of it. From their perspective, if they hooked you up with the sale, then they&#x27;re entitled to a commission. If you think you can do better without their sales, you&#x27;re welcome to pull out of their marketplace, and if they find that you&#x27;re abusing their marketplace they&#x27;ll hasten you to the door.<p>That is, as far as the judge was concerned, perfectly legal, and I&#x27;m having a hard time not seeing it as a reasonable position to take.<p>[0] <a href="https:&#x2F;&#x2F;casetext.com&#x2F;case&#x2F;epic-games-inc-v-apple-inc-2" rel="nofollow">https:&#x2F;&#x2F;casetext.com&#x2F;case&#x2F;epic-games-inc-v-apple-inc-2</a></text></item><item><author>rpmisms</author><text>There is simply no way around the fact that Apple demanding a cut of sales on an external platform is ridiculous. Steam does not do this. Google does not do this. This would be absolutely absurd for anyone else in any market to do, and this will likely be exhibit C at Apple&#x27;s inevitable antitrust trial.<p>Edit:<p>Re-reading, and I wish that the article was longer. Of course Apple doesn&#x27;t want to allow side-loading, but they&#x27;re going to have to eventually, so why not do it proactively and in a way that allows third-party apps to be extra-sandboxed or reviewed? Oh right, because they&#x27;re Apple. I appreciate the methodology, but a touch of openness will not kill their profits or trust level.</text></item></parent_chain><comment><author>lolinder</author><text>I agree that smart phones <i>should</i> be general purpose computers, but that&#x27;s why I use Android. iPhones are explicitly designed to <i>not</i> be general purpose computers, and that&#x27;s part of the appeal for a lot of people.</text></comment> |
26,617,403 | 26,617,541 | 1 | 2 | 26,615,938 | train | <story><title>Terminal escape sequences in Git commit email field</title><url>https://twitter.com/ryancdotorg/status/1375484757916672000</url></story><parent_chain><item><author>junon</author><text>I maintain chalk and a slew of other TTY related things.<p>Terminal emulators are, far and away, the most archaic computer technology we still use daily.<p>Believe me when I say, it&#x27;s a very hard problem to solve since everyone has subscribed to Unix&#x27;s philosophy of &quot;everything is text&quot;.<p>As much as I dislike Microsoft&#x27;s philosophies on software, they had the right idea with Powershell. Its execution is just abysmal.<p>Expect this stuff to change drastically in the next 5 years.</text></item></parent_chain><comment><author>st_goliath</author><text>&gt; Expect this stuff to change drastically in the next 5 years.<p>Bwahaha... is this your first encounter with backwards compatibility?<p>Changing this would be <i>very hard</i>, but this has <i>nothing</i> to do with somebody embracing some grand philosophy, but with <i>tons</i> of existing software relying on Unix like systems to, well ... be Unix-like, because that&#x27;s what the software was written for.</text></comment> | <story><title>Terminal escape sequences in Git commit email field</title><url>https://twitter.com/ryancdotorg/status/1375484757916672000</url></story><parent_chain><item><author>junon</author><text>I maintain chalk and a slew of other TTY related things.<p>Terminal emulators are, far and away, the most archaic computer technology we still use daily.<p>Believe me when I say, it&#x27;s a very hard problem to solve since everyone has subscribed to Unix&#x27;s philosophy of &quot;everything is text&quot;.<p>As much as I dislike Microsoft&#x27;s philosophies on software, they had the right idea with Powershell. Its execution is just abysmal.<p>Expect this stuff to change drastically in the next 5 years.</text></item></parent_chain><comment><author>tambourine_man</author><text>We&#x27;ve tried many times and in many ways, but text is still the main interface for programers (and even for a lot of end user tasks as well).<p>As long as this interface remains undisputed, &quot;everything is text&quot; is a feature, not a bug. Arguably, one of Unix&#x27;s greatest.</text></comment> |
16,773,443 | 16,769,239 | 1 | 2 | 16,768,021 | train | <story><title>Berkeley offers its data science course online for free</title><url>http://news.berkeley.edu/2018/03/29/berkeley-offers-its-fastest-growing-course-data-science-online-for-free/</url></story><parent_chain><item><author>jamestimmins</author><text>I find it curious that there are so many courses for data-science related subjects, which superficially seem to cover the same material, and relatively few courses covering more traditional CS topics such as computer systems, networks, OS. I suppose it has to do with the market, but also feels like colleges are skating to where the puck is, rather than where it will be (or perhaps, where it could be).</text></item></parent_chain><comment><author>sigi45</author><text>This is a general issue i have seen as well.<p>We live in 2018 and there is no open source course for everything. Instead there are probably 10-30k universities who have similar courses and professors who give the same lecture every year.<p>They get paid often enough by countries to create and do those courses. In germany most of our unversities are paid by all of us germans anyway.<p>And what do you find online? Always the starter verion like 101 computer science or videos with bad audio or video, no proper exercises, no solution helper etc. Nothing. You have to go to different sites to sometimes pay or sometimes not.<p>there are no local locations to meet up with people.<p>There should be a global initiative for global free and open access learning. Sponsored and supported by companies and countries. Build upon a core of a knowledge graph based on topics or &#x27;snippets of knowledge&#x27;. Like for example:
math -&gt; add -&gt; sub<p>Something like &#x27;The Map of Mathematics&#x27; (<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=OmJ-4B-mS-Y" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=OmJ-4B-mS-Y</a>)<p>And when you wanna get the global accepted math 101 level, you have to take specific topics &#x2F; snippets.<p>And those snippets can than be filled with different people who are making a lecture for that topic and you can choose whom you like more or who is better in explaining it to you.<p>What do i do instead? I ask around for the lecture scripts because they are always behind a simple password protected area or have multiple links to different pages of different universietses who offer different courses for free as videos for there students in sometimes&#x2F;often bad quality and &#x2F; or bad video players etc.<p>It sucks and this is stupid.</text></comment> | <story><title>Berkeley offers its data science course online for free</title><url>http://news.berkeley.edu/2018/03/29/berkeley-offers-its-fastest-growing-course-data-science-online-for-free/</url></story><parent_chain><item><author>jamestimmins</author><text>I find it curious that there are so many courses for data-science related subjects, which superficially seem to cover the same material, and relatively few courses covering more traditional CS topics such as computer systems, networks, OS. I suppose it has to do with the market, but also feels like colleges are skating to where the puck is, rather than where it will be (or perhaps, where it could be).</text></item></parent_chain><comment><author>resolaibohp</author><text>I have also found this interesting. What I don&#x27;t understand is that the amount of data science jobs are no where near the levels that people make it seem. I am not sure where all these people will end up working if they want to be a data scientist. There is not a need to hire huge teams of data scientists like you might for dev roles, it doesn&#x27;t scale the same way.</text></comment> |
33,648,692 | 33,648,793 | 1 | 2 | 33,647,689 | train | <story><title>Hardening unused (sub)domains</title><url>https://www.mailhardener.com/kb/hardening-unused-domains</url></story><parent_chain></parent_chain><comment><author>sideproject</author><text>Speaking of un-used domains, I had ~50 or ~60. I didn&#x27;t like the old domain parking tools, so I created my own<p><a href="https:&#x2F;&#x2F;newsy.co" rel="nofollow">https:&#x2F;&#x2F;newsy.co</a><p>It creates a content-aggregator site for your domain based on keywords important to your domain with a bunch of features related to building the traffic, monetizing etc.<p>But I digress. One of the features that I built was to allow users to send and receive emails using the domain names. This became an important feature once the site grows to become a bit more like a community (where users are submitting posts, comments etc) and there needs to be a way to engage with the userbase. It&#x27;s also important for people who want to sell your domains.<p>The two specific features I built was<p>1) Using your existing GMail to send and receive emails with your custom domain
2) Forwarding your email to another inbox.<p>The email hardening advice given in this post is great - I&#x27;ve also added some of these and allow users to make changes to their DNS records directly.</text></comment> | <story><title>Hardening unused (sub)domains</title><url>https://www.mailhardener.com/kb/hardening-unused-domains</url></story><parent_chain></parent_chain><comment><author>fevangelou</author><text>GOV.UK has similar recommendations since 2016: <a href="https:&#x2F;&#x2F;www.gov.uk&#x2F;guidance&#x2F;protect-domains-that-dont-send-email" rel="nofollow">https:&#x2F;&#x2F;www.gov.uk&#x2F;guidance&#x2F;protect-domains-that-dont-send-e...</a></text></comment> |
15,900,733 | 15,900,338 | 1 | 2 | 15,898,886 | train | <story><title>Estonia, the Digital Republic</title><url>https://www.newyorker.com/magazine/2017/12/18/estonia-the-digital-republic</url></story><parent_chain><item><author>masswerk</author><text>I know, this may be unpopular in context, but are there any updates on the Estonian ID-cards?<p>News as of November were that they were (temporarily) locked-down [1] and are to be reissued until next March [2] in reaction to the RSA related security flaws [3] in the libraries bundled with the Infineon chip. Is this even an issue, or is everyone using a phone app, instead of the cards, anyway?<p>[1] <a href="https:&#x2F;&#x2F;www.theregister.co.uk&#x2F;2017&#x2F;11&#x2F;03&#x2F;estonian_e_id_lockdown&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.theregister.co.uk&#x2F;2017&#x2F;11&#x2F;03&#x2F;estonian_e_id_lockd...</a><p>[2] <a href="http:&#x2F;&#x2F;www.bbc.com&#x2F;news&#x2F;technology-41858583" rel="nofollow">http:&#x2F;&#x2F;www.bbc.com&#x2F;news&#x2F;technology-41858583</a><p>[3] <a href="https:&#x2F;&#x2F;www.schneier.com&#x2F;blog&#x2F;archives&#x2F;2017&#x2F;09&#x2F;security_flaw_i.html" rel="nofollow">https:&#x2F;&#x2F;www.schneier.com&#x2F;blog&#x2F;archives&#x2F;2017&#x2F;09&#x2F;security_flaw...</a></text></item></parent_chain><comment><author>sccxy</author><text>Most people who use ID card every day have updated certs remotely or went to police office. I would say government handled it pretty well.<p>Problematic was communication with card maker Gemalto, who didn&#x27;t inform Estonia about security flaws properly. Gemalto was informed by researchers in March. These researchers informed Estonian government in August. Few days after that prime minister announced security problems.<p>Things would have been a lot of easier if Gemalto didn&#x27;t hide the problem from the government.</text></comment> | <story><title>Estonia, the Digital Republic</title><url>https://www.newyorker.com/magazine/2017/12/18/estonia-the-digital-republic</url></story><parent_chain><item><author>masswerk</author><text>I know, this may be unpopular in context, but are there any updates on the Estonian ID-cards?<p>News as of November were that they were (temporarily) locked-down [1] and are to be reissued until next March [2] in reaction to the RSA related security flaws [3] in the libraries bundled with the Infineon chip. Is this even an issue, or is everyone using a phone app, instead of the cards, anyway?<p>[1] <a href="https:&#x2F;&#x2F;www.theregister.co.uk&#x2F;2017&#x2F;11&#x2F;03&#x2F;estonian_e_id_lockdown&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.theregister.co.uk&#x2F;2017&#x2F;11&#x2F;03&#x2F;estonian_e_id_lockd...</a><p>[2] <a href="http:&#x2F;&#x2F;www.bbc.com&#x2F;news&#x2F;technology-41858583" rel="nofollow">http:&#x2F;&#x2F;www.bbc.com&#x2F;news&#x2F;technology-41858583</a><p>[3] <a href="https:&#x2F;&#x2F;www.schneier.com&#x2F;blog&#x2F;archives&#x2F;2017&#x2F;09&#x2F;security_flaw_i.html" rel="nofollow">https:&#x2F;&#x2F;www.schneier.com&#x2F;blog&#x2F;archives&#x2F;2017&#x2F;09&#x2F;security_flaw...</a></text></item></parent_chain><comment><author>clon</author><text>Most people I interact with (here in EE) were not too much affected by the problem, since a lot of people actually use MobileID, with the crypto chip embedded in the SIM card of your smartphone, which was unaffected and available for like 10€ from each telco in Estonia. Saves you from lugging around a smartcard reader. Depending on your threat model, the fact that the PIN never enters computer memory is an advantage for MobileID, unless you prefer a proper PIN-pad reader.</text></comment> |
35,523,472 | 35,521,637 | 1 | 2 | 35,513,636 | train | <story><title>I fixed a parasitic drain on my car in 408 days</title><url>https://davidmuller.github.io/posts/2023/04/10/how-i-fixed-a-parasitic-drain-in-408-days.html</url></story><parent_chain><item><author>Reason077</author><text>My flatmate does this with kitchen cupboard doors, and, most annoyingly, the microwave. She&#x27;ll open the microwave to stop it, takes her food out and, just ... leaves it open. Then when I close it later it will start up again with nothing inside. Arrrgh!</text></item><item><author>o10449366</author><text>My wife, bless her heart, leaves everything partially open. Not even just open, but she&#x27;ll screw the lid on jars just enough where if I pick it up by the top they&#x27;ll drop. It drives me crazy.</text></item><item><author>adversaryIdiot</author><text>Thats insane... To consistently not close the door like that</text></item><item><author>civilized</author><text>My wife and I gave our old car to her parents. In the subsequent years, its battery kept dying and we had to go over to their place and jump it. Never happened in the prior 7 years we&#x27;d owned the car. The mechanic said nothing wrong with the battery, but suggested there might be a parasitic drain somewhere.<p>A few days later, we were visiting them. I looked at the car and saw the door closed, but not properly latched and ever-so-slightly ajar. You know, that half-closed thing car doors do when you don&#x27;t close them hard enough.<p>It turns out someone, possibly my son, had been not closing the door completely. This did not keep the lights on or cause any other visible sign, as it would in some cars.<p>After I told them to slam the door fully shut, never a problem again for 2 years and counting.</text></item></parent_chain><comment><author>lelanthran</author><text>&gt; My flatmate does this with kitchen cupboard doors, and, most annoyingly, the microwave. She&#x27;ll open the microwave to stop it, takes her food out and, just ... leaves it open. Then when I close it later it will start up again with nothing inside. Arrrgh!<p>So? Hit the cancel button when you close it - you have to be right there to close it after all.<p>TBH, I do this too, because I hate putting in some milk to warm for cereal and getting out warm milk flavoured with and smelling of the curry we warmed last night.<p>Anytime the microwave oven is used for aromatic food or any meal with flavouring, leave the door open.</text></comment> | <story><title>I fixed a parasitic drain on my car in 408 days</title><url>https://davidmuller.github.io/posts/2023/04/10/how-i-fixed-a-parasitic-drain-in-408-days.html</url></story><parent_chain><item><author>Reason077</author><text>My flatmate does this with kitchen cupboard doors, and, most annoyingly, the microwave. She&#x27;ll open the microwave to stop it, takes her food out and, just ... leaves it open. Then when I close it later it will start up again with nothing inside. Arrrgh!</text></item><item><author>o10449366</author><text>My wife, bless her heart, leaves everything partially open. Not even just open, but she&#x27;ll screw the lid on jars just enough where if I pick it up by the top they&#x27;ll drop. It drives me crazy.</text></item><item><author>adversaryIdiot</author><text>Thats insane... To consistently not close the door like that</text></item><item><author>civilized</author><text>My wife and I gave our old car to her parents. In the subsequent years, its battery kept dying and we had to go over to their place and jump it. Never happened in the prior 7 years we&#x27;d owned the car. The mechanic said nothing wrong with the battery, but suggested there might be a parasitic drain somewhere.<p>A few days later, we were visiting them. I looked at the car and saw the door closed, but not properly latched and ever-so-slightly ajar. You know, that half-closed thing car doors do when you don&#x27;t close them hard enough.<p>It turns out someone, possibly my son, had been not closing the door completely. This did not keep the lights on or cause any other visible sign, as it would in some cars.<p>After I told them to slam the door fully shut, never a problem again for 2 years and counting.</text></item></parent_chain><comment><author>hoseja</author><text>IMO a good thing, lets them ventilate better. Not cancelling the timer is the wrong thing there.</text></comment> |
4,418,498 | 4,418,334 | 1 | 2 | 4,417,571 | train | <story><title>Status Chart: Your Personal Status Dashboard</title><url>http://statuschart.com/</url></story><parent_chain><item><author>mattwdelong</author><text>This is pretty neat, but it's not something I would enter my CC details for and pay for each month. I would however drop a one time ~$25 fee and self host it on my own server, and <i>maybe</i> use it. At least this way, I will see it running on my server and periodically update it.<p>I'm just one person of many, but when I see neat little apps like this I would always much rather pay for it outright than pay for it each month. I don't know why more people don't sell cool services like this. Chances are I am going to just cancel it after a month anyway.</text></item></parent_chain><comment><author>natep</author><text>Especially for something like this. I might not need this to land a job for years, but when I do, I'll want to know that all the work I put into adding content to this won't have been wasted (i.e. service disappears for any number of reasons, OP is already 98% busy :/).<p>That's not so say that a hosted, subscription service wouldn't be useful for some, but self-hosing would allow users to solve problems for themselves that would otherwise be feature requests, and hard to design well for everyone.<p>I know OP doesn't want to be another LinkedIn, but there's no reason why he or someone else couldn't create an opt-in browsable database of these for better discoverability. How awesome would it be if you could click a link next to your hackathon entry and see the status page of other attendees?</text></comment> | <story><title>Status Chart: Your Personal Status Dashboard</title><url>http://statuschart.com/</url></story><parent_chain><item><author>mattwdelong</author><text>This is pretty neat, but it's not something I would enter my CC details for and pay for each month. I would however drop a one time ~$25 fee and self host it on my own server, and <i>maybe</i> use it. At least this way, I will see it running on my server and periodically update it.<p>I'm just one person of many, but when I see neat little apps like this I would always much rather pay for it outright than pay for it each month. I don't know why more people don't sell cool services like this. Chances are I am going to just cancel it after a month anyway.</text></item></parent_chain><comment><author>1123581321</author><text>For hosted, an annual fee is appropriate here. A $25 annual fee is quite similar to a one-time fee of $25 because once it is paid, there is nothing to do but use it for an entire year. After a year, it's very obvious whether the app is worth another $25 or not. Either way the developer's compensation is nearly the same assuming many accounts share the low cost of the servers.</text></comment> |
13,763,641 | 13,759,923 | 1 | 3 | 13,759,472 | train | <story><title>A JavaScript deep learning and reinforcement learning library</title><url>https://github.com/janhuenermann/neurojs</url></story><parent_chain></parent_chain><comment><author>merricksb</author><text>Discussed 2 days ago (244 points):<p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=13742911" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=13742911</a></text></comment> | <story><title>A JavaScript deep learning and reinforcement learning library</title><url>https://github.com/janhuenermann/neurojs</url></story><parent_chain></parent_chain><comment><author>platz</author><text>I get why deep learning is nice but I just do not get the hype around reinforcement learning yet. RL seems great for things like training video game agents and have seen videos of this, but fail to understand where RL can be applied in the real world.<p>It reminds me a bit of genetic algorithms. GA is the &#x27;last resort&#x27; when you truly know nothing about how to model your problem.<p>What is the sweet spot for RL?</text></comment> |
27,595,465 | 27,589,179 | 1 | 2 | 27,585,208 | train | <story><title>Apple Daily to shut in days unless government agrees to plea to unfreeze assets</title><url>https://en.appledaily.com/apple-daily-to-shut-in-days-unless-government-agrees-to-last-ditch-plea-to-unfreeze-assets/JKXIS3OPZNFIFAJWU3PMO2R6R4</url></story><parent_chain><item><author>nicochrome</author><text>The majority of Hong Kong people believe ridiculous conspiracy theories, have anti-immigration sentiments, and racist ways of thinking, worse so because racial discrimination is just a way of life for many in HK, so I wouldn&#x27;t say majority rules is the best argument here. Hong Kong isn&#x27;t this shining jewel of liberalism by any means. All of it just gives China more justification for their actions.</text></item><item><author>agnesv</author><text>I would say to the majority of HK Apple Daily represents freedom and democracy, few refers it as “trash”</text></item><item><author>ilamont</author><text>To some, Apple Daily represents democratic values such as a free press. Others view it as tabloid trash. I see it as an important tool of innovation in media. Lai pushed the envelope for Chinese language media, taking newsgathering and publishing far further than peer publications in Hong Kong and Taiwan.<p>Some of his innovations - such as 3D news event simulations that Lai&#x27;s Next Media began publishing in the 2000s - made an impact far beyond Hong Kong and Taiwan (<a href="https:&#x2F;&#x2F;www.reuters.com&#x2F;article&#x2F;idUSTOE6AS04Q20101129" rel="nofollow">https:&#x2F;&#x2F;www.reuters.com&#x2F;article&#x2F;idUSTOE6AS04Q20101129</a>)<p>It&#x27;s sad to see this entrepreneurial news venture come to an end like this. It&#x27;s criminal that Lai and his top editors have been thrown in jail.</text></item></parent_chain><comment><author>dang</author><text>Sorry for this being off-topic, but could you please stop creating accounts for every few comments you post? We ban accounts that do that. This is in the site guidelines: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;newsguidelines.html" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;newsguidelines.html</a>.<p>You needn&#x27;t use your real name, of course, but for HN to be a community, users need some identity for other users to relate to. Otherwise we may as well have no usernames and no community, and that would be a different kind of forum. <a href="https:&#x2F;&#x2F;hn.algolia.com&#x2F;?sort=byDate&amp;dateRange=all&amp;type=comment&amp;storyText=false&amp;prefix&amp;page=0&amp;query=community%20identity%20by:dang" rel="nofollow">https:&#x2F;&#x2F;hn.algolia.com&#x2F;?sort=byDate&amp;dateRange=all&amp;type=comme...</a></text></comment> | <story><title>Apple Daily to shut in days unless government agrees to plea to unfreeze assets</title><url>https://en.appledaily.com/apple-daily-to-shut-in-days-unless-government-agrees-to-last-ditch-plea-to-unfreeze-assets/JKXIS3OPZNFIFAJWU3PMO2R6R4</url></story><parent_chain><item><author>nicochrome</author><text>The majority of Hong Kong people believe ridiculous conspiracy theories, have anti-immigration sentiments, and racist ways of thinking, worse so because racial discrimination is just a way of life for many in HK, so I wouldn&#x27;t say majority rules is the best argument here. Hong Kong isn&#x27;t this shining jewel of liberalism by any means. All of it just gives China more justification for their actions.</text></item><item><author>agnesv</author><text>I would say to the majority of HK Apple Daily represents freedom and democracy, few refers it as “trash”</text></item><item><author>ilamont</author><text>To some, Apple Daily represents democratic values such as a free press. Others view it as tabloid trash. I see it as an important tool of innovation in media. Lai pushed the envelope for Chinese language media, taking newsgathering and publishing far further than peer publications in Hong Kong and Taiwan.<p>Some of his innovations - such as 3D news event simulations that Lai&#x27;s Next Media began publishing in the 2000s - made an impact far beyond Hong Kong and Taiwan (<a href="https:&#x2F;&#x2F;www.reuters.com&#x2F;article&#x2F;idUSTOE6AS04Q20101129" rel="nofollow">https:&#x2F;&#x2F;www.reuters.com&#x2F;article&#x2F;idUSTOE6AS04Q20101129</a>)<p>It&#x27;s sad to see this entrepreneurial news venture come to an end like this. It&#x27;s criminal that Lai and his top editors have been thrown in jail.</text></item></parent_chain><comment><author>RavlaAlvar</author><text>Dehumanising HK people by calling them racist. I really have to ask, who is the racist here?</text></comment> |
