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 383
19.7k
| rejected_prompt
large_stringlengths 356
18.2k
|
|---|---|---|---|---|---|---|---|
33,676,990 | 33,676,248 | 1 | 3 | 33,673,128 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>zbentley</author><text>Not at all.<p>If I get floats from $somewhere, I might want to index them into a hash data structure without creating a huge sparse array.<p>If you assume float numbers have &quot;identity&quot; such that, whatever the precision, &quot;x == x&quot; always holds (other than NaN), then this is a perfectly valid thing to want.</text><parent_chain><item><author>bobbylarrybobby</author><text>Using floats as hash keys is insane, no?</text></item><item><author>derriz</author><text>Java has a specific hack for this which I discovered by accident a few years ago. Normally, given (primitive) double values d0 and d1, then boxing them does not affect equality testing - i.e. d0 == d1 if and only if Double.valueOf(d0).equals(Double.valueOf(d1)). However if d0 and d1 are both NaN, then the boxed versions ARE considered equal while d0 == d1 is false.<p>This inconsistency infuriated me when I discovered it but the Javadoc for Double.equals explicitly states that this anomaly is there to &quot;allow hash tables to work properly&quot;.</text></item></parent_chain></comment><story><title>Go 1.21 may have a clear(x) builtin</title><url>https://utcc.utoronto.ca/~cks/space/blog/programming/GoFutureClearBuiltin</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>bushbaba</author><text>Not if you’re hash table is designed to accommodate key conflicts, and the float is deterministic.</text><parent_chain><item><author>bobbylarrybobby</author><text>Using floats as hash keys is insane, no?</text></item><item><author>derriz</author><text>Java has a specific hack for this which I discovered by accident a few years ago. Normally, given (primitive) double values d0 and d1, then boxing them does not affect equality testing - i.e. d0 == d1 if and only if Double.valueOf(d0).equals(Double.valueOf(d1)). However if d0 and d1 are both NaN, then the boxed versions ARE considered equal while d0 == d1 is false.<p>This inconsistency infuriated me when I discovered it but the Javadoc for Double.equals explicitly states that this anomaly is there to &quot;allow hash tables to work properly&quot;.</text></item></parent_chain></comment><story><title>Go 1.21 may have a clear(x) builtin</title><url>https://utcc.utoronto.ca/~cks/space/blog/programming/GoFutureClearBuiltin</url></story> |
34,688,745 | 34,688,644 | 1 | 2 | 34,687,125 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>danielmarkbruce</author><text>The same happens in companies led by founders. I&#x27;ve seen it, and lots of people at google when under larry and sergey will tell you. People under Zuckerberg at FB, Bill G at MSFT, there are stories from all these places if you talk to folks who were there.<p>And they were all smart guys, courageous, right incentives etc. Large organizations are complicated. The post above is right - there is no silver bullet.</text><parent_chain><item><author>solatic</author><text>You&#x27;re describing life under caretaker CEOs, which true to form are a self-fulfilling prophecy for mediocrity. The vast majority of large public CEOs are caretaker CEOs, and it&#x27;s why working for large public companies can feel so slow and dreary.<p>But then you get turnaround CEOs, the ones the board hires because the company is in dire financial straits, who comes in, fires executives, sets new strategy, communicates openly and plainly across all layers of management and labor. Things can change <i>quickly</i> under the right leadership.</text></item><item><author>supernova87a</author><text>It would be amazing if there were a silver bullet like this that everyone could identify the root cause of companies&#x27; woes. And could be reset by flipping a switch.<p>But I think it&#x27;s much deeper -- having worked at a couple big companies now, I realize (at least to my limited observations) that the path of a company is set by the deeply ingrained culture that has been established over many years by its founders, by its evolution, its successive leaders, and in fact, the competitive environment in which it operates. Things (good or bad) that last far beyond any one leader.<p>It manifests in the little incentives that people far below the CEO understand to do their jobs in a certain way, to pursue certain things and decide to drag their feet or ignore certain other things.<p>If you were hired at a company and worked there for years understanding that if you did &lt;x&gt;, you got &lt;y&gt;, it will be hard to change a whole workforce of that notion, especially when one individual gets beaten back in line if they stray. Even if others want to change just as much. Even if the CEO says to change. It takes years for that info to percolate. Sometimes it never does.<p>No, sometimes companies need to die in order to be reborn.</text></item></parent_chain></comment><story><title>Silicon Valley needs to stop laying off workers and start firing CEOs</title><url>https://www.businessinsider.com/fire-blame-ceo-tech-employee-layoffs-google-facebook-salesforce-amazon-2023-2</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>nomel</author><text>I experienced two turnaround CEOs, and they were the ones that did all the firing. One let the company bleed away headcount until it became desirable for a buyer.</text><parent_chain><item><author>solatic</author><text>You&#x27;re describing life under caretaker CEOs, which true to form are a self-fulfilling prophecy for mediocrity. The vast majority of large public CEOs are caretaker CEOs, and it&#x27;s why working for large public companies can feel so slow and dreary.<p>But then you get turnaround CEOs, the ones the board hires because the company is in dire financial straits, who comes in, fires executives, sets new strategy, communicates openly and plainly across all layers of management and labor. Things can change <i>quickly</i> under the right leadership.</text></item><item><author>supernova87a</author><text>It would be amazing if there were a silver bullet like this that everyone could identify the root cause of companies&#x27; woes. And could be reset by flipping a switch.<p>But I think it&#x27;s much deeper -- having worked at a couple big companies now, I realize (at least to my limited observations) that the path of a company is set by the deeply ingrained culture that has been established over many years by its founders, by its evolution, its successive leaders, and in fact, the competitive environment in which it operates. Things (good or bad) that last far beyond any one leader.<p>It manifests in the little incentives that people far below the CEO understand to do their jobs in a certain way, to pursue certain things and decide to drag their feet or ignore certain other things.<p>If you were hired at a company and worked there for years understanding that if you did &lt;x&gt;, you got &lt;y&gt;, it will be hard to change a whole workforce of that notion, especially when one individual gets beaten back in line if they stray. Even if others want to change just as much. Even if the CEO says to change. It takes years for that info to percolate. Sometimes it never does.<p>No, sometimes companies need to die in order to be reborn.</text></item></parent_chain></comment><story><title>Silicon Valley needs to stop laying off workers and start firing CEOs</title><url>https://www.businessinsider.com/fire-blame-ceo-tech-employee-layoffs-google-facebook-salesforce-amazon-2023-2</url></story> |
25,645,652 | 25,644,928 | 1 | 2 | 25,644,056 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>throwaway0a5e</author><text>I think it&#x27;s the opposite. When you&#x27;re FANG or a nation state preparedness doesn&#x27;t matter. You have strings to pull to get fair treatment.<p>If you&#x27;re a small guy you get screwed and have no practical means of recourse. The little people are the ones who need to care about this kind of stuff.</text><parent_chain><item><author>whack</author><text>&gt; <i>You have relinquished so much control, why be surprised if that stares you back in the face?</i><p>We live in a market-based economy with highly specialized division of labor. The idea of &quot;keeping control&quot; of all our necessities and dependencies, is an archaic one. The system generally works, because we create sensible laws that foster trust, vet for partners who are trustworthy, and name-and-shame entities that violate our trust.<p>If you&#x27;re a behemoth the size of FANG or a nation-state, maybe it is worth the effort needed to insulate yourself against these black-swan scenarios. But for a startup or small-medium-business that no one has heard of? That just sounds like bad prioritization.<p>All of which is to say... we should absolutely be surprised when a vendor like GitHub blocks an entire company because of an employee logging in from Iran while on travel. And this surprise, and the resulting name-and-shame, is what keeps the wheels of our economy turning.</text></item><item><author>factorialboy</author><text>So many dimensions come to play here.<p>1. There&#x27;s the obvious legal aspect i.e. how these laws are framed and interpreted.<p>2. Then there&#x27;s the geopolitical aspect. Is it fair to impose sanctions on Iran.<p>3. There&#x27;s another aspect around GitHub policy that asks if an entire organization be banned for the location of one team member.<p>4. Finally, there&#x27;s the aspect of relinquishing control. Your app development is on the cloud. IDEs are on the cloud. Deployments are on the cloud. App stores are on the cloud.<p>You have relinquished so much control, why be surprised if that stares you back in the face?<p>Ironically, Git is a decentralized version control system.</text></item></parent_chain></comment><story><title>GitHub blocks entire company because one employee was in Iran</title><url>https://twitter.com/sebslomski/status/1344219609923276801</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>Erlich_Bachman</author><text>There is plenty of solutions that are keeping the data in-house. Or allow for easy exporting&#x2F;importing (github is not too bad in this regard though). None of these solutions go against the &quot;highly specialized division of labor&quot;. This is a question about what kind of solutions we build, not how labor is divided or not.</text><parent_chain><item><author>whack</author><text>&gt; <i>You have relinquished so much control, why be surprised if that stares you back in the face?</i><p>We live in a market-based economy with highly specialized division of labor. The idea of &quot;keeping control&quot; of all our necessities and dependencies, is an archaic one. The system generally works, because we create sensible laws that foster trust, vet for partners who are trustworthy, and name-and-shame entities that violate our trust.<p>If you&#x27;re a behemoth the size of FANG or a nation-state, maybe it is worth the effort needed to insulate yourself against these black-swan scenarios. But for a startup or small-medium-business that no one has heard of? That just sounds like bad prioritization.<p>All of which is to say... we should absolutely be surprised when a vendor like GitHub blocks an entire company because of an employee logging in from Iran while on travel. And this surprise, and the resulting name-and-shame, is what keeps the wheels of our economy turning.</text></item><item><author>factorialboy</author><text>So many dimensions come to play here.<p>1. There&#x27;s the obvious legal aspect i.e. how these laws are framed and interpreted.<p>2. Then there&#x27;s the geopolitical aspect. Is it fair to impose sanctions on Iran.<p>3. There&#x27;s another aspect around GitHub policy that asks if an entire organization be banned for the location of one team member.<p>4. Finally, there&#x27;s the aspect of relinquishing control. Your app development is on the cloud. IDEs are on the cloud. Deployments are on the cloud. App stores are on the cloud.<p>You have relinquished so much control, why be surprised if that stares you back in the face?<p>Ironically, Git is a decentralized version control system.</text></item></parent_chain></comment><story><title>GitHub blocks entire company because one employee was in Iran</title><url>https://twitter.com/sebslomski/status/1344219609923276801</url></story> |
19,709,553 | 19,709,442 | 1 | 2 | 19,708,620 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>13415</author><text>Wait a minute, isn&#x27;t it also the case that according to the Weierstrass approximation theorem any continuous function on a closed interval can be approximated by a polynomial function? And isn&#x27;t that kind of pointless for practical applications because we also need to avoid overfitting?<p>To clarify, I&#x27;m not trying to make a snippy remark, I just happened to have used polynomial curve fitting before and looked up the Wikipedia page for the Stone-Weierstrass theorem and am trying to figure out the relevance of that post on NNs. Is it essentially the same claim?<p>Any clarification appreciated!</text><parent_chain><item><author>a-nikolaev</author><text>Approximate, not compute. The function also must be continuous. NNs are good for approximation &#x2F; interpolation &#x2F; extrapolation, which makes them quite useful for certain domains of problems. But of course, it does not make them a kind of universal computing machine (in the computability sense, like universal Turing machines).</text></item></parent_chain></comment><story><title>A visual proof that neural nets can approximate any function</title><url>http://neuralnetworksanddeeplearning.com/chap4.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>electricslpnsld</author><text>&gt; NNs are good for approximation &#x2F; interpolation &#x2F; extrapolation<p>Extrapolation? I was under the impression that generalizability of NNs beyond the training data was one of the major problems faced by NNs.</text><parent_chain><item><author>a-nikolaev</author><text>Approximate, not compute. The function also must be continuous. NNs are good for approximation &#x2F; interpolation &#x2F; extrapolation, which makes them quite useful for certain domains of problems. But of course, it does not make them a kind of universal computing machine (in the computability sense, like universal Turing machines).</text></item></parent_chain></comment><story><title>A visual proof that neural nets can approximate any function</title><url>http://neuralnetworksanddeeplearning.com/chap4.html</url></story> |
28,066,250 | 28,065,555 | 1 | 2 | 28,063,337 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>__sy__</author><text>I thought this was an absolutely masterful explanation of engineering design thinking. If I may, I would also like to add to this list another thing he mentioned: &quot;each requirement must have a name attached to it.&quot;<p>I believe he was referring to the first step. And &quot;Name&quot; was really &quot;a person&quot; as opposed to &quot;a department.&quot; This was his way of saying DRI all the way down to each individual requirements, to force someone to be accountable for it. His example was that SpaceX interns previously listed requirements, that were later assigned to a department (e.g. avionics), and when prompted, no one in that department really knew why it was there.</text><parent_chain><item><author>spikels</author><text>Came here to post that video. Awesome!<p>My favorite part:<p>Elon&#x27;s 5-Step Design&#x2F;Development Process:<p>(1) Fix &quot;Dumb&quot; Requirements<p>(2) Remove Unnecessary Parts&#x2F;Processes<p>(3) Simplify&#x2F;Optimize<p>(4) Speed Up Cycle Time<p>(5) Automate</text></item><item><author>InTheArena</author><text>The recent interview of Elon by Tim Dodd is probably more informative and interesting this this could ever be.<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=t705r8ICkRw" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=t705r8ICkRw</a></text></item></parent_chain></comment><story><title>Netflix announces Space X documentary on civilian mission into orbit</title><url>https://news.sky.com/story/netflix-announces-space-x-documentary-on-civilian-mission-into-orbit-12372247</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>inglor_cz</author><text>Two things I took from that interview:<p>* the quip about people spending a lot of time to optimize something unnecessary,<p>* the quip that you must be wary about recommendations made by smart people, because you will tend to trust smart people too much and they can still make mistakes.</text><parent_chain><item><author>spikels</author><text>Came here to post that video. Awesome!<p>My favorite part:<p>Elon&#x27;s 5-Step Design&#x2F;Development Process:<p>(1) Fix &quot;Dumb&quot; Requirements<p>(2) Remove Unnecessary Parts&#x2F;Processes<p>(3) Simplify&#x2F;Optimize<p>(4) Speed Up Cycle Time<p>(5) Automate</text></item><item><author>InTheArena</author><text>The recent interview of Elon by Tim Dodd is probably more informative and interesting this this could ever be.<p><a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=t705r8ICkRw" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=t705r8ICkRw</a></text></item></parent_chain></comment><story><title>Netflix announces Space X documentary on civilian mission into orbit</title><url>https://news.sky.com/story/netflix-announces-space-x-documentary-on-civilian-mission-into-orbit-12372247</url></story> |
1,281,964 | 1,281,928 | 1 | 3 | 1,281,730 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>chime</author><text>I'm so psyched by the idea of games in HTML/JS. I've made a few games in Canvas myself using Processing.js: <a href="http://games.zetabee.com/" rel="nofollow">http://games.zetabee.com/</a> but frankly I'm amazed at the Akihabara games. I realized Processing.js was cool but I don't think it lends to raw speed as well as these games. I think I'll be making a lot more games in JS in the near future. Thanks for this link sandaru1.<p>Edit: Having looked into the source code... wow! For the "capman" game, he's creating the game map using ascii art and his "help.js" library has a function just for that: asciiArtToMap. This takes me back to the early 90s when making games meant you had to bitblt sprites and worry about every byte in the RAM. His library is great if you want to make sprite-based 2D scroller-type games but I don't know if it is easier to roll your own mini-library or use his for other types of games (e.g. puzzles). However, the source code itself is very extensive and I can certainly see the gamebox.font library being very useful for JS games.</text><parent_chain></parent_chain></comment><story><title>HTML5 Game Engine</title><url>http://www.kesiev.com/akihabara/</url><text></text></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>ZeroGravitas</author><text>Between this and the Apple iAd demo in HTML5, which notably demo'd pressing the screen and getting an 'inline' audio response instead of throwing you into a media player, a basic feature of most simple games currently missing from Mobile Safari, I think this is just about to get interesting.</text><parent_chain></parent_chain></comment><story><title>HTML5 Game Engine</title><url>http://www.kesiev.com/akihabara/</url><text></text></story> |
23,211,038 | 23,208,778 | 1 | 3 | 23,208,010 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>jerome-jh</author><text>From this side of the Altantic, it looks like the US economy is organized so that the lower working class only earns just enough to live. No wonder they are homeless when illness, disability or bad luck strikes.<p>I am not implying this applies to OP.</text><parent_chain><item><author>magicalhippo</author><text>When I see about half my paycheck going to taxes it feels a bit rough.<p>But then I think of stories like this, and how easily it could have been me with an illness requiring expensive medical treatment and possibly preventing me from working regular jobs.<p>And so I pay my tax with pleasure, knowing that if something were to happen to me or my fellow citizen, at least there wouldn&#x27;t be millions of dollars in hospital bills to pay back and there would be aid for a home to avoid ending up on the streets.</text></item></parent_chain></comment><story><title>No One Goes There Anymore</title><url>https://noonegoesthereanymore.blogspot.com/2020/05/no-one-goes-there-anymore.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>code_duck</author><text>As someone else with serious medical problems which have been paid for by public health systems, the financial difficulties of which are compounded by losing your ability to pay once ill, thanks! I would note though, for the purposes of fairness, it&#x27;s a small percentage of your taxes that go to paying for such programs versus things like the military and interest on debt.</text><parent_chain><item><author>magicalhippo</author><text>When I see about half my paycheck going to taxes it feels a bit rough.<p>But then I think of stories like this, and how easily it could have been me with an illness requiring expensive medical treatment and possibly preventing me from working regular jobs.<p>And so I pay my tax with pleasure, knowing that if something were to happen to me or my fellow citizen, at least there wouldn&#x27;t be millions of dollars in hospital bills to pay back and there would be aid for a home to avoid ending up on the streets.</text></item></parent_chain></comment><story><title>No One Goes There Anymore</title><url>https://noonegoesthereanymore.blogspot.com/2020/05/no-one-goes-there-anymore.html</url></story> |
16,762,563 | 16,762,268 | 1 | 2 | 16,761,349 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>nostrademons</author><text>I just had a kid 2 months ago, and 12 changes a day doesn&#x27;t seem all that unreasonable for a newborn. At our one-month checkup he was averaging 9 pees &amp; 5 poops per day - several of the poops were doubled-up where he also peed, so a dozen per day is about right. It&#x27;s dropped a bit since, but instances where a single changing results in multiple diapers used (eg. he shits the table right as I&#x27;m getting the new diaper on, or he pees all over the table including the diaper that&#x27;s waiting to be put on) have somewhat made up for that.<p>Unit cost of a diaper is about $0.25-0.30 when bought in bulk (even with your example), so $1000&#x2F;year = ~3200-4000 diapers = ~10 changes&#x2F;day. Change your assumptions on diaper use and everything else lines up.</text><parent_chain><item><author>djrogers</author><text>There are a couple of ‘facts’ listed here that don’t line up with my current reality and very recent knowledge (3 kids, most recent is 18mo).<p>First off, 12 changes a day is a <i>huge</i> outlier - even for a newborn. 8 would be a more reasonable number, and it drops down to the 4-6 range in the first year, and by now we’re at 3 if we don’t go swimming.<p>Second item that sounds waaay off is $1000&#x2F;yr for diapers. Again, that has to be an outlier based on the worst possible set of assumptions. A box of 168 diapers lasts about a month and costs ~$40. That doesn’t add up...<p>And finally, many of the charities I work with will hand out diapers or cards for free diapers to anyone who asks. If you’re really in a bind, call a local church, women’s shelter, or commissary! We really do want to help, but we have to know you need it.</text></item></parent_chain></comment><story><title>Why are diapers so expensive?</title><url>http://www.tampabay.com/projects/2018/features/baby-diaper-cost/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>brohoolio</author><text>12 changes a day is not an outlier for a newborn, it’s normal. My son is 18 months and we change him probably 6 times a day at least.<p>Diaper pricing is dependent on how many you buy at once, I buy giant boxes so my unit cost is low. If you don’t have $40 to buy the giant box, but only $10 to buy a small package. You are paying twice the unit cost.</text><parent_chain><item><author>djrogers</author><text>There are a couple of ‘facts’ listed here that don’t line up with my current reality and very recent knowledge (3 kids, most recent is 18mo).<p>First off, 12 changes a day is a <i>huge</i> outlier - even for a newborn. 8 would be a more reasonable number, and it drops down to the 4-6 range in the first year, and by now we’re at 3 if we don’t go swimming.<p>Second item that sounds waaay off is $1000&#x2F;yr for diapers. Again, that has to be an outlier based on the worst possible set of assumptions. A box of 168 diapers lasts about a month and costs ~$40. That doesn’t add up...<p>And finally, many of the charities I work with will hand out diapers or cards for free diapers to anyone who asks. If you’re really in a bind, call a local church, women’s shelter, or commissary! We really do want to help, but we have to know you need it.</text></item></parent_chain></comment><story><title>Why are diapers so expensive?</title><url>http://www.tampabay.com/projects/2018/features/baby-diaper-cost/</url></story> |
38,215,778 | 38,215,773 | 1 | 3 | 38,214,644 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>jb3689</author><text>You are overthinking some of it at least when it comes to concurrency. Look at what a process is and how send works. GenServer is a natural generalization of a pattern you’d write a thousand times. Knowledge of actors is transferable. Go has libraries which implement actor abstractions for example. Process mailboxes are just message queues like Go’s channels are. There are differences with respect to how the interpreters work and how processor yields work.<p>Stuff like LiveView though looks like magic because it is magic. There are a lot of moving parts involved in getting it working. It’s the result of work that has been going on for the past decade across multiple communities though. The ideas are mature even if there is a lot of abstraction.<p>Stuff like Riak was well ahead of its time. They basically had the idea of being able to create robust distributed systems much the same way you would a GenServer.</text><parent_chain><item><author>zoogeny</author><text>I have been watching Elixir YouTube videos pretty much every day for the last few weeks. I guess there was an Elixir conference recently and after I watched a couple, YouTube has been sending me a consistent stream of Elixir content.<p>I really want to try out this language. I love the idea of Erlang but the few times I&#x27;ve had to deal with it (an ejabberd chat server was one) I found it to be a bit too quirky. Every video I&#x27;ve seen with Joe Armstrong leads me to believe he was an under-appreciated genius. Isolated processes and message passing (Actors) seem a good candidate for the future of distributed programming (see this recent video from Crockford on his new Misty programming language [1] - notice how the questions were about Elixir&#x2F;Erlang). I love pattern matching and elixir uses this to a high degree.<p>However, I am not 100% sold. Clearly this community punches above its weight, and the BEAM is obviously no slouch and is a brilliant choice for a platform to build upon. But I get concerned looking at the magic of LiveView (and LiveBook). My experience is that if something sounds too good to be true, it often is. A lot of the jargon is also totally unfamiliar to me - things like GenServers and other esoteric kinds of platform specific knowledge. It feels like stepping into a one-way portal, I&#x27;m not sure any knowledge in that universe is transferable.<p>There is a huge risk in niche languages and platforms. Hard to hire for, hard to find libraries for, hard to find blogs&#x2F;tutorials&#x2F;etc. With alternatives like Go having a pretty respectable concurrency story ... it is pretty hard to justify taking the risk on such a small community.<p>But kudos to that community. It is honestly impressive to me what they have achieved. I&#x27;m also very excited to see what happens with their type system implementation.<p>1. <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=R2idkNdKqpQ">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=R2idkNdKqpQ</a></text></item></parent_chain></comment><story><title>Switching to Elixir</title><url>https://www.leemeichin.com/posts/switching-to-elixir.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>victorbjorklund</author><text>I actually find the opposite to be true. Elixir is less &quot;magic&quot; once you learn it. I can see and understand what most things are doing and read the code. With javascript? Not so much.<p>On the point of hard to hire and hard to find tutorials. It is true. It is way harder to find for example someone that done what you wanna do in elixir vs javascript. When it comes to libaries it isnt so big problem. There are lots of libraries and so far I havent really encountered any problems. Only thing would be if you interact with an API they might provide a client library for javascript and python (but less common for Go) but not elixir. But honestly it is usually not so hard to use an API with just a http-client.</text><parent_chain><item><author>zoogeny</author><text>I have been watching Elixir YouTube videos pretty much every day for the last few weeks. I guess there was an Elixir conference recently and after I watched a couple, YouTube has been sending me a consistent stream of Elixir content.<p>I really want to try out this language. I love the idea of Erlang but the few times I&#x27;ve had to deal with it (an ejabberd chat server was one) I found it to be a bit too quirky. Every video I&#x27;ve seen with Joe Armstrong leads me to believe he was an under-appreciated genius. Isolated processes and message passing (Actors) seem a good candidate for the future of distributed programming (see this recent video from Crockford on his new Misty programming language [1] - notice how the questions were about Elixir&#x2F;Erlang). I love pattern matching and elixir uses this to a high degree.<p>However, I am not 100% sold. Clearly this community punches above its weight, and the BEAM is obviously no slouch and is a brilliant choice for a platform to build upon. But I get concerned looking at the magic of LiveView (and LiveBook). My experience is that if something sounds too good to be true, it often is. A lot of the jargon is also totally unfamiliar to me - things like GenServers and other esoteric kinds of platform specific knowledge. It feels like stepping into a one-way portal, I&#x27;m not sure any knowledge in that universe is transferable.<p>There is a huge risk in niche languages and platforms. Hard to hire for, hard to find libraries for, hard to find blogs&#x2F;tutorials&#x2F;etc. With alternatives like Go having a pretty respectable concurrency story ... it is pretty hard to justify taking the risk on such a small community.<p>But kudos to that community. It is honestly impressive to me what they have achieved. I&#x27;m also very excited to see what happens with their type system implementation.<p>1. <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=R2idkNdKqpQ">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=R2idkNdKqpQ</a></text></item></parent_chain></comment><story><title>Switching to Elixir</title><url>https://www.leemeichin.com/posts/switching-to-elixir.html</url></story> |
37,224,959 | 37,223,655 | 1 | 2 | 37,222,191 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>seanw444</author><text>&gt; This means that the process is eternally tied to the cloud now.<p>&quot;You will own nothing, and you will be happy&quot; has followed us to... spreadsheets? We can&#x27;t even own the things we&#x27;re wageslaving away at our desk for.</text><parent_chain><item><author>baz00</author><text>I have to see some red flags here. The very nature and power of Excel comes from the fact that workbooks can stand alone. This means that the process is eternally tied to the cloud now. So when you, 3 years down the line, have to open a workbook from your deceased colleague, you are at the whim of the vendor supporting the existence of this integration.<p>Step one of any workload will always be &quot;work out how to make the software work again&quot; and that&#x27;s terrible.<p>I know this because I have been in that situation several times in the last couple of decades with random Excel, outlook and word add-ins. And those don&#x27;t even do the processing remotely!</text></item></parent_chain></comment><story><title>Microsoft is bringing Python to Excel</title><url>https://www.theverge.com/2023/8/22/23841167/microsoft-excel-python-integration-support</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>ayhanfuat</author><text>I think this is easier to manage to be honest. They are using Anaconda distributions so if you tie each workbook to a distribution with possibility to update&#x2F;rollback it makes things a lot easier than trying to manage a local installation.</text><parent_chain><item><author>baz00</author><text>I have to see some red flags here. The very nature and power of Excel comes from the fact that workbooks can stand alone. This means that the process is eternally tied to the cloud now. So when you, 3 years down the line, have to open a workbook from your deceased colleague, you are at the whim of the vendor supporting the existence of this integration.<p>Step one of any workload will always be &quot;work out how to make the software work again&quot; and that&#x27;s terrible.<p>I know this because I have been in that situation several times in the last couple of decades with random Excel, outlook and word add-ins. And those don&#x27;t even do the processing remotely!</text></item></parent_chain></comment><story><title>Microsoft is bringing Python to Excel</title><url>https://www.theverge.com/2023/8/22/23841167/microsoft-excel-python-integration-support</url></story> |
30,624,020 | 30,623,955 | 1 | 2 | 30,622,770 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>probably_wrong</author><text>I do feel sorry for him, and I think you are being too forgiving to the trolls here.<p>This was not a mere &quot;ruined reputation&quot;, but rather a persistent, coordinated mobbing assault big enough that not even a professional PR firm could do anything.<p>Did he cheat? Likely yes. Did he deserve being banned from marathons? Sounds like it. But did he deserve &quot;the pressure, attention, emailing, even trolling&quot; that he got? No, he did not.<p>If I were in his position, I would have also tried to sue.</text><parent_chain><item><author>Reubend</author><text>It&#x27;s terrible that people were harassing this man, and that those communities formed a mob mentality against him. But I don&#x27;t feel particularly sorry for him; he cheated, denied it, threatened to sue people, and then eventually took his own life after his reputation was ruined.<p>Perhaps if he had stopped competing after the first blog post exposing him, things would have de-escalated. Instead, he doubled down on his lies, and made things worse for himself.</text></item></parent_chain></comment><story><title>Accused of cheating, marathon runner Frank Meza's life fell apart (2019)</title><url>https://www.lamag.com/citythinkblog/frank-meza-marathon/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>bo1024</author><text>By all accounts (including a friend of mine) he was a wonderful person, mentor, coach, etc. back in the day. It sounds like maybe he developed some mental issues that eventually led to both the cheating and suicide.</text><parent_chain><item><author>Reubend</author><text>It&#x27;s terrible that people were harassing this man, and that those communities formed a mob mentality against him. But I don&#x27;t feel particularly sorry for him; he cheated, denied it, threatened to sue people, and then eventually took his own life after his reputation was ruined.<p>Perhaps if he had stopped competing after the first blog post exposing him, things would have de-escalated. Instead, he doubled down on his lies, and made things worse for himself.</text></item></parent_chain></comment><story><title>Accused of cheating, marathon runner Frank Meza's life fell apart (2019)</title><url>https://www.lamag.com/citythinkblog/frank-meza-marathon/</url></story> |
21,386,248 | 21,386,012 | 1 | 3 | 21,384,997 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>notacoward</author><text>&gt; like many great early works, they are cliches<p>This, a thousand times. It&#x27;s just so easy for people to fall into the trap of thinking the current list of things to do or avoid has always been obvious. The path is always obvious after a million people have trodden it. But at one time it wasn&#x27;t. At one time people had to figure out things we now take for granted - like network APIs or concurrent programming models or, most relevantly, memory management.<p><i>At the time</i> manual management of object lifetimes was the only feasible option for a systems programming language, and it was feasible in part because control flows were simpler. Yes, even in things like OS kernels. They were kept simple <i>by design</i> in part to keep lifetime management tractable. Many of the things that make that approach non-viable today - e.g. massive concurrency, callbacks, exceptions - weren&#x27;t part of the idiom then. They were irrelevant to C&#x27;s design.<p>C was good for its time. Go ahead, take a look at PL&#x2F;I and BLISS. See whether you&#x27;d rather program in those. It might or might not be relevant today, but C was better designed in its context than anything most of its modern critics have ever designed (or will design) themselves.</text><parent_chain><item><author>roenxi</author><text>C was famously well designed. The problems it was well designed for have disappeared and its good ideas are so well understood that, like many great early works, they are cliches that can no longer be recognised for their brilliance because everyone is doing that.<p>C&#x27;s flaws are real, but they exist in the context of that design. For example, C has bad memory management because it was built when programmers had kilo- to mega- bytes to play with and needed perfect control.<p>I&#x27;m not sure anyone could ever accuse anything related to the internet of being &#x27;designed&#x27;. Even being standardised is a stretch. Javascript isn&#x27;t C, because C is an extremely focused attempt to solve specific problems. Javascript simply does not attempt to tackle the same problems as C and it doesn&#x27;t attempt to tackle them in the same way.<p>It may be that they are both fail to solve the big problems in web development, but that is not really a thing worth comparing languages on.</text></item></parent_chain></comment><story><title>JavaScript Is C</title><url>https://v4.chriskrycho.com/2018/javascript-is-c.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>sjy</author><text>&gt; I&#x27;m not sure anyone could ever accuse anything related to the internet of being &#x27;designed&#x27;. Even being standardised is a stretch.<p>I think you are talking about the ecosystem surrounding JavaScript, which was created in 10 days for incoherent marketing reasons, not the Internet, which was designed via a rigorous standardisation process. The Internet protocol suite is a beautiful and lasting design that dates back to the 1970s, and it&#x27;s proved flexible enough for everything from the dial-up era to modern wireless video streaming.</text><parent_chain><item><author>roenxi</author><text>C was famously well designed. The problems it was well designed for have disappeared and its good ideas are so well understood that, like many great early works, they are cliches that can no longer be recognised for their brilliance because everyone is doing that.<p>C&#x27;s flaws are real, but they exist in the context of that design. For example, C has bad memory management because it was built when programmers had kilo- to mega- bytes to play with and needed perfect control.<p>I&#x27;m not sure anyone could ever accuse anything related to the internet of being &#x27;designed&#x27;. Even being standardised is a stretch. Javascript isn&#x27;t C, because C is an extremely focused attempt to solve specific problems. Javascript simply does not attempt to tackle the same problems as C and it doesn&#x27;t attempt to tackle them in the same way.<p>It may be that they are both fail to solve the big problems in web development, but that is not really a thing worth comparing languages on.</text></item></parent_chain></comment><story><title>JavaScript Is C</title><url>https://v4.chriskrycho.com/2018/javascript-is-c.html</url></story> |
14,547,132 | 14,547,040 | 1 | 2 | 14,536,202 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>Animats</author><text>This is an ad. <i>&quot;Jack du Rose is a cofounder of Colony, an Ethereum-based operating system for open organizations.&quot;</i><p>Whatever that is. (It seems to be a scheme for monetizing StackOverflow rankings.[1] Or something like that. If it even exists. The web site is all pretty pictures with no content.)<p>Most altcoins crash after a while. See Coin Market Cap.[2]<p>[1] <a href="https:&#x2F;&#x2F;colony.io&#x2F;" rel="nofollow">https:&#x2F;&#x2F;colony.io&#x2F;</a>
[2] <a href="https:&#x2F;&#x2F;coinmarketcap.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;coinmarketcap.com&#x2F;</a></text><parent_chain></parent_chain></comment><story><title>Why Ethereum is outpacing Bitcoin</title><url>https://venturebeat.com/2017/06/11/why-ethereum-is-outpacing-bitcoin/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>root_axis</author><text>&gt; <i>As a “hard fork” looms, which looks set to split Bitcoin into two separate currencies that will have to fight for custody of the Bitcoin moniker</i><p>This already happened to eth when the creators hard forked the chain in an effort to roll back operations of an eth application that was used in a way that the creators did not anticipate. If this didn&#x27;t kill ethereum why would it be a problem for bitcoin? Fortunately for bitcoin, there isn&#x27;t a highly influential and transparently self-interested creator lording over the project.<p>&gt; <i>Bitcoin transactions can take anywhere from tens of minutes to several hours, depending on how busy the network is.</i><p>An unsolved growth problem for the reining incumbent that remains unsolved by ethereum. Transactions take a long time because decentralized proof of work verification is slow. A lot of people will say &quot;proof of stake is coming!!!&quot; but it&#x27;s essentially vaporware and all signs point to the conclusion that it will remain that way for the foreseeable future. Yeah, people are working on it, like all vaporware.<p>&gt; <i>Ethereum is actually a platform for new kinds of decentralized (often financial) applications (dApps) that run on a peer-to-peer network of computers</i><p>Except this isn&#x27;t actually happening in practice. I am yet to see any &quot;new kinds of decentralized applications&quot;, just toy applications that have no practical purpose besides internet roulette<p>&gt; <i>TL;DR: Bitcoin’s dominance is slipping because its utility is limited and weakening versus other more recently developed, less politicized cryptocurrencies. </i><p>Bitcoin&#x27;s dominance is not slipping because it&#x27;s utility was marginal to begin with and eth certainly doesn&#x27;t offer much in the way of compelling improvements over bitcoin.</text><parent_chain></parent_chain></comment><story><title>Why Ethereum is outpacing Bitcoin</title><url>https://venturebeat.com/2017/06/11/why-ethereum-is-outpacing-bitcoin/</url></story> |
9,202,398 | 9,202,379 | 1 | 3 | 9,202,182 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>snarfy</author><text>It&#x27;s a slippery slope to pick one drug as OK and another as not. Putting substances into your own body should not be illegal, regardless of the substance. We would do a lot better if we focused on education, addiction, and rehab than focusing on prohibition.</text><parent_chain><item><author>themartorana</author><text>This is easy to get behind. Although I have doubts of ever seeing these products on store shelves in the US, one of the things that have kept my personal drug experimentation extremely low is fear of product purity and lack of quality control.<p>It&#x27;s easy to show how terrible the War on Drugs has been. I&#x27;m still against legalizing the worst of drugs like meth and heroin. But marijuana and LSD, other plant-based psychedelics, I&#x27;m mostly for.<p>Keeping drugs under ground and in the shadows funds Mexican drug cartels and puts the lives of millions at risk, while causing medical patients continuous, unnecessary suffering. Legalization and good QC is the best thing we could hope for.</text></item></parent_chain></comment><story><title>Non-profit produced MDMA 'ecstasy' and psychedelics</title><url>https://www.indiegogo.com/projects/non-profit-produced-mdma-ecstasy-psychedelics--2</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>ramblerman</author><text>Legalize drugs in group A but keep group B illegal is subjective and counterproductive to the drug legalisation movement.<p>You have to realize the big picture, which is that there will always be a fringe of society doing the worst drugs available. Accepting that and coming up with alternative solutions like just giving them their drugs in controlled environments can be far cheaper for society.<p>It&#x27;s the same as prostitution, it will always exist. Either underground or above ground.</text><parent_chain><item><author>themartorana</author><text>This is easy to get behind. Although I have doubts of ever seeing these products on store shelves in the US, one of the things that have kept my personal drug experimentation extremely low is fear of product purity and lack of quality control.<p>It&#x27;s easy to show how terrible the War on Drugs has been. I&#x27;m still against legalizing the worst of drugs like meth and heroin. But marijuana and LSD, other plant-based psychedelics, I&#x27;m mostly for.<p>Keeping drugs under ground and in the shadows funds Mexican drug cartels and puts the lives of millions at risk, while causing medical patients continuous, unnecessary suffering. Legalization and good QC is the best thing we could hope for.</text></item></parent_chain></comment><story><title>Non-profit produced MDMA 'ecstasy' and psychedelics</title><url>https://www.indiegogo.com/projects/non-profit-produced-mdma-ecstasy-psychedelics--2</url></story> |
28,990,633 | 28,990,390 | 1 | 2 | 28,989,341 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>n8cpdx</author><text>I just had an old acquaintance on the Azure team try to get me to apply at Microsoft.<p>I told him I can’t, because all the teams at Microsoft I’d want to work (particularly Windows) are suffering from poor management with user- and human-hostile values. I can’t work at a company that goes out of its way to make the world worse for people through software.<p>I gave a long list of examples of user hostile work coming out of Windows, but suggested I thought maybe DevDiv was an exception. A lot of the bad things in the world of windows dev are a direct result of the DevDiv v Windows feud that’s been going on since SteveSi was leading.<p>Oops. I was wrong. It turns out apparently all of Microsoft is driven by leadership that wants to make the world a worse place for human beings. Ads, sneaky non-optional telemetry, ripping features out of OSS code, and then lying about all of the above are management choices driven by the top.<p>I remember when they used to try to recruit for user obsession. That was a long time ago. It’s a shame, because their business model, unlike some other companies, is not fundamentally dependent on screwing users. This is all a Choice in the most profound sense, and an unnecessary choice at that.</text><parent_chain></parent_chain></comment><story><title>Microsoft .NET Devs Anonymously Responds to Microsoft .NET Leadership</title><url>https://pastebin.com/RF6015kv</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>minimaul</author><text>&gt; So that we don&#x27;t give away features to Rider?<p>Rider&#x27;s a <i>really</i> good .NET IDE - it&#x27;s my preference by far over VS Code, and over VS as well - but it&#x27;s <i>exactly</i> the kind of thing an &#x27;open&#x27; .NET ecosystem should be embracing.<p>If this is the MS management mindset (and I don&#x27;t find it that hard to believe), then .NET is <i>never</i> going to be truly open.<p>edit: the bugginess of OmniSharp + VS Code for .NET development doesn&#x27;t work to push me towards VS. VS is okay for the most part on Windows, much worse on Mac and not an option at all on Linux. It 100% pushed me away from VS Code and towards JetBrains - now I use Rider, PyCharm, and PHPStorm instead of VS Code.</text><parent_chain></parent_chain></comment><story><title>Microsoft .NET Devs Anonymously Responds to Microsoft .NET Leadership</title><url>https://pastebin.com/RF6015kv</url></story> |
6,076,037 | 6,075,557 | 1 | 2 | 6,075,262 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>mixmax</author><text>While this is a great and heartbreaking story that makes me proud to be an active member of HN it&#x27;s also a symptom of the totally broken US healthcare system.<p>From wikipedia:<p>The United States life expectancy of 78.4 years at birth, up from 75.2 years in 1990, ranks it 50th among 221 nations, and 27th out of the 34 industrialized OECD countries, down from 20th in 1990. Of 17 high-income countries studied by the National Institutes of Health in 2013, the United States had the highest or near-highest prevalence of infant mortality, heart and lung disease, sexually transmitted infections, adolescent pregnancies, injuries, homicides, and disability. Together, such issues place the U.S. at the bottom of the list for life expectancy. On average, a U.S. male can be expected to live almost four fewer years than those in the top-ranked country.<p>According to the World Health Organization (WHO), the United States spent more on health care per capita ($8,608), and more on health care as percentage of its GDP (17.9%), than any other nation in 2011. The Commonwealth Fund ranked the United States last in the quality of health care among similar countries, and notes U.S. care costs the most.<p><a href="http://en.wikipedia.org/wiki/Health_care_in_the_United_States" rel="nofollow">http:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Health_care_in_the_United_State...</a></text><parent_chain></parent_chain></comment><story><title>Hacker News Folks Get Long Overdue Thanks</title><url>http://linuxlock.blogspot.sg/2013/07/hacker-news-gets-long-overdue-thanks.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>nwenzel</author><text>Great story of compassion and triumph. So... How do we make it scale?<p>Is it mandatory insurance? Insurance doesn&#x27;t make everything affordable, but it probably wild have been helpful. Though maybe the co-pay would have been $50k.<p>Universal tax-payer funded insurance? The term &quot;tax payer&quot; is interesting because politicians and pundits forget that we&#x27;re all tax payers in one form or another. Granted some pay more, some are net consumers of govt services. But tax payers mean us, and those with more earned income more than those with less. I think the main difference between taxes and donation is choice.<p>Single-payer or government provided healthcare? Pretty sure that no one would identify the government as the picture perfect example of efficiency. Plus, putting elected officials or their appointees in charge of handing out goods and services doesnt seem to be sustainable. Not that putting profit seeking entities in charge has yielded the ideal result.<p>Making drug providers, healthcare providers and everyone else in that supply chain non-profit? Profit has enormous motivational powers. Not always for good. But it is pretty amazing what can be accomplished by organizations setup to create wealth.<p>Big Data? Sorry, I couldn&#x27;t resist. Well, lets use that as a proxy for innovation. It would seem that greater opportunity for innovation would help. Lower barriers to trying new drugs, procedures, diet, treatments would allow for potentially lower cost solutions to be created.<p>Separating health care from your job? Of your insurer only needs you to be healthy until you find a new job, there&#x27;s not much in incentive for long-term healthcare and preventative screenings to identify tumors and other problems before they become an expensive problem. Though that would seem to be an arguement in favor of a single payer system.<p>Sorry, I don&#x27;t have an answer. Hopefully, great stories like the OP continue. But if we don&#x27;t make it scale then we haven&#x27;t really done all we possibly can do.</text><parent_chain></parent_chain></comment><story><title>Hacker News Folks Get Long Overdue Thanks</title><url>http://linuxlock.blogspot.sg/2013/07/hacker-news-gets-long-overdue-thanks.html</url></story> |
25,489,235 | 25,487,298 | 1 | 3 | 25,485,938 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>contingencies</author><text>Sorry I was asleep (in China). Fair question. Well, the guy grew up on the border: he was talking to us in Chinese ... this was not a major touristy area, it was between the Japanese railway that comes down from Tonghua to Ji&#x27;an (Chinese side) and Manpo&#x2F;만포시 (NK side) at <a href="https:&#x2F;&#x2F;www.openstreetmap.org&#x2F;#map=13&#x2F;41.1369&#x2F;126.1751" rel="nofollow">https:&#x2F;&#x2F;www.openstreetmap.org&#x2F;#map=13&#x2F;41.1369&#x2F;126.1751</a> and the town of Changbaishan at <a href="https:&#x2F;&#x2F;www.openstreetmap.org&#x2F;#map=13&#x2F;41.4239&#x2F;128.1771" rel="nofollow">https:&#x2F;&#x2F;www.openstreetmap.org&#x2F;#map=13&#x2F;41.4239&#x2F;128.1771</a>. In this area you can literally look across in to North Korean villages and pillboxes, and in Changbaishan you can look across in to what I have read is allegedly the biggest NK town on the border. Along the way there is a failed attempt at building a train and the hills are denuded. Poverty is immediately evident. People are fishing with crap equipment because there is nothing else to do and they are hungry. Nobody has adequate clothing. I did not see glass. All the roads are dirt on the NK side. And so on.</text><parent_chain><item><author>the_af</author><text>How do you tell fact from fiction&#x2F;propaganda in cases such as these? North Korea is so closed that almost everything that reaches us comes from its enemies or defectors. We want to believe the strangest things about that country. And sure, some of it must be real, but how can you tell? Did your driver personally witness this, or did someone tell him and he was simply spreading a rumor?</text></item><item><author>contingencies</author><text>When I hired a car and traveled along the North Korean border circa 2005 the driver told me about how the NK villagers would, in recent memory, go up in to caves on the adjacent mountains in winter and basically lie there starving and dying in a group because their clothing and houses were so poor (no windows, no insulation) and the nearby land so denuded of firewood that they would otherwise freeze to death. The ones who survived were seen lying in the sun near the river in the spring awaiting the return of energy. I understand the first edible crops in the area are immature fern fronds which poke through the snow. According to the driver, the women would reportedly illegally cross the river to prostitute themselves in China before the winter to obtain rice to survive. It is likely these people have the same bone deformities.</text></item></parent_chain></comment><story><title>Early humans may have survived the harsh winters by hibernating</title><url>https://www.theguardian.com/science/2020/dec/20/early-humans-may-have-survived-the-harsh-winters-by-hibernating</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>stickfigure</author><text>Reputable sources have widely reported that North Korean men on average measure several inches shorter than South Koreans, and many defectors come across the border with signs of malnutrition and intestinal parasites.</text><parent_chain><item><author>the_af</author><text>How do you tell fact from fiction&#x2F;propaganda in cases such as these? North Korea is so closed that almost everything that reaches us comes from its enemies or defectors. We want to believe the strangest things about that country. And sure, some of it must be real, but how can you tell? Did your driver personally witness this, or did someone tell him and he was simply spreading a rumor?</text></item><item><author>contingencies</author><text>When I hired a car and traveled along the North Korean border circa 2005 the driver told me about how the NK villagers would, in recent memory, go up in to caves on the adjacent mountains in winter and basically lie there starving and dying in a group because their clothing and houses were so poor (no windows, no insulation) and the nearby land so denuded of firewood that they would otherwise freeze to death. The ones who survived were seen lying in the sun near the river in the spring awaiting the return of energy. I understand the first edible crops in the area are immature fern fronds which poke through the snow. According to the driver, the women would reportedly illegally cross the river to prostitute themselves in China before the winter to obtain rice to survive. It is likely these people have the same bone deformities.</text></item></parent_chain></comment><story><title>Early humans may have survived the harsh winters by hibernating</title><url>https://www.theguardian.com/science/2020/dec/20/early-humans-may-have-survived-the-harsh-winters-by-hibernating</url></story> |
8,096,530 | 8,095,736 | 1 | 2 | 8,094,134 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>chiph</author><text>If my house is on fire and I call 911, but the call doesn&#x27;t go through because my phone is connected to a nearby Stingray device and not to a real tower, that&#x27;s a big problem.</text><parent_chain></parent_chain></comment><story><title>Stingray, the fake cell phone tower</title><url>http://www.extremetech.com/mobile/184597-stingray-the-fake-cell-phone-tower-cops-and-providers-use-to-track-your-every-move</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>lucaspiller</author><text>&quot;Say a murder occurs on a particular street with an estimated time of death between 2 and 4 AM. Local law enforcement would have an obvious interest in compelling cell phone companies to turn over the records of every cell phone that moved in and out of the area between those two time periods. At rush hour, this kind of information would be useless — but if the cell phone network data shows a device in the same approximate area as the murder suddenly leaving the area at a high rate of speed, that cell phone owner is a potential suspect.&quot;<p>This similar to how CCTV is used in the UK. There is apparently one camera for every eleven people [0]. The difference is the majority of it is owned by private businesses though. Public CCTV is usually run by local councils which are independent from the police. If the police want to get any of this footage, and use it to prosecute, they need to get a court order or subpoena.<p>[0] <a href="http://www.telegraph.co.uk/technology/10172298/One-surveillance-camera-for-every-11-people-in-Britain-says-CCTV-survey.html" rel="nofollow">http:&#x2F;&#x2F;www.telegraph.co.uk&#x2F;technology&#x2F;10172298&#x2F;One-surveilla...</a></text><parent_chain></parent_chain></comment><story><title>Stingray, the fake cell phone tower</title><url>http://www.extremetech.com/mobile/184597-stingray-the-fake-cell-phone-tower-cops-and-providers-use-to-track-your-every-move</url></story> |
37,776,939 | 37,776,944 | 1 | 2 | 37,776,492 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>londons_explore</author><text>This is because google docs is now widely used as a malware vector.<p>Send the user to a google docs page, and because it is on the google domain it is trusted by corporate firewalls and AV scanners.<p>The &#x27;tracking&#x27; is in fact this page:<p><a href="https:&#x2F;&#x2F;www.google.com&#x2F;url?q=https:&#x2F;&#x2F;wikimediafoundation.org&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.google.com&#x2F;url?q=https:&#x2F;&#x2F;wikimediafoundation.org...</a><p>And that alerts the user to the fact they are leaving google and ending up on another site - which hopefully reduces the effectiveness of using google docs to distribute malware.</text><parent_chain></parent_chain></comment><story><title>Google Docs adds tracking to links in document exports</title><url>https://fosstodon.org/@Joe_0237/111145684757912952</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>srazzaque</author><text>I&#x27;m pretty sure the stated intent of the redirect is to prevent phishing (that is, provide an opportunity for Google to warn users about visiting a known dodgy site). The ability to track is just an added bonus!<p>Microsoft does this too with Teams. Links that my colleagues and I share with one another to _internal company sites_ get link checked then redirected. Microsoft must have a treasure trove of data about external company employee browsing habits as a result.<p>I would have infinitely more respect for companies that are upfront about their intentions, no matter how nefarious: &quot;we&#x27;re doing this to help protect you from phishing. But also, 99% of links are probably not phishing. So this feature really enables us to collect data to track what you do, and perform analytics to improve our bottom line&quot;.<p>Why sugar-coat it?</text><parent_chain></parent_chain></comment><story><title>Google Docs adds tracking to links in document exports</title><url>https://fosstodon.org/@Joe_0237/111145684757912952</url></story> |
22,117,105 | 22,117,149 | 1 | 3 | 22,115,280 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>tlarkworthy</author><text>Yes exactly, table comprehension is a logic driven, non-local inference problem. Critically, its the non-locality that trips up common machine learning techniques. I wrote an approach using mixed integer programming once[1]<p>[1] <a href="https:&#x2F;&#x2F;edinburghhacklab.com&#x2F;2013&#x2F;09&#x2F;probabalistic-scraping-of-plain-text-tables&#x2F;" rel="nofollow">https:&#x2F;&#x2F;edinburghhacklab.com&#x2F;2013&#x2F;09&#x2F;probabalistic-scraping-...</a></text><parent_chain><item><author>willvarfar</author><text>I&#x27;ve worked with several companies that try to parse things in PDF documents, extracting tables and paragraphs etc. This is actually challenging because a PDF is a large bag of words and fragments of words with x y positions. There is a particularly popular word processor that emits individual characters. Just determining that two fragments are part of the same word is challenging as is detecting bullet points, etc.<p>The AI approaches are definitely still worse than human-written rules. I can infer - and I&#x27;ve chatted with the devs to confirm - from the quality of the text and table extraction whether the company is using a modern NN approach or someone has sat down and handwritten some simple rules that understand indents and baselines etc.</text></item></parent_chain></comment><story><title>Table Detection and Extraction Using Deep Learning</title><url>https://nanonets.com/blog/table-extraction-deep-learning/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>crispyambulance</author><text>It was really shocking when I learned that the way pdf works is as you describe, literally fragments of text with positions and essentially no semantics.<p>I think a lot of folks find this out as I did, when they run into a project where they need to extract info from pdf documents. Without knowing anything about pdf, one can easily assume that it will be possible to do things like &quot;can&#x27;t we just extract some semantic structures like headings, tables, etc&quot;... but nooo, it don&#x27;t work that way!<p>Discovering the true nature of pdf is major WTF moment because we&#x27;re so conditioned to expect documents to have a semantic structure. It&#x27;s hard to understand how a standard can take the exact opposite approach and be so successful.</text><parent_chain><item><author>willvarfar</author><text>I&#x27;ve worked with several companies that try to parse things in PDF documents, extracting tables and paragraphs etc. This is actually challenging because a PDF is a large bag of words and fragments of words with x y positions. There is a particularly popular word processor that emits individual characters. Just determining that two fragments are part of the same word is challenging as is detecting bullet points, etc.<p>The AI approaches are definitely still worse than human-written rules. I can infer - and I&#x27;ve chatted with the devs to confirm - from the quality of the text and table extraction whether the company is using a modern NN approach or someone has sat down and handwritten some simple rules that understand indents and baselines etc.</text></item></parent_chain></comment><story><title>Table Detection and Extraction Using Deep Learning</title><url>https://nanonets.com/blog/table-extraction-deep-learning/</url></story> |
38,824,679 | 38,824,614 | 1 | 3 | 38,823,673 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>mananaysiempre</author><text>There’s a bit of a naming confusion around tail calls, but in any case “proper tail calls”, let’s call them that, are not precisely an optimization: they are a <i>guarantee</i> that any number of recursive calls of a certain kind will result in constant and not linear memory consumption. This permits some kinds of programming that can otherwise be quite awkward. If your program takes advantage of them (as e.g. often happens in Scheme), having tail calls is not an optimization issue, it’s an implementation correctness issue.<p>Now tail calls are quite annoying to implement <i>in C</i> on top of a compiler that doesn’t (and in fact I don’t think any mainstream platform has a C ABI that would allow a C compiler to natively support them between functions of arbitrary types). That has always been a (solvable) issue for Scheme-to-C translators, and it was probably a consideration for QuickJS. Chrome’s V8, though, is so far away from interpreting things in C or even translating them to C that I expect that any difficulties the developers have are of a completely different nature.<p>(As an example, LuaJIT does support tail calls but kind of sucks at inferring hot loops written using them, so has really impressively draconian limits on how many you can have before the JIT aborts. They otherwise work, though, as is required for a valid Lua implementation.)</text><parent_chain><item><author>tomashubelbauer</author><text>I find it surprising that the JS specification also includes optimizations an engine should implement. I&#x27;m not sure how difficult TCO is to implement, but I just checked if QuickJS supports it or not and it seems to be one of the few ES2020 omissions the author chose to make: <a href="https:&#x2F;&#x2F;bellard.org&#x2F;quickjs&#x2F;quickjs.pdf" rel="nofollow">https:&#x2F;&#x2F;bellard.org&#x2F;quickjs&#x2F;quickjs.pdf</a> (3.1.1). This tells me it might be non-trivial to implement which if true makes the decision to make it a part of the specification all the more surprising, because that means the specification restricts the types of trade-offs implementers can make when attempting to achieve full compatibility. In other words, until today I was under the impression you could make a fully ES compatible engine, but choose to make it slow for implementation ease. Looks like the spec defines the floor for how (non)-performant the engine implementation can be in some cases. Is this common in other languages&#x27; specs?<p>Edit: Oh, seeing the sibling comment, are TCO and &quot;tail calls&quot; different things? If so, I remain unclear on the status of TCO support in QuickJS.</text></item><item><author>pjmlp</author><text>Regardless, it has been approved as part of JavaScript specification and Chrome folks refuse for political reasons to implement it, which given the market domination everyone has helped them achieve is a bummer.</text></item><item><author>MrJohz</author><text>I think this article actually does a really good job of explaining why TCO hasn&#x27;t really been an important part of the JS ecosystem.<p>There&#x27;s a lot of situations where recursive algorithms are really neat and clear. I don&#x27;t know if this is the best example, but it shows the benefit of being able to split logic into a base case and a recurrence case.<p>But, in my experience, an algorithm that elegantly fits a recursive relationship is rarely one that naturally fits the tail-call paradigm. Often part of the benefit of recursion is that you can store state in the stack - the very thing you need to avoid to use TCO.<p>This means you often need to put in effort to create a tail recursive algorithm. But that often ends up looking a lot like the imperative case anyway - an accumulator outside the loop that you either mutate manually, or update in a tail call. And in my experience, the mutating, imperative version is usually then the easier to read and write (assuming you can keep mutations to a given scope, and not have that state leak all over the place). (In fairness, this might be more familiarity, though.)<p>In the light of this, what is the advantage of TCO? In functional languages without mutation, it&#x27;s pretty important to allow for functions to act on arbitrarily-sized inputs without constantly growing the stack. But if we have mutation, it&#x27;s really just a different way of writing the same code. And if that different way is generally less clear and almost always less performant, it probably isn&#x27;t a very useful choice.<p>Which is why I think TCO hasn&#x27;t really caught on in the other JS engines. It&#x27;s a cool idea, and there&#x27;s definitely a handful of cases where it&#x27;s the useful way to go, but usually you&#x27;ll be better served by writing things in the more traditional JS way.</text></item></parent_chain></comment><story><title>Bun, JavaScript, and TCO</title><url>https://www.onsclom.net/posts/javascript-tco</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>basil-rash</author><text>Scheme (what JavaScript was based on) also requires tail call optimizations as part of its spec.</text><parent_chain><item><author>tomashubelbauer</author><text>I find it surprising that the JS specification also includes optimizations an engine should implement. I&#x27;m not sure how difficult TCO is to implement, but I just checked if QuickJS supports it or not and it seems to be one of the few ES2020 omissions the author chose to make: <a href="https:&#x2F;&#x2F;bellard.org&#x2F;quickjs&#x2F;quickjs.pdf" rel="nofollow">https:&#x2F;&#x2F;bellard.org&#x2F;quickjs&#x2F;quickjs.pdf</a> (3.1.1). This tells me it might be non-trivial to implement which if true makes the decision to make it a part of the specification all the more surprising, because that means the specification restricts the types of trade-offs implementers can make when attempting to achieve full compatibility. In other words, until today I was under the impression you could make a fully ES compatible engine, but choose to make it slow for implementation ease. Looks like the spec defines the floor for how (non)-performant the engine implementation can be in some cases. Is this common in other languages&#x27; specs?<p>Edit: Oh, seeing the sibling comment, are TCO and &quot;tail calls&quot; different things? If so, I remain unclear on the status of TCO support in QuickJS.</text></item><item><author>pjmlp</author><text>Regardless, it has been approved as part of JavaScript specification and Chrome folks refuse for political reasons to implement it, which given the market domination everyone has helped them achieve is a bummer.</text></item><item><author>MrJohz</author><text>I think this article actually does a really good job of explaining why TCO hasn&#x27;t really been an important part of the JS ecosystem.<p>There&#x27;s a lot of situations where recursive algorithms are really neat and clear. I don&#x27;t know if this is the best example, but it shows the benefit of being able to split logic into a base case and a recurrence case.<p>But, in my experience, an algorithm that elegantly fits a recursive relationship is rarely one that naturally fits the tail-call paradigm. Often part of the benefit of recursion is that you can store state in the stack - the very thing you need to avoid to use TCO.<p>This means you often need to put in effort to create a tail recursive algorithm. But that often ends up looking a lot like the imperative case anyway - an accumulator outside the loop that you either mutate manually, or update in a tail call. And in my experience, the mutating, imperative version is usually then the easier to read and write (assuming you can keep mutations to a given scope, and not have that state leak all over the place). (In fairness, this might be more familiarity, though.)<p>In the light of this, what is the advantage of TCO? In functional languages without mutation, it&#x27;s pretty important to allow for functions to act on arbitrarily-sized inputs without constantly growing the stack. But if we have mutation, it&#x27;s really just a different way of writing the same code. And if that different way is generally less clear and almost always less performant, it probably isn&#x27;t a very useful choice.<p>Which is why I think TCO hasn&#x27;t really caught on in the other JS engines. It&#x27;s a cool idea, and there&#x27;s definitely a handful of cases where it&#x27;s the useful way to go, but usually you&#x27;ll be better served by writing things in the more traditional JS way.</text></item></parent_chain></comment><story><title>Bun, JavaScript, and TCO</title><url>https://www.onsclom.net/posts/javascript-tco</url></story> |
36,925,939 | 36,926,144 | 1 | 2 | 36,925,019 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>npteljes</author><text>What I gather from this comment is an attempt to distance from the attachment to clearly harmful things.<p>I think it would do good to just internalize what&#x27;s happening - the desire for personal gain, and the indifference on the ways that are employed. There is no shame in not caring about other people on a societal level, I don&#x27;t think most of us do, and I do think that many who say they do, don&#x27;t really actually. Calling them names like stupid or gullible, just to defend contributing to the harm of them is not successful coping attempt however. It just says that these things do bother who&#x27;s saying them, and that they feel something that&#x27;s not desirable to them, like shame, or fear of retribution, or something else that&#x27;s negative. There&#x27;s no need to do any of this, it&#x27;s okay to just not care.</text><parent_chain><item><author>sershe</author><text>Long time ago there was a moment when the best performing stocks in my individual-stock portfolio were PM or maybe MO (cigarettes), DPS (Dr Pepper, it was later acquired), MCD, and AAPL. I joked that it makes sense, the best business is selling good-feeling, harmful crap to the gullible ;)<p>However, there is another side to this... Who are you (not you personally, but anyone) to decide how others should live their lives? If someone wants to drink soda, smoke and eat fast food, why wouldn&#x27;t they? If selling what people want is somehow bad, then I guess restricting it should be good, so we should just take all these people we have decided are too stupid to know what&#x27;s good for them, and regiment their life until we are satisfied? As much as I dislike and disagree with their choices, this line of thinking seems abhorrent to me, at most I&#x27;d argue we have some say on what they are doing if they use taxpayer-funded healthcare and such, but for me that is an argument against the latter, not the former. And in any case it has no bearing on the morality of the seller - he didn&#x27;t ask or force anyone other than the buyer to deal with the 2nd order effects.<p>Viewed from that perspective, there&#x27;s nothing wrong with selling cigarettes.</text></item><item><author>sebmellen</author><text>The deification of Buffet is strange to see. A lot of the businesses he invests in are just not net positives for society - cigarettes, Dairy Queen, Coca-Cola, etc.</text></item><item><author>kingstoned</author><text>&quot;I’ll tell you why I like the cigarette business. It costs a penny to make. Sell it for a dollar. It’s addictive. And there’s fantastic brand loyalty.&quot;<p>- Warren Buffett</text></item></parent_chain></comment><story><title>Big Tobacco knew radioactive Po210 in cigarettes posed cancer risk, kept quiet</title><url>https://www.uclahealth.org/news/big-tobacco-knew-radioactive-particles-in-cigarettes</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>TheOtherHobbes</author><text>Selling an addictive substance through media carpet bombing without informed consent is absolutely a crime.<p>&quot;But people want it&quot; is not a valid argument.<p>There&#x27;s a quote about propaganda which says that the goal is to make everyone feel that forced-fed choices are their own spontaneous decisions.<p>There are entire industries devoted to making sure that those choices - often self-harming - are <i>not</i> spontaneous. At all.<p>Get rid of those and you may have a point. While they still operate, you don&#x27;t.</text><parent_chain><item><author>sershe</author><text>Long time ago there was a moment when the best performing stocks in my individual-stock portfolio were PM or maybe MO (cigarettes), DPS (Dr Pepper, it was later acquired), MCD, and AAPL. I joked that it makes sense, the best business is selling good-feeling, harmful crap to the gullible ;)<p>However, there is another side to this... Who are you (not you personally, but anyone) to decide how others should live their lives? If someone wants to drink soda, smoke and eat fast food, why wouldn&#x27;t they? If selling what people want is somehow bad, then I guess restricting it should be good, so we should just take all these people we have decided are too stupid to know what&#x27;s good for them, and regiment their life until we are satisfied? As much as I dislike and disagree with their choices, this line of thinking seems abhorrent to me, at most I&#x27;d argue we have some say on what they are doing if they use taxpayer-funded healthcare and such, but for me that is an argument against the latter, not the former. And in any case it has no bearing on the morality of the seller - he didn&#x27;t ask or force anyone other than the buyer to deal with the 2nd order effects.<p>Viewed from that perspective, there&#x27;s nothing wrong with selling cigarettes.</text></item><item><author>sebmellen</author><text>The deification of Buffet is strange to see. A lot of the businesses he invests in are just not net positives for society - cigarettes, Dairy Queen, Coca-Cola, etc.</text></item><item><author>kingstoned</author><text>&quot;I’ll tell you why I like the cigarette business. It costs a penny to make. Sell it for a dollar. It’s addictive. And there’s fantastic brand loyalty.&quot;<p>- Warren Buffett</text></item></parent_chain></comment><story><title>Big Tobacco knew radioactive Po210 in cigarettes posed cancer risk, kept quiet</title><url>https://www.uclahealth.org/news/big-tobacco-knew-radioactive-particles-in-cigarettes</url></story> |