14,333,983 | 14,333,766 | 1 | 2 | 14,332,479 | train | <story><title>Show HN: Howmanypeoplearearound – Use wifi to calculate number of people around</title><url>https://github.com/schollz/howmanypeoplearearound</url></story><parent_chain></parent_chain><comment><author>contingencies</author><text>Bluetooth equivalent would be cool, then pairing bluetooth and wifi MACs based on temporal correlation. If one changes you can infer from the other. Over time you could split it to <i>howmanylocalsaround</i> verus <i>howmanyvisitorsaround</i>.</text></comment> | <story><title>Show HN: Howmanypeoplearearound – Use wifi to calculate number of people around</title><url>https://github.com/schollz/howmanypeoplearearound</url></story><parent_chain></parent_chain><comment><author>flor1s</author><text>I&#x27;m sure this is already being done at a massive scale. It seems like disabling all connectivity when you are not using it would be good for privacy.</text></comment> |
8,267,368 | 8,267,267 | 1 | 2 | 8,267,148 | train | <story><title>React Components</title><url>http://react-components.com/</url></story><parent_chain></parent_chain><comment><author>skrebbel</author><text><i>(Marginally related rant)</i><p>I love React, but so far I&#x27;ve been a bit underwhelmed by the ecosystem of components that has sprung up. I hope that this site will help.<p>A lot of the components are stuff that aren&#x27;t really UI elements, but rather add magic to other UI elements or even do something completely unrelated to the UI.<p>I mean, I&#x27;ve seen routers written as React components![1] Wtf? Why is it an advantage to express a route as XML-like JSX? Why put it in a virtual DOM? That&#x27;s just waiting for unexpected side-effects to happen. I can imagine that a lean, to-the-point router is a good combination with React but components are for <i>UI widgets</i>, not for configuration.<p>I feel like this is the same mistake as the everything-in-XML hype of the early 21st century (Spring, anyone?), or the everything-as-a-DSL hype in early Scala (with clear, descriptive operators such as ~~=, $%% and of course &amp;^), or the current hype in C#-o-world to package web assets into NuGet packages (jquery.dll - seriously?). Just because you <i>can</i> put it in a component, doesn&#x27;t mean that you <i>should</i>.<p>Behavioral features for components (e.g. infinite-scrolling or tooltip triggers) are well distributed as a mixin. Stuff not directly related to UI widgets should just be vanilla JavaScript. Asset libraries should be asset libraries.<p>What I expect from open source components is UI elements. Color pickers, fancy dropdown selects, login widgets, form elements with pluggable validation maybe (but the validation logic shouldn&#x27;t be components). Notably, I&#x27;d love an ecosystem of UI frameworks ala Bootstrap or Foundation to spring up around React, and it appears that this is happening.<p>(Sidenote, if there&#x27;s one development we <i>do</i> need, then it&#x27;s a clear React-authors-condoned way to couple (parameterized) CSS with React components, so that we can really distribute self-contained components including style. A development like that would also help focus the React component ecosystem on what it should be about: UI widgets.)<p>[1] Random example: <a href="https://github.com/rackt/react-router#whats-it-look-like" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;rackt&#x2F;react-router#whats-it-look-like</a> - seriously, what were they thinking?</text></comment> | <story><title>React Components</title><url>http://react-components.com/</url></story><parent_chain></parent_chain><comment><author>blablabla123</author><text>Interesting... Actually last week I stumbled upon react-bootstrap. After all I wasn&#x27;t enthusiastic to use it yet, because I wonder whether it interfers with the regular bootstrap. (Right now the app I work on is only partially implemented in React.)</text></comment> |
18,040,706 | 18,040,840 | 1 | 2 | 18,039,489 | train | <story><title>NewSQL databases fail to guarantee consistency and I blame Spanner</title><url>http://dbmsmusings.blogspot.com/2018/09/newsql-database-systems-are-failing-to.html</url></story><parent_chain><item><author>Quekid5</author><text>I may be a bit of an old fart, but this is the exact reasoning behind my decision to never go with &quot;distributed X&quot; if there&#x27;s a &quot;single-machine X&quot; where you can just vertically scale.<p>If you can afford 3-5 machines&#x2F;VMs for a cluster you can almost certainly afford a single machine&#x2F;VM with 2-4x the resources&#x2F;CPU and chances are that it&#x27;ll perform just as well (or better) because it doesn&#x27;t have network latency to contend with.<p>Of course if you&#x27;re around N &gt;= 7 or N &gt;= 9, <i>then</i> you should perhaps start considering &quot;distributed X&quot;.<p>As long as your application is mostly built on very few assumptions about consistency it&#x27;s usually pretty painless to actually go distributed.<p>Of course, there <i>are</i> legitimate cases where you want to go distributed even with N=3 or N=5, but IME they&#x27;re very few and far between... but if your 3&#x2F;5 machines are co-located then it&#x27;s really likely that the &quot;partitioning&quot; problem is one of the scenarios where they actually <i>all</i> go down simultaneously or the availability goes to 0 because you can&#x27;t actually reach any of the machines (which are likely to be on the &#x27;same&#x27; network).</text></item><item><author>nemothekid</author><text>&gt;<i>Systems that guarantee consistency only experience a necessary reduction in availability in the event of a network partition. As networks become more redundant, partitions become an increasingly rare event. And even if there is a partition, it is still possible for the majority partition to be available</i><p>In my experience, yes network partitions are incredibly rare. However 99% of my distributed ststem partitions have little do with the network. When running databases on a cloud environment network partitions can occur for a variety of reasons that don’t actually include the network link between databases:<p>1. The host database is written in a GC’d language and experiences a pathological GC pause.<p>2. The Virtual machine is migrated and experiences a pathological pause<p>3. Google migrates your machine with local SSDs, fucks up that process and you lose all your data on that machine (you do have backups right?)<p>4. AWS retires your instance and you need to reboot your VM.<p>You may never see these issue if you are running a 3 or 5 cluster database. I began seeing issues like this semi regularly once the cluster grew to 30-40 machines (Cassandra). Now I will agree that none of the issues took down majority, but if your R=3, it really only takes an unlucky partition to fuck up an entire shard</text></item></parent_chain><comment><author>toast0</author><text>I think part of this is that most of the common knowledge about scaling is hard fought from the 90s&#x2F;2000 era. eBay got bigger and bigger Sun boxes to run Oracle, until they couldn&#x27;t get anything bigger -- then they had a problem and had to shard their listings into categories, etc. In the last few Intel cpu generations, computation performance has had small gains, but addressable memory has doubled about every other release, you can now get machines with 2TB of ram, and it&#x27;s not that expensive.<p>You can fit <i>a lot</i> of data in an in memory database of 2TB.</text></comment> | <story><title>NewSQL databases fail to guarantee consistency and I blame Spanner</title><url>http://dbmsmusings.blogspot.com/2018/09/newsql-database-systems-are-failing-to.html</url></story><parent_chain><item><author>Quekid5</author><text>I may be a bit of an old fart, but this is the exact reasoning behind my decision to never go with &quot;distributed X&quot; if there&#x27;s a &quot;single-machine X&quot; where you can just vertically scale.<p>If you can afford 3-5 machines&#x2F;VMs for a cluster you can almost certainly afford a single machine&#x2F;VM with 2-4x the resources&#x2F;CPU and chances are that it&#x27;ll perform just as well (or better) because it doesn&#x27;t have network latency to contend with.<p>Of course if you&#x27;re around N &gt;= 7 or N &gt;= 9, <i>then</i> you should perhaps start considering &quot;distributed X&quot;.<p>As long as your application is mostly built on very few assumptions about consistency it&#x27;s usually pretty painless to actually go distributed.<p>Of course, there <i>are</i> legitimate cases where you want to go distributed even with N=3 or N=5, but IME they&#x27;re very few and far between... but if your 3&#x2F;5 machines are co-located then it&#x27;s really likely that the &quot;partitioning&quot; problem is one of the scenarios where they actually <i>all</i> go down simultaneously or the availability goes to 0 because you can&#x27;t actually reach any of the machines (which are likely to be on the &#x27;same&#x27; network).</text></item><item><author>nemothekid</author><text>&gt;<i>Systems that guarantee consistency only experience a necessary reduction in availability in the event of a network partition. As networks become more redundant, partitions become an increasingly rare event. And even if there is a partition, it is still possible for the majority partition to be available</i><p>In my experience, yes network partitions are incredibly rare. However 99% of my distributed ststem partitions have little do with the network. When running databases on a cloud environment network partitions can occur for a variety of reasons that don’t actually include the network link between databases:<p>1. The host database is written in a GC’d language and experiences a pathological GC pause.<p>2. The Virtual machine is migrated and experiences a pathological pause<p>3. Google migrates your machine with local SSDs, fucks up that process and you lose all your data on that machine (you do have backups right?)<p>4. AWS retires your instance and you need to reboot your VM.<p>You may never see these issue if you are running a 3 or 5 cluster database. I began seeing issues like this semi regularly once the cluster grew to 30-40 machines (Cassandra). Now I will agree that none of the issues took down majority, but if your R=3, it really only takes an unlucky partition to fuck up an entire shard</text></item></parent_chain><comment><author>Serow225</author><text>My experience is that it&#x27;s unfortunately really hard to convince people who don&#x27;t deeply understand distributed systems (but think they know) that just because a system is called &#x27;HA&#x27; or can have an &#x27;HA&#x27; mode turned on, that doing so has downsides. They freak out if you try to propose _not_ running the HA mode, because they don&#x27;t (or aren&#x27;t willing to) understand the potential downsides of dealing with split-brain, bad recovery, etc. They just see it as a &quot;enable checkbox and forget it&quot; kind of thing that should always be turned on. This is a big struggle of mine, any suggestions would be appreciated...</text></comment> |
39,603,003 | 39,603,217 | 1 | 3 | 39,602,672 | train | <story><title>Google Demands That We Censor Our Content</title><url>https://www.nakedcapitalism.com/2024/03/google-demands-that-we-censor-our-content.html</url></story><parent_chain></parent_chain><comment><author>delichon</author><text>I stopped letting Google filter my world when I saw that it had de-indexed conversations between extremely well credentialed scientists when they came to unpopular conclusions regarding Covid policy. This story appears to confirm that Google sees ideological influence as part of their core mission. I don&#x27;t really object to that when the ideology is about transparency, neutrality, objectivity, so this isn&#x27;t anti-ideology. But I do object when it&#x27;s about censorship, advocacy and feelings, because my own ideology is pro-Enlightenment. So I&#x27;ve de-Googled, and I will be ready to de-Kagi, de-Zoho, de-LineageOS, etc. if they become similarly captured. I just hope that ends with me still having access to modern tech.</text></comment> | <story><title>Google Demands That We Censor Our Content</title><url>https://www.nakedcapitalism.com/2024/03/google-demands-that-we-censor-our-content.html</url></story><parent_chain></parent_chain><comment><author>shrubble</author><text>Google needs to die, in order for the Internet to live; their near-monopoly is stifling and they have repeatedly proven they are not good stewards of the outsized amount of power they have.</text></comment> |
38,425,179 | 38,425,371 | 1 | 3 | 38,423,167 | train | <story><title>Ask HN: What was the outcome of Reddit blackout?</title><text>I couldn&#x27;t find any info but what was the end result of the blackouts?<p>Did reddit agree or compromise, or did the movement run out of steam? Just curious if anyone knows..</text></story><parent_chain><item><author>rabbits_2002</author><text>A massive decline in post quality. I don’t know what happened but ever since the blackout only garbage gets posted. Even the quality of niche subreddits has fallen. I think the blackout meant that all the well moderated “good” subreddits closed while the bad ones stayed open. Now the bad subreddits are more popular and have eclipsed the good subreddits.<p>As for other websites, Lemmy and other federated aggregators have gained a bit of a foothold.</text></item></parent_chain><comment><author>OfSanguineFire</author><text>As I see it, post quality declined massively starting from when the smartphone became the device most users were browsing from. No matter how proficient people claim to be with a phone keyboard, it is a medium that discourages longform text. The blackout made no difference with regard to that, the damage was already done.<p>Post quality also declined after the 2017 redesign. The old design had a sidebar where subreddits kept a FAQ and wiki. Today, the same questions get asked again and again on many subreddits. Mods can&#x27;t lock those posts and direct the author to the FAQ, because most users can&#x27;t even see the FAQ. Mods who try to ensure a firm hand regularly get excoriated by the community, even by regulars on the sub, as &quot;gatekeepers&quot;.</text></comment> | <story><title>Ask HN: What was the outcome of Reddit blackout?</title><text>I couldn&#x27;t find any info but what was the end result of the blackouts?<p>Did reddit agree or compromise, or did the movement run out of steam? Just curious if anyone knows..</text></story><parent_chain><item><author>rabbits_2002</author><text>A massive decline in post quality. I don’t know what happened but ever since the blackout only garbage gets posted. Even the quality of niche subreddits has fallen. I think the blackout meant that all the well moderated “good” subreddits closed while the bad ones stayed open. Now the bad subreddits are more popular and have eclipsed the good subreddits.<p>As for other websites, Lemmy and other federated aggregators have gained a bit of a foothold.</text></item></parent_chain><comment><author>chaosharmonic</author><text>Yeah, several of the more technical subs that I used to frequent either just never reopened or splintered off to Lemmy. Some (like &#x2F;r&#x2F;Android) actually have entire instances.<p>I personally wrote a userscript to wipe every post comment I&#x27;ve ever made, and have limited my usage to a few particular subs that I still lurk (&#x2F;r&#x2F;LocalLLaMA in particular) just bc Lemmy still doesn&#x27;t seem to have a comparable level of activity.<p>Speaking of which I&#x27;m still trying to sort out the situation involving which instances federate with which, and where to actually set up a primary account, and what the interop situation with different Fediverse platforms is even like in general for that matter.</text></comment> |
35,276,858 | 35,273,993 | 1 | 3 | 35,271,779 | train | <story><title>A CPU is a compiler</title><url>https://outerproduct.net/boring/2023-03-22_cpu-compiler-gc-ohmy.html</url></story><parent_chain><item><author>PaulHoule</author><text>An advanced interpreter has many features of a compiler.<p>For instance there is the kind of simple interpreter that I know how to write off the top of my head which evaluates the nodes of an expression tree which is horribly inefficient.<p>Then there is something like Python which &quot;compiles&quot; code to bytecode which is then interpreted by a &quot;virtual machine&quot;. That kind of system admits very complex optimizations about as far you as can imagine, including compiling some of the bytecode all the way to machine code the way PyPy or the JVM does it.<p>Note most interpretations of the Intel architectures break complex instructions up into RISC-like &quot;micro-ops&quot;, which is a bit like bytecode interpretation.<p>One of the biggest concerns in a modern CPU is that memory accesses are very slow relative to a CPU cycle so you want to be executing a large number of instructions at a time to hide the latency of memory access. Intel&#x27;s failed Itanium had the compiler try to explicitly schedule this but it didn&#x27;t work because the compiler can&#x27;t know ahead of time (for general purpose code) what is in what level of the cache and what isn&#x27;t -- and in a worse case scenario this can hang up not only one instruction but many other instructions that depend on the result of that instruction, ether because they really depend on the result or because the CPU gets hung up. The CPU, on the other hand, does know, and can be opportunistic about taking advantage of available parallelism.</text></item></parent_chain><comment><author>PaulDavisThe1st</author><text>&gt; An advanced interpreter has many features of a compiler.<p>There&#x27;s a historical line from a CS great (I am not sure who) that goes something like:<p>When you first start writing software, you will not understand the difference between an interpreter and a compiler. After you&#x27;ve been writing software for a certain amount of time, you will never confuse an interpreter and a compiler. But after you&#x27;ve been writing software for a bit longer than that, you will again not understand what the difference between them really is.</text></comment> | <story><title>A CPU is a compiler</title><url>https://outerproduct.net/boring/2023-03-22_cpu-compiler-gc-ohmy.html</url></story><parent_chain><item><author>PaulHoule</author><text>An advanced interpreter has many features of a compiler.<p>For instance there is the kind of simple interpreter that I know how to write off the top of my head which evaluates the nodes of an expression tree which is horribly inefficient.<p>Then there is something like Python which &quot;compiles&quot; code to bytecode which is then interpreted by a &quot;virtual machine&quot;. That kind of system admits very complex optimizations about as far you as can imagine, including compiling some of the bytecode all the way to machine code the way PyPy or the JVM does it.<p>Note most interpretations of the Intel architectures break complex instructions up into RISC-like &quot;micro-ops&quot;, which is a bit like bytecode interpretation.<p>One of the biggest concerns in a modern CPU is that memory accesses are very slow relative to a CPU cycle so you want to be executing a large number of instructions at a time to hide the latency of memory access. Intel&#x27;s failed Itanium had the compiler try to explicitly schedule this but it didn&#x27;t work because the compiler can&#x27;t know ahead of time (for general purpose code) what is in what level of the cache and what isn&#x27;t -- and in a worse case scenario this can hang up not only one instruction but many other instructions that depend on the result of that instruction, ether because they really depend on the result or because the CPU gets hung up. The CPU, on the other hand, does know, and can be opportunistic about taking advantage of available parallelism.</text></item></parent_chain><comment><author>czx4f4bd</author><text>Just a tiny nitpick for clarity, I think you mean PyPy rather than &quot;PyPi&quot;. :)<p>PyPI is the Python Package Index. <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Python_Package_Index" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Python_Package_Index</a><p>PyPy is the Python implementation with JIT. <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;PyPy" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;PyPy</a><p>(Yes, it is extremely confusing that there are two Python projects with homophonous, nearly-identical names.)</text></comment> |
26,728,377 | 26,728,134 | 1 | 2 | 26,727,678 | train | <story><title>34% of remote workers would quit rather than return to full-time office work</title><url>https://www.psychnewsdaily.com/a-third-of-wfh-employees-say-theyd-rather-quit-than-return-to-full-time-office-work/</url></story><parent_chain><item><author>benbristow</author><text>Just asking this as a talking point.<p>Does a quick interruption that unblocks me and allows me to continue working outweigh allowing you to finish your thing first? Because maybe you&#x27;re unblocked but I&#x27;m blocked by you now, and the thing that&#x27;s actually blocking me. So only 1 person is able to work.</text></item><item><author>MattGaiser</author><text>&gt; What used to be swivel in your chair and ask a colleague or going to whoever you need to speak to is now<p>But your need for an instant answer often derails my work flow. I can get a lot more done now that I am not being interrupted as frequently and can address questions once I have wrapped up what I am doing or at least have time to write down where specifically I stopped.</text></item><item><author>benbristow</author><text>It&#x27;s hard enough in software engineering IMHO.<p>What used to be swivel in your chair and ask a colleague or going to whoever you need to speak to is now<p>* Send a Slack message&#x2F;email and wait an arbitrary amount of time for a response.<p>* Organise a Skype&#x2F;Teams&#x2F;whatever call in a few hours time and feel guilty about it, as it feels rude to just ring someone as they could be occupied or busy.<p>I spend a stupid amount of time having blocked stories&#x2F;tasks because I need to clarify some criteria&#x2F;parts of it and the people I need to speak to are difficult to reach because they&#x27;re busy&#x2F;AFK.</text></item><item><author>Alupis</author><text>Or, perhaps they had a year to clearly see they&#x27;re perfectly incapable of doing so.<p>Not every office job is software engineering folks... Imagine trying to manage a warehouse remotely... or bounce ideas off each other in real time at a marketing agency... or any of the other normal jobs that thrive with in-person interaction.<p>Not to mention, 34% is a minority... we can&#x27;t force the other 66% to work remotely just because a minority enjoy it.</text></item><item><author>User23</author><text>Conversely, if an employer isn&#x27;t willing to let employees do a job remotely after having had a year to see that they&#x27;re perfectly capable of doing so, they clearly have no attachment to their employees.</text></item><item><author>MattGaiser</author><text>At any given point, half of workers are contemplating leaving.<p><a href="https:&#x2F;&#x2F;www.cnbc.com&#x2F;2019&#x2F;08&#x2F;27&#x2F;47percent-of-workers-are-considering-quitting-their-jobs-right-now.html" rel="nofollow">https:&#x2F;&#x2F;www.cnbc.com&#x2F;2019&#x2F;08&#x2F;27&#x2F;47percent-of-workers-are-con...</a><p>The typical office worker spends a half hour searching for new jobs at work every day.<p><a href="https:&#x2F;&#x2F;www.inc.com&#x2F;melanie-curtin&#x2F;in-an-8-hour-day-the-average-worker-is-productive-for-this-many-hours.html" rel="nofollow">https:&#x2F;&#x2F;www.inc.com&#x2F;melanie-curtin&#x2F;in-an-8-hour-day-the-aver...</a><p>I’m not sure this is a revolution or just that plenty of people have no real attachment to their employer.</text></item></parent_chain><comment><author>mym1990</author><text>Somewhat anecdotal I guess, but at any given point I have 5-10 things that I <i>could</i> be working on. So if I come across something that I am truly blocked on and need more information, then I ask for that info through appropriate channels and move on to priority thing 2.<p>Understandably this can lead to a lot of context switching, but so can someone swiveling in a chair to ask a question or go down a rabbit hole. You can optimize the process a bit by shifting perspective and having a path to follow if you get blocked, rather than lamenting on how you&#x27;re blocked(not you in particular, but people in general).<p>*I feel like it is somewhat rare that a person only ever has 1 specific thing to work on.</text></comment> | <story><title>34% of remote workers would quit rather than return to full-time office work</title><url>https://www.psychnewsdaily.com/a-third-of-wfh-employees-say-theyd-rather-quit-than-return-to-full-time-office-work/</url></story><parent_chain><item><author>benbristow</author><text>Just asking this as a talking point.<p>Does a quick interruption that unblocks me and allows me to continue working outweigh allowing you to finish your thing first? Because maybe you&#x27;re unblocked but I&#x27;m blocked by you now, and the thing that&#x27;s actually blocking me. So only 1 person is able to work.</text></item><item><author>MattGaiser</author><text>&gt; What used to be swivel in your chair and ask a colleague or going to whoever you need to speak to is now<p>But your need for an instant answer often derails my work flow. I can get a lot more done now that I am not being interrupted as frequently and can address questions once I have wrapped up what I am doing or at least have time to write down where specifically I stopped.</text></item><item><author>benbristow</author><text>It&#x27;s hard enough in software engineering IMHO.<p>What used to be swivel in your chair and ask a colleague or going to whoever you need to speak to is now<p>* Send a Slack message&#x2F;email and wait an arbitrary amount of time for a response.<p>* Organise a Skype&#x2F;Teams&#x2F;whatever call in a few hours time and feel guilty about it, as it feels rude to just ring someone as they could be occupied or busy.<p>I spend a stupid amount of time having blocked stories&#x2F;tasks because I need to clarify some criteria&#x2F;parts of it and the people I need to speak to are difficult to reach because they&#x27;re busy&#x2F;AFK.</text></item><item><author>Alupis</author><text>Or, perhaps they had a year to clearly see they&#x27;re perfectly incapable of doing so.<p>Not every office job is software engineering folks... Imagine trying to manage a warehouse remotely... or bounce ideas off each other in real time at a marketing agency... or any of the other normal jobs that thrive with in-person interaction.<p>Not to mention, 34% is a minority... we can&#x27;t force the other 66% to work remotely just because a minority enjoy it.</text></item><item><author>User23</author><text>Conversely, if an employer isn&#x27;t willing to let employees do a job remotely after having had a year to see that they&#x27;re perfectly capable of doing so, they clearly have no attachment to their employees.</text></item><item><author>MattGaiser</author><text>At any given point, half of workers are contemplating leaving.<p><a href="https:&#x2F;&#x2F;www.cnbc.com&#x2F;2019&#x2F;08&#x2F;27&#x2F;47percent-of-workers-are-considering-quitting-their-jobs-right-now.html" rel="nofollow">https:&#x2F;&#x2F;www.cnbc.com&#x2F;2019&#x2F;08&#x2F;27&#x2F;47percent-of-workers-are-con...</a><p>The typical office worker spends a half hour searching for new jobs at work every day.<p><a href="https:&#x2F;&#x2F;www.inc.com&#x2F;melanie-curtin&#x2F;in-an-8-hour-day-the-average-worker-is-productive-for-this-many-hours.html" rel="nofollow">https:&#x2F;&#x2F;www.inc.com&#x2F;melanie-curtin&#x2F;in-an-8-hour-day-the-aver...</a><p>I’m not sure this is a revolution or just that plenty of people have no real attachment to their employer.</text></item></parent_chain><comment><author>mulmen</author><text>&gt; Does a quick interruption that unblocks me and allows me to continue working outweigh allowing you to finish your thing first?<p>No, absolutely not. As my coworker you have no right to my time, at all. Certainly not on-demand.<p>You are in no position to prioritize my time, especially in the context of you finishing your task.<p>&gt; Because maybe you&#x27;re unblocked but I&#x27;m blocked by you now, and the thing that&#x27;s actually blocking me.<p>No, you are blocked by whatever you are blocked by. Solving your problems is <i>your</i> problem. Not mine.<p>&gt; So only 1 person is able to work.<p>If you can&#x27;t do your job without also consuming my time in parallel what exactly are you contributing? If you are blocked and need input then go work on something else until you can get the input. This is elementary time management and respect for your coworkers.</text></comment> |
36,303,188 | 36,302,392 | 1 | 2 | 36,295,227 | train | <story><title>Show HN: Stable Diffusion powered level editor for a 2D game</title><url>https://generalrobots.substack.com/p/dimension-hopper-part-1</url><text>Hey folks, I’ve been working on using control-net to take in a video game level (input as a depth image) and output a beautiful illustration of that level. Play with it here: dimensionhopper.com or read the blog post about what it took to get it to work. Been a super fun project.</text></story><parent_chain><item><author>robobenjie</author><text>While I have folks attention, I want to try training a model to generate monster&#x2F;creature walk animations. Anyone know of a dataset of walk cycle sprite sheets that I could massage and label to see if I can make that work?</text></item></parent_chain><comment><author>mk_stjames</author><text>I have an idea for you to try - instead of training a model to produce subsequent animation frames (which is tough), instead, take a model trained on pixel art sprites in general, and then use a ControlNet with the input to the ControlNet being either a pose model or a higher res 3d model of a generic dummy character made in blender - and then generate output frame by frame, keeping the input prompting the same, but moving the ControlNet input frame by frame.<p>Something like how this posing works:
<a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=CiG_v61cLxI">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=CiG_v61cLxI</a><p>To get it down to small pixeled &#x27;sprite&#x27; scale, the right thing may be to actually output &#x27;realistic&#x27; character animation frames this way, and then &#x27;de-res&#x27; them via img2img into pixel art. The whole pipeline could be automated so that your only inputs are a single set of varied walking&#x2F;posing&#x2F;jumping control net poses and the prompts describing the characters.</text></comment> | <story><title>Show HN: Stable Diffusion powered level editor for a 2D game</title><url>https://generalrobots.substack.com/p/dimension-hopper-part-1</url><text>Hey folks, I’ve been working on using control-net to take in a video game level (input as a depth image) and output a beautiful illustration of that level. Play with it here: dimensionhopper.com or read the blog post about what it took to get it to work. Been a super fun project.</text></story><parent_chain><item><author>robobenjie</author><text>While I have folks attention, I want to try training a model to generate monster&#x2F;creature walk animations. Anyone know of a dataset of walk cycle sprite sheets that I could massage and label to see if I can make that work?</text></item></parent_chain><comment><author>doctorpangloss</author><text>There are a lot of sprites to work with. As I&#x27;m sure you&#x27;re aware, there are artists known for making animations, like Pedro Medeiros; spriters-resource.com has material from thousands of games; you can buy the Unity Asset Store, itch.io and stock art pixel art assets; and you can use DevX Tools Pro to extract assets from hundreds of 2D pixel art Unity games. All told, there are maybe 100,000-1m examples of high quality pixel art you can scrape. It is additionally possible that it already exists in the major crawls and needs to be labeled better.<p>A few people have tried training on sprite sheets and emitting them directly, and it did not work.<p>A few people have been working specifically on walking cycles, and it has a lot of limitations.<p>In my specific experience with other bespoke pixel art models, if you ask for a &quot;knight,&quot; you&#x27;re going to get a lot of the same looking knight. Fine-tuning will unlearn other concepts that are not represented in your dataset. LORAs have not been observed to work well for pixel art. You can try the Astropixel model, the highest quality in my opinion, for prototyping.<p>Part of this is you&#x27;re really observing how powerful ControlNet, T2I-Adapters and LORAs are and you may have the expectation that something else you, a layperson, can do will be similarly powerful. Your thing is really cool. But is there some easy trick without doing all this science, for animation? No. Those are really big scientific breakthroughs, and with all the attention on video - maybe 100-1,000 academic and industry teams working on it - there still hasn&#x27;t been something super robust for animation that uses LDMs. The most coherent video is happening in with NeRF, and a layperson isn&#x27;t going to make that coherent with pixel art. Your best bet is to wait. That said, I&#x27;m sure people are going to link here to some great hand-processed LDM videos, and maybe there&#x27;s a pipeline with hand artwork a layperson can do today that would work well.</text></comment> |
26,463,221 | 26,462,316 | 1 | 2 | 26,460,238 | train | <story><title>Why we’re removing comments on most of Inquirer.com</title><url>https://www.inquirer.com/about/philadelphia-inquirer-comments-section-changes-20210201.html</url></story><parent_chain><item><author>booleandilemma</author><text>I’m happy with the trend of removing comments from online publications. Too many are outright spam (“I make $500 per day on Facebook and so can you!”) or they’re the opinions of ill-informed people who try to spread one agenda or another.<p>I think having comments everywhere possible was an idea from the web 2.0 era that’s proven to be not all that worth it in most cases. Moderation is hard and it doesn’t make sense for newspapers and magazines to be spending resources on it. There are other forums (reddit, hn) for this sort of thing.</text></item></parent_chain><comment><author>wirrbel</author><text>Never quite understood why comment section wasn&#x27;t one of the premium subscription features for direct monetization. It could cover the moderation costs directly, provides an incentive for some to buy a subscription and sock puppet accounts are less likely if they cost money. Then, I would assume that if your comment is tied to your billing account, you may be more inclined to not write the worst comments (insulting, etc.).</text></comment> | <story><title>Why we’re removing comments on most of Inquirer.com</title><url>https://www.inquirer.com/about/philadelphia-inquirer-comments-section-changes-20210201.html</url></story><parent_chain><item><author>booleandilemma</author><text>I’m happy with the trend of removing comments from online publications. Too many are outright spam (“I make $500 per day on Facebook and so can you!”) or they’re the opinions of ill-informed people who try to spread one agenda or another.<p>I think having comments everywhere possible was an idea from the web 2.0 era that’s proven to be not all that worth it in most cases. Moderation is hard and it doesn’t make sense for newspapers and magazines to be spending resources on it. There are other forums (reddit, hn) for this sort of thing.</text></item></parent_chain><comment><author>xahrepap</author><text>I agree. I remember years ago a friend of mine was found dead (took his own life) and a local news site reported it and had a comment section.<p>It was beyond horrible. People were commenting about how glad they were that this person they *didn’t even know* was gone. “One fewer idiot” type of comments. It was one of those things where it was so bad you didn’t want to look away.<p>The moderation was non-existent.<p>I just don’t get why a website would want to harbor a community that toxic.</text></comment> |
22,110,316 | 22,109,133 | 1 | 3 | 22,104,366 | train | <story><title>Roam: Why I Love It and How I Use It</title><url>https://www.nateliason.com/blog/roam</url></story><parent_chain><item><author>mark_l_watson</author><text>I like the author’s enthusiasm for organizing personal information. That was me from about 15 years ago to about 3 years ago.<p>I stopped spending time and effort when I realized how little I used my organized notes. Specifically, I used Evernote and had my personal information wonderfully organized, but rarely used it. Now I use something simpler:<p>For work: about 20 Emacs org-mode files for various topics. I use grep to find stuff.<p>For personal: at different times I have used Apple Notes or Google Keep to maintain todo lists, shopping lists, notes on present and future writing projects, planning travel, etc. Both support search. I spend very little time writing these notes and they are useful. A few times a year, I spend a few minutes deleting notes I don’t need anymore.<p>Anyway, thinking about cost&#x2F;benefits, not spending much time organizing my own information makes sense to me.<p>The turning point was spending months of part time hacking writing my own Evernote’s clone in Clojure in the backend, a Firefox plugin, and a web app. It was a fun project, but mire fun writing it than using it.</text></item></parent_chain><comment><author>The_Colonel</author><text>For me the notes app is almost like a workspace - I need to figure something out, I write it down, start to break it down, describe, analyse - this process helps me to understand the problem. The fact that the artifacts of this process will not disappear is a nice bonus. A lot of the time I don&#x27;t ever read them again, but I got the main benefit (understanding) already anyway.<p>It&#x27;s a bit similar to writing a journal - just the act of writing it down has big therapeutic and introspective effects.<p>For me, the act of organizing the information actually does not take too much time but that might be caused by the fact that I typically don&#x27;t obsess over correct categorization or do this &quot;refactoring&quot; when I&#x27;m bored. Main tool to find notes of interest is search anyway, categorization for me serves as a way to find related notes.<p>&gt; The turning point was spending months of part time hacking writing my own Evernote’s clone in Clojure in the backend, a Firefox plugin, and a web app. It was a fun project, but mire fun writing it than using it.<p>Lol, sounds like me, except it&#x27;s been almost 3 years since I started (<a href="https:&#x2F;&#x2F;github.com&#x2F;zadam&#x2F;trilium" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;zadam&#x2F;trilium</a> if anybody&#x27;s interested)</text></comment> | <story><title>Roam: Why I Love It and How I Use It</title><url>https://www.nateliason.com/blog/roam</url></story><parent_chain><item><author>mark_l_watson</author><text>I like the author’s enthusiasm for organizing personal information. That was me from about 15 years ago to about 3 years ago.<p>I stopped spending time and effort when I realized how little I used my organized notes. Specifically, I used Evernote and had my personal information wonderfully organized, but rarely used it. Now I use something simpler:<p>For work: about 20 Emacs org-mode files for various topics. I use grep to find stuff.<p>For personal: at different times I have used Apple Notes or Google Keep to maintain todo lists, shopping lists, notes on present and future writing projects, planning travel, etc. Both support search. I spend very little time writing these notes and they are useful. A few times a year, I spend a few minutes deleting notes I don’t need anymore.<p>Anyway, thinking about cost&#x2F;benefits, not spending much time organizing my own information makes sense to me.<p>The turning point was spending months of part time hacking writing my own Evernote’s clone in Clojure in the backend, a Firefox plugin, and a web app. It was a fun project, but mire fun writing it than using it.</text></item></parent_chain><comment><author>Multiplayer</author><text>Roam appears to remove the time and effort needed to organize notes. Just write. Links will happen. No need for silos, no need for hierarchies.<p>They are removing the friction and effort. This has huge implications and potential.<p>I am with you on not going and looking for notes (I don&#x27;t often browse through my photo library either, which is a close analog).<p>This really feels like it&#x27;s onto something special if you can let go of the evernote paradigm.</text></comment> |
25,561,755 | 25,560,265 | 1 | 2 | 25,558,587 | train | <story><title>Average Rent in San Francisco Has Dropped $1k This Year</title><url>http://socketsite.com/archives/2020/12/average-rent-in-san-francisco-has-dropped-1000-this-year.html</url></story><parent_chain><item><author>ozzyoli</author><text>Don&#x27;t ask, Don&#x27;t get.<p>Everyone I know who has asked for a discount has got the discount.<p>After several months of the pandemic, and noticing the adjacent apartment being relisted by my landlord at a discount I emailed my landlord and asked if I could have my rent adjusted by the same discount. They said yes, if I committed to another years lease.<p>Saving 5% of rent, at the cost of a one year commitment didn&#x27;t seem like a win, so I politely declined explaining my reasoning, and suggested we leave things as they are.<p>A week or so later, out of the blue by my rent got adjusted by 10%+ instead of 5% with no need to commit to stay.<p>Sufficed to say, if their intention was for me to stay put, it worked!</text></item></parent_chain><comment><author>jonpurdy</author><text>Another data point. Tried to get a discount in our Inner Sunset 1BR that we paid $3250 for. Other units in the same building listed for the past few months for $2700 with 2 months free (effectively $2250).<p>Denied a decrease (citing CA Fair Housing and not giving anyone a decrease) so we paid 1 months rent to break the lease. Now living in a 2BR by the beach for the same price as before with 50% more space, W&#x2F;D, garage.<p>Old apartment went from ~10 vacant 1BR to ~25 vacant 1BR listings during the past couple of months during our negotiation and move.</text></comment> | <story><title>Average Rent in San Francisco Has Dropped $1k This Year</title><url>http://socketsite.com/archives/2020/12/average-rent-in-san-francisco-has-dropped-1000-this-year.html</url></story><parent_chain><item><author>ozzyoli</author><text>Don&#x27;t ask, Don&#x27;t get.<p>Everyone I know who has asked for a discount has got the discount.<p>After several months of the pandemic, and noticing the adjacent apartment being relisted by my landlord at a discount I emailed my landlord and asked if I could have my rent adjusted by the same discount. They said yes, if I committed to another years lease.<p>Saving 5% of rent, at the cost of a one year commitment didn&#x27;t seem like a win, so I politely declined explaining my reasoning, and suggested we leave things as they are.<p>A week or so later, out of the blue by my rent got adjusted by 10%+ instead of 5% with no need to commit to stay.<p>Sufficed to say, if their intention was for me to stay put, it worked!</text></item></parent_chain><comment><author>bfirsh</author><text>As a data point: I asked for 25% off my 1 bedroom rent (which seemed like roughly market rate). They said something along the lines of &quot;we&#x27;re not lowering any rents because we&#x27;re struggling due to the economy&quot;.<p>So, I left and they got nothing. I doubt they&#x27;re going to rent it out again for a while.</text></comment> |
30,602,326 | 30,601,612 | 1 | 2 | 30,600,304 | train | <story><title>One Way Smart Developers Make Bad Strategic Decisions</title><url>https://earthly.dev/blog/see-state/</url></story><parent_chain></parent_chain><comment><author>jmull</author><text>Nice, interesting article.<p>But I would stress less that &quot;Seeing Like a State&quot; -- that is a top-down, global solution -- was not the problem.<p>The problem was that &quot;Tim&quot; didn&#x27;t really understand the problem he was trying to solve (well, none of us truly understand very much at all, but he didn&#x27;t understand it better than many of the teams associated with the individual services).<p>&quot;Tim&quot;&#x27;s proposal probably solved some problems but created various other problems.<p>The best solution, though, (IMO) isn&#x27;t that Tim should be smarted and better informed than everyone else combined, nor that every team should continue to create an independent solution. Instead &quot;Tim&quot; could propose a solution, and the 100 micro service teams would be tasked with responding constructively. Iterations would ensue. You still really, really need &quot;Tim&quot;, though, because multiple teams, even sincere and proficient ones, will not arrive at a coherent solution without leadership&#x2F;direction.<p>&gt; A global solution, by necessity, has to ignore local conditions.<p>That&#x27;s just flat wrong. A global solution can solve global concerns and also allow for local conditions.</text></comment> | <story><title>One Way Smart Developers Make Bad Strategic Decisions</title><url>https://earthly.dev/blog/see-state/</url></story><parent_chain></parent_chain><comment><author>NateEag</author><text>For anyone interested in social systems that help avoid this top-down, centralized failure mode, I cannot recommend RFC 7282 enough:<p><a href="https:&#x2F;&#x2F;datatracker.ietf.org&#x2F;doc&#x2F;html&#x2F;rfc7282" rel="nofollow">https:&#x2F;&#x2F;datatracker.ietf.org&#x2F;doc&#x2F;html&#x2F;rfc7282</a><p>A whole lot of wisdom is captured in that document, including a deep understanding of the differences between unanimity, majority rule, and consensus.<p>If you&#x27;re involved in standardization efforts in any way, whether it&#x27;s deciding where your team will put braces in source code or running software architecture for a Fortune 100, it will well repay your reading time.</text></comment> |