17,493,255 | 17,493,165 | 1 | 2 | 17,492,750 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>madamelic</author><text>&gt;One could argue that if you have to dip down to the level of porn just to find some value, ICOs are worth dismissing<p>One could also argue that when porn starts adopting a technology, you should adopt it too because that tech is what is going to win.<p>Porn has consistently chosen the winners and any tech that discourages or disallows porn&#x27;s involvement loses.</text><parent_chain><item><author>shawn</author><text>One promising example is SpankChain. It&#x27;s a cryptocurrency specifically designed for the porn market.<p>Traditionally, it&#x27;s hard to make money in porn due to fraud and chargebacks. Most payment processors also won&#x27;t touch you. But crypto has no chargebacks, so it&#x27;s a natural fit.<p>One could argue that if you have to dip down to the level of porn just to find some value, ICOs are worth dismissing. But I would say that it&#x27;s a decent example of the future potential.</text></item><item><author>jacquesm</author><text>&gt; Eventually someone will realize that the smarter move is to create sustainable value over time.<p>Most ICO&#x27;s - if not all of them - are powered by the greater fool theory, sustainable value isn&#x27;t really on the table.<p>I see value in the blockchain and some in BTC (but not as much as others apparently do), but the whole ICO concept seems to be just a way to transfer wealth from greedy suckers to even greedier suckers.</text></item><item><author>shawn</author><text>Once ICO scams stop working, the world will move towards traditional models. Crypto is out there, and it&#x27;s not going anywhere. Eventually someone will realize that the smarter move is to create sustainable value over time.</text></item><item><author>MBCook</author><text>Why would anyone running an ICO agree to that? Clearly the current system ‘works’.<p>They get money, no accountability, and everyone just moves on.<p>No wonder crypto-currencies enjoy such a positive image among the ‘haters’ and ‘doubters’. Because they keep earning it.</text></item><item><author>mrnobody_67</author><text>I&#x27;m so surprised that smart contracts aren&#x27;t being used to release the funds over some set of time, with the ability for community to vote to block it if they feel team has stalled. Nobody needs $20 or $50m on day 1.</text></item></parent_chain></comment><story><title>Half of ICOs Die Within Four Months After Token Sales Finalized</title><url>https://www.bloomberg.com/news/articles/2018-07-09/half-of-icos-die-within-four-months-after-token-sales-finalized</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>detaro</author><text>If it is just payments, why have a special cryptocurrency? Or does it do something more clever?</text><parent_chain><item><author>shawn</author><text>One promising example is SpankChain. It&#x27;s a cryptocurrency specifically designed for the porn market.<p>Traditionally, it&#x27;s hard to make money in porn due to fraud and chargebacks. Most payment processors also won&#x27;t touch you. But crypto has no chargebacks, so it&#x27;s a natural fit.<p>One could argue that if you have to dip down to the level of porn just to find some value, ICOs are worth dismissing. But I would say that it&#x27;s a decent example of the future potential.</text></item><item><author>jacquesm</author><text>&gt; Eventually someone will realize that the smarter move is to create sustainable value over time.<p>Most ICO&#x27;s - if not all of them - are powered by the greater fool theory, sustainable value isn&#x27;t really on the table.<p>I see value in the blockchain and some in BTC (but not as much as others apparently do), but the whole ICO concept seems to be just a way to transfer wealth from greedy suckers to even greedier suckers.</text></item><item><author>shawn</author><text>Once ICO scams stop working, the world will move towards traditional models. Crypto is out there, and it&#x27;s not going anywhere. Eventually someone will realize that the smarter move is to create sustainable value over time.</text></item><item><author>MBCook</author><text>Why would anyone running an ICO agree to that? Clearly the current system ‘works’.<p>They get money, no accountability, and everyone just moves on.<p>No wonder crypto-currencies enjoy such a positive image among the ‘haters’ and ‘doubters’. Because they keep earning it.</text></item><item><author>mrnobody_67</author><text>I&#x27;m so surprised that smart contracts aren&#x27;t being used to release the funds over some set of time, with the ability for community to vote to block it if they feel team has stalled. Nobody needs $20 or $50m on day 1.</text></item></parent_chain></comment><story><title>Half of ICOs Die Within Four Months After Token Sales Finalized</title><url>https://www.bloomberg.com/news/articles/2018-07-09/half-of-icos-die-within-four-months-after-token-sales-finalized</url></story> |
31,796,869 | 31,796,927 | 1 | 3 | 31,796,239 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>praptak</author><text>A dude I know has cheap electricity on his allotment garden where he built a wooden hut&#x2F;cabin. He uses three PCs built from throwaway parts to heat the hut in the autumn and early spring (in winter there&#x27;s nothing to do there).<p>On the PCs he runs an app that basically manages the mining for you, automatically switching between cryptos to get the most microcents per watt per second.<p>I have no idea why the allotment gardens got the cheap deal on electricity and I don&#x27;t know if the mining gives him a significant &quot;discount&quot; on the heating.</text><parent_chain><item><author>RL_Quine</author><text>You don&#x27;t have to do anything dodgy to get power at an unbelievably low cost, even in north america bulk rates are a couple of cents per kilowatt hour if you know where to look, and in some cases you can even be paid to use power due to politics. You can also be mining at a loss and have it be completely rational, because it is less of a loss than turning it off and writing off the equipment. The economics are very non intuitive for people who aren&#x27;t exposed to the industry.</text></item><item><author>MengerSponge</author><text>If they&#x27;re either using subsidized or pirated electricity, and their hardware is paid for, why would miners pull out?</text></item><item><author>thematrixturtle</author><text>It&#x27;s a self-correcting equilibrium though, since the block difficulty is tied to the hashrate, which will fall as miners pull out.<p>That said, the hashrate is not showing major drops yet:<p><a href="https:&#x2F;&#x2F;www.blockchain.com&#x2F;charts&#x2F;hash-rate" rel="nofollow">https:&#x2F;&#x2F;www.blockchain.com&#x2F;charts&#x2F;hash-rate</a></text></item></parent_chain></comment><story><title>Bitcoin mining becomes unprofitable as BTC price falls to average cost of mining</title><url>https://finbold.com/bitcoin-mining-becomes-unprofitable-as-btc-price-falls-to-the-average-cost-of-mining/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>ahtihn</author><text>&gt; You can also be mining at a loss and have it be completely rational, because it is less of a loss than turning it off and writing off the equipment.<p>It depends what you mean by mining at a loss.<p>It&#x27;s never rational to mine when the cost of power is higher than the expected return. Turn off your equipment and go buy bitcoin directly.</text><parent_chain><item><author>RL_Quine</author><text>You don&#x27;t have to do anything dodgy to get power at an unbelievably low cost, even in north america bulk rates are a couple of cents per kilowatt hour if you know where to look, and in some cases you can even be paid to use power due to politics. You can also be mining at a loss and have it be completely rational, because it is less of a loss than turning it off and writing off the equipment. The economics are very non intuitive for people who aren&#x27;t exposed to the industry.</text></item><item><author>MengerSponge</author><text>If they&#x27;re either using subsidized or pirated electricity, and their hardware is paid for, why would miners pull out?</text></item><item><author>thematrixturtle</author><text>It&#x27;s a self-correcting equilibrium though, since the block difficulty is tied to the hashrate, which will fall as miners pull out.<p>That said, the hashrate is not showing major drops yet:<p><a href="https:&#x2F;&#x2F;www.blockchain.com&#x2F;charts&#x2F;hash-rate" rel="nofollow">https:&#x2F;&#x2F;www.blockchain.com&#x2F;charts&#x2F;hash-rate</a></text></item></parent_chain></comment><story><title>Bitcoin mining becomes unprofitable as BTC price falls to average cost of mining</title><url>https://finbold.com/bitcoin-mining-becomes-unprofitable-as-btc-price-falls-to-the-average-cost-of-mining/</url></story> |
41,531,625 | 41,531,633 | 1 | 2 | 41,528,266 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>alwyn</author><text>Cyberpunk != cyberpunk, unfortunately.<p>Cyberpunk 2077 is set in the Cyberpunk RPG universe that was created by Mike Pondsmith in 1988.<p>It was named after the vibe without changing the name...<p>Also a helpful article: <a href="https:&#x2F;&#x2F;www.polygon.com&#x2F;reviews&#x2F;2019&#x2F;8&#x2F;7&#x2F;20756548&#x2F;cyberpunk-red-jumpstart-kit-review-2077-prequel" rel="nofollow">https:&#x2F;&#x2F;www.polygon.com&#x2F;reviews&#x2F;2019&#x2F;8&#x2F;7&#x2F;20756548&#x2F;cyberpunk-...</a></text><parent_chain><item><author>MichaelZuo</author><text>How can anyone hold IP over an abstract vibe?</text></item><item><author>chupasaurus</author><text>&gt; how CD Project Red handled their successful Cyberpunk integration on Netflix as a model<p>A reminder that Cyberpunk IP holder is Mike Pondsmith, not CD Project.</text></item><item><author>threeseed</author><text>There is another way to look at this.<p>Annapurna Pictures in Dec 2022 produced Nimona for Netflix which debuted at #9 globally and was as high as #3 i.e. it was a massive hit.<p>So they now have the Stray IP which could be extremely lucrative and are looking at how CD Project Red handled their successful Cyberpunk integration on Netflix as a model. Which is where you cross-promote a game add-on or sequel with the movie.<p>Which means for the gaming side they really wouldn&#x27;t have any control over their direction as it would be entirely driven by the movie side. Not exactly compelling for them hence why they want to leave.<p>With the success of Fallout, The Last of Us, Cyberpunk Edgerunners etc there&#x27;s definitely big money to be made from video game IP.</text></item><item><author>loupol</author><text>Article is missing some context imo :<p>* Annapurna Pictures (the parent company of Interactive) had some financial issues previously at least (see [0] from 2019) while Annapurna Interactive was doing well for itself.<p>* Annapurna Pictures wanted to integrate the gaming division in-house (possibly to prop up the rest of the company)<p>* Staff and exec at Annapurna Interactive wanted to be spin off (see [1])<p>* Negotiations fell through, so most exec and staff at Interactive left<p>[0] <a href="https:&#x2F;&#x2F;variety.com&#x2F;2019&#x2F;film&#x2F;news&#x2F;annapurna-resolves-more-than-200-million-in-debt-pushes-ahead-without-banks-exclusive-1203314214&#x2F;" rel="nofollow">https:&#x2F;&#x2F;variety.com&#x2F;2019&#x2F;film&#x2F;news&#x2F;annapurna-resolves-more-t...</a><p>[1] <a href="https:&#x2F;&#x2F;www.bloomberg.com&#x2F;news&#x2F;articles&#x2F;2024-09-12&#x2F;annapurna-video-game-team-resigns-leaving-partners-scrambling?accessToken=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzb3VyY2UiOiJTdWJzY3JpYmVyR2lmdGVkQXJ0aWNsZSIsImlhdCI6MTcyNjE3NzQyOSwiZXhwIjoxNzI2NzgyMjI5LCJhcnRpY2xlSWQiOiJTSlBZWklUMEFGQjQwMCIsImJjb25uZWN0SWQiOiJCMUVBQkI5NjQ2QUM0REZFQTJBRkI4MjI1MzgyQTJFQSJ9.BpoA_wBJDrNbDbgj_LjnVUJQg6SM_vsIzWUEM6v85xE" rel="nofollow">https:&#x2F;&#x2F;www.bloomberg.com&#x2F;news&#x2F;articles&#x2F;2024-09-12&#x2F;annapurna...</a></text></item></parent_chain></comment><story><title>Entire staff of game publisher Annapurna Interactive has reportedly resigned</title><url>https://www.theverge.com/games/2024/9/12/24243317/annapurna-interactive-staff-reportedly-resigns</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>ivmoreau</author><text>In this context is referring as Cyberpunk the role playing game, rather than just the genre. Cyberpunk 2077 has a setting based on the role playing board game (that’s where some characters come from, like Silverhand), and that setting is the original IP.</text><parent_chain><item><author>MichaelZuo</author><text>How can anyone hold IP over an abstract vibe?</text></item><item><author>chupasaurus</author><text>&gt; how CD Project Red handled their successful Cyberpunk integration on Netflix as a model<p>A reminder that Cyberpunk IP holder is Mike Pondsmith, not CD Project.</text></item><item><author>threeseed</author><text>There is another way to look at this.<p>Annapurna Pictures in Dec 2022 produced Nimona for Netflix which debuted at #9 globally and was as high as #3 i.e. it was a massive hit.<p>So they now have the Stray IP which could be extremely lucrative and are looking at how CD Project Red handled their successful Cyberpunk integration on Netflix as a model. Which is where you cross-promote a game add-on or sequel with the movie.<p>Which means for the gaming side they really wouldn&#x27;t have any control over their direction as it would be entirely driven by the movie side. Not exactly compelling for them hence why they want to leave.<p>With the success of Fallout, The Last of Us, Cyberpunk Edgerunners etc there&#x27;s definitely big money to be made from video game IP.</text></item><item><author>loupol</author><text>Article is missing some context imo :<p>* Annapurna Pictures (the parent company of Interactive) had some financial issues previously at least (see [0] from 2019) while Annapurna Interactive was doing well for itself.<p>* Annapurna Pictures wanted to integrate the gaming division in-house (possibly to prop up the rest of the company)<p>* Staff and exec at Annapurna Interactive wanted to be spin off (see [1])<p>* Negotiations fell through, so most exec and staff at Interactive left<p>[0] <a href="https:&#x2F;&#x2F;variety.com&#x2F;2019&#x2F;film&#x2F;news&#x2F;annapurna-resolves-more-than-200-million-in-debt-pushes-ahead-without-banks-exclusive-1203314214&#x2F;" rel="nofollow">https:&#x2F;&#x2F;variety.com&#x2F;2019&#x2F;film&#x2F;news&#x2F;annapurna-resolves-more-t...</a><p>[1] <a href="https:&#x2F;&#x2F;www.bloomberg.com&#x2F;news&#x2F;articles&#x2F;2024-09-12&#x2F;annapurna-video-game-team-resigns-leaving-partners-scrambling?accessToken=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzb3VyY2UiOiJTdWJzY3JpYmVyR2lmdGVkQXJ0aWNsZSIsImlhdCI6MTcyNjE3NzQyOSwiZXhwIjoxNzI2NzgyMjI5LCJhcnRpY2xlSWQiOiJTSlBZWklUMEFGQjQwMCIsImJjb25uZWN0SWQiOiJCMUVBQkI5NjQ2QUM0REZFQTJBRkI4MjI1MzgyQTJFQSJ9.BpoA_wBJDrNbDbgj_LjnVUJQg6SM_vsIzWUEM6v85xE" rel="nofollow">https:&#x2F;&#x2F;www.bloomberg.com&#x2F;news&#x2F;articles&#x2F;2024-09-12&#x2F;annapurna...</a></text></item></parent_chain></comment><story><title>Entire staff of game publisher Annapurna Interactive has reportedly resigned</title><url>https://www.theverge.com/games/2024/9/12/24243317/annapurna-interactive-staff-reportedly-resigns</url></story> |
34,116,213 | 34,116,108 | 1 | 3 | 34,115,632 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>nordsieck</author><text>&gt; is there anyone who seriously reads poetry for fun nowadays?<p>1. IMO, there is some really great poetry out there. But the ratio is terrible. It&#x27;s honestly worse than Youtube comments.<p>2. Poetry 1.0 mostly died for... reasons. But it&#x27;s replacement - Poetry 2.0 - people absolutely love. You&#x27;d know it better by its common name &quot;rap&quot;.<p>If you want some encouragement to wade through sewage to discover gems, here&#x27;s one that really speaks to me:<p><pre><code> Aedh Wishes for the Cloths of Heaven
------------------------------------
W. B. Yeats
Had I the heavens&#x27; embroidered cloths,
Enwrought with golden and silver light,
The blue and the dim and the dark cloths
Of night and light and the half light,
I would spread the cloths under your feet:
But I, being poor, have only my dreams;
I have spread my dreams under your feet;
Tread softly because you tread on my dreams.
</code></pre>
Among other things, it really captures some of the melancholy of being a parent who isn&#x27;t particularly wealthy.</text><parent_chain><item><author>TotoHorner</author><text>&gt; Why do most people seem to hold poetry and poets in high esteem yet have approximately zero interest in reading any poetry ever?<p>I&#x27;ve wondered this for years.<p>Like seriously, is there anyone who seriously reads poetry for fun nowadays?<p>I understand if it&#x27;s the 1800s and there&#x27;s literally nothing else to do.</text></item></parent_chain></comment><story><title>Things to argue about over the holidays instead of politics</title><url>https://dynomight.net/arguments/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>mejutoco</author><text>Lots of people listen to hip hop and, while the quality varies a lot, it is remarkable that a very popular musical genre is poetry.</text><parent_chain><item><author>TotoHorner</author><text>&gt; Why do most people seem to hold poetry and poets in high esteem yet have approximately zero interest in reading any poetry ever?<p>I&#x27;ve wondered this for years.<p>Like seriously, is there anyone who seriously reads poetry for fun nowadays?<p>I understand if it&#x27;s the 1800s and there&#x27;s literally nothing else to do.</text></item></parent_chain></comment><story><title>Things to argue about over the holidays instead of politics</title><url>https://dynomight.net/arguments/</url></story> |
13,683,736 | 13,683,442 | 1 | 3 | 13,683,017 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>trome</author><text>This kernel brings nearly full support (excluding Mali support) for Allwinner H3 based boards, and adds A64 support. I compiled 4.10-rc6 for my OrangePi a few days ago, and HDMI, audio, NAND flash, gigabit, wifi and everything else I tested worked well.<p>Finally got a super cheap version of a BeagleBone Black with the OrangePi Zero ($7), and with the OrangePi PC+ you get a board with a gig of ram and 8GB of fast eMMC for under $20.<p>Hopefully the H5 based boards and Arm64 in general will get better support, been having trouble getting NodeJS 6 or 7 running on aarch64 short of compiling it myself :(<p>Edit: Also FriendlyARM has a couple fun H3 based boards with the Nanopi Neo and a few others, might wanna look at those too!</text><parent_chain></parent_chain></comment><story><title>Linux 4.10 is out</title><url>https://lwn.net/Articles/714943/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>Zpalmtree</author><text>Hopefully the improved writeback management will mean my music doesn&#x27;t start cutting out while I copy a huge file.</text><parent_chain></parent_chain></comment><story><title>Linux 4.10 is out</title><url>https://lwn.net/Articles/714943/</url></story> |
28,997,102 | 28,996,926 | 1 | 2 | 28,995,840 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>sofixa</author><text>What are you talking about civil and military police in &quot;continental Europe&quot;? In most countries there&#x27;s a military police which polices the military, a police which polices regular peope, sometimes a gendermerie which is sometimes nominally a part of the army under civilian control, and which is either for policing the countryside - France or for riot control&#x2F;backup and special cases (e.g. a football match that requires lots of police) - most of Eastern Europe. In the latter case they&#x27;re sometimes more hevily armed, but not even close to US police. And idepedently of those there are special heavy units for counterterrorism stuff and similar (akin to US SWAT), which can be a part of either entity - in France there&#x27;s one at both and they work together. But they&#x27;re deployed only in very specific and heavy cases.<p>In any case, the problems with policing in Europe aren&#x27;t even close to those in the US, and i don&#x27;t think any of then can be attributed to hving two policing entities with different scopes.</text><parent_chain><item><author>brigandish</author><text>&gt; As they handcuffed him, his 9-year-old daughter cried in terror<p>The police in America are well beyond the line of &quot;citizen&quot; police, you have the continental European model of two police forces, civil and military, and it&#x27;s hard to see that there&#x27;s much civil, it&#x27;s more like ordinarily armed military force and a ready-for-war military force. It hasn&#x27;t helped produce liberty or better enforcement in Europe, I can&#x27;t see why Americans have allowed it to become their model.<p>This discussion about no-knock warrants&#x2F;raids[1] has a similar feel, an offence against common law, liberty, and above all, good sense.<p>&gt; I was in my boxer shorts when I heard my mother‐ in‐ law scream. It was a loud, fearful scream. I ran to the window, where I saw three or four men dressed in black with high‐ caliber rifles in my yard approaching my house.<p>&gt; I then heard an explosion, which was the sound of my door being blown open, followed by immediate gun fire. There were loud noises, the sounds of boots, and then more gunfire.<p>&gt; I hit the floor and began to yell, “I’m upstairs; please don’t shoot!” The men in black had me walk downstairs backwards, in my boxer shorts, with my hands in the air. I still can see two high‐ caliber rifles pointed at me. At the bottom of the stairs, they bound my hands, pulled me across the living room, and forced me to kneel on the floor in front of my broken door. I thought it was a home invasion. I was fearful that I was about to be executed.<p>&gt; I could see my mother‐ in‐ law bound, lying face down on the kitchen floor. Payton, my older dog, was lying dead in a pool of his own blood on the other side of the living room. I soon learned that my younger dog, Chase, was dead in a back room, where he had been shot from behind as he ran away. There were perhaps a dozen men in black, just standing around in my living room. I asked for a warrant. They said that they did not have it with them, but one was en route.<p>&gt; For most of the nearly four‐ hour ordeal, I was being interrogated, half‐ dressed in my living room and then in my kitchen. It was surreal.<p>If it can happen to a mayor it can happen to anyone.<p>[1] <a href="https:&#x2F;&#x2F;www.cato.org&#x2F;policy-report&#x2F;november&#x2F;december-2008&#x2F;should-no-knock-police-raids-be-rare-or-routine" rel="nofollow">https:&#x2F;&#x2F;www.cato.org&#x2F;policy-report&#x2F;november&#x2F;december-2008&#x2F;sh...</a><p>Edit: formatting</text></item></parent_chain></comment><story><title>FBI raids researcher who discovered private patient data on public server (2016)</title><url>https://www.dailydot.com/debug/justin-shafer-fbi-raid/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>__m</author><text>This sounds more like the American model. In Germany for example the SEK was formed after SWAT, in response to a terror attack in Munich. Unless there is some serious crime, where guns are involved, the judge won’t send a special unit. Pictures of guns drawn on unarmed people seem to be mostly coming from the US.</text><parent_chain><item><author>brigandish</author><text>&gt; As they handcuffed him, his 9-year-old daughter cried in terror<p>The police in America are well beyond the line of &quot;citizen&quot; police, you have the continental European model of two police forces, civil and military, and it&#x27;s hard to see that there&#x27;s much civil, it&#x27;s more like ordinarily armed military force and a ready-for-war military force. It hasn&#x27;t helped produce liberty or better enforcement in Europe, I can&#x27;t see why Americans have allowed it to become their model.<p>This discussion about no-knock warrants&#x2F;raids[1] has a similar feel, an offence against common law, liberty, and above all, good sense.<p>&gt; I was in my boxer shorts when I heard my mother‐ in‐ law scream. It was a loud, fearful scream. I ran to the window, where I saw three or four men dressed in black with high‐ caliber rifles in my yard approaching my house.<p>&gt; I then heard an explosion, which was the sound of my door being blown open, followed by immediate gun fire. There were loud noises, the sounds of boots, and then more gunfire.<p>&gt; I hit the floor and began to yell, “I’m upstairs; please don’t shoot!” The men in black had me walk downstairs backwards, in my boxer shorts, with my hands in the air. I still can see two high‐ caliber rifles pointed at me. At the bottom of the stairs, they bound my hands, pulled me across the living room, and forced me to kneel on the floor in front of my broken door. I thought it was a home invasion. I was fearful that I was about to be executed.<p>&gt; I could see my mother‐ in‐ law bound, lying face down on the kitchen floor. Payton, my older dog, was lying dead in a pool of his own blood on the other side of the living room. I soon learned that my younger dog, Chase, was dead in a back room, where he had been shot from behind as he ran away. There were perhaps a dozen men in black, just standing around in my living room. I asked for a warrant. They said that they did not have it with them, but one was en route.<p>&gt; For most of the nearly four‐ hour ordeal, I was being interrogated, half‐ dressed in my living room and then in my kitchen. It was surreal.<p>If it can happen to a mayor it can happen to anyone.<p>[1] <a href="https:&#x2F;&#x2F;www.cato.org&#x2F;policy-report&#x2F;november&#x2F;december-2008&#x2F;should-no-knock-police-raids-be-rare-or-routine" rel="nofollow">https:&#x2F;&#x2F;www.cato.org&#x2F;policy-report&#x2F;november&#x2F;december-2008&#x2F;sh...</a><p>Edit: formatting</text></item></parent_chain></comment><story><title>FBI raids researcher who discovered private patient data on public server (2016)</title><url>https://www.dailydot.com/debug/justin-shafer-fbi-raid/</url></story> |
29,526,207 | 29,526,301 | 1 | 2 | 29,525,436 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>SECProto</author><text>&gt; So if you&#x27;re not in the habit of turning on the local station because of crappy programming (like me), then you should at least be willing to find a local station during weather.<p>How would I even go about doing that? The only display devices I have are monitors. Even for radio, I would have to go to my car to listen.</text><parent_chain><item><author>dylan604</author><text>&gt;The fall of TV<p>You mean in your daily in-take of media? Local TV stations are required to broadcast weather. It&#x27;s actually part of their licensing. So if you&#x27;re not in the habit of turning on the local station because of crappy programming (like me), then you should at least be willing to find a local station during weather. Even if regular programming is on, they will break in when requested by the NWS. Local radio will as well, but I can&#x27;t remember the last time I heard Clearcom or whatever the othe station owner is do this. I just don&#x27;t listen to radio.<p>Also, most local stations will also be running live webcasts to FB&#x2F;YT&#x2F;etc. They do this in order to avoid interrupting programming until it is urgent enough to do so.<p>I&#x27;m in North Texas, and during severe weather season, I have a web browser permantely tuned to the radar. If it&#x27;s getting bad, I&#x27;ll find a local station.<p>&gt; I imagine if nuclear armageddon ever happens, it&#x27;ll be similar<p>If you&#x27;re in Hawaii, you&#x27;ll get a text.</text></item><item><author>sillysaurusx</author><text>I slept through three tornado sirens last night. It was pretty wild. The first one, I thought it was a test. (We have tests every month on the 1st.) But it wasn&#x27;t until a few minutes in that I realized it was for real.<p>Then apparently I just... went to sleep? That wasn&#x27;t the smartest decision I&#x27;ve ever made. It went off a couple more times.<p>One strange thing was the realization that I had no idea where to turn for information. The fall of TV means that in a situation like that, there isn&#x27;t any &quot;tune to your local TV station&quot; type broadcast. All you get is a tornado siren.<p>I imagine if nuclear armageddon ever happens, it&#x27;ll be similar. Though at least with that, there&#x27;ll be some information channel to turn to.</text></item></parent_chain></comment><story><title>Six dead after tornadoes destroy Amazon warehouse near St Louis</title><url>https://www.reuters.com/world/us/injuries-reported-after-roof-collapse-amazon-warehouse-illinois-ap-2021-12-11/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>wsh</author><text><i>&gt; Local TV stations are required to broadcast weather.</i><p>Television stations in the U.S. are required, in a broad sense, to serve their local communities, and many choose to do so by providing weather forecasts and alerts, but I don’t know of any law or regulation that <i>requires</i> broadcasters to provide weather information, in emergencies or at all.<p>Stations do have to participate in the Emergency Alert System, but they don’t have to transmit anything other than the required tests and an Emergency Action Notification for a national emergency. (See 47 CFR 11.52(d)(4).)<p>The better source for tornado and other warnings is NOAA Weather Radio (<a href="https:&#x2F;&#x2F;www.weather.gov&#x2F;nwr&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.weather.gov&#x2F;nwr&#x2F;</a>), a network of dedicated FM stations transmitting in the 162 MHz band. Receivers are widely available and can be programmed to turn on only when a warning for a specific area is broadcast.</text><parent_chain><item><author>dylan604</author><text>&gt;The fall of TV<p>You mean in your daily in-take of media? Local TV stations are required to broadcast weather. It&#x27;s actually part of their licensing. So if you&#x27;re not in the habit of turning on the local station because of crappy programming (like me), then you should at least be willing to find a local station during weather. Even if regular programming is on, they will break in when requested by the NWS. Local radio will as well, but I can&#x27;t remember the last time I heard Clearcom or whatever the othe station owner is do this. I just don&#x27;t listen to radio.<p>Also, most local stations will also be running live webcasts to FB&#x2F;YT&#x2F;etc. They do this in order to avoid interrupting programming until it is urgent enough to do so.<p>I&#x27;m in North Texas, and during severe weather season, I have a web browser permantely tuned to the radar. If it&#x27;s getting bad, I&#x27;ll find a local station.<p>&gt; I imagine if nuclear armageddon ever happens, it&#x27;ll be similar<p>If you&#x27;re in Hawaii, you&#x27;ll get a text.</text></item><item><author>sillysaurusx</author><text>I slept through three tornado sirens last night. It was pretty wild. The first one, I thought it was a test. (We have tests every month on the 1st.) But it wasn&#x27;t until a few minutes in that I realized it was for real.<p>Then apparently I just... went to sleep? That wasn&#x27;t the smartest decision I&#x27;ve ever made. It went off a couple more times.<p>One strange thing was the realization that I had no idea where to turn for information. The fall of TV means that in a situation like that, there isn&#x27;t any &quot;tune to your local TV station&quot; type broadcast. All you get is a tornado siren.<p>I imagine if nuclear armageddon ever happens, it&#x27;ll be similar. Though at least with that, there&#x27;ll be some information channel to turn to.</text></item></parent_chain></comment><story><title>Six dead after tornadoes destroy Amazon warehouse near St Louis</title><url>https://www.reuters.com/world/us/injuries-reported-after-roof-collapse-amazon-warehouse-illinois-ap-2021-12-11/</url></story> |
18,261,171 | 18,259,694 | 1 | 3 | 18,258,971 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>redmattred</author><text>One potential idea is a &quot;pay it forward&quot; model where you&#x27;re asked to pay for someone else using the service, but only after you have successfully found a job.<p>When a job seeker signs up they would see that their subscription was paid by someone else and it will instantly build goodwill&#x2F;stickiness for the product.<p>It&#x27;s generally hard to monetize from job seekers since they don&#x27;t have an income in many cases, but many would be happy to once they land a job and may even choose to buy a subscription for personal friends&#x2F;family who are looking for a job. Similarly companies could also pay to buy X # of subscriptions for job seekers to attract people to their jobs and build goodwill&#x2F;positive employment branding.<p>Could make for a good viral loop, could drum up some great PR, and help a lot of people</text><parent_chain><item><author>WestCoastJustin</author><text>How do you plan on making money? My concern would be that you need to be extremely upfront about what data you&#x27;re collecting and if you&#x27;re selling it back to these companies whom the person interviewed with (even if anonymized). This is a <i>very</i> personal exchange between an employee and employer that could have significant impact on employment negotiations. For example, I might not want employer A, knowing that I&#x27;m also interviewing with employer B&#x2F;C&#x2F;D, unless I choose to use it for negotiation. This could be used to target folks into lower paying jobs if they don&#x27;t have prospects, multiple offers, etc.<p>I&#x27;m not trying to be harsh here or blow up your idea. Maybe it&#x27;s a totally free app. I&#x27;m not sure. But, if you are selling user data, you could be inadvertently increasing companies bargaining power through hidden knowledge of what someone is doing too. If a company uses this added data on me, and gets me to take an offer that&#x27;s 30k less per year, and I stay there 4 years, that ends up costing me 120k over 4 years (30k*4y) all for using an interview note taking app.</text></item></parent_chain></comment><story><title>Show HN: Applying for jobs? Manage all your interviews in one place</title><url>https://afterinterview.com/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>Malic</author><text>Honestly, if this were to take off, I could see Microsoft&#x2F;LinkedIn having some acquisition interest.</text><parent_chain><item><author>WestCoastJustin</author><text>How do you plan on making money? My concern would be that you need to be extremely upfront about what data you&#x27;re collecting and if you&#x27;re selling it back to these companies whom the person interviewed with (even if anonymized). This is a <i>very</i> personal exchange between an employee and employer that could have significant impact on employment negotiations. For example, I might not want employer A, knowing that I&#x27;m also interviewing with employer B&#x2F;C&#x2F;D, unless I choose to use it for negotiation. This could be used to target folks into lower paying jobs if they don&#x27;t have prospects, multiple offers, etc.<p>I&#x27;m not trying to be harsh here or blow up your idea. Maybe it&#x27;s a totally free app. I&#x27;m not sure. But, if you are selling user data, you could be inadvertently increasing companies bargaining power through hidden knowledge of what someone is doing too. If a company uses this added data on me, and gets me to take an offer that&#x27;s 30k less per year, and I stay there 4 years, that ends up costing me 120k over 4 years (30k*4y) all for using an interview note taking app.</text></item></parent_chain></comment><story><title>Show HN: Applying for jobs? Manage all your interviews in one place</title><url>https://afterinterview.com/</url></story> |
34,614,912 | 34,615,143 | 1 | 2 | 34,613,039 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>phawksworth</author><text>[Disclaimer: I work in the Netlify DX team]<p>I recognize that fear. And have made similar observations of the current landscape.<p>Our hope in this instance is actually that the opposite is true.<p>The goal of this acquisition is not to OWN a JavaScript framework. Gatsby Inc is far bigger than Gatsby.js<p>The Gatsby.js project will join the Solid.js and Eleventy open source projects that Netlify already support through full time employment but who&#x27;s roadmaps and operations are their own. Using those tools is not a means for Netlify to funnel developers into our platform, nor a means to attempt to lock users in. Our philosophy is that an abundance and variety of such tools is good for the web (and as a result good for us). Also that more tools will come in future and that we&#x27;d like to try to provide the best experience and support for whatever those might be down the line. We can&#x27;t own it all. We&#x27;d prefer to support it.<p>Meanwhile, Gatsby Inc have created very powerful build and content orchestration tooling which is currently only available to Gatsby.js users. This acquisition will result in those capabilities being made available to any frameworks further helping all comers to the frameworks landscape.</text><parent_chain><item><author>joshmanders</author><text>Vercel has Next.js, Shopify just acquired Remix, now Netlify Gatsby.<p>This is bad news for full stack JavaScript applications and ecosystem. This is gonna cause vendor lock-in, it&#x27;s already showing in some of them. Open source is losing and something needs to change.<p>I am seeing a future where you have to rewrite your whole app in a different framework just to change hosts.</text></item></parent_chain></comment><story><title>Netlify acquires Gatsby</title><url>https://www.netlify.com/press/netlify-acquires-gatsby-inc-to-accelerate-adoption-of-composable-web-architectures/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>ascorbic</author><text>I work at Netlify on framework integrations.<p>We plan to do the exact opposite. Right now there are features in Gatsby that were built to support only Gatsby Cloud. I know this all too well as I had to reverse engineer them to implement them on Netlify! We don&#x27;t want that anymore. I am hoping that Gatsby will be like SvelteKit, Remix, Astro, Nuxt etc and will be platform agnostic again. Whether that&#x27;s via an adapter pattern (my preference) or something else remains to be seen. This acquisition was not about controlling a framework, just as we don&#x27;t attempt to control SolidJS or 11ty now.</text><parent_chain><item><author>joshmanders</author><text>Vercel has Next.js, Shopify just acquired Remix, now Netlify Gatsby.<p>This is bad news for full stack JavaScript applications and ecosystem. This is gonna cause vendor lock-in, it&#x27;s already showing in some of them. Open source is losing and something needs to change.<p>I am seeing a future where you have to rewrite your whole app in a different framework just to change hosts.</text></item></parent_chain></comment><story><title>Netlify acquires Gatsby</title><url>https://www.netlify.com/press/netlify-acquires-gatsby-inc-to-accelerate-adoption-of-composable-web-architectures/</url></story> |
24,474,793 | 24,474,047 | 1 | 2 | 24,472,061 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>mariushn</author><text>First, thanks for providing the `npm install` way to run it. Too many apps require Docker and that&#x27;s it.<p>Question: Could we use Grouparoo to replace mixpanel? Would we need to build the client side to collect events and dump that into Grouparoo?</text><parent_chain><item><author>bleonard</author><text>Thanks for checking us out! Co-founder here, happy to answer any questions. There is so much to do in this space, but we’re excited to be getting started.<p>No engineer wakes up in the morning excited to sync data to Marketo, so we started there - `npm install` and so you can get back to building the core product. We make data self-serve for your non-technical colleagues and we handle all the exhausting integration stuff you don’t want to think about (API nuances, rate limiting, retrying, batching, etc).</text></item></parent_chain></comment><story><title>Grouparoo: Open-source app to sync customer data with 3rd party tools</title><url>https://www.grouparoo.com</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>brainbag</author><text>How does this differ from something like Stitch (other than being open source)? We are in the planning stages of a data warehouse upgrade and Stitch seems to fit our needs, but your product looks great. I&#x27;m curious how it compares.</text><parent_chain><item><author>bleonard</author><text>Thanks for checking us out! Co-founder here, happy to answer any questions. There is so much to do in this space, but we’re excited to be getting started.<p>No engineer wakes up in the morning excited to sync data to Marketo, so we started there - `npm install` and so you can get back to building the core product. We make data self-serve for your non-technical colleagues and we handle all the exhausting integration stuff you don’t want to think about (API nuances, rate limiting, retrying, batching, etc).</text></item></parent_chain></comment><story><title>Grouparoo: Open-source app to sync customer data with 3rd party tools</title><url>https://www.grouparoo.com</url></story> |
11,910,062 | 11,907,370 | 1 | 2 | 11,907,060 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>ianmiers</author><text>This is something Apple really needs to release all the details of. Even if they got the crypto exactly right, they could have picked a privacy budget&#x2F; security parameters that just leaks everything.<p>And there is every reason to be skeptical about Apple&#x27;s ability to design even mildly complex crypto given iMessage&#x27;s flaws. Although the break in iMessage wasn&#x27;t practically exploitable, that was luck and the fact that the only way to detect if a mulled ciphertext decrypted required attachment messages. The cryptographic mistakes were bad. Given any way to detect decryption of mulled ciphertexts for standard messages (e.g. sequence numbers, timing, actively synching messages between devices, delivery receipts from iMessage instead of APSD), Apple&#x27;s crypto design bugs would have eliminated nearly all of the E2E security of iMessage.<p>Remember, this isn&#x27;t a boon for user privacy. Apple is now collecting far more invasive data about users under the claim that they have protections in place. At best it preserves the status quo and does so only if Apple both picked the parameters correctly and implemented it correctly.<p>At this point Apple&#x27;s position should be best summed up as: we have drastically reduced your privacy except not because magic that we (i.e. Apple) do not fully understand.</text><parent_chain></parent_chain></comment><story><title>What is Differential Privacy?</title><url>http://blog.cryptographyengineering.com/2016/06/what-is-differential-privacy.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>bo1024</author><text>I&#x27;ve read a couple articles and haven&#x27;t seen any details about how they&#x27;re going to apply DP (differential privacy).<p>It&#x27;s important to clearly distinguish what DP can and cannot do. DP is just a technique for taking a database and outputting some statistic or fact about it. The output has some noise added to it.<p>The guarantee of DP is (roughly) that anyone looking at the output alone won&#x27;t learn much about anyone in the database. This also holds for anything you do with that statistic.<p>Think about this carefully when thinking about what DP does and doesn&#x27;t promise. Also think about the difference between &quot;privacy&quot; and &quot;security&quot;.<p>Example of what DP does protect against: If Apple is recommending products to people based on others&#x27; download habits, and this recommendation is based on differentially private statistics, then no other user or group of users can infer anything about my downloads. In fact, even engineers at Apple, if they can only see the statistics and not the original database, cannot infer anything about my downloads.<p>Example of what DP does not protect against: government accessing the data. The database still has to exist on Apple&#x27;s servers. The government can get to it just as easily as before via warrants or so on. DP is not cryptography.<p>My assessment: On one hand it is awesome that Apple is taking a lead in using differential privacy and thinking about mathematical approaches to privacy. On the other, there are many facets of privacy and right now I think people are more concerned about <i>security</i> of their data and privacy from the government, or else privacy from companies like Apple itself. DP doesn&#x27;t address these; it only addresses the case where Apple has a bunch of data and wants the algorithms it runs not to leak much info about that data to the world at large.</text><parent_chain></parent_chain></comment><story><title>What is Differential Privacy?</title><url>http://blog.cryptographyengineering.com/2016/06/what-is-differential-privacy.html</url></story> |
12,920,813 | 12,920,843 | 1 | 2 | 12,920,496 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>Inconel</author><text>The article starts off stating that Hillary Clinton was the choice of nearly every newspaper editorial review board, and that despite those endorsements it didn&#x27;t matter. Does anyone else find this incredibly tone deaf, particularly after last night&#x27;s results?<p>To be clear, I did not vote for Trump, but my rejection of his candidacy was certainly not based on the stance of the LA Times editorial board. To be honest, with the amount of biased and sloppy journalism I read from even the venerated newspapers like the LA and NY Times, I&#x27;m not sure why the author assumes anyone should listen to the suggestions of their respective editorial boards.</text><parent_chain></parent_chain></comment><story><title>Some in Silicon Valley wonder if Facebook has grown too influential</title><url>http://www.latimes.com/business/la-fi-election-media-20161109-story.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>onewaystreet</author><text>This fear is rooted in a continued misunderstanding of the election result by people in tech. Voters didn&#x27;t vote for Trump because they read some fake news story on Facebook, they voted for him out of economic desperation. They weren&#x27;t tricked or mislead into it.</text><parent_chain></parent_chain></comment><story><title>Some in Silicon Valley wonder if Facebook has grown too influential</title><url>http://www.latimes.com/business/la-fi-election-media-20161109-story.html</url></story> |
1,298,872 | 1,298,744 | 1 | 2 | 1,298,541 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>slmbrhrt</author><text>You can add Unix Manpages to your "Subscribed Links" in your Google preferences, and then you <i>will</i> get your answer on the first try.</text><parent_chain><item><author>oakenshield</author><text>It's like people don't know about man pages anymore. Google is the man page... only you may not get your answer on the first try.</text></item></parent_chain></comment><story><title>How to kill an unresponsive ssh session</title><url>http://www.laszlo.nu/post/553591402/how-to-kill-an-unresponsive-ssh-session</url><text></text></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>yason</author><text>They do but nobody wants to memorize everything off some man page. There are thousands and generally, man pages are considered references where you dig up one thing at a time.<p>Then there are man pages that are actually being studied with great care, such as bash. And even bash man page is notorious for containing an endless amount of information. You can read it several times and still you will bump into a blog post or HN comment that reveals some previously missed (but documented) bash feature.<p>Telnet conveniently prints "Escape character is ^]" and that's why everybody knows it. I must admit it probably never occurred to me that ssh must have some sort of escaping method as well.<p>Well, thanks to HN for that link anyway :)</text><parent_chain><item><author>oakenshield</author><text>It's like people don't know about man pages anymore. Google is the man page... only you may not get your answer on the first try.</text></item></parent_chain></comment><story><title>How to kill an unresponsive ssh session</title><url>http://www.laszlo.nu/post/553591402/how-to-kill-an-unresponsive-ssh-session</url><text></text></story> |
7,917,579 | 7,917,518 | 1 | 2 | 7,916,911 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>notahacker</author><text>You can of course achieve the same &quot;the top guys at this growing company are sufficiently interested in me for this not to be an HR-lead timewaste&quot; effect with a senior non-recruiter email that&#x27;s actually honest, more along the lines of<p><i>My colleague Bob was impressed by your [personalised details]. I&#x27;ve asked Bob to look for people with X and our stack is based entirely on Y which I understand you&#x27;re very familiar with. If you&#x27;re interested in working on Z in future perhaps you and Bob could grab a quick coffee, and if that works out I&#x27;d love to have the chance to learn more about [personalised detail] for myself at some point.</i></text><parent_chain><item><author>Jemaclus</author><text>&gt; Always have the ping come from a non-recruiter.<p>I got an email a few days ago from the CEO of a startup in SF. In the email, he followed all of the rules in this email, including trying to get face-to-face chat by offering to get coffee. I&#x27;m not really looking for a job but I am open to new opportunities, so I replied and agreed to get coffee.<p>The response comes from a recruiter.<p>What? The CEO sends me an email and then hands my response off to a recruiter? Or did the recruiter send the email on behalf of the CEO? I&#x27;m not even sure what&#x27;s going on, but it&#x27;s incredibly misleading. And then when I respond and politely decline to proceed further, the recruiter tries to set me up with a phone call with yet another person that isn&#x27;t the original CEO.<p>What part of this makes sense? What happened to the original, informal face-to-face chat?<p>You totally blew it, dude. <i>YOU</i> contacted <i>me</i>, not the other way around. <i>You</i> have the burden of proof of attracting <i>me</i> to your company. <i>You</i> should be the one jumping through hoops, not me.<p>Would you do this bait-and-switch to your biggest customer? If the answer is yes, you probably don&#x27;t need to be CEO. And if not, then why would you treat a potential team member worse than you would treat your best customer? C&#x27;mon. Be smart about this recruiting thing.</text></item></parent_chain></comment><story><title>Startup advice: cold recruiting</title><url>https://stripe.com/blog/startup-advice-cold-recruiting</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>Ologn</author><text>&gt; YOU contacted me, not the other way around. You have the burden of proof of attracting me to your company. You should be the one jumping through hoops, not me.<p>Yes.<p>I get contacted by a headhunter that says they know of a company looking for engineers. I go on an interview and someone at the company asks me very officiously, &quot;Why do you want to work for this company?&quot; I respond, &quot;I don&#x27;t know that I do want to work here. I have a job. The headhunter called me and told me there was an opportunity here so I came to check it out&quot;. The interviewer didn&#x27;t say anything, but their expression was slightly shocked. I guess I was supposed to launch into a pitch about how it was always my dream to work at that company.<p>I think you put your finger on it. They present it to you as the CEO begging you to come work at the company. Then you start finding out it is a bait and switch, they want you to play the role of a desperate job seeker, begging some low-level manager for an opportunity to work at the company.<p>It&#x27;s a power thing. We see CEO&#x27;s here and in the tech news complain that they can&#x27;t find good technical talent. Yet every part of the job process is designed to demonstrate they have the power in the relationship from the offset. They want references - before you have a job offer often, they want you to ask a favor from two to three people to sing your praises to them. If you tell them you won&#x27;t give them references until it&#x27;s the last step before a job offer they look surprised. Or they just hand you a form to fill out, which will be incomplete if you don&#x27;t put references. They want you to come interview for hours in the middle of your work day. Often you get there and they tell you some important person who has to interview you to get the job is not there, and you have to come back again. You also have to go through the indignity of not being candid - if you want the job offer. When they ask you why you left your last company, that your boss was a jerk is not an acceptable answer. If they ask you about unit tests at your current job, and you say you have asked management to allow time for putting in unit tests but they refused - it becomes your fault that your management told you no. And on and on and on. That I have to ask for a favor from 2-3 former coworkers or bosses that they give me a reference every time I apply for a job is probably the most annoying part.<p>Who wants to go through all of this? It&#x27;s why a lot of my jobs are at companies my friends work for. At least I know the score before I go in.</text><parent_chain><item><author>Jemaclus</author><text>&gt; Always have the ping come from a non-recruiter.<p>I got an email a few days ago from the CEO of a startup in SF. In the email, he followed all of the rules in this email, including trying to get face-to-face chat by offering to get coffee. I&#x27;m not really looking for a job but I am open to new opportunities, so I replied and agreed to get coffee.<p>The response comes from a recruiter.<p>What? The CEO sends me an email and then hands my response off to a recruiter? Or did the recruiter send the email on behalf of the CEO? I&#x27;m not even sure what&#x27;s going on, but it&#x27;s incredibly misleading. And then when I respond and politely decline to proceed further, the recruiter tries to set me up with a phone call with yet another person that isn&#x27;t the original CEO.<p>What part of this makes sense? What happened to the original, informal face-to-face chat?<p>You totally blew it, dude. <i>YOU</i> contacted <i>me</i>, not the other way around. <i>You</i> have the burden of proof of attracting <i>me</i> to your company. <i>You</i> should be the one jumping through hoops, not me.<p>Would you do this bait-and-switch to your biggest customer? If the answer is yes, you probably don&#x27;t need to be CEO. And if not, then why would you treat a potential team member worse than you would treat your best customer? C&#x27;mon. Be smart about this recruiting thing.</text></item></parent_chain></comment><story><title>Startup advice: cold recruiting</title><url>https://stripe.com/blog/startup-advice-cold-recruiting</url></story> |
26,171,356 | 26,170,871 | 1 | 2 | 26,165,809 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>yks</author><text>Often workers are perfectly capable and eager of Really Caring but then the company incentives and politics force them into Just A Job category. Especially when joining Big Tech not via acquihire.</text><parent_chain><item><author>JohnCarmack</author><text>I can certainly see a lot of parallels with Oculus &#x2F; Facebook.<p>Perhaps unusually, I actually wanted FB to impress itself more strongly on Oculus post acquisition because, frankly, Oculus was a bit of a mess. Instead, Oculus was given an enormous amount of freedom for many years.<p>Personally, nobody ever told me what to do, even though I was willing to &quot;shut up and soldier&quot; if necessary -- they bought that capability! Conversely, I couldn&#x27;t tell anyone what to do from my position; the important shots were always called when I wasn&#x27;t around. Some of that was on me for not being willing to relocate to HQ, but a lot of it was built into early Oculus DNA.<p>I could only lead by example and argument, and the arguments only took on weight after years of evidence accumulated. I could have taken a more traditional management position, but I would have hated it, so that&#x27;s also on me. The political dynamics never quite aligned with an optimal set of leadership personalities and beliefs where I would have had the best leverage, but there was progress, and I am reasonably happy and effective as a part time consultant today, seven years later.<p>Talking about &quot;entitled workers&quot; almost certainly derails the conversation. Perhaps a less charged framing that still captures some of the matter is the mixing of people who Really Care about their work with the Just A Job crowd. The wealth of the mega corps does allow most goals to be accomplished, at great expense, with Just A Job workers, but people that have experienced being embedded with Really Care workers are going to be appalled at the relative effectiveness.<p>The communication culture does tend a bit passive-aggressive for my taste, but I can see why it evolves that way in large organizations. I&#x27;ve only been officially dinged by HR once for insensitive language in a post, but a few people have reached out privately with some gentle suggestions about better communication.<p>All in all, not a perfect fairy tale outcome, but I still consider taking the acquisition offer as the correct thing for the company in hindsight.</text></item></parent_chain></comment><story><title>Why did I leave Google or, why did I stay so long?</title><url>https://paygo.media/p/25171</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>allenu</author><text>Thanks for sharing this. It just goes to show that even the best of us can find it difficult to effect change in a big company. The nature of a large organization is it requires lots of communication, alignment, and on-the-ground politics to make things happen, which is definitely a challenge for those of us who just want to get shit done.</text><parent_chain><item><author>JohnCarmack</author><text>I can certainly see a lot of parallels with Oculus &#x2F; Facebook.<p>Perhaps unusually, I actually wanted FB to impress itself more strongly on Oculus post acquisition because, frankly, Oculus was a bit of a mess. Instead, Oculus was given an enormous amount of freedom for many years.<p>Personally, nobody ever told me what to do, even though I was willing to &quot;shut up and soldier&quot; if necessary -- they bought that capability! Conversely, I couldn&#x27;t tell anyone what to do from my position; the important shots were always called when I wasn&#x27;t around. Some of that was on me for not being willing to relocate to HQ, but a lot of it was built into early Oculus DNA.<p>I could only lead by example and argument, and the arguments only took on weight after years of evidence accumulated. I could have taken a more traditional management position, but I would have hated it, so that&#x27;s also on me. The political dynamics never quite aligned with an optimal set of leadership personalities and beliefs where I would have had the best leverage, but there was progress, and I am reasonably happy and effective as a part time consultant today, seven years later.<p>Talking about &quot;entitled workers&quot; almost certainly derails the conversation. Perhaps a less charged framing that still captures some of the matter is the mixing of people who Really Care about their work with the Just A Job crowd. The wealth of the mega corps does allow most goals to be accomplished, at great expense, with Just A Job workers, but people that have experienced being embedded with Really Care workers are going to be appalled at the relative effectiveness.<p>The communication culture does tend a bit passive-aggressive for my taste, but I can see why it evolves that way in large organizations. I&#x27;ve only been officially dinged by HR once for insensitive language in a post, but a few people have reached out privately with some gentle suggestions about better communication.<p>All in all, not a perfect fairy tale outcome, but I still consider taking the acquisition offer as the correct thing for the company in hindsight.</text></item></parent_chain></comment><story><title>Why did I leave Google or, why did I stay so long?</title><url>https://paygo.media/p/25171</url></story> |
28,865,105 | 28,865,312 | 1 | 2 | 28,864,619 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>drcode</author><text>Putting together all the messaging I&#x27;ve gotten recently: Regular sunscreen is bad, zinc oxide sunscreen is bad, getting sun is bad, not getting sun is bad (Vitamin D).</text><parent_chain></parent_chain></comment><story><title>After two hours zinc oxide sunscreen loses effectiveness, becomes toxic: study</title><url>https://phys.org/news/2021-10-hours-sunscreen-zinc-oxide-effectiveness.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>markenqualitaet</author><text>What a horrible article, repeating the ever same superficial factoid in variation, without ever adding more info.<p>So apparently zinc oxide acts as a catalyst, which reacts with some sunscreen ingredients to form substances toxic to zebra fish, under laboratory conditions.<p>No qualitative analysis of what&#x27;s reacting with what? Which substances make the toxicity? Hardly worth anyone&#x27;s time at that point no?</text><parent_chain></parent_chain></comment><story><title>After two hours zinc oxide sunscreen loses effectiveness, becomes toxic: study</title><url>https://phys.org/news/2021-10-hours-sunscreen-zinc-oxide-effectiveness.html</url></story> |
36,404,360 | 36,404,654 | 1 | 2 | 36,401,999 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>gs17</author><text>&gt; Discord has [...] zero &quot;3rd party apps&quot;<p>Most people don&#x27;t want third party Reddit apps because they inherently like third party apps (some people do want FOSS apps, but that&#x27;s the minority). People largely want third party apps because the first party app is terrible.</text><parent_chain><item><author>avree</author><text>Discord has lower API limits and zero &quot;3rd party apps&quot; so the fact that it&#x27;s the recommended darling child of people fleeing reddit because of &quot;low API limits&quot; and &quot;them taking away 3rd party apps&quot; makes zero sense.<p>The &quot;Lemmy&quot; thing is even worse; a complete mess. For example, &#x2F;r&#x2F;aww has two different links, with different content, etc. And yes, I understand how the &quot;fediverse&quot; works, it just makes no sense in the context that most consumers want their media in.</text></item><item><author>haunter</author><text>I don&#x27;t get this list<p>&#x2F;r&#x2F;3DS is active and not moving. The Discord is there for years. The lemmy instance is not affiliated with the sub (and it has 0 activity compared to the sub)<p>The kbin AITA has only 2 posts from a week ago. While the main sub is still alive and active with thousands of comments on each posts<p>etc.<p>Feels like this a site for showing alternatives to the subs not &quot;where Reddit communities have relocated&quot; which is very misleading</text></item></parent_chain></comment><story><title>Sub.Rehab – See where Reddit communities have relocated</title><url>https://sub.rehab/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>revscat</author><text>I would politely remind you that people, myself included, are fully cognizant of everything you have said but are still switching away from Reddit. You may want to take a minute to think about why that is, without sarcasm or the presumption of stupidity.</text><parent_chain><item><author>avree</author><text>Discord has lower API limits and zero &quot;3rd party apps&quot; so the fact that it&#x27;s the recommended darling child of people fleeing reddit because of &quot;low API limits&quot; and &quot;them taking away 3rd party apps&quot; makes zero sense.<p>The &quot;Lemmy&quot; thing is even worse; a complete mess. For example, &#x2F;r&#x2F;aww has two different links, with different content, etc. And yes, I understand how the &quot;fediverse&quot; works, it just makes no sense in the context that most consumers want their media in.</text></item><item><author>haunter</author><text>I don&#x27;t get this list<p>&#x2F;r&#x2F;3DS is active and not moving. The Discord is there for years. The lemmy instance is not affiliated with the sub (and it has 0 activity compared to the sub)<p>The kbin AITA has only 2 posts from a week ago. While the main sub is still alive and active with thousands of comments on each posts<p>etc.<p>Feels like this a site for showing alternatives to the subs not &quot;where Reddit communities have relocated&quot; which is very misleading</text></item></parent_chain></comment><story><title>Sub.Rehab – See where Reddit communities have relocated</title><url>https://sub.rehab/</url></story> |
17,601,087 | 17,601,309 | 1 | 2 | 17,597,626 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>supertrope</author><text>Job seekers and those with medically needy relatives are among those who cannot tolerate any false positive especially if calls are entirely rejected and cannot even leave a voicemail.</text><parent_chain><item><author>r00fus</author><text>Not sure what carrier you&#x27;re using but T-Mobile in the US just released &quot;scam block&quot; ( I had &quot;scam ID&quot; turned on previously).<p>In addition to marking calls as scam, now they simply block them outright. Getting approximately 0 scam calls in the past 2 days.</text></item><item><author>anonymous5133</author><text>I think the problem has gotten so serious that the traditional voice-based phone system is pretty much unusable. I don&#x27;t even bother to answer the phone. Instead I have a voice mail message that tells people to send a text message instead. I can&#x27;t be the only one who does something like this or has some other system in place to not have to deal with robocalls&#x2F;scam callers.</text></item><item><author>jonathanmayer</author><text>I worked on countering phone scams and robocalls at the Federal Communications Commission for over a year. This operation was a big win and an impressive international collaboration.<p>That said, the robocall problem is getting worse, not better. Robocall volume is at an all-time high: <a href="https:&#x2F;&#x2F;robocallindex.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;robocallindex.com&#x2F;</a><p>In many respects, the problem of telephone spam today is similar to the problem of email spam in the early 2000s. Litigating against spammers had limited efficacy, so the community developed blacklists, better filtering, and stronger authentication (SPF, DKIM, and DMARC).<p>Until the major carriers get serious about similar steps, especially filtering and authentication (i.e. SHAKEN and STIR), these fraudulent calls won&#x27;t stop. And, in the interim, vulnerable populations will continue to be disproportionately victimized.</text></item></parent_chain></comment><story><title>US breaks up IRS phone scam operation</title><url>https://www.nytimes.com/2018/07/23/business/irs-phone-scams-jeff-sessions.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>kurthr</author><text>I hope it works... it&#x27;s kinda terrifying that getting no scam calls for 2 days is significant!<p>I have a test&#x2F;dev phone that I used for a project several years ago with an associated ph#. I forgot about it (don&#x27;t think about the charges accrued 8^) for several years, but just charged it and turned it on.<p>It&#x27;s a number that was never used or answered for 3 years and it gets several scam calls a day. They must be calling every valid number.</text><parent_chain><item><author>r00fus</author><text>Not sure what carrier you&#x27;re using but T-Mobile in the US just released &quot;scam block&quot; ( I had &quot;scam ID&quot; turned on previously).<p>In addition to marking calls as scam, now they simply block them outright. Getting approximately 0 scam calls in the past 2 days.</text></item><item><author>anonymous5133</author><text>I think the problem has gotten so serious that the traditional voice-based phone system is pretty much unusable. I don&#x27;t even bother to answer the phone. Instead I have a voice mail message that tells people to send a text message instead. I can&#x27;t be the only one who does something like this or has some other system in place to not have to deal with robocalls&#x2F;scam callers.</text></item><item><author>jonathanmayer</author><text>I worked on countering phone scams and robocalls at the Federal Communications Commission for over a year. This operation was a big win and an impressive international collaboration.<p>That said, the robocall problem is getting worse, not better. Robocall volume is at an all-time high: <a href="https:&#x2F;&#x2F;robocallindex.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;robocallindex.com&#x2F;</a><p>In many respects, the problem of telephone spam today is similar to the problem of email spam in the early 2000s. Litigating against spammers had limited efficacy, so the community developed blacklists, better filtering, and stronger authentication (SPF, DKIM, and DMARC).<p>Until the major carriers get serious about similar steps, especially filtering and authentication (i.e. SHAKEN and STIR), these fraudulent calls won&#x27;t stop. And, in the interim, vulnerable populations will continue to be disproportionately victimized.</text></item></parent_chain></comment><story><title>US breaks up IRS phone scam operation</title><url>https://www.nytimes.com/2018/07/23/business/irs-phone-scams-jeff-sessions.html</url></story> |
10,083,259 | 10,082,976 | 1 | 2 | 10,080,415 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>alephone</author><text>&quot;square matrices have as many eigenvectors as they have linearly independent dimensions; i.e. a 2 x 2 matrix would have two eigenvectors, a 3 x 3 matrix three, and an n x n matrix would have n eigenvectors, each one representing its line of action in one dimension.&quot;<p>This is not quite right. First of all, if v is an eigenvector of A, then a*v for any non-zero a is also an eigenvector of A, so it makes no sense to say &quot;there are n eigenvectors&quot;. Perhaps you meant to say n linearly independent eigenvectors?<p>But this is also not correct. An n x n matrix does not necessarily have to have n linearly independent eigenvectors; consider for instance A = [1, 1; 0, 1], which has dim N(A - I) = 1 (hence 1 linearly independent eigenvector). Basically, not every matrix is diagonalizable. This example also shows that rank(A) is also not necessarily equal to the number of linearly independent eigenvectors (is that what you meant by linearly independent dimensions?).<p>A more correct statement would be to say every symmetric matrix has n linearly independent eigenvectors (and its eigenvectors can be chosen to form an orthonormal basis for R^n).</text><parent_chain></parent_chain></comment><story><title>A Beginner’s Guide to Eigenvectors, Covariance, PCA and Entropy</title><url>http://deeplearning4j.org/eigenvector</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>tsumnia</author><text>You linked it on the bottom of the page, but how do you think the article compares with <a href="http:&#x2F;&#x2F;www.cs.otago.ac.nz&#x2F;cosc453&#x2F;student_tutorials&#x2F;principal_components.pdf" rel="nofollow">http:&#x2F;&#x2F;www.cs.otago.ac.nz&#x2F;cosc453&#x2F;student_tutorials&#x2F;principa...</a> ?<p>I&#x27;m planning to read through it a little more this weekend, but I remember using the PDF and a whiteboard back in the day to understand PCA.</text><parent_chain></parent_chain></comment><story><title>A Beginner’s Guide to Eigenvectors, Covariance, PCA and Entropy</title><url>http://deeplearning4j.org/eigenvector</url></story> |
8,437,038 | 8,436,716 | 1 | 3 | 8,436,309 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>zorbo</author><text>Text is the universal interface. You can do things with it. You can strip it, cut it, transform it, send it to other places. Humans can read it, programs can read it, your printer can output it. It can be sent to web APIs, it can be stored anywhere. It&#x27;s compressible, can be colored and can be copy-pasted and is infinitely extendable. Thousands of protocols run over it.<p>The command line works with text. The command line remains the best interface I&#x27;ve ever used. It&#x27;s user friendly, composable and available everywhere. It&#x27;s easy to automate and easy to extend.<p>I wish the &quot;command line with pictures&quot; idea would just go away already. It adds nothing for the general public. I can already view pictures on remote machines with X forwarding.<p>Command line with pictures never made it, because there are ten competing standards. With text, everybody just agreed on ASCII and now Unicode&#x2F;UTF8. Text has hundreds of ugly clutches on top of it (Extended ASCII, ANSI, Escape codes, etc, etc). It still works. It&#x27;s still simple. It has its problems, but nowhere near as many problems as GUIs.<p>Those who don&#x27;t understand Unix are doomed to reimplement it... poorly.</text><parent_chain></parent_chain></comment><story><title>Rich Command Shells</title><url>http://waywardmonkeys.org/2014/10/10/rich-command-shells/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>tubelite</author><text>If I might plug a rich command shell I&#x27;m developing: <a href="http://pigshell.com" rel="nofollow">http:&#x2F;&#x2F;pigshell.com</a> (Source at <a href="https://github.com/pigshell/pigshell" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;pigshell&#x2F;pigshell</a>)<p>It provides<p>- A shell for the web. Runs in the browser, pure client-side.<p>- File-like abstraction for URLs and other entities exposed by web APIs<p>- Unix-like style of composing commands using pipes.<p>- Visualization using HTML<p>For instance, cp -r &#x2F;gdrive&#x2F;&lt;username&gt; &#x2F;home will backup the contents of your Google Drive to your desktop (see <a href="http://pigshell.com/v/0.6.2/doc/gdrive.html" rel="nofollow">http:&#x2F;&#x2F;pigshell.com&#x2F;v&#x2F;0.6.2&#x2F;doc&#x2F;gdrive.html</a> for details). Replace &#x2F;home with &#x2F;dropbox&#x2F;&lt;username&gt;, and the same command will back up GDrive to Dropbox. And so on.<p>While it is already useful, there is still some work, especially around hardening the file abstraction&#x2F;APIs (and reams of documentation) before before it can be horizontally expanded to support a bunch more APIs and cloud stores. I am actively working on these and expect they&#x27;ll take ~2 months.</text><parent_chain></parent_chain></comment><story><title>Rich Command Shells</title><url>http://waywardmonkeys.org/2014/10/10/rich-command-shells/</url></story> |