26,894,169 | 26,889,368 | 1 | 2 | 26,887,670 | train | <story><title>“They introduce kernel bugs on purpose”</title><url>https://lore.kernel.org/linux-nfs/YH+zwQgBBGUJdiVK@unreal/</url></story><parent_chain><item><author>duncaen</author><text>See page 9 of the already published paper:<p><a href="https:&#x2F;&#x2F;raw.githubusercontent.com&#x2F;QiushiWu&#x2F;qiushiwu.github.io&#x2F;main&#x2F;papers&#x2F;OpenSourceInsecurity.pdf" rel="nofollow">https:&#x2F;&#x2F;raw.githubusercontent.com&#x2F;QiushiWu&#x2F;qiushiwu.github.i...</a><p>&gt; We send the emails to the Linux communityand seek their feedback. The experiment is not to blame any maintainers but to reveal issues in the process. The IRB of University of Minnesota reviewed the procedures of the experiment and determined that this is not human research. We obtained a formal IRB-exempt letter. The experiment will not collect any personal data, individual behaviors, or personal opinions. It is limited to studying the patching process OSS communities follow, instead of individuals.</text></item><item><author>bluGill</author><text>If the IRB is any good the professor doesn&#x27;t get that. Universities are publish or perish, and the IRB should force the withdrawal of all papers they submitted. This is might be enough to fire the professor with cause - including remove any tenure protection they might have - which means they get a bad reference.<p>I hope we hear from the IRB in about a year stating exactly what happened. Real investigations of bad conduct should take time to complete correctly and I want them to do their job correctly so I&#x27;ll give them that time. (there is the possibility that these are good faith patches and someone in the linux community just hates this person - seems unlikely but until a proper independent investigation is done I&#x27;ll leave that open.)</text></item><item><author>rzwitserloot</author><text>The professor gets exactly what they want here, no?<p>&quot;We experimented on the linux kernel team to see what would happen. Our non-double-blind test of 1 FOSS maintenance group has produced the following result: We get banned and our entire university gets dragged through the muck 100% of the time&quot;.<p>That&#x27;ll be a fun paper to write, no doubt.<p>Additional context:<p>* One of the committers of these faulty patches, Aditya Pakki, writes a reply taking offense at the &#x27;slander&#x27; and indicating that the commit was in good faith[1].<p>Greg KH then immediately calls bullshit on this, and then proceeds to ban the entire university from making commits [2].<p>The thread then gets down to business and starts coordinating revert patches for everything committed by University of Minnesota email addresses.<p>As was noted, this obviously has a bunch of collateral damage, but such drastic measures seem like a balanced response, considering that this university decided to _experiment_ on the kernel team and then lie about it when confronted (presumably, that lie is simply continuing their experiment of &#x27;what would someone intentionally trying to add malicious code to the kernel do&#x27;)?<p>* Abhi Shelat also chimes in with links to UMN&#x27;s Institutional Review Board along with documentation on the UMN policies for ethical review. [3]<p>[1]: Message has since been deleted, so I&#x27;m going by the content of it as quoted in Greg KH&#x27;s followup, see footnote 2<p>[2]: <a href="https:&#x2F;&#x2F;lore.kernel.org&#x2F;linux-nfs&#x2F;YH%2FfM%[email protected]&#x2F;" rel="nofollow">https:&#x2F;&#x2F;lore.kernel.org&#x2F;linux-nfs&#x2F;YH%2FfM%2FTsbmcZzwnX@kroah...</a><p>[3]: <a href="https:&#x2F;&#x2F;lore.kernel.org&#x2F;linux-nfs&#x2F;[email protected]&#x2F;#t" rel="nofollow">https:&#x2F;&#x2F;lore.kernel.org&#x2F;linux-nfs&#x2F;3B9A54F7-6A61-4A34-9EAC-95...</a></text></item></parent_chain><comment><author>nkurz</author><text>&gt; The IRB of University of Minnesota reviewed the procedures of the experiment and determined that this is not human research.<p>I&#x27;m not sure how it affects things, but I think it&#x27;s important to clarify that they did not obtain the IRB-exempt letter in advance of doing the research, but after the ethically questionable actions had already been taken:<p><i>The IRB of UMN reviewed the study and determined that this is not human research (a formal IRB exempt letter was obtained). Throughout the study, we honestly did not think this is human research, so we did not apply for an IRB approval in the beginning. ... We would like to thank the people who suggested us to talk to IRB after seeing the paper abstract.</i><p><a href="https:&#x2F;&#x2F;www-users.cs.umn.edu&#x2F;~kjlu&#x2F;papers&#x2F;clarifications-hc.pdf" rel="nofollow">https:&#x2F;&#x2F;www-users.cs.umn.edu&#x2F;~kjlu&#x2F;papers&#x2F;clarifications-hc....</a></text></comment> | <story><title>“They introduce kernel bugs on purpose”</title><url>https://lore.kernel.org/linux-nfs/YH+zwQgBBGUJdiVK@unreal/</url></story><parent_chain><item><author>duncaen</author><text>See page 9 of the already published paper:<p><a href="https:&#x2F;&#x2F;raw.githubusercontent.com&#x2F;QiushiWu&#x2F;qiushiwu.github.io&#x2F;main&#x2F;papers&#x2F;OpenSourceInsecurity.pdf" rel="nofollow">https:&#x2F;&#x2F;raw.githubusercontent.com&#x2F;QiushiWu&#x2F;qiushiwu.github.i...</a><p>&gt; We send the emails to the Linux communityand seek their feedback. The experiment is not to blame any maintainers but to reveal issues in the process. The IRB of University of Minnesota reviewed the procedures of the experiment and determined that this is not human research. We obtained a formal IRB-exempt letter. The experiment will not collect any personal data, individual behaviors, or personal opinions. It is limited to studying the patching process OSS communities follow, instead of individuals.</text></item><item><author>bluGill</author><text>If the IRB is any good the professor doesn&#x27;t get that. Universities are publish or perish, and the IRB should force the withdrawal of all papers they submitted. This is might be enough to fire the professor with cause - including remove any tenure protection they might have - which means they get a bad reference.<p>I hope we hear from the IRB in about a year stating exactly what happened. Real investigations of bad conduct should take time to complete correctly and I want them to do their job correctly so I&#x27;ll give them that time. (there is the possibility that these are good faith patches and someone in the linux community just hates this person - seems unlikely but until a proper independent investigation is done I&#x27;ll leave that open.)</text></item><item><author>rzwitserloot</author><text>The professor gets exactly what they want here, no?<p>&quot;We experimented on the linux kernel team to see what would happen. Our non-double-blind test of 1 FOSS maintenance group has produced the following result: We get banned and our entire university gets dragged through the muck 100% of the time&quot;.<p>That&#x27;ll be a fun paper to write, no doubt.<p>Additional context:<p>* One of the committers of these faulty patches, Aditya Pakki, writes a reply taking offense at the &#x27;slander&#x27; and indicating that the commit was in good faith[1].<p>Greg KH then immediately calls bullshit on this, and then proceeds to ban the entire university from making commits [2].<p>The thread then gets down to business and starts coordinating revert patches for everything committed by University of Minnesota email addresses.<p>As was noted, this obviously has a bunch of collateral damage, but such drastic measures seem like a balanced response, considering that this university decided to _experiment_ on the kernel team and then lie about it when confronted (presumably, that lie is simply continuing their experiment of &#x27;what would someone intentionally trying to add malicious code to the kernel do&#x27;)?<p>* Abhi Shelat also chimes in with links to UMN&#x27;s Institutional Review Board along with documentation on the UMN policies for ethical review. [3]<p>[1]: Message has since been deleted, so I&#x27;m going by the content of it as quoted in Greg KH&#x27;s followup, see footnote 2<p>[2]: <a href="https:&#x2F;&#x2F;lore.kernel.org&#x2F;linux-nfs&#x2F;YH%2FfM%[email protected]&#x2F;" rel="nofollow">https:&#x2F;&#x2F;lore.kernel.org&#x2F;linux-nfs&#x2F;YH%2FfM%2FTsbmcZzwnX@kroah...</a><p>[3]: <a href="https:&#x2F;&#x2F;lore.kernel.org&#x2F;linux-nfs&#x2F;[email protected]&#x2F;#t" rel="nofollow">https:&#x2F;&#x2F;lore.kernel.org&#x2F;linux-nfs&#x2F;3B9A54F7-6A61-4A34-9EAC-95...</a></text></item></parent_chain><comment><author>volta83</author><text>&gt; We send the emails to the Linux communityand seek their feedback.<p>That&#x27;s not really what they did.<p>They sent the patches, the patches where either merged or rejected.<p>And they never let anybody knew that they had introduced security vulnerabilities on the kernel on purpose until they got caught and people started reverting all the patches from their university and banned the whole university.</text></comment> |
32,849,277 | 32,847,660 | 1 | 2 | 32,846,691 | train | <story><title>I figured out how to get GitHub Copilot to run in the terminal</title><url>https://github.com/maxwell-bland/copilot-in-the-terminal</url></story><parent_chain></parent_chain><comment><author>teddyh</author><text>It’s generally claimed that reading other people’s code is harder than writing your own. I mean, everybody loves writing code on a greenfield project but hates maintenance of legacy code, right? So, <i>why</i> do people like these code generators? The only explanation I can see is that people use them and then <i>don’t read the code</i>. Which would be horrifying.<p>(I stay away for obvious copyright reasons.)</text></comment> | <story><title>I figured out how to get GitHub Copilot to run in the terminal</title><url>https://github.com/maxwell-bland/copilot-in-the-terminal</url></story><parent_chain></parent_chain><comment><author>Retr0id</author><text>By the way, the example snippet given to &quot;echo a random number between 1 and 10&quot; is incorrect, pedantically speaking. It&#x27;s random, but not uniformly so. It&#x27;s biased towards lower numbers (1-6).</text></comment> |
4,313,122 | 4,313,268 | 1 | 2 | 4,312,731 | train | <story><title>Company withdrawing from Facebook as analytics show 80% of ad clicks from bots</title><url>https://www.facebook.com/limitedpressing/posts/209534972507958</url></story><parent_chain><item><author>reustle</author><text>Copying the text just incase FB decides they don't like it<p>---<p>Hey everyone, we're going to be deleting our Facebook page in the next couple of weeks, but we wanted to explain why before we do. A couple months ago, when we were preparing to launch the new Limited Run, we started to experiment with Facebook ads. Unfortunately, while testing their ad system, we noticed some very strange things. Facebook was charging us for clicks, yet we could only verify about 20% of them actually showing up on our site. At first, we thought it was our analytics service. We tried signing up for a handful of other big name companies, and still, we couldn't verify more than 15-20% of clicks. So we did what any good developers would do. We built our own analytic software. Here's what we found: on about 80% of the clicks Facebook was charging us for, JavaScript wasn't on. And if the person clicking the ad doesn't have JavaScript, it's very difficult for an analytics service to verify the click. What's important here is that in all of our years of experience, only about 1-2% of people coming to us have JavaScript disabled, not 80% like these clicks coming from Facebook. So we did what any good developers would do. We built a page logger. Any time a page was loaded, we'd keep track of it. You know what we found? The 80% of clicks we were paying for were from bots. That's correct. Bots were loading pages and driving up our advertising costs. So we tried contacting Facebook about this. Unfortunately, they wouldn't reply. Do we know who the bots belong too? No. Are we accusing Facebook of using bots to drive up advertising revenue. No. Is it strange? Yes. But let's move on, because who the bots belong to isn't provable.<p>While we were testing Facebook ads, we were also trying to get Facebook to let us change our name, because we're not Limited Pressing anymore. We contacted them on many occasions about this. Finally, we got a call from someone at Facebook. They said they would allow us to change our name. NICE! But only if we agreed to spend $2000 or more in advertising a month. That's correct. Facebook was holding our name hostage. So we did what any good hardcore kids would do. We cursed that piece of shit out! Damn we were so pissed. We still are. This is why we need to delete this page and move away from Facebook. They're scumbags and we just don't have the patience for scumbags.<p>Thanks to everyone who has supported this page and liked our posts. We really appreciate it. If you'd like to follow us on Twitter, where we don't get shaken down, you can do so here: <a href="http://twitter.com/limitedrun" rel="nofollow">http://twitter.com/limitedrun</a></text></item></parent_chain><comment><author>eytanlevit</author><text>Happend to us too!! we first thought kissmetrics was wrong, so we built a logger that logged server side requests and a client side code that executes on load of the landing page, and we found that 70% of the server side hits had javascript disabled(or that hit the page and left it before the js executed, which seems improbable for such a large number - 70%).</text></comment> | <story><title>Company withdrawing from Facebook as analytics show 80% of ad clicks from bots</title><url>https://www.facebook.com/limitedpressing/posts/209534972507958</url></story><parent_chain><item><author>reustle</author><text>Copying the text just incase FB decides they don't like it<p>---<p>Hey everyone, we're going to be deleting our Facebook page in the next couple of weeks, but we wanted to explain why before we do. A couple months ago, when we were preparing to launch the new Limited Run, we started to experiment with Facebook ads. Unfortunately, while testing their ad system, we noticed some very strange things. Facebook was charging us for clicks, yet we could only verify about 20% of them actually showing up on our site. At first, we thought it was our analytics service. We tried signing up for a handful of other big name companies, and still, we couldn't verify more than 15-20% of clicks. So we did what any good developers would do. We built our own analytic software. Here's what we found: on about 80% of the clicks Facebook was charging us for, JavaScript wasn't on. And if the person clicking the ad doesn't have JavaScript, it's very difficult for an analytics service to verify the click. What's important here is that in all of our years of experience, only about 1-2% of people coming to us have JavaScript disabled, not 80% like these clicks coming from Facebook. So we did what any good developers would do. We built a page logger. Any time a page was loaded, we'd keep track of it. You know what we found? The 80% of clicks we were paying for were from bots. That's correct. Bots were loading pages and driving up our advertising costs. So we tried contacting Facebook about this. Unfortunately, they wouldn't reply. Do we know who the bots belong too? No. Are we accusing Facebook of using bots to drive up advertising revenue. No. Is it strange? Yes. But let's move on, because who the bots belong to isn't provable.<p>While we were testing Facebook ads, we were also trying to get Facebook to let us change our name, because we're not Limited Pressing anymore. We contacted them on many occasions about this. Finally, we got a call from someone at Facebook. They said they would allow us to change our name. NICE! But only if we agreed to spend $2000 or more in advertising a month. That's correct. Facebook was holding our name hostage. So we did what any good hardcore kids would do. We cursed that piece of shit out! Damn we were so pissed. We still are. This is why we need to delete this page and move away from Facebook. They're scumbags and we just don't have the patience for scumbags.<p>Thanks to everyone who has supported this page and liked our posts. We really appreciate it. If you'd like to follow us on Twitter, where we don't get shaken down, you can do so here: <a href="http://twitter.com/limitedrun" rel="nofollow">http://twitter.com/limitedrun</a></text></item></parent_chain><comment><author>seiji</author><text><i>We built a page logger. Any time a page was loaded, we'd keep track of it.</i><p>They reinvented the access log? By hand? Are people really that detached from how servers work?</text></comment> |
34,009,547 | 34,007,888 | 1 | 2 | 34,006,463 | train | <story><title>Things I want from Devs as SRE/DevOps</title><url>https://oschvr.com/posts/what-id-like-as-sre/</url></story><parent_chain><item><author>chrsig</author><text>&gt; If you’re a Software Engineer&#x2F;Developer, then consider that a service (at least, for me), is a piece of code running in a live production system, that YOU wrote, only YOU know how it works, thus YOU own.<p>I&#x27;ve grown unfond of this attitude. I most certainly don&#x27;t own it. I have no IP rights to it at all. We&#x27;re both being paid to solve different facets of the same problem. Coming at me with &quot;this is your problem&quot; isn&#x27;t going to foster a collaborative environment with me. Which is much more pleasant than an adversarial environment.<p>Also: I&#x27;m not the only one that knows how it works, it&#x27;s been peer reviewed in no small part to reduce my bus factor. All documentation requested is perfectly reasonable, and should be part of the organizations standard operating procedure.<p>If it&#x27;s not part of the SOP, then no, you wont have those things. You need to work at a cultural level to change that, and for that you&#x27;re much better off making allies than anything else. Make it clear how those things help you, and what you&#x27;ll do to make the developers life easier when you don&#x27;t need to worry about the basics. If altruism fails you, you can usually count on people to act in their own best interests.</text></item></parent_chain><comment><author>klodolph</author><text>&gt; We&#x27;re both being paid to solve different facets of the same problem. Coming at me with &quot;this is your problem&quot; isn&#x27;t going to foster a collaborative environment with me.<p>SRE here.<p>My takeaway from this is: If you want SRE support running this service, then you need to provide SREs with knowledge of how the system works. As long as only the devs have this knowledge, it&#x27;s a bit unfair to put the SREs on the hook for supporting it.<p>Maybe I&#x27;m reading between the lines too much--the wording in the article is sloppy at best, and at worst, it doesn&#x27;t actually say what I&#x27;m saying.<p>It&#x27;s nice that your code has been through peer review and other people on your team know how it works too. That&#x27;s less helpful for the SREs running it. SREs bear the burden of the pager--sometimes getting woken up at odd hours of the night to fix problems that were, in a sense, created by developers.<p>The SOP for getting SRE support for new services should include things like runbooks and design reviews. SREs should be in the loop when you figure out what metrics to expose from your service, because SREs will be the ones using those metrics to figure out the alerting systems. Very few companies have decent &quot;SOP&quot; for SRE support--there are a few companies which are really good at it, like Google, and then a long tail of companies which dump services on SREs without including SREs in the process.<p>IMO--the right thing to do is to give SRE teams the power to say &quot;no&quot; and refuse to take the pager for any particular service, barring exceptional circumstances. There&#x27;s a deeper discussion to be had about why this should be the case--basically, devs and SREs have different incentives, and neither team should be put in a subordinate position to the other, because both teams have goals that support the business.</text></comment> | <story><title>Things I want from Devs as SRE/DevOps</title><url>https://oschvr.com/posts/what-id-like-as-sre/</url></story><parent_chain><item><author>chrsig</author><text>&gt; If you’re a Software Engineer&#x2F;Developer, then consider that a service (at least, for me), is a piece of code running in a live production system, that YOU wrote, only YOU know how it works, thus YOU own.<p>I&#x27;ve grown unfond of this attitude. I most certainly don&#x27;t own it. I have no IP rights to it at all. We&#x27;re both being paid to solve different facets of the same problem. Coming at me with &quot;this is your problem&quot; isn&#x27;t going to foster a collaborative environment with me. Which is much more pleasant than an adversarial environment.<p>Also: I&#x27;m not the only one that knows how it works, it&#x27;s been peer reviewed in no small part to reduce my bus factor. All documentation requested is perfectly reasonable, and should be part of the organizations standard operating procedure.<p>If it&#x27;s not part of the SOP, then no, you wont have those things. You need to work at a cultural level to change that, and for that you&#x27;re much better off making allies than anything else. Make it clear how those things help you, and what you&#x27;ll do to make the developers life easier when you don&#x27;t need to worry about the basics. If altruism fails you, you can usually count on people to act in their own best interests.</text></item></parent_chain><comment><author>hayst4ck</author><text>Ownership is important to be explicit about, less as a means of assigning blame, but more as a means of coordination and resource allocation.<p>The author is using ownership as a tool to avoid responsibility, and is thus creating an `us vs them` mindset rather than an `us vs the problem` mindset.<p>Having a strong definition of ownership (like committing your organizational structure to your monorepo as config file) is invaluable for building tooling.<p>If you have a strong definition of code ownership it allows for things like people less familiar with a particular piece of code being able to make changes with the approval of the owners, while simultaneously notifying them of the change.<p>Likewise, if you are working on a platform that multiple teams use, you can write tooling that automatically assigns bugs or tickets.<p>Ownership problems and &quot;us vs them&quot; is a clear sign of poor leadership. Most devs that experience it become cyncial or hostile without being able to understand that it is leadership that failed them.</text></comment> |
9,374,637 | 9,373,374 | 1 | 2 | 9,373,240 | train | <story><title>Npm Private Modules</title><url>https://www.npmjs.com/private-modules</url></story><parent_chain></parent_chain><comment><author>BinaryIdiot</author><text>So this reads to me that they&#x27;re simply not going to update the ability to use GIT. Right now you can point to a repo or specific branch &#x2F; tag but it doesn&#x27;t read any of the versioning like bower does, so it can&#x27;t handle versioning properly. If they updated the use of GIT you could completely eliminate the need for this feature.<p>That kinda rubs me the wrong way; it feels like they&#x27;re trying to force this monetization as they&#x27;ve had plenty of us from the community wanting better GIT support for this very reason.<p>Honestly npm isn&#x27;t a very complex piece of software, you could even replace it with bower if you want git with versions. I wonder if any competitors are going to spring up who can simply iterate faster. I won&#x27;t even get started on their login system, ugh.</text></comment> | <story><title>Npm Private Modules</title><url>https://www.npmjs.com/private-modules</url></story><parent_chain></parent_chain><comment><author>archgrove</author><text>We&#x27;re already using &quot;private&quot; modules, by hosting them in a private git repo. NPM can install from these, e.g., git+ssh:&#x2F;&#x2F;user@server:Account&#x2F;Repo.git, without problems. I&#x27;m not sure what value this would add for us, and the URL doesn&#x27;t sell me well on it.</text></comment> |