23,922,742 | 23,919,878 | 1 | 2 | 23,919,579 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>throwawaygh</author><text>These articles are essentially an instance of the fallacy that all labor is equivalent.<p>If you are self-motivated and intelligent enough to learn the equivalent of a CS degree on your own, then the upper bound on your career trajectory is often significantly higher than &quot;senior software engineer&quot;.<p>So even if you can self-learn, the article is still bad advice. Better advice would be &quot;if you can learn this on your own, maybe aim higher than code monkey jobs&quot;.<p>Go ahead and major in CS because it&#x27;ll be easy and enjoyable and a good fallback. But also pick up a second major in pre-med&#x2F;pre-law&#x2F;econ&#x2F;finance&#x2F;engineering&#x2F;etc. Or get involved in research projects, etc.<p>So, yes, this is bad advice for weak students. But it&#x27;s <i>also</i> often bad advice for strong students, who should be aiming high.</text><parent_chain><item><author>kstrauser</author><text>I think the biggest disadvantage of a DIY degree is that there&#x27;s no one requiring you to take classes that don&#x27;t interest you. Thing is, when I was studying, I was grossly incorrect about 1) which classes I would come to enjoy, and 2) which subjects I would actually use every day at work. There were lots of things I studied only because someone was making me, but that I found to be incredibly fascinating or useful once I had learned a little about them.<p>That&#x27;s the biggest thing I think someone would give up by not pursuing a traditional degree.</text></item></parent_chain></comment><story><title>Consider getting a “DIY” degree online instead of a traditional CS major</title><url>https://www.pashabitz.com/posts/undergrad-altenative/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>ocdtrekkie</author><text>In my view, the two college topics everyone should take is Physics and Constitutional Law (or equivalent in another country). Both will literally radically change how you look at the world, and provide a foundational basis for conversation in nearly any field.</text><parent_chain><item><author>kstrauser</author><text>I think the biggest disadvantage of a DIY degree is that there&#x27;s no one requiring you to take classes that don&#x27;t interest you. Thing is, when I was studying, I was grossly incorrect about 1) which classes I would come to enjoy, and 2) which subjects I would actually use every day at work. There were lots of things I studied only because someone was making me, but that I found to be incredibly fascinating or useful once I had learned a little about them.<p>That&#x27;s the biggest thing I think someone would give up by not pursuing a traditional degree.</text></item></parent_chain></comment><story><title>Consider getting a “DIY” degree online instead of a traditional CS major</title><url>https://www.pashabitz.com/posts/undergrad-altenative/</url></story> |
27,584,719 | 27,584,854 | 1 | 2 | 27,580,744 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>nightski</author><text>It&#x27;s interesting that an academic conference now feels like a marketing op for industrial research labs more than anything. His claims about how accurate their vision system is and how it is exceeding other sensors is not verifiable in any way to the public. Given how well qualified he is I am sure he is not wrong! Andrej is brilliant. But this is an academic conference right? This isn&#x27;t open science, it&#x27;s a discussion about an engineered system. I&#x27;m afraid this is the future of ML research (which CV is so heavily dependent on now). Long gone are the days of reading a paper and understanding the approach. Now you need the data and model which may not even be computationally feasible without millions of dollars in hardware. This isn&#x27;t Tesla&#x27;s fault or anything, it just makes me sad.</text><parent_chain></parent_chain></comment><story><title>Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles [video]</title><url>https://www.youtube.com/watch?v=eOL_rCK59ZI&t=28293s</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>Robotbeat</author><text>He made a very good argument for vision-only, but it seems like training actually uses radar data to help calibrate vision measurements, so it seems to me there’s value in making some vehicles still contain radar (say, one out of 10) even if it’s not used for controlling the vehicle directly at drive time.<p>Also, the sensor resolution issue he mentioned could be addressed by using a higher resolution radar sensor.<p>I find the list of 221 triggers to be interesting. In principle, the NHTSA or NTSB could help contribute lists of triggers to companies to validate their training sets on.<p>Every time there is a fatal airliner accident, the NTSB does a safety investigation and airliners get a little bit safer each time. In the same way, each fatal accident in a vehicle with this kind of autonomy could end up being captured by these triggers, improving safety over time in a sort of mixture between expert human analysis and ML.<p>(Nobody does this for all regular car crashes because fatal car crashes happen every day! And you’re not going to retrain human drivers about some new edge case every day, although you can for vehicles like this.)</text><parent_chain></parent_chain></comment><story><title>Andrej Karpathy (Tesla): CVPR 2021 Workshop on Autonomous Vehicles [video]</title><url>https://www.youtube.com/watch?v=eOL_rCK59ZI&t=28293s</url></story> |
22,533,402 | 22,532,193 | 1 | 3 | 22,529,670 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>zelphirkalt</author><text>As the EU is mostly only its parts and everyone now in alert, I highly doubt it. Everyone is keeping their medical items to themselves now, because there is not even sufficient for their own country. EU will mostly be talk.</text><parent_chain><item><author>paganel</author><text>I hope (and suspect) that the ECB (and Europe as a whole) will financially stand behind Italy, no questions asked (I&#x27;m a fellow European).</text></item><item><author>fosk</author><text>Italy is a country of 60M+ people and the 8th largest economy in the world, with a very high national debt and that significantly relies on tourism for its economy. Above and beyond the Coronavirus, this can terribly affect the long-term solvency of the country.</text></item></parent_chain></comment><story><title>Italy is extending its coronavirus quarantine measures to the entire country</title><url>https://www.bbc.com/news/world-europe-51810673</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>luckydata</author><text>Allow me to doubt this until I see it become reality. The European government has been less than helpful to Italy throughout its history.</text><parent_chain><item><author>paganel</author><text>I hope (and suspect) that the ECB (and Europe as a whole) will financially stand behind Italy, no questions asked (I&#x27;m a fellow European).</text></item><item><author>fosk</author><text>Italy is a country of 60M+ people and the 8th largest economy in the world, with a very high national debt and that significantly relies on tourism for its economy. Above and beyond the Coronavirus, this can terribly affect the long-term solvency of the country.</text></item></parent_chain></comment><story><title>Italy is extending its coronavirus quarantine measures to the entire country</title><url>https://www.bbc.com/news/world-europe-51810673</url></story> |
9,054,065 | 9,053,811 | 1 | 3 | 9,053,621 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>x0n</author><text>&quot;We noticed the hot wallets dwindling but assuming it was members moving their funds off site during the DDOS, we loaded all the cold balances onto the site so that users would not have withdrawals interrupted during our periods of up time.This fatal mistake allowed Ambiorx to continue to drain the site.&quot; -- World&#x27;s stupidest bitcoin exchange admins, or some of the ballsiest? Inside job?</text><parent_chain></parent_chain></comment><story><title>Excoin exchange's Bitcoins stolen, will be shutting down</title><url>https://exco.in/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>akerl_</author><text>&quot;We noticed the hot wallets dwindling but assuming it was members moving their funds off site during the DDOS, we loaded all the cold balances onto the site&quot;<p>I&#x27;m a bit shocked that their tracking of their transactions was so easily broken as to prevent them from seeing that all the funds were being pulled by so few users.<p>Also, the part at the bottom where they basically post a wall of IPs and addresses seems like a weird way to move forward. Do they not plan on there being an official investigation?</text><parent_chain></parent_chain></comment><story><title>Excoin exchange's Bitcoins stolen, will be shutting down</title><url>https://exco.in/</url></story> |
13,663,061 | 13,661,742 | 1 | 2 | 13,661,218 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>openasocket</author><text>I hate to pile on to the complaints about sending usage metrics to a server, but this is pretty funky. The metrics include the instance id, account id, a list of the commands run with timestamps, the region, a bunch of metadata about the number of VPCs, Subnets, IAM users and policies, etc. Which is kind of a lot to get, and definitely isn&#x27;t anonymous. Why do they need to know how many VPCs, Subnets, IAM users, and IAM roles I have?<p>Then there&#x27;s how the data is sent. The metrics are converted to JSON, gzipped, then AES encrypted with a random key. The random key is then encrypted with a constant public key. the encrypted key and encrypted payload are serialized into some JSON, and is then POST-ed to an HTTPS URL. This seems unnecessarily convoluted, and even with my meager knowledge of crypto I already see some problems (compressing then encrypting is a no-no) which could spell trouble. Shouldn&#x27;t you just need to upload the JSON of the metrics over an SSL connection?</text><parent_chain></parent_chain></comment><story><title>Awless: A Mighty CLI for AWS</title><url>https://github.com/wallix/awless</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>heartsucker</author><text>&gt; We also collect a few anonymous data (CLI errors, most frequently used commands and count of resources).<p>Looks cool, but this is an instant no for me. Sorry guys.</text><parent_chain></parent_chain></comment><story><title>Awless: A Mighty CLI for AWS</title><url>https://github.com/wallix/awless</url></story> |
14,871,419 | 14,870,698 | 1 | 2 | 14,870,550 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>tmerr</author><text>The concern about stack space is slightly misleading since many languages, i.e. Scheme, can easily optimize such functions to use O(1) space by reusing stack frames across recursive calls. The problem is that while Scheme guarantees this tail-call optimization in the spec the are many other languages that leave it up to implementation, or intentionally omit it because they don&#x27;t want to lose stack traces.<p>Anyway I agree with the overall sentiment, and will check out the talk you linked. There&#x27;s another good one along similar lines: &quot;The Clean Architecture in Python&quot; by Brandon Rhodes: <a href="http:&#x2F;&#x2F;pyvideo.org&#x2F;pyohio-2014&#x2F;the-clean-architecture-in-python.html" rel="nofollow">http:&#x2F;&#x2F;pyvideo.org&#x2F;pyohio-2014&#x2F;the-clean-architecture-in-pyt...</a></text><parent_chain><item><author>eropple</author><text>If what you care about is &quot;everything is a beautifully curried function that actually doesn&#x27;t do anything&quot;, the concern about loops is definitely a thing (but any loop can be turned into a recursive function so long as your stack is big enough, even if they&#x27;re usually hideous). But pretty much everybody I&#x27;ve ever worked with considers functional purity in the logic layer to be &quot;functional programming&quot; at its most useful (Gary Berhardt&#x27;s functional-core, imperative-shell talk is a good one). Is it easier to write with a loop? <i>Then use a loop!</i> If that loop is contained in a pure function that has no side effects and encapsulates something that isn&#x27;t the most beautiful crystalline code formation anybody ever did see, <i>nobody cares</i>.<p>It&#x27;s the mindset, not the implementation, that actually makes functional programming so valuable a tool.</text></item><item><author>surement</author><text>Biggest disadvantage for me comes when trying to implement a complex algorithm where the paper uses pseudocode that&#x27;s imperative (which is almost always). In the best case you can implement parts of it functionally but when it comes time to put these together you will likely use some kind of loop, but that&#x27;s not possible in &quot;purely&quot; functional languages.<p>Otherwise -- and in particular when coming up with algorithms -- I find it preferable for languages to be efficient with functional idioms (recursion, map, filter, etc.).<p>Edit: I understand that anything&#x27;s possible in a functional language that&#x27;s possible in other languages. My point is that conversion from imperative to functional can be complex and might not be worth the trouble, and that doing it purely functionally might defeat the purpose: it will be nearly impossible to read or incredibly inefficient.</text></item></parent_chain></comment><story><title>What are potential disadvantages of functional programming?</title><url>https://www.reddit.com/r/compsci/comments/6pnq7e/what_are_potential_disadvantages_of_functional/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>RBerenguel</author><text>Functional API, efficient implementation. It&#x27;s always a good rule of thumb</text><parent_chain><item><author>eropple</author><text>If what you care about is &quot;everything is a beautifully curried function that actually doesn&#x27;t do anything&quot;, the concern about loops is definitely a thing (but any loop can be turned into a recursive function so long as your stack is big enough, even if they&#x27;re usually hideous). But pretty much everybody I&#x27;ve ever worked with considers functional purity in the logic layer to be &quot;functional programming&quot; at its most useful (Gary Berhardt&#x27;s functional-core, imperative-shell talk is a good one). Is it easier to write with a loop? <i>Then use a loop!</i> If that loop is contained in a pure function that has no side effects and encapsulates something that isn&#x27;t the most beautiful crystalline code formation anybody ever did see, <i>nobody cares</i>.<p>It&#x27;s the mindset, not the implementation, that actually makes functional programming so valuable a tool.</text></item><item><author>surement</author><text>Biggest disadvantage for me comes when trying to implement a complex algorithm where the paper uses pseudocode that&#x27;s imperative (which is almost always). In the best case you can implement parts of it functionally but when it comes time to put these together you will likely use some kind of loop, but that&#x27;s not possible in &quot;purely&quot; functional languages.<p>Otherwise -- and in particular when coming up with algorithms -- I find it preferable for languages to be efficient with functional idioms (recursion, map, filter, etc.).<p>Edit: I understand that anything&#x27;s possible in a functional language that&#x27;s possible in other languages. My point is that conversion from imperative to functional can be complex and might not be worth the trouble, and that doing it purely functionally might defeat the purpose: it will be nearly impossible to read or incredibly inefficient.</text></item></parent_chain></comment><story><title>What are potential disadvantages of functional programming?</title><url>https://www.reddit.com/r/compsci/comments/6pnq7e/what_are_potential_disadvantages_of_functional/</url></story> |
13,614,432 | 13,612,865 | 1 | 2 | 13,611,220 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>keybits</author><text>To easily make a modern feeling frontend, whilst taking advantage of Django&#x27;s backend, and without taking on all of the complexity of frontend SPA focused frameworks, I can highly recommend IntercoolerJS: <a href="http:&#x2F;&#x2F;intercoolerjs.org&#x2F;" rel="nofollow">http:&#x2F;&#x2F;intercoolerjs.org&#x2F;</a><p>Clearly it depends what your use-cae is, but for a large class of apps that you&#x27;d build with Django it feels just right for me: <a href="http:&#x2F;&#x2F;intercoolerjs.org&#x2F;2016&#x2F;10&#x2F;05&#x2F;how-it-feels-to-learn-intercooler-in-2016.html" rel="nofollow">http:&#x2F;&#x2F;intercoolerjs.org&#x2F;2016&#x2F;10&#x2F;05&#x2F;how-it-feels-to-learn-in...</a></text><parent_chain><item><author>nikisweeting</author><text>If you&#x27;re curious about how to set up a modern JS frontend on top of Django, I wrote up a tutorial recently.
It might be helpful if you&#x27;re debating between trying a Single Page App approach or some other design: <a href="https:&#x2F;&#x2F;medium.com&#x2F;@theSquashSH&#x2F;reconciling-djangos-mvc-templates-with-react-components-3aa986cf510a" rel="nofollow">https:&#x2F;&#x2F;medium.com&#x2F;@theSquashSH&#x2F;reconciling-djangos-mvc-temp...</a></text></item></parent_chain></comment><story><title>Learn web development: Django Web Framework</title><url>https://developer.mozilla.org/en-US/docs/Learn/Server-side/Django</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>dopeboy</author><text>And if you&#x27;re going down the React + Redux + REST framework path and need a boilerplate to start off on, I&#x27;d highly recommend Seedstars&#x27;: <a href="https:&#x2F;&#x2F;github.com&#x2F;Seedstars&#x2F;django-react-redux-base" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;Seedstars&#x2F;django-react-redux-base</a></text><parent_chain><item><author>nikisweeting</author><text>If you&#x27;re curious about how to set up a modern JS frontend on top of Django, I wrote up a tutorial recently.
It might be helpful if you&#x27;re debating between trying a Single Page App approach or some other design: <a href="https:&#x2F;&#x2F;medium.com&#x2F;@theSquashSH&#x2F;reconciling-djangos-mvc-templates-with-react-components-3aa986cf510a" rel="nofollow">https:&#x2F;&#x2F;medium.com&#x2F;@theSquashSH&#x2F;reconciling-djangos-mvc-temp...</a></text></item></parent_chain></comment><story><title>Learn web development: Django Web Framework</title><url>https://developer.mozilla.org/en-US/docs/Learn/Server-side/Django</url></story> |
12,247,150 | 12,245,792 | 1 | 3 | 12,245,587 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>heavenlyhash</author><text>Everyone: Read this. At least the threat models.<p>Do not assume all software you currently use gets these things right.</text><parent_chain></parent_chain></comment><story><title>The Update Framework</title><url>https://theupdateframework.github.io/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>doublerebel</author><text>So obviously we have to wonder why TUF hasn&#x27;t been applied to NodeJS&#x27;s npm. All I can find is a suggestion that maybe someone from TUF posted to a node mailing list in 2014 [1]. Any more recent info?<p>[1]: <a href="https:&#x2F;&#x2F;groups.google.com&#x2F;forum&#x2F;m&#x2F;?fromgroups#!topic&#x2F;theupdateframework&#x2F;GbWtUbnO8_I" rel="nofollow">https:&#x2F;&#x2F;groups.google.com&#x2F;forum&#x2F;m&#x2F;?fromgroups#!topic&#x2F;theupda...</a></text><parent_chain></parent_chain></comment><story><title>The Update Framework</title><url>https://theupdateframework.github.io/</url></story> |
19,571,814 | 19,571,934 | 1 | 3 | 19,571,150 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>SolaceQuantum</author><text><i>&quot;I personally have lower taxes, high quality healthcare, and live in an awesome location, and I got all of that through an education and training. That is available to almost every American if they just put in the work.&quot;</i><p>I don&#x27;t know if that&#x27;s true. If I&#x27;m a child with food insecurity, my lack of nourishment, poor home life, overtaxed regional social programs, and government disincentives will cause me to be unable to focus on my education at my overtaxed school program, thereby setting me back for the rest of my life through no fault of my own.<p>If I&#x27;m one of many children born in a county or state with no access to clean water, I am more likely to develop a chronic illness that will prevent me from putting in the work necessary to achieve your lifestyle through no fault of my own.<p>If I&#x27;m one of many blue collar workers who destroyed my body in my 40s putting in work, I no longer have access to my way of work and the industries I can go into are plagued with known ageism. I am now stuck through no fault of my own save for a lack of future-sight that technology will be the thing to get into 40 years ago.<p>Moral correctness is all well and good, but if we are gleaning over those less fortunate with our morals, we&#x27;re not being moral at all- we&#x27;re just providing justifications for why we deserve what we have and more importantly <i>why people who do not have what we have deserve their poverty</i>.</text><parent_chain><item><author>bepotts</author><text>Americans don&#x27;t believe the onus is on the whole to make sure the individual lives a happy life. We just don&#x27;t have the collectivist culture the Europeans have. I think this is a great thing, and is why America is where most of the innovation, cultural, and political power is.<p>I personally have lower taxes, high quality healthcare, and live in an awesome location, and I got all of that through an education and training. That is available to almost every American if they just put in the work.<p>That, to me, is not just a great thing but the morally right thing. Apply yourself and make a better future for you and your family.<p>To the people responding to me with the most <i>predictable</i> lines: poverty exists in Europe; so does homelessness; as does food insecurity. Please don&#x27;t tell me that Europe is some great place where poverty doesn&#x27;t exist and everyone is living great lives.<p>It is also possible to be sympathetic toward the most needy while not supporting collectivism. You know what the poor need most? A marketable skill. A good job. Support programs that give people the skills they need in order to compete in a globalized market. It&#x27;s funny how collectivists never push that though, and instead push for more collectivism.</text></item><item><author>cribbles</author><text>&gt; One reason that Europe has very few innovative new companies created in the last 25 years is that everyone is at the coffee shop writing poetry.<p>This does not dispute the central point of the quoted piece, which is that the quality of life of most Americans is very poor contrast to that of the average person in some subset of European countries. I would wager that most coffee shop employees are more concerned with labor protections, healthcare, social welfare, the ability to afford housing and take vacations than whether their country’s economy is producing “innovative companies” (read: tech startups?). This was certainly true of myself when I worked in food service.<p>Even so, this point does not stand well on its own. It may be that Europeans are deincentivized from creating enormously overvalued startups because their quality of life is much better (although I question whether this is worth bragging about, from a US standpoint). Nevertheless, I’d consider things like lack of a single market, fragmented languages and cultures, completely different VC environment, and so on to be much more impactful in that regard.</text></item><item><author>seibelj</author><text>&gt; <i>In London, Paris, Berlin, I hop on the train, head to the cafe — it’s the afternoon, and nobody’s gotten to work until 9am, and even then, maybe not until 10 — order a carefully made coffee and a newly baked croissant, do some writing, pick up some fresh groceries, maybe a meal or two, head home — now it’s 6 or 7, and everyone else has already gone home around 5 — and watch something interesting, maybe a documentary by an academic, the BBC’s Blue Planet, or a Swedish crime-noir. I think back on my day and remember the people smiling and laughing at the pubs and cafes.</i>[0]<p>No, not everyone in Europe gets to live white-collar worker dream of writing poetry at the coffee shop and coming in late. See the people working at the coffee shop, the construction workers, garbage men, etc.<p>One thing I love about America is that people still get shit done here. One reason that Europe has very few innovative new companies created in the last 25 years is that everyone is at the coffee shop writing poetry.<p>An old joke - <i>&quot;Every MBA in America dreams of starting a billion dollar business. Every MBA in Europe dreams of starting a satellite office of the American business.&quot;</i><p>[0] From the actual blog the author quoted from <a href="https:&#x2F;&#x2F;eand.co&#x2F;what-do-you-call-a-world-that-cant-learn-from-itself-58ae28cefd23" rel="nofollow">https:&#x2F;&#x2F;eand.co&#x2F;what-do-you-call-a-world-that-cant-learn-fro...</a></text></item></parent_chain></comment><story><title>Why Don't Americans Understand How Poor Their Lives Are?</title><url>http://www.danielsjourney.com/2017/12/21/america.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>coldtea</author><text>&gt;<i>You know what the poor need most? A marketable skill. A good job</i><p>I thought freedom to play and study as kids. A full belly. A supporting family. Family connections. Not fearing for tomorrow (eviction, money trouble, muggings, etc). Money for college. Not having to work to support anybody but themselves.<p>You know, the kinds of things it would be statistically (if not entirely) safe to presume you had as a child, or that most successful (e.g. college wise) kids have, and most unsuccessful kids lacked.<p><a href="https:&#x2F;&#x2F;www.radionz.co.nz&#x2F;news&#x2F;the-wireless&#x2F;373065&#x2F;the-pencilsword-on-a-plate" rel="nofollow">https:&#x2F;&#x2F;www.radionz.co.nz&#x2F;news&#x2F;the-wireless&#x2F;373065&#x2F;the-penci...</a><p>But yeah, lacking all that, a marketable skill and a support program will do.<p>And they might even be able to make it, if they work doubly as hard, and manage twice as many hardships as those who had all of above provided for them from birth.</text><parent_chain><item><author>bepotts</author><text>Americans don&#x27;t believe the onus is on the whole to make sure the individual lives a happy life. We just don&#x27;t have the collectivist culture the Europeans have. I think this is a great thing, and is why America is where most of the innovation, cultural, and political power is.<p>I personally have lower taxes, high quality healthcare, and live in an awesome location, and I got all of that through an education and training. That is available to almost every American if they just put in the work.<p>That, to me, is not just a great thing but the morally right thing. Apply yourself and make a better future for you and your family.<p>To the people responding to me with the most <i>predictable</i> lines: poverty exists in Europe; so does homelessness; as does food insecurity. Please don&#x27;t tell me that Europe is some great place where poverty doesn&#x27;t exist and everyone is living great lives.<p>It is also possible to be sympathetic toward the most needy while not supporting collectivism. You know what the poor need most? A marketable skill. A good job. Support programs that give people the skills they need in order to compete in a globalized market. It&#x27;s funny how collectivists never push that though, and instead push for more collectivism.</text></item><item><author>cribbles</author><text>&gt; One reason that Europe has very few innovative new companies created in the last 25 years is that everyone is at the coffee shop writing poetry.<p>This does not dispute the central point of the quoted piece, which is that the quality of life of most Americans is very poor contrast to that of the average person in some subset of European countries. I would wager that most coffee shop employees are more concerned with labor protections, healthcare, social welfare, the ability to afford housing and take vacations than whether their country’s economy is producing “innovative companies” (read: tech startups?). This was certainly true of myself when I worked in food service.<p>Even so, this point does not stand well on its own. It may be that Europeans are deincentivized from creating enormously overvalued startups because their quality of life is much better (although I question whether this is worth bragging about, from a US standpoint). Nevertheless, I’d consider things like lack of a single market, fragmented languages and cultures, completely different VC environment, and so on to be much more impactful in that regard.</text></item><item><author>seibelj</author><text>&gt; <i>In London, Paris, Berlin, I hop on the train, head to the cafe — it’s the afternoon, and nobody’s gotten to work until 9am, and even then, maybe not until 10 — order a carefully made coffee and a newly baked croissant, do some writing, pick up some fresh groceries, maybe a meal or two, head home — now it’s 6 or 7, and everyone else has already gone home around 5 — and watch something interesting, maybe a documentary by an academic, the BBC’s Blue Planet, or a Swedish crime-noir. I think back on my day and remember the people smiling and laughing at the pubs and cafes.</i>[0]<p>No, not everyone in Europe gets to live white-collar worker dream of writing poetry at the coffee shop and coming in late. See the people working at the coffee shop, the construction workers, garbage men, etc.<p>One thing I love about America is that people still get shit done here. One reason that Europe has very few innovative new companies created in the last 25 years is that everyone is at the coffee shop writing poetry.<p>An old joke - <i>&quot;Every MBA in America dreams of starting a billion dollar business. Every MBA in Europe dreams of starting a satellite office of the American business.&quot;</i><p>[0] From the actual blog the author quoted from <a href="https:&#x2F;&#x2F;eand.co&#x2F;what-do-you-call-a-world-that-cant-learn-from-itself-58ae28cefd23" rel="nofollow">https:&#x2F;&#x2F;eand.co&#x2F;what-do-you-call-a-world-that-cant-learn-fro...</a></text></item></parent_chain></comment><story><title>Why Don't Americans Understand How Poor Their Lives Are?</title><url>http://www.danielsjourney.com/2017/12/21/america.html</url></story> |
16,580,828 | 16,580,805 | 1 | 2 | 16,580,178 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>Waterluvian</author><text>I have ADHD. Drugs like ritalin never &quot;fixed&quot; me. They basically allowed me an exchange: give up the charisma, personality, sociability, and appetite for 8 hours of being able to focus on something. I won&#x27;t write an essay here but trust me that the two versions of me were day and night and both had significant benefits and challenges. I <i>really</i> struggled growing up.<p>By the time I got to college I learned to use the drugs as a switch I could flip when I needed the focused version of me.<p>Not that ADHD and ASD can be compared, but I wonder if maybe ASD treatments could offer that option. Ie. Not to &quot;fix&quot; you but to give you a tool to be wielded under your own control.</text><parent_chain><item><author>exelius</author><text>As someone on the spectrum, I don’t necessarily know if this is something I would want. My ASD is a big part of my personality; if these social “difficulties” (which really just mean I click with a different type of person) were “solved” I don’t know I would be the same person.<p>Maybe this can offer some hope for others with more profound issues, but if you’ve found a way to function in society I’m not sure this will be very attractive outside a “let me try and see what it feels like” scenario.</text></item></parent_chain></comment><story><title>Autism's social deficits in animal model are reversed by an anti-cancer drug</title><url>https://www.sciencedaily.com/releases/2018/03/180312201647.htm</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>whatshisface</author><text>I think the experience of being a person goes a lot deeper than having any specific personality, if it didn&#x27;t we wouldn&#x27;t be sorting traits into good and bad. If not having learned to read has kept someone away from the influences of literature, we could say that it has impacted their personality, but would that be an excuse to never teach them?<p>Some behaviors associated with autism are really results of having less social influence acting on one&#x27;s self (due to both slower learning and isolation). Would we consider them a fundamental part of the person, or just evidence of areas that the person still can grow in?</text><parent_chain><item><author>exelius</author><text>As someone on the spectrum, I don’t necessarily know if this is something I would want. My ASD is a big part of my personality; if these social “difficulties” (which really just mean I click with a different type of person) were “solved” I don’t know I would be the same person.<p>Maybe this can offer some hope for others with more profound issues, but if you’ve found a way to function in society I’m not sure this will be very attractive outside a “let me try and see what it feels like” scenario.</text></item></parent_chain></comment><story><title>Autism's social deficits in animal model are reversed by an anti-cancer drug</title><url>https://www.sciencedaily.com/releases/2018/03/180312201647.htm</url></story> |
31,076,510 | 31,076,348 | 1 | 2 | 31,074,881 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>lr</author><text>I think you just answered the question: All of the categories you note have both high-end and, sadly, mostly low-end options. What is surprising is that, in the world of computing, there is very little at the high end (Apple -- from going by this original thread), and almost all of it is at the low end. I guess some company could make an amazing PC that ran Windows, but the, you&#x27;d have an amazing piece of hardware that... ran Windows.</text><parent_chain><item><author>uniqueuid</author><text>All true, but why is the <i>culture</i> and <i>aesthetic</i> of computers inherently trashy?<p>Look at all the fields where superior quality is a completely natural criterion (whether it exists may be another question): Watches, cars, pens, paper notebooks, furniture, fashion, jewellery, architecture, bikes, coffee machines ...<p>What&#x27;s more - if you look at the visual representations of computers - i.e. marketing material, art, illustrations, unix porn etc - all that highly values aesthetics and beauty. But the actual products are a disgrace to all of that!</text></item><item><author>kmeisthax</author><text>Because every other computer manufacturer realized they can save on the BOM cost by shoving the whole computer under plastic gingerbread. That weight distribution? It&#x27;d cost way too much to redesign the product correctly. Flickering redraws? We don&#x27;t make the OS, we just sell Microsoft&#x27;s.<p>Occasionally you <i>do</i> see PC OEMs that try for taste in the Windows ecosystem. Sony did that with their VAIO laptops, with the somewhat-inflated price tag to match. In fact, it impressed Jobs so much he literally just offered them an OSX license (which they didn&#x27;t bite on).</text></item><item><author>uniqueuid</author><text>I may be an outlier, but for me, the problem with non-mac machines is that they seem just careless.<p>Steve jobs famously said &quot;The only problem with Microsoft is they just have no taste.&quot;, and this seems true to me for almost all hardware manufacturers, and to a larger degree still for software.<p>Why does nobody care about creaking plastic? About sticky-feeling texture? About uneven weight distribution? About the sound that materials make when handling them? About flickering in software? About inconsistent spacing? About janky color combinations?<p>There has been amazing workmanship for thousands of years. The Minoan culture made golden jewellery out of sub-milimeter spheres. Why should we now tolerate the insult that consumer computers are?</text></item></parent_chain></comment><story><title>Ask HN: MacBooks seems to be the only viable option these days</title><text>I&#x27;ve used ThinkPads all the way from the IBM days and those good old solid Dell computers too.<p>Recently, I decided it was time for an update. I use Linux on the often so it was important for me to purchase a laptop that was compatible.<p>I bought 2 laptops, all of which I had to return in the last 2 months.<p>1. Dell XPS: I spent over 20+ hours with their support going back and forth. I also had a tech come to my house to replace my motherboard before I gave up and demanded a return<p>2. Lenovo Carbon X1: The laptop came with a faulty keyboard so I just returned it because I didn&#x27;t want to wait 30 days for a mail-in repair or drive 2 hours to go to a &quot;local&quot; repair shop. They also made me order the laptop 3 times because their system kept cancelling it for whatever reason so it took an insane amount of time to just purchase the laptop (I spent ~6 hours to just purchase the laptop)<p>Maybe I&#x27;m just unlucky but the time I spent and energy I spent to just purchase these laptops shows you why people buy from Apple instead. I strongly dislike MacOS because they force the &quot;apple way&quot; of doing things. But it seems to be the only option these days to buy a computer with ease and get a computer &quot;that just works&quot;. My Macbook was more expensive but the time I saved outweighs the price imo.</text></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>chaostheory</author><text>&gt; All true, but why is the culture and aesthetic of computers inherently trashy?<p>Because it needs to be affordable to the masses as a whole, and not just the upper middle class and up.</text><parent_chain><item><author>uniqueuid</author><text>All true, but why is the <i>culture</i> and <i>aesthetic</i> of computers inherently trashy?<p>Look at all the fields where superior quality is a completely natural criterion (whether it exists may be another question): Watches, cars, pens, paper notebooks, furniture, fashion, jewellery, architecture, bikes, coffee machines ...<p>What&#x27;s more - if you look at the visual representations of computers - i.e. marketing material, art, illustrations, unix porn etc - all that highly values aesthetics and beauty. But the actual products are a disgrace to all of that!</text></item><item><author>kmeisthax</author><text>Because every other computer manufacturer realized they can save on the BOM cost by shoving the whole computer under plastic gingerbread. That weight distribution? It&#x27;d cost way too much to redesign the product correctly. Flickering redraws? We don&#x27;t make the OS, we just sell Microsoft&#x27;s.<p>Occasionally you <i>do</i> see PC OEMs that try for taste in the Windows ecosystem. Sony did that with their VAIO laptops, with the somewhat-inflated price tag to match. In fact, it impressed Jobs so much he literally just offered them an OSX license (which they didn&#x27;t bite on).</text></item><item><author>uniqueuid</author><text>I may be an outlier, but for me, the problem with non-mac machines is that they seem just careless.<p>Steve jobs famously said &quot;The only problem with Microsoft is they just have no taste.&quot;, and this seems true to me for almost all hardware manufacturers, and to a larger degree still for software.<p>Why does nobody care about creaking plastic? About sticky-feeling texture? About uneven weight distribution? About the sound that materials make when handling them? About flickering in software? About inconsistent spacing? About janky color combinations?<p>There has been amazing workmanship for thousands of years. The Minoan culture made golden jewellery out of sub-milimeter spheres. Why should we now tolerate the insult that consumer computers are?</text></item></parent_chain></comment><story><title>Ask HN: MacBooks seems to be the only viable option these days</title><text>I&#x27;ve used ThinkPads all the way from the IBM days and those good old solid Dell computers too.<p>Recently, I decided it was time for an update. I use Linux on the often so it was important for me to purchase a laptop that was compatible.<p>I bought 2 laptops, all of which I had to return in the last 2 months.<p>1. Dell XPS: I spent over 20+ hours with their support going back and forth. I also had a tech come to my house to replace my motherboard before I gave up and demanded a return<p>2. Lenovo Carbon X1: The laptop came with a faulty keyboard so I just returned it because I didn&#x27;t want to wait 30 days for a mail-in repair or drive 2 hours to go to a &quot;local&quot; repair shop. They also made me order the laptop 3 times because their system kept cancelling it for whatever reason so it took an insane amount of time to just purchase the laptop (I spent ~6 hours to just purchase the laptop)<p>Maybe I&#x27;m just unlucky but the time I spent and energy I spent to just purchase these laptops shows you why people buy from Apple instead. I strongly dislike MacOS because they force the &quot;apple way&quot; of doing things. But it seems to be the only option these days to buy a computer with ease and get a computer &quot;that just works&quot;. My Macbook was more expensive but the time I saved outweighs the price imo.</text></story> |
14,684,200 | 14,683,862 | 1 | 2 | 14,683,767 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>vorg</author><text>&gt; the digits for 3 have either three horizonal strokes ౾ or three vertical strokes ౻, and the others similarly. I have an idea that the alternating vertical-horizontal system might have served as an error-detection mechanism<p>The Chinese Suzhou numerals use alternating 〡〢〣 and 一二三 but for a different reason:<p><pre><code> &quot;21&quot; is written as &quot;〢一&quot; instead of &quot;〢〡&quot; which can be confused with &quot;3&quot; (〣)
</code></pre>
from <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Suzhou_numerals" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Suzhou_numerals</a></text><parent_chain></parent_chain></comment><story><title>Base-4 fractions in Telugu</title><url>http://blog.plover.com/math/telugu.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>eponeponepon</author><text>Telugu&#x27;s a spectacular language - it&#x27;s ancient, it&#x27;s spoken by tens of millions of people, it has its own cinema industry and an enormous literary corpus reaching back to before English even existed... and yet almost nobody outside the subcontinent even knows it exists.</text><parent_chain></parent_chain></comment><story><title>Base-4 fractions in Telugu</title><url>http://blog.plover.com/math/telugu.html</url></story> |
31,489,437 | 31,489,463 | 1 | 3 | 31,486,590 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>deltaonefour</author><text>No you&#x27;re wrong. It&#x27;s literally creativity. Machine learning models literally work because they fill in gaps where the data doesn&#x27;t exist.<p>Any content generated by ML is very unlikely to be anything else other then original.<p>Imagine linear regression. Then pick a random point on that line. How likely is it that that point on that trend line coincides with an actual data point? Very unlikely.<p>ML is simply a multidimensional version of this. Some 1000 dimensional surface and the result you see is simply a point on that surface. The likelihood of that point on the surface to coincide with an actual data point is astronomically low.<p>Nobody is being carried away here. What you are seeing is raw creativity by an AI. It is a highly simplified version of human creativity, but the deep fundamentals are identical.<p>In fact all intelligence is simply a huge thousands or more dimensional surface. A giant curve fitting methodology. The only gap between ML and human intelligence as of now is the amount of neurons, the training algorithm and the actual template for the equation describing the model. But in essence we have the fundamentals down at a high level.</text><parent_chain><item><author>hackernewds</author><text>Let&#x27;s not get carried away. it is still original<i>only</i> to the extent that it is a different combination of <i>existing</i> prose - just unrecognizable due to the vastness of online content.<p>It is both beautiful and scary that it is indeed indistinguishable from original creative content.</text></item><item><author>qwertox</author><text>I think we&#x27;re currently witnessing something truly unique with the rise of AI, something which is as special as life being born on earth.<p>There&#x27;ll still be the discussion around conscience, but having a tool which can emulate human thinking is really wild.<p>The next 5 years will be really interesting. Also to see how this will be absorbed by society.</text></item><item><author>goodside</author><text>The following is an un-curated text-davinci-002 generation, completing the text:<p>&gt; Write an insightful reply to this Hacker News comment on a link to an article titled &quot;I made an AI write a story about AI then I made another AI illustrate it&quot;. The comment is left by user &quot;turtledove&quot;, and reads, &quot;How many attempts and how much human curation was involved. Every &#x27;I made AI do...&#x27; story seems to necessarily omit the &#x27;and I filtered out a LOT of rubbish before picking this one good example.&#x27;&quot;<p>The completion:<p>&gt; I&#x27;m not sure how many attempts were made, but I imagine it wasn&#x27;t too many. As for human curation, I&#x27;m sure there was some involved in choosing which story and illustration to publish. But overall, I think the point of the article is that the AI was able to produce something fairly coherent on its own.</text></item><item><author>turtledove</author><text>How many attempts and how much human curation was involved. Every &quot;I made AI do...&quot; story seems to necessarily omit the &quot;and I filtered out a LOT of rubbish before picking this one good example.&quot;</text></item></parent_chain></comment><story><title>I made an AI write a story about AI then I made another AI illustrate it</title><url>https://tristrumtuttle.medium.com/the-day-i-became-friends-with-a-robot-86433f707fad</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>nl</author><text>&gt; it is a different combination of existing prose<p>This isn&#x27;t true. It&#x27;s been explained numerous times on HN how mistaken this view is.<p>Language models do not work like this. They <i>can</i> copy content but usually that&#x27;s for something like the GPL language text.<p>Generally they work on a character by character basis predicting what is the most likely character to appear next.<p>This very rarely results in copying text, and almost never rare text.</text><parent_chain><item><author>hackernewds</author><text>Let&#x27;s not get carried away. it is still original<i>only</i> to the extent that it is a different combination of <i>existing</i> prose - just unrecognizable due to the vastness of online content.<p>It is both beautiful and scary that it is indeed indistinguishable from original creative content.</text></item><item><author>qwertox</author><text>I think we&#x27;re currently witnessing something truly unique with the rise of AI, something which is as special as life being born on earth.<p>There&#x27;ll still be the discussion around conscience, but having a tool which can emulate human thinking is really wild.<p>The next 5 years will be really interesting. Also to see how this will be absorbed by society.</text></item><item><author>goodside</author><text>The following is an un-curated text-davinci-002 generation, completing the text:<p>&gt; Write an insightful reply to this Hacker News comment on a link to an article titled &quot;I made an AI write a story about AI then I made another AI illustrate it&quot;. The comment is left by user &quot;turtledove&quot;, and reads, &quot;How many attempts and how much human curation was involved. Every &#x27;I made AI do...&#x27; story seems to necessarily omit the &#x27;and I filtered out a LOT of rubbish before picking this one good example.&#x27;&quot;<p>The completion:<p>&gt; I&#x27;m not sure how many attempts were made, but I imagine it wasn&#x27;t too many. As for human curation, I&#x27;m sure there was some involved in choosing which story and illustration to publish. But overall, I think the point of the article is that the AI was able to produce something fairly coherent on its own.</text></item><item><author>turtledove</author><text>How many attempts and how much human curation was involved. Every &quot;I made AI do...&quot; story seems to necessarily omit the &quot;and I filtered out a LOT of rubbish before picking this one good example.&quot;</text></item></parent_chain></comment><story><title>I made an AI write a story about AI then I made another AI illustrate it</title><url>https://tristrumtuttle.medium.com/the-day-i-became-friends-with-a-robot-86433f707fad</url></story> |
19,062,105 | 19,061,999 | 1 | 2 | 19,060,256 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>throwaway77384</author><text><a href="https:&#x2F;&#x2F;mimugloves.com&#x2F;" rel="nofollow">https:&#x2F;&#x2F;mimugloves.com&#x2F;</a><p>I worked with these folks for a while. I also work with the deaf community.<p>Sign Language gloves are an interesting idea, but they don&#x27;t work. Sign language relies heavily on facial expressions and body language beyond the hands.<p>This was also tried here before: <a href="https:&#x2F;&#x2F;www.huffingtonpost.com&#x2F;entry&#x2F;navid-azodi-and-thomas-pryor-signaloud-gloves-translate-american-sign-language-into-speech-text_us_571fb38ae4b0f309baeee06d?guccounter=1" rel="nofollow">https:&#x2F;&#x2F;www.huffingtonpost.com&#x2F;entry&#x2F;navid-azodi-and-thomas-...</a><p>But deaf people aren&#x27;t actually that keen on these solutions, as I found out when I proposed this to some of them myself.</text><parent_chain></parent_chain></comment><story><title>A Kenyan Engineer Who Created Gloves That Turn Sign Language into Speech</title><url>https://www.becauseofthemwecan.com/blogs/culture/meet-the-kenyan-engineer-who-created-gloves-that-turn-sign-language-into-audible-speech</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>dbt00</author><text>Seems like a fun hardware hack, but if he wants his niece to be able to communicate effectively he should probably just learn frickin sign language. It&#x27;s unlikely that these can read a vocabulary, just the alphabet, which is incredibly limiting.<p>So, cool, looks like fun to hack on, almost certainly not newsworthy.</text><parent_chain></parent_chain></comment><story><title>A Kenyan Engineer Who Created Gloves That Turn Sign Language into Speech</title><url>https://www.becauseofthemwecan.com/blogs/culture/meet-the-kenyan-engineer-who-created-gloves-that-turn-sign-language-into-audible-speech</url></story> |
26,389,603 | 26,382,452 | 1 | 2 | 26,380,822 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>jboog</author><text>I&#x27;d go even further and say that the way most people treat &quot;documentary&quot; to be equivalent to &quot;unbiased recitation of factual events&quot; is problematic itself.<p>I love docs but often research the subject after watching and it&#x27;s INCREDIBLY rare to see a doc that doesn&#x27;t play fast and loose with the facts for the sake of creating a dramatic arc or thrilling moments.<p>It&#x27;s ESPECIALLY true in &quot;true crime&quot; docs. The director has an idea of painting the subject as either sympathetic guy who was wronged by a corrupt system (Making a Murderer) or evil mastermind (The Jinx) just to give two recent examples.<p>Turned out years later the giant reveal at the center of The Jinx which made it such a viral hit was 100% manufactured by the director cutting up audio to make Durst say things he didn&#x27;t. He also lied to the police about the audio so it wouldn&#x27;t spoil the ending of the doc.<p>Jarecki never had to apologize for the blatant dishonesty in the doc, never had to give back the Emmy. It&#x27;s still universally acclaimed.<p><a href="https:&#x2F;&#x2F;www.nytimes.com&#x2F;2019&#x2F;04&#x2F;24&#x2F;arts&#x2F;television&#x2F;robert-durst-the-jinx.html" rel="nofollow">https:&#x2F;&#x2F;www.nytimes.com&#x2F;2019&#x2F;04&#x2F;24&#x2F;arts&#x2F;television&#x2F;robert-du...</a><p>Sorry to rant, but the &quot;documentary&quot; film industry is a fucking joke. I have so many more examples...</text><parent_chain><item><author>oivey</author><text>HBO’s Chernobyl is more of a dramatization than a documentary. It certainly doesn’t contain interviews of people who were actually involved. There are quite a few good bits highlighting the dangers of nuclear energy, particularly in the context of the Soviet bureaucracy, but there also a few liberties taken with the science and reality of the event. The fact that people think of it is a documentary despite that is also concerning.</text></item><item><author>softwaredoug</author><text>It&#x27;s interesting to contrast this with the Chernobyl HBO documentary. Both are engineering disasters, both have very complicated cultural and political underpinnings to why they were allowed to happen. It&#x27;s not to say the Challenger disaster is comparable to the scale of the Chernobyl disaster, but more crucially: what if the same poor incentives and decisions in place that cause Challenger caused other engineering disasters in the US.</text></item><item><author>zb</author><text>The film “Challenger: The Final Flight” on Netflix includes interviews with the most important participants in the launch decision, including McDonald. (It also has interviews with many of the astronauts’ families and does a great job at putting their experience front and centre.)<p>The guy whose job it was to send the fax because he happened to be the one who knew how to operate the fax machine is to this day utterly devastated; weeping.<p>The MTI VP who signed off (although the decision was made above his head) admits that he agreed with it at the time, but acknowledges it was a mistake. He’s being interviewed in a large room full of very expensive furniture.<p>The NASA manager who bullied them into agreeing to launch because they couldn’t prove that it was unsafe basically says that if he had his time over he would kill all of the astronauts again. Truly terrifying.</text></item></parent_chain></comment><story><title>Remembering Allan McDonald, who refused to approve the Challenger launch</title><url>https://text.npr.org/974534021</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>lostlogin</author><text>Serhii Plokhy’s Chernobyl: History of Tragedy seems a great text on the subject, and while the tv series is undoubtedly dramatised and many characters are morphed into one, the tv series seems to broadly follow the history of events as described in the book. Serhii seems to have a favourable view of the tv series.<p>Is there something glaring I am missing?<p><a href="https:&#x2F;&#x2F;en.hromadske.ua&#x2F;posts&#x2F;chernobyl-expert-serhii-plokhii-on-the-accuracy-of-the-hbo-series" rel="nofollow">https:&#x2F;&#x2F;en.hromadske.ua&#x2F;posts&#x2F;chernobyl-expert-serhii-plokhi...</a></text><parent_chain><item><author>oivey</author><text>HBO’s Chernobyl is more of a dramatization than a documentary. It certainly doesn’t contain interviews of people who were actually involved. There are quite a few good bits highlighting the dangers of nuclear energy, particularly in the context of the Soviet bureaucracy, but there also a few liberties taken with the science and reality of the event. The fact that people think of it is a documentary despite that is also concerning.</text></item><item><author>softwaredoug</author><text>It&#x27;s interesting to contrast this with the Chernobyl HBO documentary. Both are engineering disasters, both have very complicated cultural and political underpinnings to why they were allowed to happen. It&#x27;s not to say the Challenger disaster is comparable to the scale of the Chernobyl disaster, but more crucially: what if the same poor incentives and decisions in place that cause Challenger caused other engineering disasters in the US.</text></item><item><author>zb</author><text>The film “Challenger: The Final Flight” on Netflix includes interviews with the most important participants in the launch decision, including McDonald. (It also has interviews with many of the astronauts’ families and does a great job at putting their experience front and centre.)<p>The guy whose job it was to send the fax because he happened to be the one who knew how to operate the fax machine is to this day utterly devastated; weeping.<p>The MTI VP who signed off (although the decision was made above his head) admits that he agreed with it at the time, but acknowledges it was a mistake. He’s being interviewed in a large room full of very expensive furniture.<p>The NASA manager who bullied them into agreeing to launch because they couldn’t prove that it was unsafe basically says that if he had his time over he would kill all of the astronauts again. Truly terrifying.</text></item></parent_chain></comment><story><title>Remembering Allan McDonald, who refused to approve the Challenger launch</title><url>https://text.npr.org/974534021</url></story> |
26,808,598 | 26,808,461 | 1 | 2 | 26,806,898 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>etripe</author><text>&gt; You can&#x27;t put Exxon in jail.<p>If a corporation is a legal person with inalienable rights (as the SCOTUS seems to have decided on), but is intangible and immortal at the same time, what can you do? Any of the below:<p>* freezing assets (=~ reclamation)<p>* seizing accounts (=~ civil forfeiture)<p>* suspend a business license (=~ locking them up)<p>* introduce a revenue cap (=~ prison labour)<p>* remove lobbyists (=~ losing voting rights)<p>* dissolve or nationalise the company (=~ death penalty)<p>This is by no means an exhaustive list.</text><parent_chain><item><author>ryandrake</author><text>Corporations (which are usually the payer of fines for bad behavior) don&#x27;t fear prison because they can&#x27;t be physically imprisoned. You can&#x27;t put Exxon in jail. And, lawmakers deliberately make it so damn hard to pierce the corporate liability veil and hold shareholders or directors personally liable for the corporation&#x27;s actions.<p>So, we need to both move more towards prison <i>and</i> start digging in to which actual people inside bad corporations were responsible for deciding to do wrongdoing.<p>&quot;BigCo settled and paid an insignificant $20M out of their river of money&quot; is not very satisfying to read. &quot;Joe Bigshot, former SVP at BigCo, was sentenced to 5 years in jail, and had to sell two of his nine houses to pay the $20M fine&quot; is much better.</text></item><item><author>cletus</author><text>Here&#x27;s the one lesson I really want us to all learn from this: the only thing the rich fear is prison because prison robs them of time.<p>Fines are just the cost of doing business.<p>There are many other scandals: the whole subprime disaster, pollution from plants and the like where no one went to prison and people really should&#x27;ve.</text></item></parent_chain></comment><story><title>Bernie Madoff has died</title><url>https://www.bloomberg.com/news/articles/2021-04-14/ap-source-ponzi-schemer-bernie-madoff-dies-in-prison</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>john_moscow</author><text>&gt;Joe Bigshot, former SVP at BigCo, was sentenced to 5 years in jail, and had to sell two of his nine houses to pay the $20M fine&quot; is much better.<p>Well, they sort of do that in Russia. So the CEO&#x2F;founder of almost any sketchy company is a homeless person that signed the paperwork in exchange for some free vodka. Didn&#x27;t particularly solve the problem.<p>Corporate fines just need to be sufficient to make such &quot;business&quot; unprofitable. &quot;BigCo fined for 5% of its market cap&quot; would be quite a deterrent. Except, it won&#x27;t be happening as long as the regulators are in bed with the big business they are supposed to regulate.</text><parent_chain><item><author>ryandrake</author><text>Corporations (which are usually the payer of fines for bad behavior) don&#x27;t fear prison because they can&#x27;t be physically imprisoned. You can&#x27;t put Exxon in jail. And, lawmakers deliberately make it so damn hard to pierce the corporate liability veil and hold shareholders or directors personally liable for the corporation&#x27;s actions.<p>So, we need to both move more towards prison <i>and</i> start digging in to which actual people inside bad corporations were responsible for deciding to do wrongdoing.<p>&quot;BigCo settled and paid an insignificant $20M out of their river of money&quot; is not very satisfying to read. &quot;Joe Bigshot, former SVP at BigCo, was sentenced to 5 years in jail, and had to sell two of his nine houses to pay the $20M fine&quot; is much better.</text></item><item><author>cletus</author><text>Here&#x27;s the one lesson I really want us to all learn from this: the only thing the rich fear is prison because prison robs them of time.<p>Fines are just the cost of doing business.<p>There are many other scandals: the whole subprime disaster, pollution from plants and the like where no one went to prison and people really should&#x27;ve.</text></item></parent_chain></comment><story><title>Bernie Madoff has died</title><url>https://www.bloomberg.com/news/articles/2021-04-14/ap-source-ponzi-schemer-bernie-madoff-dies-in-prison</url></story> |
7,942,634 | 7,942,582 | 1 | 2 | 7,942,188 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>ashishgandhi</author><text>I&#x27;m glad this was found independently and reported. While I was at PayPal I had started email threads about it but nothing was done. I am sure I was not the only one there who &quot;discovered&quot; this. For instance, even if you have 2FA you can add PayPal to Uber as if you never had 2FA.<p>The other big issue with their 2FA authentication is that it really isn&#x27;t two factor. You can say you don&#x27;t have the token and instead can answer security questions. Two factor is supposed to be something you know plus something you have. &quot;Falling back&quot; to security questions is basically just relying on things you know.</text><parent_chain></parent_chain></comment><story><title>Bypass PayPal's Two-Factor Authentication</title><url>https://www.duosecurity.com/blog/duo-security-researchers-uncover-bypass-of-paypal-s-two-factor-authentication</url><text></text></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>rdl</author><text>Based on this timeline, I don&#x27;t understand why Duo didn&#x27;t go public on 2014-04-28 when PayPal began being weasely about their bug bounty program. This probably would be better for users for two reasons: one, in the past 2 months, this bug may have been exploited in the wild, and two, it would make it easier for users to make informed decisions about which payments providers to use in the future (as well as which 2fa providers are technically competent).</text><parent_chain></parent_chain></comment><story><title>Bypass PayPal's Two-Factor Authentication</title><url>https://www.duosecurity.com/blog/duo-security-researchers-uncover-bypass-of-paypal-s-two-factor-authentication</url><text></text></story> |
8,144,689 | 8,144,805 | 1 | 2 | 8,144,212 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>nfoz</author><text>&gt; Your browser doesn&#x27;t support all of the features required for this demo. Please consider using the latest version of Chrome.<p>I guess &quot;today&#x27;s web&quot; is not an Open web, and has a single-point-of-failure hard-dependency on Google (at multiple levels).</text><parent_chain><item><author>html5web</author><text>Holy shit! This is great presentation <a href="http://hello.p5js.org/" rel="nofollow">http:&#x2F;&#x2F;hello.p5js.org&#x2F;</a></text></item></parent_chain></comment><story><title>P5.js: Processing for today’s web</title><url>http://p5js.org</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>JoshTriplett</author><text>Definitely interesting, but it&#x27;s unfortunately not very accessible; much of the information is only conveyed through the audio, and the video doesn&#x27;t have any subtitles or a transcript.</text><parent_chain><item><author>html5web</author><text>Holy shit! This is great presentation <a href="http://hello.p5js.org/" rel="nofollow">http:&#x2F;&#x2F;hello.p5js.org&#x2F;</a></text></item></parent_chain></comment><story><title>P5.js: Processing for today’s web</title><url>http://p5js.org</url></story> |
14,051,819 | 14,052,071 | 1 | 2 | 14,050,692 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>nickik</author><text>&gt; So, the implicit assumption of markets as the &#x27;natural state&#x27; of human organization has not real basis.<p>I would agree. I don&#x27;t think such a general statement is valid.<p>&gt; Even money is an invention of the state.<p>This I highly disagree with. I think the evidence is quite clear that money was independently arrived at both by state and by trade. It depends a bit on how you define it, but I think no other conclusion is possible.<p>&gt; It&#x27;s the idea that markets know what is better for us what many reject.<p>I don&#x27;t understand who is making that argument.The hole point of Hayek is that you can follow your own goals and as long as you are in a market structure you will be helped in doing so.<p>If with &#x27;us&#x27; you mean a state by democratic rule then the matter gets more complicated because its not at all clear that the outcome of the democratic process is a better &#x27;aggregation of wills&#x27; then a market process.</text><parent_chain><item><author>RobertoG</author><text>&quot;[..] Exchange, as practised by people for about the last 100,000 years [..]&quot;<p>We know that exchange is just one more activity that humans do, but, historically, in the thousand of years context, it was not fundamental.<p>We could argue that in the palaeolithic the social organization had little to do with markets. We could argue that in the neolithic, the social organization was, in most cases, hierarchical and top-down.<p>So, the implicit assumption of markets as the &#x27;natural state&#x27; of human organization has not real basis. Even money is an invention of the state.<p>The idea that markets are powerful tools don&#x27;t need to be defended. It&#x27;s the idea that markets know what is better for us what many reject.<p>It&#x27;s like saying that we should just start the lawnmower and leave it to decide what to cut. Then, when we don&#x27;t like the garden, we have to accept it&#x27;s for the best, because if a better garden was possible is what we would have.</text></item></parent_chain></comment><story><title>Friedrich Hayek and the Collective Brain</title><url>https://capx.co/friedrich-hayek-and-the-collective-brain/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>jasode</author><text><i>&gt;Even money is an invention of the state.</i><p>The existence of money precedes sovereign governments. The only prerequisite for &quot;money&quot; is consumption decoupled from the instantaneous moment of the trade (aka not direct barter) and human memories to keep track of them. That form of &quot;money&quot; has been happening for thousands of years. The prerequisite for &quot;currency&quot; is any item (coins, cigarettes, hotel loyalty points, scrips, etc) that&#x27;s frequently used as an intermediate store of value to obtain other items.<p>However, a <i>fiat</i> currency requires a modern state to convince citizens to put faith into authorized pieces of paper instead of cattle&#x2F;tobacco&#x2F;yams&#x2F;gold&#x2F;diamonds&#x2F;etc. If the citizens lose faith in government-printed money (e.g. Zimbabwe, Germany Weimar Republic), people will fall back on underground &quot;organic money&quot;.</text><parent_chain><item><author>RobertoG</author><text>&quot;[..] Exchange, as practised by people for about the last 100,000 years [..]&quot;<p>We know that exchange is just one more activity that humans do, but, historically, in the thousand of years context, it was not fundamental.<p>We could argue that in the palaeolithic the social organization had little to do with markets. We could argue that in the neolithic, the social organization was, in most cases, hierarchical and top-down.<p>So, the implicit assumption of markets as the &#x27;natural state&#x27; of human organization has not real basis. Even money is an invention of the state.<p>The idea that markets are powerful tools don&#x27;t need to be defended. It&#x27;s the idea that markets know what is better for us what many reject.<p>It&#x27;s like saying that we should just start the lawnmower and leave it to decide what to cut. Then, when we don&#x27;t like the garden, we have to accept it&#x27;s for the best, because if a better garden was possible is what we would have.</text></item></parent_chain></comment><story><title>Friedrich Hayek and the Collective Brain</title><url>https://capx.co/friedrich-hayek-and-the-collective-brain/</url></story> |
35,021,214 | 35,019,241 | 1 | 2 | 35,003,587 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>blackshaw</author><text>Fun fact: the 20p and 50p coins are Reuleaux heptagons[0]. This means that they have a constant diameter even though they&#x27;re not circular, which means that they can be accurately sorted by vending machines.<p>[0] <a href="https:&#x2F;&#x2F;wikiless.org&#x2F;wiki&#x2F;Reuleaux_polygon?lang=en" rel="nofollow">https:&#x2F;&#x2F;wikiless.org&#x2F;wiki&#x2F;Reuleaux_polygon?lang=en</a></text><parent_chain></parent_chain></comment><story><title>Understanding British Money: What's a Quid? A Shilling? (2020)</title><url>https://www.iheartbritain.com/understanding-british-money-whats-a-quid-a-shilling/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>MarcScott</author><text>There are also coins called the Sovereign and Britannia, which are both legal tender, although not in general circulation. Both are minted from 24 carat gold. The Sovereign has a face value of 1 pound and I think the Britannia has a face value of 5. There actual value, on gold markets, is hundreds of pounds, and for a Britannia is over a thousand. Because they are legal tender, and could theoretically be used to buy a bottle of milk, they are exempt from VAT and capital gains tax, when buying or selling.<p>There&#x27;s also enduring slang for some some values of cash, that doesn&#x27;t necessarily have an accompanying bank note. A Pony for 25 pounds and a Ton for 100 is still fairly widely understood, but mostly heard these days in Guy Ritchie movies,.</text><parent_chain></parent_chain></comment><story><title>Understanding British Money: What's a Quid? A Shilling? (2020)</title><url>https://www.iheartbritain.com/understanding-british-money-whats-a-quid-a-shilling/</url></story> |
16,060,252 | 16,059,392 | 1 | 3 | 16,056,669 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>codingdave</author><text>You don&#x27;t even need to get into the science to dislike this article. And I&#x27;m not trying to argue against low-carb... I feel better on low-carb diets myself. But this article lays out a couple scientific facts, while shaming the reader into unquestioning agreement by saying, &quot;This is X 101&quot;. But then lists a pseudo-scientific premise tied to their third &quot;fact&quot;, and tries again to shame the reader into agreement. This is simply a manipulative writing style, and we should be ignoring it, not discussing it.</text><parent_chain></parent_chain></comment><story><title>Genetic Study Supports Carbohydrate-Insulin Model of Obesity</title><url>https://medium.com/@davidludwigmd/genetic-study-supports-carbohydrate-insulin-model-of-obesity-327d84be6d2b</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>cageface</author><text>If this is true then why have many many studies shown that vegans, who generally eat a relatively high-carb &amp; low fat diet, are the <i>only</i> demographic with normal body mass index and also have much, much lower chances of developing type 2 diabetes?<p>In fact we have a lot of evidence linking high-fat diets to diabetes:<p><a href="https:&#x2F;&#x2F;nutritionfacts.org&#x2F;2016&#x2F;11&#x2F;17&#x2F;fat-is-the-cause-of-type-2-diabetes&#x2F;" rel="nofollow">https:&#x2F;&#x2F;nutritionfacts.org&#x2F;2016&#x2F;11&#x2F;17&#x2F;fat-is-the-cause-of-ty...</a><p>High fat diets also do a lot of bad things to your cardiovascular system. Proceed with caution.</text><parent_chain></parent_chain></comment><story><title>Genetic Study Supports Carbohydrate-Insulin Model of Obesity</title><url>https://medium.com/@davidludwigmd/genetic-study-supports-carbohydrate-insulin-model-of-obesity-327d84be6d2b</url></story> |
11,561,836 | 11,561,414 | 1 | 3 | 11,557,707 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>xorblurb</author><text>&gt; An implementation is not bound by the standard in its own use of the standard library functions. The implementation can use a function like memcpy in ways that would be formally undefined if they occured in user code; its implementation of memcpy just has to harmonize with that use, so that the intended behavior is ensured. This is because implementations can add their own requirements to areas that the standard leaves undefined. For instance, an implementation can add the requirement to its memcpy that the copy may overlap, if the destination has a lower address. Then, the implementation can generate code which uses memcpy that way, or make internal uses of memcpy from other library functions which use it that way. It&#x27;s just using its own (possibly not publicly documented) extension.<p>Yes. But right now they do not do that, and it&#x27;s not their implementation of memcpy they rely on, and they are exactly doing the kind of things they disallow their users to do, so the whole picture is just plain insane. They just call libc memcpy in some cases, and their rational is that &quot;it happens to work&quot;. Except nobody is actually sure about that, it might be already buggy on PPC, and the guarantee is not documented anywhere. Completely insane - especially given their very own approach in similar situations. As usual, they are prioritizing &quot;optimizations&quot; over correctness, and lets not even think about defense in depth. It&#x27;s a brand new level of insanity, even beyond their usual &quot;the standard allows us to do that&quot; excuse, because here it does not even allow that, and it seems that neither do officially all the used implementations!<p>Software engineers must loose the habit of taking all kind of crazy risks that can only lead to marginally faster execution of newly introduced bugs. That does not serve any purpose.</text><parent_chain><item><author>kazinator</author><text>The compiler is the implementation; it cannot <i>cause</i> &quot;undefined behavior&quot;.<p>What it can be is &quot;nonconforming&quot;.<p>A correct program which hits that situation continues to have well-defined behavior (which we know from the text of the program and the standard). Just the implementation isn&#x27;t handling the requirements correctly; it is not conforming.<p>An implementation is not bound by the standard in its own use of the standard library functions. The implementation can use a function like memcpy in ways that would be formally undefined if they occured in user code; its implementation of memcpy just has to harmonize with that use, so that the intended behavior is ensured.
This is because implementations can add their own requirements to areas that the standard leaves undefined. For instance, an implementation can add the requirement to its memcpy that the copy may overlap, if the destination has a lower address. Then, the implementation can generate code which uses memcpy that way, or make internal uses of memcpy from other library functions which use it that way. It&#x27;s just using its own (possibly not publicly documented) extension.</text></item></parent_chain></comment><story><title>Clang emits memcpy for std::swap, which can introduce undefined behavior</title><url>https://llvm.org/bugs/show_bug.cgi?id=27498</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>electrograv</author><text>Are you saying that Clang guarantees its own memcpy implementation will be used? I don&#x27;t know; but it seems odd that if this is fully intended that the compiler&#x2F;linker would generate warnings from its own handling of perfectly valid C code (as shown in the bug).</text><parent_chain><item><author>kazinator</author><text>The compiler is the implementation; it cannot <i>cause</i> &quot;undefined behavior&quot;.<p>What it can be is &quot;nonconforming&quot;.<p>A correct program which hits that situation continues to have well-defined behavior (which we know from the text of the program and the standard). Just the implementation isn&#x27;t handling the requirements correctly; it is not conforming.<p>An implementation is not bound by the standard in its own use of the standard library functions. The implementation can use a function like memcpy in ways that would be formally undefined if they occured in user code; its implementation of memcpy just has to harmonize with that use, so that the intended behavior is ensured.