8,479,062 | 8,478,846 | 1 | 2 | 8,478,427 | train | <story><title>Making sure crypto remains insecure [pdf]</title><url>http://cr.yp.to/talks/2014.10.18/slides-djb-20141018-a4.pdf</url></story><parent_chain><item><author>tptacek</author><text>This is a fun slide deck, but if you&#x27;ll forgive me for sucking some of the mystique out of it: it&#x27;s just a reframing of DJB&#x27;s hobby horses:<p>* The group that standardized AES rejected cache timing as a viable attack vector: <a href="http://cr.yp.to/antiforgery/cachetiming-20050414.pdf" rel="nofollow">http:&#x2F;&#x2F;cr.yp.to&#x2F;antiforgery&#x2F;cachetiming-20050414.pdf</a> --- more generally, that constant-time algorithms and constructions (a feature of virtually all of Bernstein&#x27;s work for the last 15+ years) aren&#x27;t taken seriously in industry. Also helpful to know: there&#x27;s a defensible argument that Bernstein more or less started AES cache timing research.<p>* Side-channel attacks weren&#x27;t taken seriously by TLS, and Bernstein is affiliated with one of the research groups that found a TLS side-channel attack: <a href="http://www.isg.rhul.ac.uk/tls/Lucky13.html" rel="nofollow">http:&#x2F;&#x2F;www.isg.rhul.ac.uk&#x2F;tls&#x2F;Lucky13.html</a><p>* Application-layer randomness is a bad idea, and, like Nacl does, everyone should just use a single, carefully audit kernel RNG: <a href="http://blog.cr.yp.to/20140205-entropy.html" rel="nofollow">http:&#x2F;&#x2F;blog.cr.yp.to&#x2F;20140205-entropy.html</a><p>* Protocols and constructions should be designed to minimize dependence on randomness, the way DJB&#x27;s EdDSA does: <a href="http://ed25519.cr.yp.to/ed25519-20110926.pdf" rel="nofollow">http:&#x2F;&#x2F;ed25519.cr.yp.to&#x2F;ed25519-20110926.pdf</a><p>* Crypto performance is both not taken seriously as a research goal and an excuse for the deployment of terrible cryptography. This isn&#x27;t so much a hobby horse of DJB&#x27;s as it is <i>his entire research career</i>: <a href="http://cr.yp.to/cv/research-net-20070115.pdf" rel="nofollow">http:&#x2F;&#x2F;cr.yp.to&#x2F;cv&#x2F;research-net-20070115.pdf</a><p>* DNSSEC, with its core design goals of &quot;sign-only&quot;, &quot;sign offline&quot;, and &quot;sign from the root down&quot; is a terrible idea. A sane design would look more like DNSCurve: <a href="http://dnscurve.org/" rel="nofollow">http:&#x2F;&#x2F;dnscurve.org&#x2F;</a> (helps also to know that DJB has a longstanding feud with both the design team for BIND, the flagship DNSSEC implementation, and with Namedroppers, the IETF DNS standardization list).<p>Unsurprisingly, considering the source, these are all really great important ideas. Bernstein is one of my heroes, and I&#x27;m certainly not trying to take him down a peg here. I just thought it might be interesting for people to know that this deck is less a revelation about cryptography than it is a survey of DJB&#x27;s research over the last 15 years.<p>I&#x27;m surprised he didn&#x27;t take more time on RC4, which he was closely involved with breaking. The story about how something as dazzlingly broken as RC4 could have gotten so entrenched in the industry is much more interesting than the story about how AES was standardized despite its performance relying so much on table lookups.</text></item></parent_chain><comment><author>hendzen</author><text>&quot;Protocols and constructions should be designed to minimize dependence on randomness, the way DJB&#x27;s EdDSA does:&quot;<p>I think a lot of the reason that ECDSA&#x2F;DSA are so inelegant was that they were designed to get around the patent on the (quite elegant) Schnorr signature algorithm, which EdDSA is based on. Thankfully, the patent expired in 2008, so moving to better signature algorithms that don&#x27;t rely on per-message randomness is a matter of institutional inertia at this point.</text></comment> | <story><title>Making sure crypto remains insecure [pdf]</title><url>http://cr.yp.to/talks/2014.10.18/slides-djb-20141018-a4.pdf</url></story><parent_chain><item><author>tptacek</author><text>This is a fun slide deck, but if you&#x27;ll forgive me for sucking some of the mystique out of it: it&#x27;s just a reframing of DJB&#x27;s hobby horses:<p>* The group that standardized AES rejected cache timing as a viable attack vector: <a href="http://cr.yp.to/antiforgery/cachetiming-20050414.pdf" rel="nofollow">http:&#x2F;&#x2F;cr.yp.to&#x2F;antiforgery&#x2F;cachetiming-20050414.pdf</a> --- more generally, that constant-time algorithms and constructions (a feature of virtually all of Bernstein&#x27;s work for the last 15+ years) aren&#x27;t taken seriously in industry. Also helpful to know: there&#x27;s a defensible argument that Bernstein more or less started AES cache timing research.<p>* Side-channel attacks weren&#x27;t taken seriously by TLS, and Bernstein is affiliated with one of the research groups that found a TLS side-channel attack: <a href="http://www.isg.rhul.ac.uk/tls/Lucky13.html" rel="nofollow">http:&#x2F;&#x2F;www.isg.rhul.ac.uk&#x2F;tls&#x2F;Lucky13.html</a><p>* Application-layer randomness is a bad idea, and, like Nacl does, everyone should just use a single, carefully audit kernel RNG: <a href="http://blog.cr.yp.to/20140205-entropy.html" rel="nofollow">http:&#x2F;&#x2F;blog.cr.yp.to&#x2F;20140205-entropy.html</a><p>* Protocols and constructions should be designed to minimize dependence on randomness, the way DJB&#x27;s EdDSA does: <a href="http://ed25519.cr.yp.to/ed25519-20110926.pdf" rel="nofollow">http:&#x2F;&#x2F;ed25519.cr.yp.to&#x2F;ed25519-20110926.pdf</a><p>* Crypto performance is both not taken seriously as a research goal and an excuse for the deployment of terrible cryptography. This isn&#x27;t so much a hobby horse of DJB&#x27;s as it is <i>his entire research career</i>: <a href="http://cr.yp.to/cv/research-net-20070115.pdf" rel="nofollow">http:&#x2F;&#x2F;cr.yp.to&#x2F;cv&#x2F;research-net-20070115.pdf</a><p>* DNSSEC, with its core design goals of &quot;sign-only&quot;, &quot;sign offline&quot;, and &quot;sign from the root down&quot; is a terrible idea. A sane design would look more like DNSCurve: <a href="http://dnscurve.org/" rel="nofollow">http:&#x2F;&#x2F;dnscurve.org&#x2F;</a> (helps also to know that DJB has a longstanding feud with both the design team for BIND, the flagship DNSSEC implementation, and with Namedroppers, the IETF DNS standardization list).<p>Unsurprisingly, considering the source, these are all really great important ideas. Bernstein is one of my heroes, and I&#x27;m certainly not trying to take him down a peg here. I just thought it might be interesting for people to know that this deck is less a revelation about cryptography than it is a survey of DJB&#x27;s research over the last 15 years.<p>I&#x27;m surprised he didn&#x27;t take more time on RC4, which he was closely involved with breaking. The story about how something as dazzlingly broken as RC4 could have gotten so entrenched in the industry is much more interesting than the story about how AES was standardized despite its performance relying so much on table lookups.</text></item></parent_chain><comment><author>jvehent</author><text>I found this particular talk to be different that the usual DJB. It felt more like a self-reflection on why, despite being technically correct, his cryptographic solutions always fail to gain mainstream traction.<p>I have a lot of respect for DJB and for the way he always challenges the status-quo. This talk is an excellent summary of the current issues in the crypto industry. But he ignores the fact that we use AES, SHA and RC4 because _it&#x27;s easy to use them_. And his solutions are never easy to use.<p>Make Nacl dead simple to use. Write clients and servers that use it. Integrate it into Firefox, Chrome, Dovecot, Nginx, Postfix, cUrl, etc... and people will slowly move away from TLS and its broken crypto.</text></comment> |
38,302,576 | 38,302,495 | 1 | 3 | 38,301,480 | train | <story><title>'Energy independent' Uruguay runs on 100% renewables for four straight months</title><url>https://theprogressplaybook.com/2023/10/19/energy-independent-uruguay-runs-on-100-renewables-for-four-straight-months/</url></story><parent_chain><item><author>skrause</author><text>Technically coal is also a closed loop of carbon because the CO2 once came from the atmosphere.<p>Which brings us to the problem: The CO2 shouldn&#x27;t be in the atmosphere <i>right now</i>: If you burn wood today and the CO2 gets removed again by new plants within the next 100 years, that&#x27;s still a problem.</text></item><item><author>woodisgood</author><text>Is wood not a renewable resource? Closed loop of carbon.</text></item><item><author>dhoe</author><text>I don&#x27;t have numbers, but huge parts of Montevideo must be relying on wood burning for heating. The effect is very noticeable in the air quality in winter (I&#x27;ve lived there for three years recently).</text></item></parent_chain><comment><author>fjni</author><text>I don’t understand why you’re being downvoted.<p>Your point is absolutely correct and as far as I can tell you pointed it out genuinely, not facetiously.
Edit: read other later posts here: didn’t know about the bacteria part. Learned something today!<p>This is absolutely not my area of expertise but intuitively there are two categories of energy sources: one which releases co2 (or other climate change impacting gases) and one which doesn’t. Wood, oil, gas, coal falls into the former. It’s just a question of time as you say until the loop closes. Solar, wind, thermal, etc would fall into the latter as far as I can tell.</text></comment> | <story><title>'Energy independent' Uruguay runs on 100% renewables for four straight months</title><url>https://theprogressplaybook.com/2023/10/19/energy-independent-uruguay-runs-on-100-renewables-for-four-straight-months/</url></story><parent_chain><item><author>skrause</author><text>Technically coal is also a closed loop of carbon because the CO2 once came from the atmosphere.<p>Which brings us to the problem: The CO2 shouldn&#x27;t be in the atmosphere <i>right now</i>: If you burn wood today and the CO2 gets removed again by new plants within the next 100 years, that&#x27;s still a problem.</text></item><item><author>woodisgood</author><text>Is wood not a renewable resource? Closed loop of carbon.</text></item><item><author>dhoe</author><text>I don&#x27;t have numbers, but huge parts of Montevideo must be relying on wood burning for heating. The effect is very noticeable in the air quality in winter (I&#x27;ve lived there for three years recently).</text></item></parent_chain><comment><author>ajuc</author><text>Coal is not a renewable resource because bacteria and fungi evolved to decompose wood before it turns into coal. That&#x27;s why almost all coal comes from (nomen omen) Carboniferous Period.</text></comment> |
13,854,775 | 13,854,506 | 1 | 2 | 13,853,150 | train | <story><title>How the Maker of TurboTax Fought Free, Simple Tax Filing (2013)</title><url>https://www.propublica.org/article/how-the-maker-of-turbotax-fought-free-simple-tax-filing</url></story><parent_chain><item><author>xupybd</author><text>Yes you have to file an IR3 if you make other income.<p><a href="http:&#x2F;&#x2F;www.ird.govt.nz&#x2F;income-tax-individual&#x2F;end-year&#x2F;ir3&#x2F;iit-what-is-ir3.html" rel="nofollow">http:&#x2F;&#x2F;www.ird.govt.nz&#x2F;income-tax-individual&#x2F;end-year&#x2F;ir3&#x2F;ii...</a><p>My favourite part of our tax system is the advice to file if you have &quot;income from an illegal enterprise&quot;<p>EDIT:
Just as a reply to the original point. I&#x27;m not sure how complicated the US system is. I&#x27;m not trying to say it&#x27;s bad either, it just seems to me that we have a system similar to the one that is getting lobbied against. And I like our system, it works well for me..</text></item><item><author>jjeaff</author><text>It&#x27;s almost that simple in the US if your situation is that simple. What happens in NZ if you make $400 selling vintage cabbage patch dolls on eBay? What if you earned $1k in returns on your investment account? What if you are renting your place out on Airbnb?<p>If all you have is a simple income in the US, then the 1040ez is a single page and you can file it for free online if you make under a certain amount. You can pay a few dollars to file online if you make more.<p>Obamacare has added an extra level of complexity now, but that is also very simple if you don&#x27;t need or want the subsidy.</text></item><item><author>xupybd</author><text>I live in New Zealand. I don&#x27;t have to file taxes if my income is a standard wage my tax payments are automatic. My employer deducts them from my wage and they are sent to the IRD (Our government tax dept). My student loan and super payments are also automatic. If there is anything wrong then at the end of the tax year I can file to correct things.<p>I also get donations rebates, this is a one page form that lists all my charitable donations. Very easy very quick.<p>All my details are available to me online. All transactions are there and it&#x27;s very transparent.<p>Why would anyone oppose a simple system like this?</text></item></parent_chain><comment><author>jwilliams</author><text><i>I&#x27;m not sure how complicated the US system is</i><p>FYI - At various stages of my life I&#x27;ve filed in New Zealand, Australia, UK, Switzerland and the US (California).<p>I can&#x27;t generalize to all persons, but I do have a decent spread of countries in my own experience - and the US was by some serious margin the most complicated.</text></comment> | <story><title>How the Maker of TurboTax Fought Free, Simple Tax Filing (2013)</title><url>https://www.propublica.org/article/how-the-maker-of-turbotax-fought-free-simple-tax-filing</url></story><parent_chain><item><author>xupybd</author><text>Yes you have to file an IR3 if you make other income.<p><a href="http:&#x2F;&#x2F;www.ird.govt.nz&#x2F;income-tax-individual&#x2F;end-year&#x2F;ir3&#x2F;iit-what-is-ir3.html" rel="nofollow">http:&#x2F;&#x2F;www.ird.govt.nz&#x2F;income-tax-individual&#x2F;end-year&#x2F;ir3&#x2F;ii...</a><p>My favourite part of our tax system is the advice to file if you have &quot;income from an illegal enterprise&quot;<p>EDIT:
Just as a reply to the original point. I&#x27;m not sure how complicated the US system is. I&#x27;m not trying to say it&#x27;s bad either, it just seems to me that we have a system similar to the one that is getting lobbied against. And I like our system, it works well for me..</text></item><item><author>jjeaff</author><text>It&#x27;s almost that simple in the US if your situation is that simple. What happens in NZ if you make $400 selling vintage cabbage patch dolls on eBay? What if you earned $1k in returns on your investment account? What if you are renting your place out on Airbnb?<p>If all you have is a simple income in the US, then the 1040ez is a single page and you can file it for free online if you make under a certain amount. You can pay a few dollars to file online if you make more.<p>Obamacare has added an extra level of complexity now, but that is also very simple if you don&#x27;t need or want the subsidy.</text></item><item><author>xupybd</author><text>I live in New Zealand. I don&#x27;t have to file taxes if my income is a standard wage my tax payments are automatic. My employer deducts them from my wage and they are sent to the IRD (Our government tax dept). My student loan and super payments are also automatic. If there is anything wrong then at the end of the tax year I can file to correct things.<p>I also get donations rebates, this is a one page form that lists all my charitable donations. Very easy very quick.<p>All my details are available to me online. All transactions are there and it&#x27;s very transparent.<p>Why would anyone oppose a simple system like this?</text></item></parent_chain><comment><author>azernik</author><text>This advice is probably not explicitly given by the IRS, but it is what any decent tax attorney will tell you. They got Al Capone not for his other crimes, but for tax evasion.</text></comment> |
21,457,503 | 21,457,527 | 1 | 2 | 21,457,207 | train | <story><title>Ogre 1.12.3</title><url>https://www.ogre3d.org/2019/11/05/ogre-1-12-3-released</url></story><parent_chain></parent_chain><comment><author>NickBusey</author><text>For those who don&#x27;t know what Ogre is like I didn&#x27;t &quot;OGRE (Object-Oriented Graphics Rendering Engine) is a scene-oriented, flexible 3D engine written in C++ designed to make it easier and more intuitive for developers to produce applications utilising hardware-accelerated 3D graphics. The class library abstracts all the details of using the underlying system libraries like Direct3D and OpenGL and provides an interface based on world objects and other intuitive classes.&quot;</text></comment> | <story><title>Ogre 1.12.3</title><url>https://www.ogre3d.org/2019/11/05/ogre-1-12-3-released</url></story><parent_chain></parent_chain><comment><author>BubRoss</author><text>Ogre is a great little 3D engine. It is small and elegant with some tools surrounding it to make it work. One big downside though is that it is&#x2F;was made in an &#x27;object oriented&#x27; style where everything is a pointer to a virtual table that then points to a heap allocated object. This makes everything slower and more difficult to debug. Small games usually don&#x27;t have enough entities to make it a problem though.</text></comment> |
7,866,684 | 7,865,475 | 1 | 2 | 7,864,813 | train | <story><title>iOS 8 randomises the MAC address while scanning for WiFi networks</title><url>https://twitter.com/fredericjacobs/status/475601665836744704</url></story><parent_chain><item><author>brunnsbe</author><text>If this becomes the trend (which in my opinon would be nice) it will become a big problem for companies that specialise in customer tracking e.g. for supermarkets and big department stores. Previously it was quite easy to track a customer, how long he or she spends time in the store, which floors he or she visits, etc. by putting up dummy WiFI-networks that the customers phones find by giving out their MAC-addresses.</text></item></parent_chain><comment><author>userbinator</author><text>It&#x27;s disturbingly creepy to think that stores would even think of doing this, but on the other hand it&#x27;s also an indication of how clueless the general population is about the amount of identifiable data they&#x27;re unconsciously &quot;leaking&quot; through personal, (nearly) always-on devices. My laptop is setup with a random MAC precisely to prevent this sort of tracking.<p>Interestingly, the unbranded Android phones I have (one looks very much like an iPhone, ironically enough) all came with this &quot;feature&quot; of a random MAC every time the WiFi is turned on&#x2F;off, although that was more likely the manufacturer not bothering to give each one a unique MAC.<p>All the more reason to keep the WiFi turned off unless you&#x27;re actually using it, and this might be a bit on the paranoid side, but I do the same for the cell radio (airplane mode) - it&#x27;s on only when I&#x27;m expecting a call or making one.<p>At the other end of the scale, this tracking via MAC almost invites making them think several million customers have suddenly entered the store...</text></comment> | <story><title>iOS 8 randomises the MAC address while scanning for WiFi networks</title><url>https://twitter.com/fredericjacobs/status/475601665836744704</url></story><parent_chain><item><author>brunnsbe</author><text>If this becomes the trend (which in my opinon would be nice) it will become a big problem for companies that specialise in customer tracking e.g. for supermarkets and big department stores. Previously it was quite easy to track a customer, how long he or she spends time in the store, which floors he or she visits, etc. by putting up dummy WiFI-networks that the customers phones find by giving out their MAC-addresses.</text></item></parent_chain><comment><author>LoganCale</author><text>Good. It should be a problem for them.</text></comment> |
25,043,357 | 25,043,190 | 1 | 2 | 25,037,064 | train | <story><title>Students have to jump through absurd hoops to use exam monitoring software</title><url>https://www.vice.com/en/article/88anxg/students-have-to-jump-through-absurd-hoops-to-use-exam-monitoring-software</url></story><parent_chain><item><author>gravypod</author><text>Most code reviews I&#x27;ve done at work take between 5 minutes to 10 minutes. To assume the worst possible case of 200 students, 20 deliverable per student, and a 10 minutes meeting per MR you&#x27;d be at ~28 days (~84 8hr-days). Get 1 TA and you now have 42 days of the semester dedicated to 1:1 time (35%) and the remainder of the semester dedicated to producing learning content. Learning content (lecture videos, etc) can be produced ahead of time and in this case you can replace this with more 1:1 tutoring time effectively allowing you to give each student ~10hr (10 min * 20 sessions * 1&#x2F;.35) direct 1:1 time over the course.<p>From the students perspective all they need to do is:<p>1. Write a &quot;project proposal&quot; where they define a project, define goals, schedule a checkin with you to see if that project is large enough (1&#x2F;20th the grade of the class)<p>2. Watch lecture videos and go through exercises on their own time.<p>3. Write code and bring it in to teacher. (18&#x2F;20th of their grade)<p>4. Demo their finished project to professor (1&#x2F;20th their grade)<p>This does work for later classes. I never had the ability to test this workflow out for earlier (100-level) classes as all of those classes I TA&#x27;d for followed the same model you&#x27;re talking about.<p>The 200+ level classes that followed the model I&#x27;m talking about had ~10% to 30% pass rate which was in line (~2x) with the pass rate of similarly leveled courses from our college&#x27;s Math and Physics department which was used as a sanity check.<p>edit: that&#x27;s not to say you&#x27;re incorrect that it would be difficult to do at scale, this is just the way I&#x27;ve seen it done at moderate scale (20 to 40 students).</text></item><item><author>acbart</author><text>This will never work because it absolutely fails to scale, at a time when we have a complete lack of computing educators. Customized projects for each student? I have 159 students in my CS1 this semester, and I can barely keep track of them with the massive amounts of data I collect. The idea of making individualized assignments is beautiful but unrealistic.</text></item><item><author>gravypod</author><text>Could you make your class project based and give everyone different, but equally difficult, projects of their choosing. Each check in into master would then be merged after a code review with you where you ask questions about why implementations are done specific ways to solve the problem&#x2F;refactor. Code is only merged when it hits a quality marker you set. Students are graded by percentage of deliverable hit from original project specs.<p>Ex: student is to implement a K&amp;R C compiler + code generator in 1 semester. Help them break up the project into manageable chunks (tokenize, AST, register allocation, etc). Each feature includes tests, comments, docs, and is presented to you by X date. Code review and cycle as many times as needed as long as it gets in by X date. By the end of the class the student hit 100% of their deadlines but only pass 70% of some test C files you create so they get a 70% (or higher if their code was consistently good and did not need cleanup) in the class or something.<p>It would never work because &quot;you need to have a final exam&quot; but it&#x27;s the ideal I think we should strive for if you are &quot;teaching programming&quot; since this is how most work I&#x27;ve done in the real world has gone.</text></item><item><author>sn41</author><text>I teach programming. What prevents students from colluding over their tablets&#x2F;mobiles&#x2F;laptops while taking the exam from another device? Can&#x27;t the student mirror the screen elsewhere, leading to interesting possibilities for cheating?<p>Proctoring is not a solution that I am comfortable with. I do not want to peer into the private lives of students and their home environments. Not every student is well-off, and has a private space all to their own for 3 hours.<p>I think taking tests from home does not really work with any of the models I have seen discussed this year. Cheating is real. It has nothing to do with rote learning. I am out of ideas which are foolproof.</text></item><item><author>cloud5ir</author><text>To me, this underscores notion that schools continue to test for the wrong thing. With the exception of professions&#x2F;trades that require impulse application of knowledge, I don&#x27;t know why I would want&#x2F;need someone to memorize a concept in order to apply it. Productive members of our society&#x2F;workforce think critically, they ask good questions, and they research and leverage the information at their disposal to make data-driven decisions. Let&#x27;s test for that.