This is because implementations can add their own requirements to areas that the standard leaves undefined. For instance, an implementation can add the requirement to its memcpy that the copy may overlap, if the destination has a lower address. Then, the implementation can generate code which uses memcpy that way, or make internal uses of memcpy from other library functions which use it that way. It&#x27;s just using its own (possibly not publicly documented) extension.</text></item></parent_chain></comment><story><title>Clang emits memcpy for std::swap, which can introduce undefined behavior</title><url>https://llvm.org/bugs/show_bug.cgi?id=27498</url></story> |
27,998,968 | 27,999,029 | 1 | 2 | 27,998,282 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>analyte123</author><text>Making it harder to evict drives up rents and worsens the housing crisis by restricting supply (why rent out a home or build units if the government can force you to let people live in it for free for well over a year) and by raising the bar for tenant selection (someone with poor credit or unconventional life history is a far greater risk if it will take months on end to get them out for not paying). I&#x27;m not a homeowner or a landlord, so I&#x27;m not exactly talking my book here.</text><parent_chain></parent_chain></comment><story><title>US states brace for ‘avalanche’ of evictions as federal moratorium ends</title><url>https://www.theguardian.com/us-news/2021/jul/29/eviction-moratorium-expiration-renters</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>post_break</author><text>I just don&#x27;t understand how the government postponed evictions without paying landlords. Can you just tell people they don&#x27;t have to work while forcing companies to pay employees? Etc it&#x27;s just bizarre. I feel for the people who needed these protections, but also recognize the people on the other side of the coin who have mortgages, utilities, etc.</text><parent_chain></parent_chain></comment><story><title>US states brace for ‘avalanche’ of evictions as federal moratorium ends</title><url>https://www.theguardian.com/us-news/2021/jul/29/eviction-moratorium-expiration-renters</url></story> |
3,089,650 | 3,089,668 | 1 | 2 | 3,089,352 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>astrofinch</author><text>&#62;“The problem is that we’re creating an international norm” — asserting the right to strike preemptively against those we suspect of planning attacks, argues Dennis M. Gormley, a senior research fellow at the University of Pittsburgh and author of “Missile Contagion,” who has called for tougher export controls on American drone technology. “The copycatting is what I worry about most.”<p>How about the fact that we're doing it, period?<p><a href="http://www.ted.com/talks/sam_richards_a_radical_experiment_in_empathy.html" rel="nofollow">http://www.ted.com/talks/sam_richards_a_radical_experiment_i...</a></text><parent_chain></parent_chain></comment><story><title>Coming Soon: the Drone Arms Race</title><url>http://www.nytimes.com/2011/10/09/sunday-review/coming-soon-the-drone-arms-race.html</url><text></text></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>grandalf</author><text>Imagine when drones the size of dragonflies carry needles containing poison to assassination targets. Today's drones are very crude in comparison.<p>Once it becomes plausible that any squirrel, mouse, dragon fly, etc. could be an assassination weapon, it will become necessary for heads of state to travel surrounded by swarms of friendly robots, in all sorts of form factors.</text><parent_chain></parent_chain></comment><story><title>Coming Soon: the Drone Arms Race</title><url>http://www.nytimes.com/2011/10/09/sunday-review/coming-soon-the-drone-arms-race.html</url><text></text></story> |
33,920,624 | 33,919,357 | 1 | 2 | 33,917,157 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>rakoo</author><text>The quote also perpetuates the free market myth: every actor is on an equal foot, has infinite amounts of time and energy to consider options, the alternatives exist and&#x2F;or are essentially free to build, and money is not a problem. That&#x27;s never been true. Somehow, there is no environment, no society at large, no inequality. I understand how someone living in the richest country working for the richest company could fool themselves into believing it, but it&#x27;s incredibly shortsighted.<p>The society we live in demands that you earn money, if you don&#x27;t want to die. The only thing that you have in a high enough amount is time, so if you use time to do anything, at some point it must earn money or you die. In the digital world there is no scarcity, so the old model of physical stuff you sell for $X a piece doesn&#x27;t work. There are no systems to guarantee a life to everyone, everyone has to fight for themselves. If you want to produce content, content that is not necessary to live, you necessarily enter non a competition for attention, for money, against everyone else. If people justifiably can&#x27;t give you money, you must resort to the only way that gives you a survival fee: shove crap in the eyes of the reader. Give them not what they want, but what others want. Influence their decisions.<p>It&#x27;s a shitty system. The analogy is interesting because if there&#x27;s a single vendor that holds what you need to survive, and they price it at an outrageously high price just for their profit, is it acceptable ? Is it OK, as a society, to say no to this practice ?</text><parent_chain><item><author>xg15</author><text>&gt; <i>People seem to think it&#x27;s the browser&#x27;s job to block ads, but my perspective is that if a business owner wants to make their business repulsive, the only sensible response is to stop using the business. Somehow once technology is involved to abstract what&#x27;s happening, people start talking about how it&#x27;s their right to unilaterally renegotiate the transaction. Or for another analogy that will likely make you upset: &quot;I hate how this store charges $10 for a banana, so I am just going to pay $2 and take the banana anyway&quot;.</i><p>What if <i>every</i> business owner has decided to make their business repulsive, because that&#x27;s a winning strategy for them?<p>The &quot;don&#x27;t just use that business&quot; idea has never worked if your goal is actually to change how the market at large behaves. See the much larger industries such as food (boycott factory farming) or energy (boycott fossil fuels).<p>Ultimately, when boycotting a business, the customer has to bear a harder cost than the business owner: The business owner loses one transaction while the customer loses the entire service. It&#x27;s only effective if large numbers of customers would quit as the same time, which is almost impossible to pull off (see above).<p>&quot;Cheating&quot;, such as blocking ads but using the service anyway is one way to solve that power imbalance and actually put pressure on sites to look for another business model.</text></item></parent_chain></comment><story><title>Chrome, 10 Years Later</title><url>https://neugierig.org/software/blog/2022/12/chrome.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>yakubin</author><text>I find the entire analogy dubious. When I see a link, I don’t know what sort of ads or JS is on the page it leads to. By blocking ads I am not renegotiating any transactions, because I never entered any transaction. If anything, it seems the author of the post thinks it’s okay for website owners to unilaterally dictate the terms of transaction and force visitors into them.<p>When I buy a banana, I see the price beforehand. With ads on websites it’s more as if upon me taking the banana, the banana seller gained the right to search my pockets and take anything they fancy.</text><parent_chain><item><author>xg15</author><text>&gt; <i>People seem to think it&#x27;s the browser&#x27;s job to block ads, but my perspective is that if a business owner wants to make their business repulsive, the only sensible response is to stop using the business. Somehow once technology is involved to abstract what&#x27;s happening, people start talking about how it&#x27;s their right to unilaterally renegotiate the transaction. Or for another analogy that will likely make you upset: &quot;I hate how this store charges $10 for a banana, so I am just going to pay $2 and take the banana anyway&quot;.</i><p>What if <i>every</i> business owner has decided to make their business repulsive, because that&#x27;s a winning strategy for them?<p>The &quot;don&#x27;t just use that business&quot; idea has never worked if your goal is actually to change how the market at large behaves. See the much larger industries such as food (boycott factory farming) or energy (boycott fossil fuels).<p>Ultimately, when boycotting a business, the customer has to bear a harder cost than the business owner: The business owner loses one transaction while the customer loses the entire service. It&#x27;s only effective if large numbers of customers would quit as the same time, which is almost impossible to pull off (see above).<p>&quot;Cheating&quot;, such as blocking ads but using the service anyway is one way to solve that power imbalance and actually put pressure on sites to look for another business model.</text></item></parent_chain></comment><story><title>Chrome, 10 Years Later</title><url>https://neugierig.org/software/blog/2022/12/chrome.html</url></story> |
37,533,085 | 37,532,940 | 1 | 3 | 37,531,801 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>layer8</author><text>Where I work, having internal services be accessed by employees’ own, unmanaged devices would be a no-go anyway. It would be considered a huge security loophole.</text><parent_chain><item><author>paranoidrobot</author><text>Adding CAs to trust stores on devices and in apps is a major pain.<p>If you have unmanaged devices this becomes even more painful.<p>&quot;Oh, hi, welcome to the company, please install this Root CA onto your machine to access &lt;internal service&gt;&quot;<p>Because you can&#x27;t scope CAs to specific domains, this causes everyone with any idea about security to start being concerned.</text></item><item><author>proto_lambda</author><text>If the subdomains aren&#x27;t supposed to be public, the public also doesn&#x27;t need to trust the TLS certs. Sign them with your own CA and trust it on the devices that should be able to access the domains.</text></item><item><author>TekMol</author><text>That&#x27;s why HTTPS is still a pain in the butt. 30 years after it was invented.<p>I don&#x27;t want internally used subdomains to be public. Because of certificate transparency, the only way to achieve that is via wildcard certs.<p>Let&#x27;s encrypt only supports cumbersome validation methods for those. Like changing DNS records every time you need to renew the cert.<p>Pretty annoying.</text></item><item><author>Brananarchy</author><text>As others have said, certificate transparency seems to be doing some heavy lifting here. It reports subdomains for me that have never had a public CNAME or A record, but have had let&#x27;s encrypt certs issued for internal use.<p>It&#x27;s also missing some that have not had certs issued, but that are in public DNS</text></item></parent_chain></comment><story><title>Subdomain.center – discover all subdomains for a domain</title><url>https://www.subdomain.center/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>bostik</author><text>As sibling poster already wrote, technically you <i>can</i> scope a CA to a set of subdomains only. Or try. The spec entry is &quot;nameConstraints&quot; but for a number of reasons it may not be well supported.<p>Some of those reasons are absolutely hilarious. I needed to set up an internal CA back in 2015, and wanted to limit the blast radius in case the private key was leaked. (Usually a &quot;when&quot;, not &quot;if&quot; scenario.) I learned about the nameConstraints field and tried to use it. OpenSSL would ignore the key in a CSR input file. Okay, fine, the spec has an OID for the field so I reached for the nearest ASN.1 library to construct a modified CSR with the field in place.<p>OpenSSL broke trying to parse the file. Go&#x27;s implementation blew up with a magnificent trace. I gave up and the internal CA was generated with a global validity scope.<p>I later learned that apparently Microsoft&#x27;s PKI libraries had support for scope limits, but the feature was not used in real life. Likely because if such a thing came into contact with anything else in the wild, the underlying libraries would just implode.<p>If you had a self-signed client cert with a nameConstraints in the supplied CA chain, you could probably still crash a non-trivial fraction of web servers.</text><parent_chain><item><author>paranoidrobot</author><text>Adding CAs to trust stores on devices and in apps is a major pain.<p>If you have unmanaged devices this becomes even more painful.<p>&quot;Oh, hi, welcome to the company, please install this Root CA onto your machine to access &lt;internal service&gt;&quot;<p>Because you can&#x27;t scope CAs to specific domains, this causes everyone with any idea about security to start being concerned.</text></item><item><author>proto_lambda</author><text>If the subdomains aren&#x27;t supposed to be public, the public also doesn&#x27;t need to trust the TLS certs. Sign them with your own CA and trust it on the devices that should be able to access the domains.</text></item><item><author>TekMol</author><text>That&#x27;s why HTTPS is still a pain in the butt. 30 years after it was invented.<p>I don&#x27;t want internally used subdomains to be public. Because of certificate transparency, the only way to achieve that is via wildcard certs.<p>Let&#x27;s encrypt only supports cumbersome validation methods for those. Like changing DNS records every time you need to renew the cert.<p>Pretty annoying.</text></item><item><author>Brananarchy</author><text>As others have said, certificate transparency seems to be doing some heavy lifting here. It reports subdomains for me that have never had a public CNAME or A record, but have had let&#x27;s encrypt certs issued for internal use.<p>It&#x27;s also missing some that have not had certs issued, but that are in public DNS</text></item></parent_chain></comment><story><title>Subdomain.center – discover all subdomains for a domain</title><url>https://www.subdomain.center/</url></story> |
38,595,123 | 38,594,888 | 1 | 2 | 38,594,139 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>cperciva</author><text>Note: In most cases you don&#x27;t want to split pages prior to insertion as is being done here. Instead, you want to insert data first, and then restore the page size invariants at the end (prior to committing the operation &#x2F; writing to disk &#x2F; etc). If you&#x27;re doing multiple operations at once (e.g. adding new keys and deleting others) it may turn out that you can avoid the expensive page-splitting operation by postponing it.</text><parent_chain></parent_chain></comment><story><title>The subtleties of proper B+Tree implementation</title><url>https://ayende.com/blog/198241-B/the-subtleties-of-proper-b-tree-implementation</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>travisjungroth</author><text>There’s something to generalize here. If you run out of X, split by X. This bug happens when you run out of <i>space</i>, but split by <i>count</i>. Author’s comment said he fixed it by splitting by size (space taken).</text><parent_chain></parent_chain></comment><story><title>The subtleties of proper B+Tree implementation</title><url>https://ayende.com/blog/198241-B/the-subtleties-of-proper-b-tree-implementation</url></story> |
2,870,381 | 2,869,551 | 1 | 2 | 2,869,194 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>hristov</author><text>Here is a bit of 2000 bubble lore about a company that did the same thing.<p><a href="http://www.jamesaltucher.com/2011/02/my-name-is-james-a-and-im-an-alcoholic/" rel="nofollow">http://www.jamesaltucher.com/2011/02/my-name-is-james-a-and-...</a><p>I am not saying this is relvant to anything, but it is just interesting.<p>In any event good luck to Envolve. I am sure they will do much better than gooey, mostly because they do not require users to download or install anything.</text><parent_chain></parent_chain></comment><story><title>Envolve (YC S11) Launches An API For Real-Time Chat</title><url>http://techcrunch.com/2011/08/10/yc-funded-envolve-launches-an-api-for-real-time-chat/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>staunch</author><text>I hope this one makes it to its full potential. A heck of a lot more sites should have chat embedded on them than currently do. HN is a perfect example. We should have a "Chat" link in the navigation bar where we can hang out. We should be automatically signed in with our existing usernames.<p>A while ago I looked into doing this and were no good options. Mibbit was the closest but it's a bit ugly, doesn't have much of an API, and relies on IRC (which has pros and cons).<p>Personally I hate the Meebo-style bar they've implemented, but the actual chat is good and you can embed it in a page and disable the bar entirely.</text><parent_chain></parent_chain></comment><story><title>Envolve (YC S11) Launches An API For Real-Time Chat</title><url>http://techcrunch.com/2011/08/10/yc-funded-envolve-launches-an-api-for-real-time-chat/</url></story> |
25,093,476 | 25,093,572 | 1 | 2 | 25,092,605 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>bigbubba</author><text>It sounds to me like goodells is relating their experiences.<p>&gt; <i>Presumably there would be some up front report and assessment of whether the person is exhibiting violent behavior.</i><p>That&#x27;s a very presumptuous thing to presume, when the person who actually has personal experience with the matter says that dispatch is notorious for misevaluating situations (surely through no fault of their own much of the time, since dispatch is not on the scene and can only relay what they&#x27;ve been told.)</text><parent_chain><item><author>psyc</author><text>Sounds to me like you’re falling right into the stigmatizing myth that the mentally ill are especially likely to be violent. Even calling them “the worst society has to offer”, and so far nobody is calling you on it. Presumably there would be some up front report and assessment of whether the person is exhibiting violent behavior. The <i>actual</i> “worst of society” should obviously be dealt with by police.</text></item><item><author>goodells</author><text>I work as an EMT for a 911 service. The general attitude that I have and other EMS providers I’ve talked with seem to share is that this won’t end well.<p>The first thing we’re taught is that the scene must be safe. If it’s not safe, we stage nearby until law enforcement or fire tell us to come in. The 911 dispatch is notorious for misevaluating the nature and severity of a situation, and generally we are toned out to an address and keep getting updates with call details as we are driving there. In this country where anyone can have a gun on them, there is no way in hell that I and my partner are approaching an emotionally disturbed person with no way to defend ourselves. If something goes wrong, the most effective weapon we have is an oxygen tank. And now the public’s perception of drugs like ketamine for chemical restraint is souring, so the message seems to be “Go deal with the worst our society has to offer, with no backup in case they try to hurt you, no not even safe chemical restraints. And no sorry we can’t pay you more than a cashier at WalMart... but you’re heroes!” Just last year a firefighter paramedic in my state was shot dead after administering naloxone to a man and saving his life.<p>Part of it is the compensation. Law enforcement officers are paid substantially more than the EMS folks here with the understanding that they take on more risk. We make $12 hourly... not enough to accept drastically increasing our chances of being hurt or killed.</text></item></parent_chain></comment><story><title>NYC pilot tries mental health responders in place of police</title><url>https://www.bloomberg.com/news/articles/2020-11-13/nyc-pilot-sends-health-workers-in-place-of-police</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>NoOneNew</author><text>And you&#x27;re falling into the trap of &quot;everything works in theory&quot;. Dont pretend the real world is a clear cut place. Boots on the ground experience breats armchair keyboard academics.</text><parent_chain><item><author>psyc</author><text>Sounds to me like you’re falling right into the stigmatizing myth that the mentally ill are especially likely to be violent. Even calling them “the worst society has to offer”, and so far nobody is calling you on it. Presumably there would be some up front report and assessment of whether the person is exhibiting violent behavior. The <i>actual</i> “worst of society” should obviously be dealt with by police.</text></item><item><author>goodells</author><text>I work as an EMT for a 911 service. The general attitude that I have and other EMS providers I’ve talked with seem to share is that this won’t end well.<p>The first thing we’re taught is that the scene must be safe. If it’s not safe, we stage nearby until law enforcement or fire tell us to come in. The 911 dispatch is notorious for misevaluating the nature and severity of a situation, and generally we are toned out to an address and keep getting updates with call details as we are driving there. In this country where anyone can have a gun on them, there is no way in hell that I and my partner are approaching an emotionally disturbed person with no way to defend ourselves. If something goes wrong, the most effective weapon we have is an oxygen tank. And now the public’s perception of drugs like ketamine for chemical restraint is souring, so the message seems to be “Go deal with the worst our society has to offer, with no backup in case they try to hurt you, no not even safe chemical restraints. And no sorry we can’t pay you more than a cashier at WalMart... but you’re heroes!” Just last year a firefighter paramedic in my state was shot dead after administering naloxone to a man and saving his life.<p>Part of it is the compensation. Law enforcement officers are paid substantially more than the EMS folks here with the understanding that they take on more risk. We make $12 hourly... not enough to accept drastically increasing our chances of being hurt or killed.</text></item></parent_chain></comment><story><title>NYC pilot tries mental health responders in place of police</title><url>https://www.bloomberg.com/news/articles/2020-11-13/nyc-pilot-sends-health-workers-in-place-of-police</url></story> |
5,243,738 | 5,243,325 | 1 | 3 | 5,239,673 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>grey-area</author><text>Don't you have a dev db somewhere that you can replicate the live db to? Time spent setting that up will be more than repaid by the time and stress saved when you have to do a quick fix - you can simply run your changes, check it all works on your replicated site, and <i>then</i> make the changes on your live db (preferably with some sort of migration tool which applies the same sql and backs up first). If you have a regular backup process you could tie into that to populate the dev database.<p>Even if you can't replicate the entire live db, if you can automate backup, deployment of changes and test first elsewhere it makes the entire process far less fraught.</text><parent_chain><item><author>mafro</author><text>This. Back in the day when I was in more of an analyst role, I ended up /having/ to hack on the live DB frequently (reasons for this were myriad).<p>1. Always, always make a backup just before the hack.<p>2. Write a small set queries like 3pt14159's to check uniqueness and other pertinent properties.<p>3. Write a SELECT query to show the data you are going to change.<p>4. Borrow the WHERE clause from 3, and write your UPDATE statement.<p>5. Run 4, and then run 3 again to see that you successfully fixed it.<p>6. When it goes wrong, restore the backup from 1 :0</text></item><item><author>3pt14159</author><text>I've never screwed it up on a live database, but I do take about 5 mins, first reviewing the keys, the type, whether or not something can be null, checking to see if critical columns have<p><pre><code> select count(distinct column_name) having count(distinct column_name) &#62; 1;
</code></pre>
To make sure that there isn't an underlying uniqueness assumption.<p>Sure I <i>could</i> do it in 10 seconds and save myself 290 seconds (a 97% savings!) but then one day I'd have to scramble like crazy in the middle of the night trying to figure out what I screwed up for hours on end.<p>I'm not saying don't build an admin tool, obviously those are needed for things like banning users, but just get in there and carefully fix the data if something is wrong.</text></item><item><author>lmm</author><text>Typing sudo won't save you, but using a higher-level interface will. Everyone I've ever known to change something in the database by hand, everyone at all, even on a hobby project that they know like the back of their hand, has screwed it up sooner or later. At some point the pain tells you you should stop doing that, and you create an admin tool that lets you do what you need to repeatably and safely.</text></item><item><author>lifeisstillgood</author><text>There are a number of comments that add up to "what steps will you take to ensure this does not happen again" - akin to a incident review. As speculation that's fine, as advice, I don't think it <i>should</i> be listened to.<p>I am reminded of an long-in-the-tooth sysadmin of my acquaintance who logged in everywhere as root. His theory - "they are my boxes. I screw it up, I fix it."
I eventually realised that typing sudo every time he touched a box was no defence against doing the wrong thing.<p>An awful lot of sites at 1.2m views would have outsourced the running and development of the whole thing - there are entreprenuers who say its not even worth our time to code up the MVP. I find this approach sensible from a business point of view, but still it does not sit right with me.<p>I am supposed to have a nice website with lots of good content to attract inbound marketing - so I tried getting someone on textbroker to write an article for me. It read like a High School essay - no life, no anime. And so I will probably write my own CMS and my own content.<p>And pg sits there and writes his site in his own language, with his own moderation tools. Apart from the hilarious idea he could find a ten person ruby shop to outsource to, its nice to see someone taking the time to play again. Its why I like to see jgc on here too.<p>I am not entirely sure those thoughts are joined up (I am procrasting like crazy) but if they come to mean anything its we are playing in pg's sandbox. If the sand leaks it's his sand, and the only company this is mission critical to is YC.</text></item></parent_chain></comment><story><title>Why HN was down</title><text>Hacker News was down all last night. The problem was not due to
the new server. In fact the cause was embarrassingly stupid.<p>On a comment thread, a new user had posted some replies as siblings
instead of children. I posted a comment explaining how HN worked.
But then I decided to just fix it for him by doing some surgery in
the repl. Unfortunately I used the wrong id for one of the comments
and created a loop in the comment tree; I caused an item to be its
own grandchild. After which, when anyone tried to view the thread,
the server would try to generate an infinitely long page. The
story in question was on the frontpage, so this happened a lot.<p>For some reason I didn't check the comments after the surgery to
see if they were in the right place. I must have been distracted
by something. So I didn't notice anything was wrong till a bit
later when the server seemed to be swamped.<p>When I tailed the logs to see what was going on, the pattern looked
a lot like what happens when HN runs short of memory and starts
GCing too much. Whether it was that or something else, such problems
can usually be fixed by restarting HN. So that's what I did. But
first, since I had been writing code that day, I pushed the latest
version to the server. As long as I was going to have to restart
HN, I might as well get a fresh version.<p>After I restarted HN, the problem was still there. So I guessed
the problem must be due to something in the code I'd written that
day, and tried reverting to the previous version, and restarting the
server again. But the problem was still there. Then we (because
by this point I'd managed to get hold of Nick Sivo, YC's hacker in
residence) tried reverting to the version of HN that was on the old
server, and that didn't work either. We knew that code had worked
fine, so we figured the problem must be with the new server. So
we tried to switch back to the old server. I don't know if Nick
succeeded, because in the middle of this I gave up and went to bed.<p>When I woke up this morning, Rtm had HN running on the new server.
The bad thread was still there, but it had been pushed off the
frontpage by newer stuff. So HN as a whole wasn't dying, but there
were still signs something was amiss, e.g. that /threads?id=pg
didn't work, because of the comment I made on the thread with the
loop in it.<p>Eventually Rtm noticed that the problem seemed to be related to a
certain item id. When I looked at the item on disk I realized what
must have happened.<p>So I did some more surgery in the repl, this time more carefully,
and everything seems fine now.<p>Sorry about that.</text></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>stusmith1977</author><text>I'm going to add step 5b - save what SQL you executed (against what server, and for what reason), ideally in source control, as an audit trail.<p>Otherwise, I end up having this conversation (which actually happened):<p>Him: &#60;Big Client&#62; is having troubles! Features X, Y, and Z aren't working!
Me: Hmm, has anything changed? It was all OK on Friday.
Him: No, nothing's changed.
Me: Really?
Him: Well I ran a bunch of scripts on Saturday while I was visiting them.
Me: OK, so what exactly did you run?
Him: Just a bunch of scripts.</text><parent_chain><item><author>mafro</author><text>This. Back in the day when I was in more of an analyst role, I ended up /having/ to hack on the live DB frequently (reasons for this were myriad).<p>1. Always, always make a backup just before the hack.<p>2. Write a small set queries like 3pt14159's to check uniqueness and other pertinent properties.<p>3. Write a SELECT query to show the data you are going to change.<p>4. Borrow the WHERE clause from 3, and write your UPDATE statement.<p>5. Run 4, and then run 3 again to see that you successfully fixed it.<p>6. When it goes wrong, restore the backup from 1 :0</text></item><item><author>3pt14159</author><text>I've never screwed it up on a live database, but I do take about 5 mins, first reviewing the keys, the type, whether or not something can be null, checking to see if critical columns have<p><pre><code> select count(distinct column_name) having count(distinct column_name) &#62; 1;
</code></pre>
To make sure that there isn't an underlying uniqueness assumption.<p>Sure I <i>could</i> do it in 10 seconds and save myself 290 seconds (a 97% savings!) but then one day I'd have to scramble like crazy in the middle of the night trying to figure out what I screwed up for hours on end.<p>I'm not saying don't build an admin tool, obviously those are needed for things like banning users, but just get in there and carefully fix the data if something is wrong.</text></item><item><author>lmm</author><text>Typing sudo won't save you, but using a higher-level interface will. Everyone I've ever known to change something in the database by hand, everyone at all, even on a hobby project that they know like the back of their hand, has screwed it up sooner or later. At some point the pain tells you you should stop doing that, and you create an admin tool that lets you do what you need to repeatably and safely.</text></item><item><author>lifeisstillgood</author><text>There are a number of comments that add up to "what steps will you take to ensure this does not happen again" - akin to a incident review. As speculation that's fine, as advice, I don't think it <i>should</i> be listened to.<p>I am reminded of an long-in-the-tooth sysadmin of my acquaintance who logged in everywhere as root. His theory - "they are my boxes. I screw it up, I fix it."
I eventually realised that typing sudo every time he touched a box was no defence against doing the wrong thing.<p>An awful lot of sites at 1.2m views would have outsourced the running and development of the whole thing - there are entreprenuers who say its not even worth our time to code up the MVP. I find this approach sensible from a business point of view, but still it does not sit right with me.<p>I am supposed to have a nice website with lots of good content to attract inbound marketing - so I tried getting someone on textbroker to write an article for me. It read like a High School essay - no life, no anime. And so I will probably write my own CMS and my own content.<p>And pg sits there and writes his site in his own language, with his own moderation tools. Apart from the hilarious idea he could find a ten person ruby shop to outsource to, its nice to see someone taking the time to play again. Its why I like to see jgc on here too.<p>I am not entirely sure those thoughts are joined up (I am procrasting like crazy) but if they come to mean anything its we are playing in pg's sandbox. If the sand leaks it's his sand, and the only company this is mission critical to is YC.</text></item></parent_chain></comment><story><title>Why HN was down</title><text>Hacker News was down all last night. The problem was not due to
the new server. In fact the cause was embarrassingly stupid.<p>On a comment thread, a new user had posted some replies as siblings
instead of children. I posted a comment explaining how HN worked.
But then I decided to just fix it for him by doing some surgery in
the repl. Unfortunately I used the wrong id for one of the comments
and created a loop in the comment tree; I caused an item to be its
own grandchild. After which, when anyone tried to view the thread,
the server would try to generate an infinitely long page. The
story in question was on the frontpage, so this happened a lot.<p>For some reason I didn't check the comments after the surgery to
see if they were in the right place. I must have been distracted
by something. So I didn't notice anything was wrong till a bit
later when the server seemed to be swamped.<p>When I tailed the logs to see what was going on, the pattern looked
a lot like what happens when HN runs short of memory and starts
GCing too much. Whether it was that or something else, such problems
can usually be fixed by restarting HN. So that's what I did. But
first, since I had been writing code that day, I pushed the latest
version to the server. As long as I was going to have to restart
HN, I might as well get a fresh version.<p>After I restarted HN, the problem was still there. So I guessed
the problem must be due to something in the code I'd written that
day, and tried reverting to the previous version, and restarting the
server again. But the problem was still there. Then we (because
by this point I'd managed to get hold of Nick Sivo, YC's hacker in
residence) tried reverting to the version of HN that was on the old
server, and that didn't work either. We knew that code had worked
fine, so we figured the problem must be with the new server. So
we tried to switch back to the old server. I don't know if Nick
succeeded, because in the middle of this I gave up and went to bed.<p>When I woke up this morning, Rtm had HN running on the new server.