</text></item></parent_chain><comment><author>unishark</author><text>It&#x27;s easy (even a bit fun) to grade and give feedback for good students. Meanwhile it&#x27;s a huge pain to do for the weak students. You need to first figure out what they heck they&#x27;re trying to do before you can tell them how to fix it, which may take a lot. I suspect code reviews for professionals is much more like the good student category.<p>If you&#x27;re asking the students to define unique projects themselves, you run into new problems as students dig up the most obscure blogs they can find on the internet to download and give you. It&#x27;s a never-ending adversarial struggle.</text></comment> | <story><title>Students have to jump through absurd hoops to use exam monitoring software</title><url>https://www.vice.com/en/article/88anxg/students-have-to-jump-through-absurd-hoops-to-use-exam-monitoring-software</url></story><parent_chain><item><author>gravypod</author><text>Most code reviews I&#x27;ve done at work take between 5 minutes to 10 minutes. To assume the worst possible case of 200 students, 20 deliverable per student, and a 10 minutes meeting per MR you&#x27;d be at ~28 days (~84 8hr-days). Get 1 TA and you now have 42 days of the semester dedicated to 1:1 time (35%) and the remainder of the semester dedicated to producing learning content. Learning content (lecture videos, etc) can be produced ahead of time and in this case you can replace this with more 1:1 tutoring time effectively allowing you to give each student ~10hr (10 min * 20 sessions * 1&#x2F;.35) direct 1:1 time over the course.<p>From the students perspective all they need to do is:<p>1. Write a &quot;project proposal&quot; where they define a project, define goals, schedule a checkin with you to see if that project is large enough (1&#x2F;20th the grade of the class)<p>2. Watch lecture videos and go through exercises on their own time.<p>3. Write code and bring it in to teacher. (18&#x2F;20th of their grade)<p>4. Demo their finished project to professor (1&#x2F;20th their grade)<p>This does work for later classes. I never had the ability to test this workflow out for earlier (100-level) classes as all of those classes I TA&#x27;d for followed the same model you&#x27;re talking about.<p>The 200+ level classes that followed the model I&#x27;m talking about had ~10% to 30% pass rate which was in line (~2x) with the pass rate of similarly leveled courses from our college&#x27;s Math and Physics department which was used as a sanity check.<p>edit: that&#x27;s not to say you&#x27;re incorrect that it would be difficult to do at scale, this is just the way I&#x27;ve seen it done at moderate scale (20 to 40 students).</text></item><item><author>acbart</author><text>This will never work because it absolutely fails to scale, at a time when we have a complete lack of computing educators. Customized projects for each student? I have 159 students in my CS1 this semester, and I can barely keep track of them with the massive amounts of data I collect. The idea of making individualized assignments is beautiful but unrealistic.</text></item><item><author>gravypod</author><text>Could you make your class project based and give everyone different, but equally difficult, projects of their choosing. Each check in into master would then be merged after a code review with you where you ask questions about why implementations are done specific ways to solve the problem&#x2F;refactor. Code is only merged when it hits a quality marker you set. Students are graded by percentage of deliverable hit from original project specs.<p>Ex: student is to implement a K&amp;R C compiler + code generator in 1 semester. Help them break up the project into manageable chunks (tokenize, AST, register allocation, etc). Each feature includes tests, comments, docs, and is presented to you by X date. Code review and cycle as many times as needed as long as it gets in by X date. By the end of the class the student hit 100% of their deadlines but only pass 70% of some test C files you create so they get a 70% (or higher if their code was consistently good and did not need cleanup) in the class or something.<p>It would never work because &quot;you need to have a final exam&quot; but it&#x27;s the ideal I think we should strive for if you are &quot;teaching programming&quot; since this is how most work I&#x27;ve done in the real world has gone.</text></item><item><author>sn41</author><text>I teach programming. What prevents students from colluding over their tablets&#x2F;mobiles&#x2F;laptops while taking the exam from another device? Can&#x27;t the student mirror the screen elsewhere, leading to interesting possibilities for cheating?<p>Proctoring is not a solution that I am comfortable with. I do not want to peer into the private lives of students and their home environments. Not every student is well-off, and has a private space all to their own for 3 hours.<p>I think taking tests from home does not really work with any of the models I have seen discussed this year. Cheating is real. It has nothing to do with rote learning. I am out of ideas which are foolproof.</text></item><item><author>cloud5ir</author><text>To me, this underscores notion that schools continue to test for the wrong thing. With the exception of professions&#x2F;trades that require impulse application of knowledge, I don&#x27;t know why I would want&#x2F;need someone to memorize a concept in order to apply it. Productive members of our society&#x2F;workforce think critically, they ask good questions, and they research and leverage the information at their disposal to make data-driven decisions. Let&#x27;s test for that.</text></item></parent_chain><comment><author>quiescant_dodo</author><text>Code reviews I have done for unrelated bits of code often take me 90 minutes. And that&#x27;s for code that fits into the idea of my product space, but not super familiar to my everyday life. I don&#x27;t think 5-10 minutes is anywhere close to reasonable.</text></comment> |
18,385,142 | 18,384,977 | 1 | 3 | 18,381,627 | train | <story><title>Apple’s Social Network</title><url>https://stratechery.com/2018/apples-social-network/</url></story><parent_chain><item><author>cronix</author><text>I think the single biggest thing they could do to get to $2T is build their own search engine, and ditch google completely. I think it&#x27;s funny how some people (and Apple themselves) always say how Apple is so privacy conscious, while at the same time they made 9 Billion Dollars from Google by using Google as the default search engine in Safari (which most people don&#x27;t change). So it seems they&#x27;re willing to sell some of their users privacy for profit, and a very nice one at that.<p>If they just built their own search engine and used it as default, and it provided high quality un-manipulated results, I think even more would flock to Apple. Yes they&#x27;d take a (big) hit up front by losing out on all of that free Google money (estimated to be ~$12B in 2019), but then they could <i>actually</i> say with a straight face they were truly privacy advocates and won&#x27;t sell their users data to Google via the Google Search Engine.<p>Saying how privacy conscious a company is, while literally making billions of dollars by indirectly selling a lot of their customers data, really rings hollow with me. Build a search engine. It&#x27;s not as hard as building Apple Maps, and will do more good in many ways. Hell, even non-Apple people might use Apple search and fall in love with the results, bringing them into the Apple fold.</text></item><item><author>ethagknight</author><text>Ha, I&#x27;m speaking from Apple&#x27;s perspective thinking through how they could double in value. I don&#x27;t think the current method of bills coming from everywhere with different payment requirements is all that great. If this new &quot;middleman&quot; provides value and protects me, then what&#x27;s the problem? I wouldn&#x27;t see direct integration with my apple device as a middleman but an endpoint. Furthermore, there are loads of whitelabelled middlemen in the current process, you just see it in one big bottom line number for each bill and may appear as service charges, admin fees, billing services, compliance, etc. Apple moving into this space kinda removes middlemen, reducing the number of touches between the biller and your wallet.</text></item><item><author>moolcool</author><text>&gt;Imagine if those “luxury” expenses were intermixed with a dozen other large, more legitimate bills? Apple could be processing $1000s a month per household, taking a hefty fee from some of them.<p>That&#x27;s what we need-- another middle man taking a even more off the top of every transaction.</text></item><item><author>ethagknight</author><text>I don’t think he mentioned it, but the easy way for Apple to grow to a $2T company is to get my household, a typical locked-in Apple household with an iPad or iPhone for every person and a computer for each adult and an AppleTV at every TV, to start paying for ever more services through those Apple devices. TV service. Ubiquitous internet service. Financial services like payments but grow into banking. manage all my regularly scheduled bills like utilities, rent or mortgages. I would love for a trusted intermediary to handle these things.<p>I was recently taken aback by the amount of money I was paying for high-quality subscriptions “oh my god, I’ve paid $20&#x2F;month for the last 12 months to subscribe to high quality streaming to Phish concerts via their app?!?” I signed up for it thinking I would only do it for a month. I forgot. I spent $240 on Phish audio, more than I spent on my Apple Watch. Apple’s real social network could be just getting started. Imagine if those “luxury” expenses were intermixed with a dozen other large, more legitimate bills? Apple could be processing $1000s a month per household, taking a hefty fee from some of them. And then launch a loyalty program :).<p>If I had to guess, I’d say this comment resembles Buffet’s view of Apple’s opportunity.</text></item></parent_chain><comment><author>reaperducer</author><text><i>I think the single biggest thing they could do to get to $2T is build their own search engine, and ditch google completely.</i><p>Based on the series of frustrating searches I did in iTunes last night, Apple either isn&#x27;t working on this at all, or isn&#x27;t using iTunes as a testbed.</text></comment> | <story><title>Apple’s Social Network</title><url>https://stratechery.com/2018/apples-social-network/</url></story><parent_chain><item><author>cronix</author><text>I think the single biggest thing they could do to get to $2T is build their own search engine, and ditch google completely. I think it&#x27;s funny how some people (and Apple themselves) always say how Apple is so privacy conscious, while at the same time they made 9 Billion Dollars from Google by using Google as the default search engine in Safari (which most people don&#x27;t change). So it seems they&#x27;re willing to sell some of their users privacy for profit, and a very nice one at that.<p>If they just built their own search engine and used it as default, and it provided high quality un-manipulated results, I think even more would flock to Apple. Yes they&#x27;d take a (big) hit up front by losing out on all of that free Google money (estimated to be ~$12B in 2019), but then they could <i>actually</i> say with a straight face they were truly privacy advocates and won&#x27;t sell their users data to Google via the Google Search Engine.<p>Saying how privacy conscious a company is, while literally making billions of dollars by indirectly selling a lot of their customers data, really rings hollow with me. Build a search engine. It&#x27;s not as hard as building Apple Maps, and will do more good in many ways. Hell, even non-Apple people might use Apple search and fall in love with the results, bringing them into the Apple fold.</text></item><item><author>ethagknight</author><text>Ha, I&#x27;m speaking from Apple&#x27;s perspective thinking through how they could double in value. I don&#x27;t think the current method of bills coming from everywhere with different payment requirements is all that great. If this new &quot;middleman&quot; provides value and protects me, then what&#x27;s the problem? I wouldn&#x27;t see direct integration with my apple device as a middleman but an endpoint. Furthermore, there are loads of whitelabelled middlemen in the current process, you just see it in one big bottom line number for each bill and may appear as service charges, admin fees, billing services, compliance, etc. Apple moving into this space kinda removes middlemen, reducing the number of touches between the biller and your wallet.</text></item><item><author>moolcool</author><text>&gt;Imagine if those “luxury” expenses were intermixed with a dozen other large, more legitimate bills? Apple could be processing $1000s a month per household, taking a hefty fee from some of them.<p>That&#x27;s what we need-- another middle man taking a even more off the top of every transaction.</text></item><item><author>ethagknight</author><text>I don’t think he mentioned it, but the easy way for Apple to grow to a $2T company is to get my household, a typical locked-in Apple household with an iPad or iPhone for every person and a computer for each adult and an AppleTV at every TV, to start paying for ever more services through those Apple devices. TV service. Ubiquitous internet service. Financial services like payments but grow into banking. manage all my regularly scheduled bills like utilities, rent or mortgages. I would love for a trusted intermediary to handle these things.<p>I was recently taken aback by the amount of money I was paying for high-quality subscriptions “oh my god, I’ve paid $20&#x2F;month for the last 12 months to subscribe to high quality streaming to Phish concerts via their app?!?” I signed up for it thinking I would only do it for a month. I forgot. I spent $240 on Phish audio, more than I spent on my Apple Watch. Apple’s real social network could be just getting started. Imagine if those “luxury” expenses were intermixed with a dozen other large, more legitimate bills? Apple could be processing $1000s a month per household, taking a hefty fee from some of them. And then launch a loyalty program :).<p>If I had to guess, I’d say this comment resembles Buffet’s view of Apple’s opportunity.</text></item></parent_chain><comment><author>ummonk</author><text>This is unlikely to happen but I&#x27;d certainly like to see it happen, as Duck Duck Go simply does not work as a substitute for me, and I don&#x27;t know that Bing is any better than Google privacy-wise. If Microsoft can make Bing, Apple can certainly make Apple Search - they have plenty of cash to throw at the problem.</text></comment> |
39,631,454 | 39,630,231 | 1 | 2 | 39,625,919 | train | <story><title>Nikon to acquire RED</title><url>https://www.nikon.com/company/news/2024/0307_01.html</url></story><parent_chain><item><author>cfr2023</author><text>I started following the RED story before those folks ever released a camera, and I liked their spirit and mission.<p>Some time passed and ultimately it was Black Magic Design that accomplished what RED said they wanted to do.<p>If you say you want to make high end cinema technology, or even just high quality imagery, accessible to the average person, a $17,500 price tag for just the camera body shows that you might have strange ideas about what constitutes an average person.</text></item></parent_chain><comment><author>kkukshtel</author><text>I think if you know the RED story you know that at the time there were effectively 0 consumer-tier high end digital cameras. We&#x27;re talking basically the advent of the DSLR revolution, where either you shot on a Canon 5D MK II or... an Alexa? Alexas retail around $50,000 (and weren&#x27;t out until 2010), so RED offering actual 4K video digital camera with an easy conversion to EF mount glass (Canon) and a body that is literally half the size of an Alexa AND was consumer-purchasable at $17,500 (Alexa purchase process isn&#x27;t &quot;just buy on B&amp;H&quot;) - it was huge.<p>The other thing is that the camera market and the concept of &quot;consumer&quot; isn&#x27;t really like normal &quot;consumer&quot; end stuff. High-end digital camera &quot;consumer&quot; stuff has different purchase cycles that traditional &quot;consumer&quot; things like iPhones don&#x27;t have. Camera Operators&#x2F;DPs typically buy these huge cameras and then rent them out or bill their cost back into their day rate.<p>When RED says consumer, they mean that any person with money can buy one. Alexas, Panavision Cameras, Fony F65s, etc. all usually need to be bought by a cinema rental house and then are rented to operators. RED went around that and allowed people to buy cinema-tier cameras directly, which was huge. The market has adjusted since then and I think Blackmagic (and the Sony Alpha line) now more directly serve traditional definitions of &quot;Consumer&quot;, but IMO none of that would have happened without RED paving the path.</text></comment> | <story><title>Nikon to acquire RED</title><url>https://www.nikon.com/company/news/2024/0307_01.html</url></story><parent_chain><item><author>cfr2023</author><text>I started following the RED story before those folks ever released a camera, and I liked their spirit and mission.<p>Some time passed and ultimately it was Black Magic Design that accomplished what RED said they wanted to do.<p>If you say you want to make high end cinema technology, or even just high quality imagery, accessible to the average person, a $17,500 price tag for just the camera body shows that you might have strange ideas about what constitutes an average person.</text></item></parent_chain><comment><author>stephen_g</author><text>The most affordable kinds of cameras at the time that you could realistically use for something going to theatrical release was the (1080p) Sony F900 and then F950, which were in the $250K ballpark… Then the Arri D-21 came out, I can’t even remember what price but same ballpark, it was a bit higher than 2K res. $17,500 for 4K was wild, and it was insane they actually managed to deliver it with the RED ONE.</text></comment> |
38,756,857 | 38,756,658 | 1 | 2 | 38,756,044 | train | <story><title>Toyota's Daihatsu to halt all vehicle shipments as safety scandal widens</title><url>https://www.cnbc.com/2023/12/20/toyotas-daihatsu-to-halt-vehicle-shipments-as-safety-scandal-widens.html</url></story><parent_chain></parent_chain><comment><author>xyst</author><text>“… The problems were found in 64 models and three vehicle engines, including 22 models and an engine sold by Toyota, Daihatsu said in a statement. The investigation also found the problems affected some models of Mazda Motor Corp. and Subaru Corp. sold in Japan, and Toyota and Daihatsu models sold abroad. …” [1]<p><a href="https:&#x2F;&#x2F;www.usnews.com&#x2F;news&#x2F;business&#x2F;articles&#x2F;2023-12-20&#x2F;toyotas-small-car-unit-daihatsu-will-suspend-all-vehicle-shipments-over-widespread-safety-cheating" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.usnews.com&#x2F;news&#x2F;business&#x2F;articles&#x2F;2023-12-20&#x2F;toy...</a><p>Does anybody know the exact list of models impacted? I am not familiar with “Daihatsu” and Toyota relationship.<p>Neither US News or CNBC article mention exact manufacturer and model names</text></comment> | <story><title>Toyota's Daihatsu to halt all vehicle shipments as safety scandal widens</title><url>https://www.cnbc.com/2023/12/20/toyotas-daihatsu-to-halt-vehicle-shipments-as-safety-scandal-widens.html</url></story><parent_chain></parent_chain><comment><author>Waterluvian</author><text>Daihatsu’s charade. Committing fraud in <i>safety testing</i> needs to be punished severely.<p>It’s good to see that they’re stopping shipments. I hope there’s more than just fines.</text></comment> |
17,542,581 | 17,542,601 | 1 | 2 | 17,541,065 | train | <story><title>To cash in on Kindle Unlimited, a cabal of authors gamed Amazon’s algorithm</title><url>https://www.theverge.com/2018/7/16/17566276/cockygate-amazon-kindle-unlimited-algorithm-self-published-romance-novel-cabal</url></story><parent_chain><item><author>gfo</author><text>Are there examples of businesses out there which have done product recommendation correctly?<p>Amazon is notorious for trying to sell you the same kind of product after you&#x27;ve already purchased it (e.g. I bought a ladder and now all of my recommendations are for more ladders). How hard can it be to uncover which items are more likely to be one-time buys and recommend the products people buy with those items instead (ex. show me painting supplies when I buy a ladder)?</text></item><item><author>guitarbill</author><text>The Kindle store is already garbage for any kind of discovery, and Unlimited makes it worse being just more marketing BS to hide the real price and displace good content. Their suggestion algorithms are terrible, and only really work if you want something from the same author.<p>Steam has exactly the same problem, although ar least they‘re trying to solve it in various ways.</text></item></parent_chain><comment><author>s-shellfish</author><text>I really feel like this just happens because they don&#x27;t have enough people looking over the data recommendations and the actual market economics, or enough communication between both divisions, if those divisions are sufficiently black boxed from one another. The difference may be purchasing one ladder versus purchasing a ladder, returning a ladder, and purchasing another ladder. Or companies, contractors, etc. purchasing in bulk. Obviously if their core recommendation algorithms are sufficiently generalized to all item types, it doesn&#x27;t matter that it&#x27;s a ladder. You could be getting side effects from people buying pencils for classrooms in bulk or survivalists stocking up on canned goods. If the recommendation algorithms account for some categorical relation between item types, it still doesn&#x27;t remove the problem, because different people in the world use different products differently and they can&#x27;t all be classified and generalized to a collection of people&#x27;s rule systems. It doesn&#x27;t even begin to factor in the sorts of &#x27;second order&#x27; logic required when new economic systems begin to grow on top of the existing supply-demand relation. You could be getting side effects from competitive buyers on amazon treating amazon products like they are stocks.<p>It is hard. Dynamical systems.</text></comment> | <story><title>To cash in on Kindle Unlimited, a cabal of authors gamed Amazon’s algorithm</title><url>https://www.theverge.com/2018/7/16/17566276/cockygate-amazon-kindle-unlimited-algorithm-self-published-romance-novel-cabal</url></story><parent_chain><item><author>gfo</author><text>Are there examples of businesses out there which have done product recommendation correctly?<p>Amazon is notorious for trying to sell you the same kind of product after you&#x27;ve already purchased it (e.g. I bought a ladder and now all of my recommendations are for more ladders). How hard can it be to uncover which items are more likely to be one-time buys and recommend the products people buy with those items instead (ex. show me painting supplies when I buy a ladder)?</text></item><item><author>guitarbill</author><text>The Kindle store is already garbage for any kind of discovery, and Unlimited makes it worse being just more marketing BS to hide the real price and displace good content. Their suggestion algorithms are terrible, and only really work if you want something from the same author.<p>Steam has exactly the same problem, although ar least they‘re trying to solve it in various ways.</text></item></parent_chain><comment><author>mattbierner</author><text>Slightly different but spotify’s algorithmic recommendations have been great. I’ve found some really amazing stuff through “discover weekly”, “new releases”, and “related artists”. Same with Bandcamp. (Maybe the problem is easier for music?)<p>For content, I also find that user curated lists can be far better than automated systems. They give me an upfront sense of the curator’s tastes and define niches that algorithms would never recognize</text></comment> |
12,021,952 | 12,021,409 | 1 | 3 | 12,019,805 | train | <story><title>Spain Runs Out of Workers with Almost 5M Unemployed</title><url>http://www.bloomberg.com/news/articles/2016-07-01/spain-is-running-out-of-workers-with-almost-5-million-unemployed</url></story><parent_chain><item><author>vemv</author><text>I agree that measuring productivity is a hard, universal problem.<p>While I don&#x27;t claim to commit 10x more LOCs, I do write exceptional abstractions that allow me to get things done in a quick, robust way.<p>I&#x27;ve met far too many &#x27;senior&#x27; developers blatantly breaking DRY because they don&#x27;t really know&#x2F;use all features $language or $framework has to offer.</text></item><item><author>Jare</author><text>Leaving aside the validity of the 10x programmer concept, the company still needs to be able to extract that extra performance in actual value. Most software jobs in Spain don&#x27;t have productivity of that kind. Almost no companies here develop software products or services whose effectiveness translates directly into revenue. Very few of those who have tried have had any sort of long-term success.</text></item><item><author>vemv</author><text>Spanish dev here, 3 years in the business, been twice a freelancer and twice an employee. My main complaints:<p>- The maximum salary a developer can earn at any given company is almost written in stone - around 36000 euros. Every public job posting will have that figure as the max. When it&#x27;s higher, they&#x27;ll water it down in the interview.<p>Why? Probably because they don&#x27;t have the notion of a 10x programmer at all. We all are perceived as &#x27;equal&#x27; or even replaceable.<p>- Also, companies are scared of the mere possibility of their programmers leaving. The sole hint of that you may leave will turn their red alarms on, and they&#x27;ll start searching a replacement.<p>There rarely exists here the mentality that a work relationship is a commercial exchange, not an intimate family-like relationship. Being open to the market is not &#x27;treason&#x27;.<p>- Tech stacks tend to be years behind San Francisco, whether is languages, frameworks, ops practices...<p>- Functional programming opportunities extremely scarce. Elixir is gaining traction here though.</text></item></parent_chain><comment><author>thinkloop</author><text>Several years ago I took over the lead UI position at a company. Jira has a feature to display lines of code contributed by developer. After 10 months of adding features, and getting the product to shipping, I had contributed -1500 lines. There were less lines than when I started, and the code was simpler for it. I&#x27;d _almost_ say that LOC is a good measure of bad coding.</text></comment> | <story><title>Spain Runs Out of Workers with Almost 5M Unemployed</title><url>http://www.bloomberg.com/news/articles/2016-07-01/spain-is-running-out-of-workers-with-almost-5-million-unemployed</url></story><parent_chain><item><author>vemv</author><text>I agree that measuring productivity is a hard, universal problem.<p>While I don&#x27;t claim to commit 10x more LOCs, I do write exceptional abstractions that allow me to get things done in a quick, robust way.<p>I&#x27;ve met far too many &#x27;senior&#x27; developers blatantly breaking DRY because they don&#x27;t really know&#x2F;use all features $language or $framework has to offer.</text></item><item><author>Jare</author><text>Leaving aside the validity of the 10x programmer concept, the company still needs to be able to extract that extra performance in actual value. Most software jobs in Spain don&#x27;t have productivity of that kind. Almost no companies here develop software products or services whose effectiveness translates directly into revenue. Very few of those who have tried have had any sort of long-term success.</text></item><item><author>vemv</author><text>Spanish dev here, 3 years in the business, been twice a freelancer and twice an employee. My main complaints:<p>- The maximum salary a developer can earn at any given company is almost written in stone - around 36000 euros. Every public job posting will have that figure as the max. When it&#x27;s higher, they&#x27;ll water it down in the interview.<p>Why? Probably because they don&#x27;t have the notion of a 10x programmer at all. We all are perceived as &#x27;equal&#x27; or even replaceable.<p>- Also, companies are scared of the mere possibility of their programmers leaving. The sole hint of that you may leave will turn their red alarms on, and they&#x27;ll start searching a replacement.<p>There rarely exists here the mentality that a work relationship is a commercial exchange, not an intimate family-like relationship. Being open to the market is not &#x27;treason&#x27;.<p>- Tech stacks tend to be years behind San Francisco, whether is languages, frameworks, ops practices...<p>- Functional programming opportunities extremely scarce. Elixir is gaining traction here though.</text></item></parent_chain><comment><author>jfoutz</author><text>I&#x27;ve worked with developers that commit far far more code than i do. I still find it intimidating. I take solice in replacing those 50kloc subsystems with a few interfaces and a handful of implementations. Those -40kloc days are awesome.<p>To be fair, those guys that throw out tons of code really explore the problem space. it&#x27;s tough to start with a clean design when the spec is vague.</text></comment> |
38,848,784 | 38,848,197 | 1 | 3 | 38,842,079 | train | <story><title>An untold story of LSD psychotherapy in communist Czechoslovakia</title><url>https://thereader.mitpress.mit.edu/an-untold-story-of-lsd-psychotherapy-in-communist-czechoslovakia/</url></story><parent_chain><item><author>FredPret</author><text>And if you screw this extremely delicate self-administered chemical mind alteration up, the rest of us have to foot the bill for the resulting care &#x2F; homelessnes &#x2F; crime.<p>I’m a huge free marketeer, but a minimal amount of regulation really goes a very long way to improving outcomes.<p>Plus, you don’t get a second chance fixing your own brain.</text></item><item><author>labrador</author><text>I&#x27;ve successfully done self-therapy using nitrous oxide, psilocybin, 5-MeO-DMT and LSD, most recently to come to terms with my difficult father to forgive him. My problem with the current push for this type of therapy is the requirment that it be done by professionals charging hundreds or thousands of dollars. One must never mention &quot;self-therapy&quot; because that might scare legislatures into keeping these drugs illegal. I remain resistant to this insertion of the state into what should be my right to use my own mind the way I see fit.</text></item></parent_chain><comment><author>cf1241290841</author><text>&gt;Plus, you don’t get a second chance fixing your own brain.<p>Says who?<p>I also believe your argument suffers from an attention fallacy. We allow (and encourage) people to do quite a lot of things that are outright more destructive and dangerous. Just walk past any gambling hall and have a look inside if you need an example. There are proper addicts there driven to extreme measures by desperation and tunnel views.<p>edit: If you need an example, a class mate of a very good friend of mine got into the habit of spending his pay check playing slots. He is currently serving time for cocaine smuggling after he ran out of options and couldnt see any other way out. Once losses are mounting peoples sanity goes quickly. Cocaine smuggling is by far not the worst thing he could have gotten himself into. And its not like putting him in detox for a week would have cleared his mind up as long as the debt is still there.</text></comment> | <story><title>An untold story of LSD psychotherapy in communist Czechoslovakia</title><url>https://thereader.mitpress.mit.edu/an-untold-story-of-lsd-psychotherapy-in-communist-czechoslovakia/</url></story><parent_chain><item><author>FredPret</author><text>And if you screw this extremely delicate self-administered chemical mind alteration up, the rest of us have to foot the bill for the resulting care &#x2F; homelessnes &#x2F; crime.<p>I’m a huge free marketeer, but a minimal amount of regulation really goes a very long way to improving outcomes.<p>Plus, you don’t get a second chance fixing your own brain.</text></item><item><author>labrador</author><text>I&#x27;ve successfully done self-therapy using nitrous oxide, psilocybin, 5-MeO-DMT and LSD, most recently to come to terms with my difficult father to forgive him. My problem with the current push for this type of therapy is the requirment that it be done by professionals charging hundreds or thousands of dollars. One must never mention &quot;self-therapy&quot; because that might scare legislatures into keeping these drugs illegal. I remain resistant to this insertion of the state into what should be my right to use my own mind the way I see fit.</text></item></parent_chain><comment><author>foxhill</author><text>yes, that’s what collective health care means, regardless of if it’s state-mandated, or fully private.<p>you, or i, don’t get to decide what’s fair to treat, or who’s deserving of treatment.</text></comment> |
10,496,927 | 10,496,095 | 1 | 2 | 10,494,512 | train | <story><title>Object.observe withdrawn from TC39</title><url>https://mail.mozilla.org/pipermail/es-discuss/2015-November/044684.html</url></story><parent_chain><item><author>haberman</author><text>I like the React model, but it does make one key assumption. It assumes that DOM mutation is so slow that re-rendering and diffing the entire virtual DOM for every update is basically free in comparison. I like the simplicity of React&#x27;s approach, but this assumption makes me a little uncomfortable.</text></item><item><author>tolmasky</author><text>I now subscribe to the React-style &quot;wait, why are you listening to anything?&quot; mindset. However, if you&#x27;re going to go down the mutable path, I think KVO was particularly well designed.<p>The main reason was that it made composition pretty sane and created clear places to handle changes. With KVO, you implement your KVO-compliant mutation methods, and all changes would then get funneled through there (most notable container ones). Compare the mess that is NSView (addSubview&#x2F;insertSubview:positioned:relativeTo:&#x2F;removeFromSuperview&#x2F;etc) to the post-KVO NSTreeNode. NSTreeNode simply exposes .mutableChildNodes, which you treat as a normal array (addObject:&#x2F;etc) and after adding a child, it then has parentNode set to the parent after. This was great for lots of reasons: 1. No need to re-create API, you just used NSMutableArray&#x27;s existing API. So [someNode.mutableChildNodes removeObjectsWithPredicate:somePredicate] and all the parentNode relationships get handled for free. Compare this to pre-KVO methods where every time you wanted to take advantage of a neat NSMutableArray feature, you&#x27;d have to re-expose it yourself like removeSubviewsWithPredicate:, or wind up having to copy out the array, mutate, then re-assign with setSubviews: 2. Less room for error since all your cleanup code just happens in removeObjectFrom&lt;Key&gt;AtIndex:, one funnel.<p>Again, I believe this to be a great local maxima for this style of programming, one that was never that fully explored since the move to more KVO-ness was eclipsed by the attention to iOS. I think most the problems are better solved through React&#x27;s top-down approach.</text></item><item><author>pavlov</author><text>In my experience, observing individual properties on model objects just isn&#x27;t very useful in real world apps. Cocoa has long offered &quot;key-value observing&quot; (KVO) for this purpose, but other mechanisms like notifications tend to be more practical, usually because listeners need some context in order to do the best thing in response to a change, and an individual property change won&#x27;t carry any of that context.<p>Here&#x27;s a practical example... Imagine an editor where an on-screen element is deleted. The controller might do a bunch of stuff such as:<p><pre><code> element.parent = nil
scene.clearReferencesToElement(element)
container.delete(element)
self.selection = []
</code></pre>
If there&#x27;s a listener on &quot;container&quot;, it will get notified even before the selection was cleared. That&#x27;s probably not the intention.<p>If we know that&#x27;s going to happen, we could move the selection manipulation before the container access... But then we have fragile code that depends on implicit behavior in a model class. Always better to send an explicit event.</text></item></parent_chain><comment><author>nostrademons</author><text>React&#x27;s assumption isn&#x27;t actually true. DOM manipulation is fast - all modern browsers use a dirty-bit system where modifying the DOM is basically a few pointer swaps. <i>Layout</i>, however, is slow, and dirtying the DOM requires <i>at least one</i> layout as soon as control returns from JS. If you intersperse measure and modify calls, it&#x27;s more.<p>However, what is true is that:<p>1. Both JS and the DOM are fast enough that you can lay out most reasonable pages within the threshold of visual perception (~150-200ms).<p>2. If you need to layout the page during an animation frame, you&#x27;re hosed anyway. You have a frame budget of 16.67ms and layout will take 100ms+ on mobile.<p>And so the practical, qualitative conclusion is the same: you can use React for your basic page transformations &amp; rendering, but you need to use CSS transforms and offload the work to the GPU if you want to have a prayer of making animations work on mobile. And React also protects you from completely fucking up performance (which is trivially easy with JQuery), so many real-world pages from inexperienced webdevs experience a very significant speedup.</text></comment> | <story><title>Object.observe withdrawn from TC39</title><url>https://mail.mozilla.org/pipermail/es-discuss/2015-November/044684.html</url></story><parent_chain><item><author>haberman</author><text>I like the React model, but it does make one key assumption. It assumes that DOM mutation is so slow that re-rendering and diffing the entire virtual DOM for every update is basically free in comparison. I like the simplicity of React&#x27;s approach, but this assumption makes me a little uncomfortable.</text></item><item><author>tolmasky</author><text>I now subscribe to the React-style &quot;wait, why are you listening to anything?&quot; mindset. However, if you&#x27;re going to go down the mutable path, I think KVO was particularly well designed.<p>The main reason was that it made composition pretty sane and created clear places to handle changes. With KVO, you implement your KVO-compliant mutation methods, and all changes would then get funneled through there (most notable container ones). Compare the mess that is NSView (addSubview&#x2F;insertSubview:positioned:relativeTo:&#x2F;removeFromSuperview&#x2F;etc) to the post-KVO NSTreeNode. NSTreeNode simply exposes .mutableChildNodes, which you treat as a normal array (addObject:&#x2F;etc) and after adding a child, it then has parentNode set to the parent after. This was great for lots of reasons: 1. No need to re-create API, you just used NSMutableArray&#x27;s existing API. So [someNode.mutableChildNodes removeObjectsWithPredicate:somePredicate] and all the parentNode relationships get handled for free. Compare this to pre-KVO methods where every time you wanted to take advantage of a neat NSMutableArray feature, you&#x27;d have to re-expose it yourself like removeSubviewsWithPredicate:, or wind up having to copy out the array, mutate, then re-assign with setSubviews: 2. Less room for error since all your cleanup code just happens in removeObjectFrom&lt;Key&gt;AtIndex:, one funnel.<p>Again, I believe this to be a great local maxima for this style of programming, one that was never that fully explored since the move to more KVO-ness was eclipsed by the attention to iOS. I think most the problems are better solved through React&#x27;s top-down approach.</text></item><item><author>pavlov</author><text>In my experience, observing individual properties on model objects just isn&#x27;t very useful in real world apps. Cocoa has long offered &quot;key-value observing&quot; (KVO) for this purpose, but other mechanisms like notifications tend to be more practical, usually because listeners need some context in order to do the best thing in response to a change, and an individual property change won&#x27;t carry any of that context.<p>Here&#x27;s a practical example... Imagine an editor where an on-screen element is deleted. The controller might do a bunch of stuff such as:<p><pre><code> element.parent = nil
scene.clearReferencesToElement(element)
container.delete(element)
self.selection = []
</code></pre>
If there&#x27;s a listener on &quot;container&quot;, it will get notified even before the selection was cleared. That&#x27;s probably not the intention.<p>If we know that&#x27;s going to happen, we could move the selection manipulation before the container access... But then we have fragile code that depends on implicit behavior in a model class. Always better to send an explicit event.</text></item></parent_chain><comment><author>tlrobinson</author><text><i>&quot;diffing the entire virtual DOM for every update is basically free in comparison&quot;</i><p>If you use something like Immutable.js you can avoid a lot (most? all?) of the diffing since comparing trees of objects becomes a simple object reference comparison. This is common in the Om world, and becoming more popular in JS too.</text></comment> |
8,848,757 | 8,847,548 | 1 | 3 | 8,847,141 | train | <story><title>Pythonpy – Command-line Kung Fu with Python</title><url>https://github.com/Russell91/pythonpy/</url><text></text></story><parent_chain></parent_chain><comment><author>sametmax</author><text>Note that :<p>- sony did a project like this : power at prompt (<a href="https://code.google.com/p/pyp/" rel="nofollow">https:&#x2F;&#x2F;code.google.com&#x2F;p&#x2F;pyp&#x2F;</a>).<p>- an alternative exists to both : pyped (<a href="https://pypi.python.org/pypi/Pyped/1.4" rel="nofollow">https:&#x2F;&#x2F;pypi.python.org&#x2F;pypi&#x2F;Pyped&#x2F;1.4</a>) I like it better because it packs many utilities, but that&#x27;s a matter of taste.<p>- other projects like that existed prior this one doing the same thing. The author choose to reinvent the wheel instead of contributing. I tend to dislike this behavior.<p>- both alternatives uses the &quot;pyp&quot; command, instead of the &quot;py&quot; command. The reason is that the &quot;py&quot; command is now an official command in Python on Windows. Installing pythonpy will cause a conflict.</text></comment> | <story><title>Pythonpy – Command-line Kung Fu with Python</title><url>https://github.com/Russell91/pythonpy/</url><text></text></story><parent_chain></parent_chain><comment><author>tucif</author><text>I had used a very similar one for a while <a href="https://github.com/ksamuel/Pyped" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;ksamuel&#x2F;Pyped</a> and found it quite useful. In that other utility they mention &quot;&#x27;py&#x27; has been renamed to &#x27;pyp&#x27; to avoid conflict with the new tool in the Python stdlib named &#x27;py&#x27;&quot; I wonder if such a problem would arise for your project.</text></comment> |
35,574,693 | 35,574,530 | 1 | 3 | 35,573,624 | train | <story><title>Monolith: The Recommendation System Behind TikTok</title><url>https://gantry.io/blog/papers-to-know-20230110/</url></story><parent_chain><item><author>chadrs</author><text>I must be rare in that the longer I use tiktok, the less relevant the recommendations feel. Maybe because I compulsively watch videos until the end even if I don&#x27;t like them.</text></item></parent_chain><comment><author>dmix</author><text>&gt; Maybe because I compulsively watch videos until the end even if I don&#x27;t like them.<p>That would definitely do it, basically destroying their most important signal.<p>TikTok is best in class for recommendeding content and I personally haven&#x27;t see a dip in quality. Aka I never get trashy videos or anything cringe, just a consistent stream of science&#x2F;tech, local Toronto restaurant reviews, cat videos, etc</text></comment> | <story><title>Monolith: The Recommendation System Behind TikTok</title><url>https://gantry.io/blog/papers-to-know-20230110/</url></story><parent_chain><item><author>chadrs</author><text>I must be rare in that the longer I use tiktok, the less relevant the recommendations feel. Maybe because I compulsively watch videos until the end even if I don&#x27;t like them.</text></item></parent_chain><comment><author>jabbany</author><text>Seems like a common problem of recommenders tbh.<p>Like binary search, they&#x27;re really good at finding local optima quickly, and then are rather bad at getting out of them once they get there.</text></comment> |
25,488,407 | 25,488,324 | 1 | 2 | 25,487,130 | train | <story><title>An Engineer’s Guide to Stock Options (2013)</title><url>https://blog.alexmaccaw.com/an-engineers-guide-to-stock-options#</url></story><parent_chain><item><author>tempsy</author><text>Then 2020 happened and startups are going public at a rate not seen since the dot com days.<p>Whenever an article like this is posted HN seems to immediately raise this issue about how startup equity is just a lottery ticket when the probability of it paying off is clearly so much higher especially at a time when so many startups this year and next are going public at $10B plus valuations.<p>If there was a time to have options at a growing, revenue generating startup it’s today.</text></item><item><author>ludwigvan</author><text>&quot;For most startup employee’s startup stock options are now a bad deal.&quot;<p>&quot;Startup Stock Options – Why A Good Deal Has Gone Bad&quot;<p><a href="https:&#x2F;&#x2F;steveblank.com&#x2F;2019&#x2F;04&#x2F;10&#x2F;startup-stock-options-why-a-good-deal-has-gone-bad&#x2F;" rel="nofollow">https:&#x2F;&#x2F;steveblank.com&#x2F;2019&#x2F;04&#x2F;10&#x2F;startup-stock-options-why-...</a></text></item></parent_chain><comment><author>TuringNYC</author><text>I&#x27;m not sure I agree. How many tech IPOs have there been this year? 20 or 30? Of those 20 or 30 companies, how many of their peers at founding (~2010-2013) have survived?<p>If I take knowledge of 2020, go back in time, and take a job, it seems like a great deal. If I&#x27;m back in 2010 or 2011, and take only knowledge of the world at that time, would I have chosen AirBNB? I&#x27;m not sure.<p>Even if I did, what are the odds I could&#x2F;would stick around long enough to make it to the IPO -- or was willing to exercise illiquid stock at departure with years to go before the stock can be sold?<p>To make it fair, one should of course also consider companies which did not IPO but had good acquisitions. I&#x27;m not sure what that number is, 300? 3000? Still, across a field of 20,000 or more startups it is unclear how I&#x27;d get to this smaller set.<p>I think there are def things that can increase the odds, but I dont think it is fair to look backwards using 2020 knowledge.</text></comment> | <story><title>An Engineer’s Guide to Stock Options (2013)</title><url>https://blog.alexmaccaw.com/an-engineers-guide-to-stock-options#</url></story><parent_chain><item><author>tempsy</author><text>Then 2020 happened and startups are going public at a rate not seen since the dot com days.<p>Whenever an article like this is posted HN seems to immediately raise this issue about how startup equity is just a lottery ticket when the probability of it paying off is clearly so much higher especially at a time when so many startups this year and next are going public at $10B plus valuations.<p>If there was a time to have options at a growing, revenue generating startup it’s today.</text></item><item><author>ludwigvan</author><text>&quot;For most startup employee’s startup stock options are now a bad deal.&quot;<p>&quot;Startup Stock Options – Why A Good Deal Has Gone Bad&quot;<p><a href="https:&#x2F;&#x2F;steveblank.com&#x2F;2019&#x2F;04&#x2F;10&#x2F;startup-stock-options-why-a-good-deal-has-gone-bad&#x2F;" rel="nofollow">https:&#x2F;&#x2F;steveblank.com&#x2F;2019&#x2F;04&#x2F;10&#x2F;startup-stock-options-why-...</a></text></item></parent_chain><comment><author>slumpt_</author><text>How many HN posts did we have for all the startups that went under or sold for pennies on the dollar?<p>My friends who spent 6 years at a startup just found out his equity is literally worth pennies on the dollar. It will be a write off at best.<p>2020 as well. This mentality of looking at successful exits is the same now as it was a decade ago or more.</text></comment> |
16,515,325 | 16,515,089 | 1 | 2 | 16,514,020 | train | <story><title>The best Nintendo Switch feature is its lack of region-locking</title><url>https://www.theverge.com/2017/3/9/14867076/nintendo-switch-no-region-locking-awesome</url></story><parent_chain><item><author>CM30</author><text>The lack of region locking was also one of the best things about most of the handheld consoles Nintendo released beforehand. The original Game Boy, the Game Boy Colour, the GBA and the Nintendo DS were all region free as well, and it likely helped their popularity a ton, especially given how it meant you could travel with the system and be sure any games you bought while away would work with it.<p>Those systems may not have had an eShop, but in the days before it, I suspect not having region locking was as helpful there too.</text></item></parent_chain><comment><author>AdmiralAsshat</author><text>I remember the lack of region lock being a boon for the GBA and DS. The game &quot;Osu! Tatakae! Ouendan&quot; was popular in Japan, but Nintendo refused to localize it. It became an import favorite in the West, driving up prices on eBay and the like. Nintendo took notice and eventually made Elite Beat Agents as a Western-tailored sequel &#x2F; successor to it.<p>Additionally, when Phoenix Wright first got localized for the DS, the print run was very small. Someone realized that the English script was already embedded into the Japanese version of the game--you simply had to go to the language options and toggle a button to switch it to English. This made importing a popular option for people who couldn&#x27;t find--or didn&#x27;t want to wait--for the Stateside version. I remember vividly discussing with my brothers whether we wanted to &quot;risk&quot; waiting for the US edition and not being able to find one, or importing and having to deal with toggling the language at every startup.</text></comment> | <story><title>The best Nintendo Switch feature is its lack of region-locking</title><url>https://www.theverge.com/2017/3/9/14867076/nintendo-switch-no-region-locking-awesome</url></story><parent_chain><item><author>CM30</author><text>The lack of region locking was also one of the best things about most of the handheld consoles Nintendo released beforehand. The original Game Boy, the Game Boy Colour, the GBA and the Nintendo DS were all region free as well, and it likely helped their popularity a ton, especially given how it meant you could travel with the system and be sure any games you bought while away would work with it.<p>Those systems may not have had an eShop, but in the days before it, I suspect not having region locking was as helpful there too.</text></item></parent_chain><comment><author>laumars</author><text>Originally region locking was more a byproduct of TV&#x27;s having different output standards (NTSC vs PAL). But we&#x27;re talking back in the 8bit era (and to a lesser degree, 16bit as well).<p>Which might explain why most handhelds were never region locked.</text></comment> |
36,618,999 | 36,618,368 | 1 | 3 | 36,615,849 | train | <story><title>Tor’s history of D/DoS attacks and future strategies for mitigation</title><url>https://forum.torproject.org/t/tor-project-tors-history-of-d-dos-attacks-strategy-for-mitigation/8145</url></story><parent_chain></parent_chain><comment><author>cf141q5325</author><text>I think its worth mentioning that DDOS protection has become a tool to control online discourse. Once you get kicked off Cloudfare, thats mostly it for you if you have a determined attacker. Thats quite a beneficial situation for governments.</text></comment> | <story><title>Tor’s history of D/DoS attacks and future strategies for mitigation</title><url>https://forum.torproject.org/t/tor-project-tors-history-of-d-dos-attacks-strategy-for-mitigation/8145</url></story><parent_chain></parent_chain><comment><author>Arch-TK</author><text>I wish people stopped using discourse.<p>Sending pictures of pieces of hand written paper over email would be a more user friendly and usable interface than this javascript mess.</text></comment> |
29,202,801 | 29,202,262 | 1 | 3 | 29,201,027 | train | <story><title>Microsoft to Block Windows 11 Browser Workarounds</title><url>https://www.thurrott.com/windows/windows-11/259208/windows-11-to-block-windows-11-browser-workarounds</url></story><parent_chain><item><author>gavinray</author><text>I upvoted you but I disagree with<p><pre><code> &quot;Then they get dragged through Linux&#x27;s rough new user experience.&quot;
</code></pre>
What distros do you feel have a poor experience for new Linux users?<p>Arch, Gentoo, etc -- yeah those are terrible recommendations for &quot;I want to use Linux for the first time.&quot;<p>The first Linux distro I installed, I was 14 and had grown up on Windows XP + Vista. I went with Linux Mint and it felt like Windows (the UX).<p>And that was a decade ago. Things were so much worse + more difficult on Linux then too.<p>You have distros now like ElementaryOS that are made to mimic OSx, which is about as &quot;I dunno computers&quot; as you can get.<p>And Ubuntu or any derivative like PopOS are also friendly and great first experiences.<p>This is all opinion of course.<p>-----<p>EDIT: For context&#x2F;bias: posted this from Windows 11 Insider<p>Switched to Windows ~1 year ago, and mostly regret it. I had (what I consider) a better experience on Ubuntu&#x2F;Pop with Regolith as a tiling WM. YMMV, etc.</text></item><item><author>rackjack</author><text>I previously stated:<p>&gt; Ah, the eternal cycle of: Microsoft does something bad, then people move to Linux, then they get dragged by Linux&#x27;s rough new user experience, then they leave Linux, then things are fine for a while, then people mock Linux users for being paranoid, then Microsoft does something bad...<p>here: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=28971110" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=28971110</a><p>Looks like we&#x27;re going for another whirl around the cycle! Wheee!</text></item></parent_chain><comment><author>betterunix2</author><text>I am an <i>experienced</i> Linux user and I sometimes find myself wondering how much more I will put up with. Oh, sorry, did you not like that unexpected UI change? Fsck off, some GNOME developer decided to do it and you are not allowed to change it unless you install some random &quot;extension&quot; from some random developer on Reddit. Oh, sorry, did you spend a day getting Pulseaudio to work as well as ALSA had worked? Great news, Pulseaudio was replaced with PipeWire, which is &quot;functionally compatible&quot; but only for the specific configuration a handful of developers happened to have on their systems, so get ready to spend another day trying to get audio working. Oh, you had a ZaphodHeads configuration working with Xorg for a few years? Cool story bro, now we use Wayland, and it is definitely the same as X11 in all the ways <i>we</i> care about, but that does not include anything like Zaphod, because we&#x27;re busy with other stuff and anyway who cares about multihead systems?<p>I suppose that is what I get for using Fedora, which was supposedly Red Hat&#x27;s &quot;desktop strategy&quot; but was never even remotely ready for a typical desktop user...</text></comment> | <story><title>Microsoft to Block Windows 11 Browser Workarounds</title><url>https://www.thurrott.com/windows/windows-11/259208/windows-11-to-block-windows-11-browser-workarounds</url></story><parent_chain><item><author>gavinray</author><text>I upvoted you but I disagree with<p><pre><code> &quot;Then they get dragged through Linux&#x27;s rough new user experience.&quot;
</code></pre>
What distros do you feel have a poor experience for new Linux users?<p>Arch, Gentoo, etc -- yeah those are terrible recommendations for &quot;I want to use Linux for the first time.&quot;<p>The first Linux distro I installed, I was 14 and had grown up on Windows XP + Vista. I went with Linux Mint and it felt like Windows (the UX).<p>And that was a decade ago. Things were so much worse + more difficult on Linux then too.<p>You have distros now like ElementaryOS that are made to mimic OSx, which is about as &quot;I dunno computers&quot; as you can get.<p>And Ubuntu or any derivative like PopOS are also friendly and great first experiences.<p>This is all opinion of course.<p>-----<p>EDIT: For context&#x2F;bias: posted this from Windows 11 Insider<p>Switched to Windows ~1 year ago, and mostly regret it. I had (what I consider) a better experience on Ubuntu&#x2F;Pop with Regolith as a tiling WM. YMMV, etc.</text></item><item><author>rackjack</author><text>I previously stated:<p>&gt; Ah, the eternal cycle of: Microsoft does something bad, then people move to Linux, then they get dragged by Linux&#x27;s rough new user experience, then they leave Linux, then things are fine for a while, then people mock Linux users for being paranoid, then Microsoft does something bad...<p>here: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=28971110" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=28971110</a><p>Looks like we&#x27;re going for another whirl around the cycle! Wheee!</text></item></parent_chain><comment><author>pjmlp</author><text>Then the typical user goes into the shopping mal during the weekend, sees a nice gadget in sales, does an impulsive buy.<p>Back at home they wonder why it doesn&#x27;t work at all.<p>After 30 years, unless one is deep into Linux technical knowledge and &quot;search before buy&quot;, that impulsive buy is going to end in tears.<p>Even with &quot;search before buy&quot; the adventure can turn out bad, because the device that apparently has Linux support, actually only works in specific serial numbers with the right firmware in place.</text></comment> |
9,722,420 | 9,721,759 | 1 | 3 | 9,721,212 | train | <story><title>LastPass Security Notice</title><url>https://blog.lastpass.com/2015/06/lastpass-security-notice.html/</url></story><parent_chain><item><author>pdabbadabba</author><text>But this depends on the alternative. If, instead of using a password manager, uses only one (or even two or three) passwords across all the websites they frequent, then you are still, in effect, trusting <i>numerous</i> third parties to keep your password safe in the cloud--if any one of these sites is compromised, then your password for all (or half, or 1&#x2F;3rd, etc.) is compromised along with it.<p>I agree with you that an offline password manager is better in theory. But the problem is that I am aware of no such service that is easy to use across numerous devices, so much so that none has struck me as a viable option given my patterns of usage. Maybe there are people out there who will accept much more inconvenience in exchange for avoiding the risk associated with a cloud-based service. But, for me, the inconvenience is simply too much.<p>So the choice once more, for me, becomes cloud-based password manager or no password manager at all.<p>(Though if you&#x27;ve found a good option, that will allow me to easily sync across my home desktop, laptop, office pc, tablet, and smartphone, without using the cloud, I would absolutely love to hear about it! Maybe something Bluetooth based?)</text></item><item><author>jjarmoc</author><text>While LastPass seems to be responding well, I find their entire service exceeds my tolerance for risk.<p>If you don&#x27;t use a password manager, you&#x27;ve got 99 problems, but a centralized store of your credentials for everything that&#x27;s a huge target by virtue of having thousands of similarly centralized users ain&#x27;t one.<p>Using a password manager (good idea) and then storing all your passwords on a 3rd party service of which you have no control seems inherently risky. Lastpass is a huge target, and while I believe they generally take reasonable security measures, for many the risk of compromise may be greater than an encrypted stand-alone password database. Use a password manager, please, but keep it offline and don&#x27;t aggregate it with loads of other people&#x27;s databases.<p>This is one area where I feel strongly that the conveniences of &#x27;Cloud&#x27; are outweighed by the risks.</text></item></parent_chain><comment><author>tbabb</author><text>My compromise has been to come up with a password permutation scheme-- I have a long, secure, high-entropy password which I can modify&#x2F;salt in a way that&#x27;s predictable (to me) across sites, such that each site&#x27;s credentials are unique. Obviously this works across all devices, because the scheme is in my head, and it&#x27;s simple enough to remember. I don&#x27;t use any password manager, because like OP, that seems like too much of an eggs-and-baskets risk for my taste.<p>A catastrophic compromise would require an attacker to see actual credentials (not just the hashes) across many sites, and on top of that reverse engineer my specific permutation scheme. This seems much less likely to me than a very public, high-profile centralized cloud service forgetting to cross a T somewhere and getting hacked.</text></comment> | <story><title>LastPass Security Notice</title><url>https://blog.lastpass.com/2015/06/lastpass-security-notice.html/</url></story><parent_chain><item><author>pdabbadabba</author><text>But this depends on the alternative. If, instead of using a password manager, uses only one (or even two or three) passwords across all the websites they frequent, then you are still, in effect, trusting <i>numerous</i> third parties to keep your password safe in the cloud--if any one of these sites is compromised, then your password for all (or half, or 1&#x2F;3rd, etc.) is compromised along with it.<p>I agree with you that an offline password manager is better in theory. But the problem is that I am aware of no such service that is easy to use across numerous devices, so much so that none has struck me as a viable option given my patterns of usage. Maybe there are people out there who will accept much more inconvenience in exchange for avoiding the risk associated with a cloud-based service. But, for me, the inconvenience is simply too much.<p>So the choice once more, for me, becomes cloud-based password manager or no password manager at all.<p>(Though if you&#x27;ve found a good option, that will allow me to easily sync across my home desktop, laptop, office pc, tablet, and smartphone, without using the cloud, I would absolutely love to hear about it! Maybe something Bluetooth based?)</text></item><item><author>jjarmoc</author><text>While LastPass seems to be responding well, I find their entire service exceeds my tolerance for risk.<p>If you don&#x27;t use a password manager, you&#x27;ve got 99 problems, but a centralized store of your credentials for everything that&#x27;s a huge target by virtue of having thousands of similarly centralized users ain&#x27;t one.<p>Using a password manager (good idea) and then storing all your passwords on a 3rd party service of which you have no control seems inherently risky. Lastpass is a huge target, and while I believe they generally take reasonable security measures, for many the risk of compromise may be greater than an encrypted stand-alone password database. Use a password manager, please, but keep it offline and don&#x27;t aggregate it with loads of other people&#x27;s databases.<p>This is one area where I feel strongly that the conveniences of &#x27;Cloud&#x27; are outweighed by the risks.</text></item></parent_chain><comment><author>JadeNB</author><text>&gt; (Though if you&#x27;ve found a good option, that will allow me to easily sync across my home desktop, laptop, office pc, tablet, and smartphone, without using the cloud, I would absolutely love to hear about it! Maybe something Bluetooth based?)<p>I don&#x27;t know if it meets but your needs, but I love PasswordMaker (<a href="http:&#x2F;&#x2F;passwordmaker.org" rel="nofollow">http:&#x2F;&#x2F;passwordmaker.org</a>). There is no need for sync&#x27;ing, because the password is <i>generated</i> from a master password and configureable per-site data (by default, the web-site address; but you can add more data sources if you don&#x27;t like that). It has an extension for Firefox that auto-completes passwords (configureably, remembering the master password per session so that you don&#x27;t ever have to type it); there are widgets for Windows and Mac OS; there are Android and iOS apps; and, always, there is the fallback web page, which you can use anywhere that you have a web browser.<p>EDIT: Since I am trying to indulge in quite a bit of advocacy here, I want to make it clear that I am in no way affiliated with the project. I just stumbled on it a long time ago, and have been delighted with the way that it fills my needs.</text></comment> |
38,687,492 | 38,687,057 | 1 | 2 | 38,685,458 | train | <story><title>New PFAS discovered with novel testing method</title><url>https://research.unc.edu/2023/12/12/carolina-chemists-discover-eight-new-pfas-with-novel-testing-method/</url></story><parent_chain></parent_chain><comment><author>agtech_andy</author><text>What will become clear over the next 5 years is the extent to which the worldwide environment is polluted with PFAS.<p>Given how much PFAS has been found in remote corners of the world, I think it is safe to assume that most of the world has been touched by PFAS. Everywhere humans try to find PFAS, we find it. The reason we hear about it so often now is that we are checking for it everywhere. And like the article describes, there are new PFAS being discovered all the time.<p>This is a generational issue.</text></comment> | <story><title>New PFAS discovered with novel testing method</title><url>https://research.unc.edu/2023/12/12/carolina-chemists-discover-eight-new-pfas-with-novel-testing-method/</url></story><parent_chain></parent_chain><comment><author>kacy</author><text>I grew up in a poor town that sourced water from the Cape Fear river. There were two major factories in our immediate area: one that made paper and the other made industrial chemicals. The Dupont plant mentioned in the article was 10 miles upstream from where we were. We knew it was better to buy bottled water than to drink what came through the pipes. Grateful for the scientists and journalists for their work exposing all of this.</text></comment> |
16,293,307 | 16,292,796 | 1 | 2 | 16,292,143 | train | <story><title>How a Medical Catastrophe Can Bankrupt a Life</title><url>https://longreads.com/2018/02/01/how-a-medical-catastrophe-can-bankrupt-a-life/</url></story><parent_chain><item><author>radoslawc</author><text>I&#x27;ve heard multiple times that medical care in USA is pretty expansive if you don&#x27;t have insurance. But I had no idea to what extent, until someone posted comments section form amazon&#x27;s page for fish antibiotics. People are buying those for them self (well, still it&#x27;s amoxycycline), just check any comment, most of them have something like: my &#x27;fish&#x27; is better, $300 saved.
That&#x27;s just inhumane.</text></item></parent_chain><comment><author>owenversteeg</author><text>I am not a doctor and don&#x27;t play one on TV, but it&#x27;s worth noting that the pills should actually be safe for consumption by humans (I do not encourage this.) A couple of things:<p>- Many fish antibiotic producers just purchase pills intended for humans, because the cost is so low. Generic amoxicillin for humans can cost less than two cents a pill. The cheapest fish antibiotics I found were $20 for 100 pills at Walmart, so the actual pills could be less than 10% of the cost of the product.<p>- There aren&#x27;t any currently USP-certified fish antibiotics, however. As a result, there are no regulations on how they are stored. This could mean they are exposed to heat and&#x2F;or moisture, which antibiotics are sensitive to. That said, given that they&#x27;re stored in sealed plastic containers, they should be fine.<p>- The differences in the actual pills should be limited to fillers and things that do not affect the potency, in the USA. None of these should be harmful however, although they could affect taste.<p>Again, I don&#x27;t recommend consuming fish antibiotics, and amoxicillin is actually available cheaper (with a prescription) from online pharmacies.</text></comment> | <story><title>How a Medical Catastrophe Can Bankrupt a Life</title><url>https://longreads.com/2018/02/01/how-a-medical-catastrophe-can-bankrupt-a-life/</url></story><parent_chain><item><author>radoslawc</author><text>I&#x27;ve heard multiple times that medical care in USA is pretty expansive if you don&#x27;t have insurance. But I had no idea to what extent, until someone posted comments section form amazon&#x27;s page for fish antibiotics. People are buying those for them self (well, still it&#x27;s amoxycycline), just check any comment, most of them have something like: my &#x27;fish&#x27; is better, $300 saved.
That&#x27;s just inhumane.</text></item></parent_chain><comment><author>tptacek</author><text>People also buy fish antibiotics because their doctor won&#x27;t prescribe antibiotics for common colds.</text></comment> |
7,500,835 | 7,500,132 | 1 | 2 | 7,499,101 | train | <story><title>Chicken Scheme internals: the garbage collector</title><url>http://www.more-magic.net/posts/internals-gc.html</url><text>An overview of how the Garbage Collector in Chicken Scheme works. Contains some good diagrams and code sample to help understand the topic and also a set of links to read more about the subject.</text></story><parent_chain></parent_chain><comment><author>gjm11</author><text>Henry Baker&#x27;s &quot;Cheney on the M.T.A.&quot; paper (which is the basis for the stuff described here) is very nice. There&#x27;s a collection of Baker&#x27;s research papers here:<p><a href="http://www.pipeline.com/~hbaker1/" rel="nofollow">http:&#x2F;&#x2F;www.pipeline.com&#x2F;~hbaker1&#x2F;</a><p>which includes the &quot;Cheney on the M.T.A.&quot; paper (<a href="http://www.pipeline.com/~hbaker1/CheneyMTA.html" rel="nofollow">http:&#x2F;&#x2F;www.pipeline.com&#x2F;~hbaker1&#x2F;CheneyMTA.html</a>) and a bunch of other interesting things (mostly with a lispy flavour). A few specific examples:<p><a href="http://www.pipeline.com/~hbaker1/Prag-Parse.html" rel="nofollow">http:&#x2F;&#x2F;www.pipeline.com&#x2F;~hbaker1&#x2F;Prag-Parse.html</a> -- a nice technique (not invented by Baker) for simple parsing tasks, and a neat Lisp implementation.<p><a href="http://www.pipeline.com/~hbaker1/LazyAlloc.html" rel="nofollow">http:&#x2F;&#x2F;www.pipeline.com&#x2F;~hbaker1&#x2F;LazyAlloc.html</a> -- you might notice that the &quot;M.T.A.&quot; paper is subtitled &quot;CONS should not CONS its arguments, part II&quot;; this is the original &quot;CONS should not CONS its arguments&quot; and is also about allocating things on the stack that you might not expect to be stack-allocatable.<p><a href="http://www.pipeline.com/~hbaker1/Use1Var.html" rel="nofollow">http:&#x2F;&#x2F;www.pipeline.com&#x2F;~hbaker1&#x2F;Use1Var.html</a> -- &quot;use-once&quot; variables (related to &quot;linear logic&quot;, which is not Baker&#x27;s creation), not a million miles from C++&#x27;s auto_ptr&#x2F;unique_ptr but Baker was advocating this stuff as early as 1993.<p>And some other interesting things due to people other than Baker, such as a copy of the famous HAKMEM (<a href="http://www.pipeline.com/~hbaker1/hakmem/hakmem.html" rel="nofollow">http:&#x2F;&#x2F;www.pipeline.com&#x2F;~hbaker1&#x2F;hakmem&#x2F;hakmem.html</a>).</text></comment> | <story><title>Chicken Scheme internals: the garbage collector</title><url>http://www.more-magic.net/posts/internals-gc.html</url><text>An overview of how the Garbage Collector in Chicken Scheme works. Contains some good diagrams and code sample to help understand the topic and also a set of links to read more about the subject.</text></story><parent_chain></parent_chain><comment><author>girvo</author><text>I was looking at Chicken Scheme the other day for building a Entity-Component-System 2D game engine, as I love Lisps, but alas, the SDL bindings were quite out of date, and I didn&#x27;t want to take my first project on as writing bindings for a C library!<p>It&#x27;s a very cool system, and this article is awesome. I find garbage collectors fascinating.</text></comment> |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.