The bad thread was still there, but it had been pushed off the
frontpage by newer stuff. So HN as a whole wasn't dying, but there
were still signs something was amiss, e.g. that /threads?id=pg
didn't work, because of the comment I made on the thread with the
loop in it.<p>Eventually Rtm noticed that the problem seemed to be related to a
certain item id. When I looked at the item on disk I realized what
must have happened.<p>So I did some more surgery in the repl, this time more carefully,
and everything seems fine now.<p>Sorry about that.</text></story> |
9,336,610 | 9,336,496 | 1 | 2 | 9,336,297 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>maxmcd</author><text>This formatting style for annotated sources always seems to work so well: <a href="http:&#x2F;&#x2F;robflaherty.github.io&#x2F;jquery-annotated-source&#x2F;docs&#x2F;01-core.html" rel="nofollow">http:&#x2F;&#x2F;robflaherty.github.io&#x2F;jquery-annotated-source&#x2F;docs&#x2F;01...</a></text><parent_chain><item><author>cryptoz</author><text>Very neat content, but does it have to be formatted like this? I respect that it preserves the original file, but it makes it very difficult to read. Comments added to the source code would serve much better for the purposes of understanding the code.<p>This tool makes it impossible to read the annotation and the source code at the same time. Clicking on &#x27;set&#x27; for example, about 20-30 lines in, lets you read the annotation, but not the function. You have to hide the annotation to read the code.<p>Wouldn&#x27;t inline&#x2F;multiline comments be so much better than this?<p>Edit: Citation&#x2F;example: <a href="http:&#x2F;&#x2F;i.imgur.com&#x2F;CHOFGML.png" rel="nofollow">http:&#x2F;&#x2F;i.imgur.com&#x2F;CHOFGML.png</a></text></item></parent_chain></comment><story><title>John Resig annotates original jQuery source code</title><url>http://genius.com/5088475</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>jasonlotito</author><text>Came here to say this. I cannot fathom how this is considered usable at all. There are also times that you click on the block of code to read, and it sends you back to the top of the page.<p>I&#x27;m more interested now in how this application got pushed to production in its current state.</text><parent_chain><item><author>cryptoz</author><text>Very neat content, but does it have to be formatted like this? I respect that it preserves the original file, but it makes it very difficult to read. Comments added to the source code would serve much better for the purposes of understanding the code.<p>This tool makes it impossible to read the annotation and the source code at the same time. Clicking on &#x27;set&#x27; for example, about 20-30 lines in, lets you read the annotation, but not the function. You have to hide the annotation to read the code.<p>Wouldn&#x27;t inline&#x2F;multiline comments be so much better than this?<p>Edit: Citation&#x2F;example: <a href="http:&#x2F;&#x2F;i.imgur.com&#x2F;CHOFGML.png" rel="nofollow">http:&#x2F;&#x2F;i.imgur.com&#x2F;CHOFGML.png</a></text></item></parent_chain></comment><story><title>John Resig annotates original jQuery source code</title><url>http://genius.com/5088475</url></story> |
41,682,008 | 41,681,157 | 1 | 3 | 41,680,621 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>ProllyInfamous</author><text>As a retired electrician attempting hobby-level &quot;learn to code&quot; (i.e. I don&#x27;t know anything about modern programming and did not even understand anything from OP&#x27;s link), this Amazon review helped me understand OP&#x27;s link:<p>&gt;..I’ve been (slowly) working my way through The Little Typer. It’s a deep dive on dependent types, starting with the very basics and building up a toy language one step at a time. I can feel it gradually changing how I think about programming (heck, how I think about thinking).<p>&gt;..It’s really, really enjoyable. The format is very approachable, even fun. Rigorous and demanding, yet doesn’t take itself too seriously. Some lisp experience is helpful, but probably (maybe?) not necessary. But do yourself a favor and learn lisp anyway ;-)<p>Maybe some day I&#x27;ll motivate myself to even figure out how to first <i>install Racket&#x2F;Pie</i> (first, I have to figure out what even these are).<p>Thanks for the motivation&#x2F;educational resource, OP.</text><parent_chain></parent_chain></comment><story><title>The Little Typer (2018)</title><url>https://thelittletyper.com/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>kevindamm</author><text>I liked the dialogue-driven format of this and the others in the series (I&#x27;ve read Schemer and Learner too), at least once I got used to the split-mind feel of it, but I feel it would be better as an interactive media instead of the books.<p>There&#x27;s an expectation that you&#x27;re following along and typing nearly every line into the appropriate REPL. I found this difficult to do while juggling the hardcopies and not any easier on an ebook reader -- I could stop worrying about cracking the spine but the digital copies I sampled or purchased always completely ruined the typesetting. All the REPL interactions are transcribed as images, and the constant focus-and-pinch-zoom disrupts the engagement.<p>I ended up just reading through and hoping to catch enough of the gist of things then doing my usual side-project-as-learning instrument thing. I hope somebody tries to build an interactive playground for this book or the Little Learner, complete with guiding dialog.<p>The typesetting in the hardcopies is really unique and impressive.</text><parent_chain></parent_chain></comment><story><title>The Little Typer (2018)</title><url>https://thelittletyper.com/</url></story> |
14,614,554 | 14,614,567 | 1 | 2 | 14,608,918 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>alacombe</author><text>&gt; It needs to separate out Vancouver and the rest. Vancouver is its own bubble of self-perpetuating nonsense propagated by Chinese money.<p>Not just Chinese money, see my comment below.<p>To summarize: 1) best climate for Canada, 2) bounded north, west, and south, 3) land already developed, 4) high immigration</text><parent_chain><item><author>cletus</author><text>So I have two issues with this post.<p>1. It needs to separate out Vancouver and the rest. Vancouver is its own bubble of self-perpetuating nonsense propagated by Chinese money.<p>2. The article states shares are better because companies can plow money back into the business, which completely misses the point because price rises aren&#x27;t pure speculation. There is a HUGE labour cost in housing such that housing prices track inflation (particularly wage inflation).<p>And that&#x27;s the real value in property investment in periods like the 1970s that saw really high inflation.<p>What&#x27;s more land represents a largely non-renewable resource. Take Manhattan as a fairly extreme example. They&#x27;re not making more land to put things on. Other cities like Chicago, LA and especially Atlanta can basically spread forever. But even in those cities, inner city land is irreplaceable and finite.<p>Now I&#x27;m not saying Canada isn&#x27;t in a bubble or that bubble won&#x27;t burst. But the author takes a naive stock-centric view of things.</text></item></parent_chain></comment><story><title>Canada's Housing Bubble Will Burst</title><url>https://www.bloomberg.com/view/articles/2017-06-21/canada-s-housing-bubble-will-burst</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>bhouston</author><text>&gt; There is a HUGE labour cost in housing<p>Not for cities like Vancouver. The cost is land. That is where the inflation is. Whenever you price out a house in the far outskirts, it is crazy cheap in comparison.</text><parent_chain><item><author>cletus</author><text>So I have two issues with this post.<p>1. It needs to separate out Vancouver and the rest. Vancouver is its own bubble of self-perpetuating nonsense propagated by Chinese money.<p>2. The article states shares are better because companies can plow money back into the business, which completely misses the point because price rises aren&#x27;t pure speculation. There is a HUGE labour cost in housing such that housing prices track inflation (particularly wage inflation).<p>And that&#x27;s the real value in property investment in periods like the 1970s that saw really high inflation.<p>What&#x27;s more land represents a largely non-renewable resource. Take Manhattan as a fairly extreme example. They&#x27;re not making more land to put things on. Other cities like Chicago, LA and especially Atlanta can basically spread forever. But even in those cities, inner city land is irreplaceable and finite.<p>Now I&#x27;m not saying Canada isn&#x27;t in a bubble or that bubble won&#x27;t burst. But the author takes a naive stock-centric view of things.</text></item></parent_chain></comment><story><title>Canada's Housing Bubble Will Burst</title><url>https://www.bloomberg.com/view/articles/2017-06-21/canada-s-housing-bubble-will-burst</url></story> |
38,221,875 | 38,220,473 | 1 | 3 | 38,216,353 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>tmacam</author><text><p><pre><code> &quot; I fear the day that technology will surpass our human
interaction. The world will have a generation of idiots.&quot;
</code></pre>
While I loved this quote (because I aligns with my opinion), it doesn&#x27;t look it is from Einstein. At least searching for it in google I&#x27;ve found quite a few pages precisely debunking this attribution.</text><parent_chain><item><author>nonrandomstring</author><text>This is surely the strongest endorsement of education. Einstein nails
what Emma Goldman said, &quot;The most violent element in society is
ignorance.&quot;<p>There is such straightforward simplicity to his writing that it is
over-interpreted today. Chiefly, Einstein&#x27;s writing is compassionate,
often comparable to Erich Fromm. Here we take him as an &quot;elitist&quot;
insulting &quot;the masses&quot;, who are by our definition today &quot;poor&quot;.<p>He often calls people idiots and is scathing about the uses to which
we put technology;<p><pre><code> &quot; I fear the day that technology will surpass our human
interaction. The world will have a generation of idiots.&quot;
&quot;Technological progress is like an axe in the hands of a
pathological criminal&quot;
</code></pre>
Albert Einstein would not survive for one moment in what we call
&quot;Academia&quot; today. One of my students once remarked that he&#x27;d have been
a Ted Kaczynski, only he built bigger bombs.<p>Yet my favourite, which I&#x27;d hope people of the 7th Millennium will
read and nod at:<p><pre><code> &quot;In any conflict between humanity and technology, humanity will win.&quot;</code></pre></text></item></parent_chain></comment><story><title>Albert Einstein in 1939 composed a message for the people of AD 6939</title><url>https://www.futilitycloset.com/2023/11/10/comment-8/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>josu</author><text>&gt;&quot;In any conflict between humanity and technology, humanity will win.&quot;<p>If humanity loses even once it&#x27;s Game Over.</text><parent_chain><item><author>nonrandomstring</author><text>This is surely the strongest endorsement of education. Einstein nails
what Emma Goldman said, &quot;The most violent element in society is
ignorance.&quot;<p>There is such straightforward simplicity to his writing that it is
over-interpreted today. Chiefly, Einstein&#x27;s writing is compassionate,
often comparable to Erich Fromm. Here we take him as an &quot;elitist&quot;
insulting &quot;the masses&quot;, who are by our definition today &quot;poor&quot;.<p>He often calls people idiots and is scathing about the uses to which
we put technology;<p><pre><code> &quot; I fear the day that technology will surpass our human
interaction. The world will have a generation of idiots.&quot;
&quot;Technological progress is like an axe in the hands of a
pathological criminal&quot;
</code></pre>
Albert Einstein would not survive for one moment in what we call
&quot;Academia&quot; today. One of my students once remarked that he&#x27;d have been
a Ted Kaczynski, only he built bigger bombs.<p>Yet my favourite, which I&#x27;d hope people of the 7th Millennium will
read and nod at:<p><pre><code> &quot;In any conflict between humanity and technology, humanity will win.&quot;</code></pre></text></item></parent_chain></comment><story><title>Albert Einstein in 1939 composed a message for the people of AD 6939</title><url>https://www.futilitycloset.com/2023/11/10/comment-8/</url></story> |
18,165,330 | 18,164,604 | 1 | 3 | 18,163,552 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>gns24</author><text>To be honest my rational view is that the situation is hopeless. We haven&#x27;t even managed to stop global emissions increasing annually yet. That&#x27;s the second derivative of temperature (even ignoring any feedback loops); the rate at which we&#x27;re causing temperatures to increase is itself still increasing.<p>I disagree about special interest groups being the main problem; political will of the population is just as much of an issue. Even in the UK where the majority of people do believe in climate change, successive governments have failed to increase duty on fuel because of a popular outcry every time they attempt to.<p>I have friends who alternate posts on social media between complaining about a lack of action on climate change and posting photos of their latest intercontinental travel. People are prepared to do quite a lot to look after the planet. What they seem less accepting of is <i>not</i> doing things.</text><parent_chain><item><author>554070</author><text>Does anyone else feel like we&#x27;ll fail to make reasonable progress on climate change? I&#x27;m naturally inclined towards pessimism, but I feel that the political solutions aren&#x27;t going to work out and that the market isn&#x27;t moving fast enough for humanity to get ahead of it.<p>Edit: to clarify, I think that political solutions won&#x27;t work not because there aren&#x27;t good ideas or that we couldn&#x27;t collectively do a lot, but because there&#x27;s too much money and power held by special interest groups that pollute.</text></item></parent_chain></comment><story><title>Major Climate Report Describes a Strong Risk of Crisis as Early as 2040</title><url>https://www.nytimes.com/2018/10/07/climate/ipcc-climate-report-2040.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>twblalock</author><text>I have zero confidence that enough action will be taken before it is too late.<p>Even if almost every country in the world takes immediate drastic action, all it takes is inaction by a single major polluter to ensure that the negative consequences of climate change will occur anyway.<p>Voters will think, why should we make sacrifices when we will get screwed anyway, because other countries won&#x27;t take action?</text><parent_chain><item><author>554070</author><text>Does anyone else feel like we&#x27;ll fail to make reasonable progress on climate change? I&#x27;m naturally inclined towards pessimism, but I feel that the political solutions aren&#x27;t going to work out and that the market isn&#x27;t moving fast enough for humanity to get ahead of it.<p>Edit: to clarify, I think that political solutions won&#x27;t work not because there aren&#x27;t good ideas or that we couldn&#x27;t collectively do a lot, but because there&#x27;s too much money and power held by special interest groups that pollute.</text></item></parent_chain></comment><story><title>Major Climate Report Describes a Strong Risk of Crisis as Early as 2040</title><url>https://www.nytimes.com/2018/10/07/climate/ipcc-climate-report-2040.html</url></story> |
9,227,036 | 9,226,507 | 1 | 2 | 9,225,842 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>kbenson</author><text>I think it can be broken up into three parts. First:<p><i>Like Dropbox, but behind your firewall.</i><p>For many people, that&#x27;s a sufficient description to get the idea. If not, you have the second part:<p><i>File Sync and Share for the enterprise.</i><p>Not as descriptive as the first part if you know what Dropbox is, but if you don&#x27;t it will at least let you know how to categorize the product and whether it&#x27;s something you might remotely be interested in. Finally:<p><i>Free up to 30 users.</i><p>Now they&#x27;ve made sure the next most salient point is given, the next thing you would most likely want to know. Everything else is something you can dig a little deeper for, but for the most part you know whether this is something you want to pursue or not. I think it&#x27;s brilliant.</text><parent_chain><item><author>tnorthcutt</author><text>I mostly agree with you, but their first sentence (&quot;Like Dropbox...&quot;) relies on you knowing what Dropbox is. Which, as you pointed out, isn&#x27;t good enough for people who don&#x27;t ;).</text></item><item><author>chrisdotcode</author><text>On a tangential note, I had no idea what AeroFS is, so I clicked on their landing page.<p>&gt; Like Dropbox, but behind your firewall. File Sync and Share for the enterprise. Free up to 30 users.<p>Boom. I immediately am fully educated about what this does. I wasn&#x27;t forced to watch a 2 minute video with no sound at work, or to google the product - questioning about why it&#x27;s popular[0].<p>This is how you write effective copy.<p>[0] Notable offenders are yeoman and dropbox itself - both of which, while widely-used products - are completely opaque in what they do from their initial text. &quot;You already know what I do&quot; isn&#x27;t good enough for people who don&#x27;t.</text></item></parent_chain></comment><story><title>AeroFS is now free up to 30 users</title><url>https://www.aerofs.com/blog/aerofs-is-now-free-up-to-30-users/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>chrisdotcode</author><text>You&#x27;re totally right. Nobody has infinite context.<p>Even still, &quot;Like X for Y&quot; is far better than &quot;The product you&#x27;ll love from the people you love&quot;.</text><parent_chain><item><author>tnorthcutt</author><text>I mostly agree with you, but their first sentence (&quot;Like Dropbox...&quot;) relies on you knowing what Dropbox is. Which, as you pointed out, isn&#x27;t good enough for people who don&#x27;t ;).</text></item><item><author>chrisdotcode</author><text>On a tangential note, I had no idea what AeroFS is, so I clicked on their landing page.<p>&gt; Like Dropbox, but behind your firewall. File Sync and Share for the enterprise. Free up to 30 users.<p>Boom. I immediately am fully educated about what this does. I wasn&#x27;t forced to watch a 2 minute video with no sound at work, or to google the product - questioning about why it&#x27;s popular[0].<p>This is how you write effective copy.<p>[0] Notable offenders are yeoman and dropbox itself - both of which, while widely-used products - are completely opaque in what they do from their initial text. &quot;You already know what I do&quot; isn&#x27;t good enough for people who don&#x27;t.</text></item></parent_chain></comment><story><title>AeroFS is now free up to 30 users</title><url>https://www.aerofs.com/blog/aerofs-is-now-free-up-to-30-users/</url></story> |
18,243,413 | 18,243,368 | 1 | 3 | 18,227,794 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>torpidor</author><text>Color <i>is</i> overrated <i>in a world where most are colorblind</i>. Red means danger or stop because you have seen a lot of stop signs. In a world of colorblind people, stop sign colors are chosen by the colorblind, based on something like &quot;is this a cheap metal&quot; rather than design language (which no longer exists for color). Instead we would use reflectivity or something to indicate danger. As to whether or not the varying-colored stop signs leads to a statistically significant number of color-sighted people blowing through them it is hard to say, but does seem a legitimate safety concern.<p>And this is the situation in music; keys are chosen based on the technical details of the musician rather than a design language. Meanwhile, we do have a design language based on relative pitch (e.g. a 5&#x2F;7 chord &quot;leads&quot; to the tonic). Of course you can see that the same way you can see a purple stop sign, but you may lack some of the pattern-matching intuition of your peers.<p>As a musician with relative pitch and the child of a musician with perfect pitch, I have watched them get puzzled a lot navigating a design language that is very obvious to me. Perhaps you are a better musician than they are, or perhaps you avoid areas where the design language dominates. Either way, I would not trade places with you, unless the rest of society did also.</text><parent_chain><item><author>psychometry</author><text>Your comment is analogous to a colorblind person telling everyone how overrated red and green are.<p>First, someone with &quot;untrained&quot; AP (I assume you mean no musical training) wouldn&#x27;t be in a position where they&#x27;d be needing to transcribe a Bach chorale, would they? Any AP possessor with musical training--I am one--finds transcription trivially easy since there&#x27;s only rhythm to figure out.<p>While it can be momentarily distracting when music doesn&#x27;t match its normal key due to transposition or tuning issues, I can move past it without too much effort, although I am continually aware of the discrepancy. It&#x27;s like the visual illusion where the ballerina can spin both clockwise and counterclockwise depending on your perspective.<p>The biggest benefit is being able to identify the key without having to do the initial hunt for the tonic by testing notes. This is very useful in an accompaniment situation.</text></item><item><author>tunesmith</author><text>Perfect pitch is overrated. In college as a music student with excellent relative pitch, I routinely outscored peer students with perfect pitch when taking classical ear training courses. Perfect pitch is more of a parlor trick. It&#x27;s occasionally useful when trying to tune a stringed instrument by yourself, and distracting if your ensemble starts to drift off key while remaining in tune with each other.<p>Also, trained relative pitch is better than untrained perfect pitch. For instance, if my instructor played four bars of a four-part bach chorale on the piano (sixteen quarter notes, perhaps a couple of eighth-note passing tones), I could fully notate it within three repetitions, sometimes on first listen - <i>if</i> I were initially told what key it was in. Someone with untrained perfect pitch would be able to tell if the instructor was lying about what key it was in, but they wouldn&#x27;t be able to notate it. So in that scenario, the only thing it&#x27;s useful for is recognizing what key it&#x27;s in. If I hadn&#x27;t been told, I could have just notated it in C and then transposed it to the right key later.<p>I would later learn that being able to notate a bach chorale by ear is nothing compared to the kind of ear skills you need as a jazz musician - but again, there, perfect pitch isn&#x27;t important or super useful. We learn chord relations - it&#x27;s <i>all</i> relative.</text></item></parent_chain></comment><story><title>Acquiring absolute pitch in adulthood is difficult but possible</title><url>https://www.biorxiv.org/content/early/2018/07/03/355933</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>aczerepinski</author><text>Agreed. I had a special ear training class at Berklee for all the incoming freshman who aced placements, and if I recall correctly everyone in the class had perfect pitch. Transcribing was trivial across the board. I transcribed solos for jazz magazines as a side gig, and filled notebooks with solos in my personal practice.<p>Without a doubt, relative pitch and learning theory are important skills too, but they aren&#x27;t mutually exclusive.</text><parent_chain><item><author>psychometry</author><text>Your comment is analogous to a colorblind person telling everyone how overrated red and green are.<p>First, someone with &quot;untrained&quot; AP (I assume you mean no musical training) wouldn&#x27;t be in a position where they&#x27;d be needing to transcribe a Bach chorale, would they? Any AP possessor with musical training--I am one--finds transcription trivially easy since there&#x27;s only rhythm to figure out.<p>While it can be momentarily distracting when music doesn&#x27;t match its normal key due to transposition or tuning issues, I can move past it without too much effort, although I am continually aware of the discrepancy. It&#x27;s like the visual illusion where the ballerina can spin both clockwise and counterclockwise depending on your perspective.<p>The biggest benefit is being able to identify the key without having to do the initial hunt for the tonic by testing notes. This is very useful in an accompaniment situation.</text></item><item><author>tunesmith</author><text>Perfect pitch is overrated. In college as a music student with excellent relative pitch, I routinely outscored peer students with perfect pitch when taking classical ear training courses. Perfect pitch is more of a parlor trick. It&#x27;s occasionally useful when trying to tune a stringed instrument by yourself, and distracting if your ensemble starts to drift off key while remaining in tune with each other.<p>Also, trained relative pitch is better than untrained perfect pitch. For instance, if my instructor played four bars of a four-part bach chorale on the piano (sixteen quarter notes, perhaps a couple of eighth-note passing tones), I could fully notate it within three repetitions, sometimes on first listen - <i>if</i> I were initially told what key it was in. Someone with untrained perfect pitch would be able to tell if the instructor was lying about what key it was in, but they wouldn&#x27;t be able to notate it. So in that scenario, the only thing it&#x27;s useful for is recognizing what key it&#x27;s in. If I hadn&#x27;t been told, I could have just notated it in C and then transposed it to the right key later.<p>I would later learn that being able to notate a bach chorale by ear is nothing compared to the kind of ear skills you need as a jazz musician - but again, there, perfect pitch isn&#x27;t important or super useful. We learn chord relations - it&#x27;s <i>all</i> relative.</text></item></parent_chain></comment><story><title>Acquiring absolute pitch in adulthood is difficult but possible</title><url>https://www.biorxiv.org/content/early/2018/07/03/355933</url></story> |
247,782 | 247,783 | 1 | 2 | 247,720 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>jbyers</author><text>It's a great accomplishment to book thousands of dollars of revenue within a few weeks of launch. But as the article states, this is profitability without covering salary -- a big disclaimer.</text><parent_chain></parent_chain></comment><story><title>Profitable After 3 Weeks</title><url>http://www.balsamiq.com/blog/?p=95</url><text></text></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>Maro</author><text>The mockup app rocks.<p>Is it just me or is your site a lot like 37signals?<p>I personally had some trouble finding my way around. To me, it's not clear what confluence is, what the flatworld thing is and how the mockup app ties in. No big deal though.<p>Overall, congrats!</text><parent_chain></parent_chain></comment><story><title>Profitable After 3 Weeks</title><url>http://www.balsamiq.com/blog/?p=95</url><text></text></story> |
11,258,973 | 11,257,522 | 1 | 2 | 11,257,280 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>rail2rail</author><text>We&#x27;re using TitanDB. One of the main benefits for us is that AWS has provided backend integration with DynamoDB. This affords you practically infinite and painless scaling on a pay-as-you-go model. Love it.<p><a href="https:&#x2F;&#x2F;aws.amazon.com&#x2F;blogs&#x2F;aws&#x2F;new-store-and-process-graph-data-using-the-dynamodb-storage-backend-for-titan&#x2F;" rel="nofollow">https:&#x2F;&#x2F;aws.amazon.com&#x2F;blogs&#x2F;aws&#x2F;new-store-and-process-graph...</a></text><parent_chain><item><author>valine</author><text>Question as someone new to graph databases: Are there any open source graph databases worth looking into?</text></item></parent_chain></comment><story><title>Graph Databases 101</title><url>http://www.cray.com/blog/graph-databases-101/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>kinow</author><text>Depends on what kind of data and graph you are going to store&#x2F;use. Neo4j is quite popular, cypher isn&#x27;t very hard to learn, and it has lots of examples. Might be a good choice for a beginner.<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Graph_database#List_of_graph_databases" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Graph_database#List_of_graph_d...</a></text><parent_chain><item><author>valine</author><text>Question as someone new to graph databases: Are there any open source graph databases worth looking into?</text></item></parent_chain></comment><story><title>Graph Databases 101</title><url>http://www.cray.com/blog/graph-databases-101/</url></story> |
25,556,433 | 25,556,509 | 1 | 2 | 25,555,111 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>hombre_fatal</author><text>All of us with seldom exception use our glowing rectangles as addictive dopamine drips that exploit our innate desire to scavenge for information that ends up disconnecting us from the world and, likely, things we actually find fulfilling. And we watch our own children suffer the exact same way and wonder what can actually be done about it.<p>There was a submission this morning or yesterday about &quot;if we could live our lives over&quot; where many HNers were lamenting how they felt like they were wasting their precious hours. How many of those people would say that their screen time wasn&#x27;t contributing? Or that it was actually fulfilling?<p>Not sure who here relates to the idea of spending the bulk of their screen time organizing transport and planning dinner parties or whatever. Or the idea of &quot;no, I actually do like how much time I spend on &lt;vice&gt; and I&#x27;m trying to get those numbers up even higher.&quot;<p>For some reason whenever this topic comes up, we have people playing coy with what &quot;screen time&quot; could possibly be referring to. &quot;What, you&#x27;re saying it&#x27;s bad to use my iPhone to Facetime my dying father?&quot;</text><parent_chain><item><author>repsilat</author><text>Because this thread always needs someone to say the obvious truth: &quot;Screen time&quot; isn&#x27;t the most useful concept. Maybe it was in the TV days (though with diverse programming it may not have been), but with phones&#x2F;tablets&#x2F;laptops it&#x27;s as broad a label as &quot;technology company&quot;.<p>Are we talking about chatting with friends? Doing work? Watching a show? Playing a game? Reading the news? A novel? Meeting with people? Organising transport? Finding a place to eat?<p>There is a diversity of rectangles, and for each rectangle there is a diversity of uses.</text></item></parent_chain></comment><story><title>90% of Waking Hours Spent Staring at Glowing Rectangles (2009)</title><url>https://www.theonion.com/report-90-of-waking-hours-spent-staring-at-glowing-re-1819570829</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>momokoko</author><text>I think this is a strange thing to hear from being a bit older. 30-40 years ago, most people did not spend their time reading the paper and watching TV.<p>There was vastly more time spent interacting directly with friends and family as well as hobbies and interests that were not consuming media. It was much more common for people to stop by, often unannounced and hang out and talk for several hours. Just talking in person was very popular. Also, people spent much more time on errands and house tasks. It was very rare to have landscapers or housekeepers. This was before dishwashers and people rarely ate out. So cooking and cleaning were common. Super cheap goods from China had not yet arrived so maintenance on things around the house was more common than replacement.<p>This isn’t at all to be taken as things were better, or worse, it is simply to relay that people did a lot more than consume media and communicate electronically.</text><parent_chain><item><author>repsilat</author><text>Because this thread always needs someone to say the obvious truth: &quot;Screen time&quot; isn&#x27;t the most useful concept. Maybe it was in the TV days (though with diverse programming it may not have been), but with phones&#x2F;tablets&#x2F;laptops it&#x27;s as broad a label as &quot;technology company&quot;.<p>Are we talking about chatting with friends? Doing work? Watching a show? Playing a game? Reading the news? A novel? Meeting with people? Organising transport? Finding a place to eat?<p>There is a diversity of rectangles, and for each rectangle there is a diversity of uses.</text></item></parent_chain></comment><story><title>90% of Waking Hours Spent Staring at Glowing Rectangles (2009)</title><url>https://www.theonion.com/report-90-of-waking-hours-spent-staring-at-glowing-re-1819570829</url></story> |
33,398,348 | 33,397,650 | 1 | 3 | 33,394,486 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>lamontcg</author><text>You&#x27;re sort of describing the current conditions without any analysis of how those conditions are likely to change. For example, the high interest rates right now are due to central banks looking at the rising labor prices and inflation and probably overreacting. It is very likely that the next step is going to be a massive global slowdown.<p>You&#x27;re also very likely massively overstating the case that Russia and Taiwan mean that &quot;globalization has ended&quot;.<p>I do think there&#x27;s important secular changes happening (the tight labor market and inflation are very obviously something new that hasn&#x27;t happened in 30 years), but I strongly doubt the idea that everything has turned on a dime 180 degrees to the opposite.</text><parent_chain><item><author>mmaunder</author><text>Excellent article that paints a grim picture in an understated way. To put it differently:<p>We&#x27;ve seen a huge run-up in the stock market thanks to cheap domestic and cheap foreign labor, globalization, historically low interest rates and historically low corporate taxes.<p>Interest rates are rising massively and globally to combat inflation.<p>Labor prices are increasing, globally.<p>There is a global decoupling thanks to the Russia&#x2F;Ukraine situation and the China&#x2F;Taiwan tension. This is bringing the era of globalization to its end.<p>Corporate US taxes have been as low as they&#x27;ll get for a long time due to the TCJA and will most likely only go up from current rates.<p>Given all these factors combined, it&#x27;s unlikely that price&#x2F;earnings will hold at the current high ratio i.e. stock prices have a long way to fall still. This article was published almost two months ago, but I believe it will be relevant for the next several years. We&#x27;re in for a long slow decline and then a plateau. The era of cheap labor, free money, low taxes and open global markets has come to an end.</text></item></parent_chain></comment><story><title>The coming long-run slowdown in corporate profit growth and stock returns</title><url>https://www.federalreserve.gov//econres/notes/feds-notes/the-coming-long-run-slowdown-in-corporate-profit-growth-and-stock-returns-20220906.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>afpx</author><text>How can this be? The world still seems flooded with cash, huge populations still aren’t industrialized and want development, there’s shortages of products and services in demand by middle classes. Why wouldn&#x27;t this point to more growth?</text><parent_chain><item><author>mmaunder</author><text>Excellent article that paints a grim picture in an understated way. To put it differently:<p>We&#x27;ve seen a huge run-up in the stock market thanks to cheap domestic and cheap foreign labor, globalization, historically low interest rates and historically low corporate taxes.<p>Interest rates are rising massively and globally to combat inflation.<p>Labor prices are increasing, globally.<p>There is a global decoupling thanks to the Russia&#x2F;Ukraine situation and the China&#x2F;Taiwan tension. This is bringing the era of globalization to its end.<p>Corporate US taxes have been as low as they&#x27;ll get for a long time due to the TCJA and will most likely only go up from current rates.<p>Given all these factors combined, it&#x27;s unlikely that price&#x2F;earnings will hold at the current high ratio i.e. stock prices have a long way to fall still. This article was published almost two months ago, but I believe it will be relevant for the next several years. We&#x27;re in for a long slow decline and then a plateau. The era of cheap labor, free money, low taxes and open global markets has come to an end.</text></item></parent_chain></comment><story><title>The coming long-run slowdown in corporate profit growth and stock returns</title><url>https://www.federalreserve.gov//econres/notes/feds-notes/the-coming-long-run-slowdown-in-corporate-profit-growth-and-stock-returns-20220906.html</url></story> |
20,780,762 | 20,780,648 | 1 | 2 | 20,779,142 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>xenocyon</author><text>At least part of the cause of the visible squalor we see in Seattle is that the tough-on-crime crowd has consistently opposed safe injection, harm reduction, trash pickup, housing-first, and other evidence-based policies in favor of expensive, inhumane, and pointless measures like sweeps and incarceration. Any measure the city government takes that is not overtly cruel gets slammed as coddling the homeless or &quot;attracting&quot; homeless to the city, despite the fact that the data show this trope to be a fiction.</text><parent_chain><item><author>just_lurkin</author><text>The reporters designation of &quot;figured out&quot; seems to stem more from the fact that the solution fits his own view than any actual real evidence. There is mention of the difficulties such lax policies has brought to the city, but they are waved away as being &quot;growing pains&quot; toward a new utopia.<p>I can&#x27;t say, living here, that I feel that the problem is solved. I view the needles outside my apartment as evidence to the contrary - though I suppose I&#x27;m an ignoramus for thinking that.<p>Simply strolling through Pioneer Square or most parts of International District paints a significantly different picture. One can dine at a Chinese place on Jackson and look out their window and see junkies peddling stolen goods at the bus stop. The non-enforcement of so-called &quot;petty crime&quot; used to fund drug addictions is egregious and continues to undermine the already little sense of community there is in this city of transients.<p>What I&#x27;m trying to say is that while I appreciate the difference in approach from the traditional one, I do believe that there needs to be an honest discussion about the limits of rehabilitation. More research on the subject, as it relates to Seattle, shows that there are many, many, people who take advantage of these lax policies to abuse the system, hurting others who actually need help.</text></item></parent_chain></comment><story><title>In effect, Seattle is decriminalizing the use of hard drugs</title><url>https://www.nytimes.com/2019/08/23/opinion/sunday/opioid-crisis-drug-seattle.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>rayiner</author><text>It&#x27;s interesting people always point to Portugal to support the idea that decriminalization is the way to address substance abuse. But compare Sweden, which has similar levels of drug dependency to Portugal, but takes a &quot;zero tolerance&quot; approach to drug use: <a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Drug_policy_of_Sweden" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Drug_policy_of_Sweden</a>. While Sweden does include treatment as part of its drug policy, that is a complement to, not replacement for, strict law enforcement.<p>(Swedes are very anti-drug. While a narrow majority of even <i>Republicans</i> in the US support legalization of cannabis, 83% of Swedes support keeping it illegal: <a href="https:&#x2F;&#x2F;www.reuters.com&#x2F;article&#x2F;us-sweden-cannabis&#x2F;in-anti-drug-sweden-investors-take-shine-to-cannabis-stocks-idUSKBN1GZ2FQ." rel="nofollow">https:&#x2F;&#x2F;www.reuters.com&#x2F;article&#x2F;us-sweden-cannabis&#x2F;in-anti-d...</a>)</text><parent_chain><item><author>just_lurkin</author><text>The reporters designation of &quot;figured out&quot; seems to stem more from the fact that the solution fits his own view than any actual real evidence. There is mention of the difficulties such lax policies has brought to the city, but they are waved away as being &quot;growing pains&quot; toward a new utopia.<p>I can&#x27;t say, living here, that I feel that the problem is solved. I view the needles outside my apartment as evidence to the contrary - though I suppose I&#x27;m an ignoramus for thinking that.<p>Simply strolling through Pioneer Square or most parts of International District paints a significantly different picture. One can dine at a Chinese place on Jackson and look out their window and see junkies peddling stolen goods at the bus stop. The non-enforcement of so-called &quot;petty crime&quot; used to fund drug addictions is egregious and continues to undermine the already little sense of community there is in this city of transients.<p>What I&#x27;m trying to say is that while I appreciate the difference in approach from the traditional one, I do believe that there needs to be an honest discussion about the limits of rehabilitation. More research on the subject, as it relates to Seattle, shows that there are many, many, people who take advantage of these lax policies to abuse the system, hurting others who actually need help.</text></item></parent_chain></comment><story><title>In effect, Seattle is decriminalizing the use of hard drugs</title><url>https://www.nytimes.com/2019/08/23/opinion/sunday/opioid-crisis-drug-seattle.html</url></story> |
25,189,982 | 25,190,132 | 1 | 2 | 25,189,673 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>msla</author><text>Previously:<p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=25186843" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=25186843</a></text><parent_chain></parent_chain></comment><story><title>Walmart Exclusive Wi-Fi Router Contains Backdoor to Control Devices</title><url>https://hfet.org/walmart-exclusive-wi-fi-router-contains-backdoor-to-control-devices/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>lights0123</author><text>Here&#x27;s their source, which actually contains details: <a href="https:&#x2F;&#x2F;cybernews.com&#x2F;security&#x2F;walmart-exclusive-routers-others-made-in-china-contain-backdoors-to-control-devices&#x2F;" rel="nofollow">https:&#x2F;&#x2F;cybernews.com&#x2F;security&#x2F;walmart-exclusive-routers-oth...</a></text><parent_chain></parent_chain></comment><story><title>Walmart Exclusive Wi-Fi Router Contains Backdoor to Control Devices</title><url>https://hfet.org/walmart-exclusive-wi-fi-router-contains-backdoor-to-control-devices/</url></story> |
28,678,521 | 28,678,495 | 1 | 3 | 28,678,182 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>Shank</author><text>A decade ago, Java was derided for letting developers ship apps on multiple platforms while forgoing native controls, with a high memory and storage footprint with the JRE through the JVM. While JavaScript is not Java, it has essentially become Java: instead of shipping a JRE and Jars, it’s the entirety of Chromium, with its JS VM, and a relatively high memory and storage footprint.<p>It seems to me like we haven’t changed much here, resource wise.<p>Then, particularly on mobile devices, many apps recreate native controls with weird quirks or defects that don’t play nicely with the native conventions. Just like in the Java world, you can get “almost perfect” but if the OS updates or a convention changes, the non-native apps are stuck reinventing the wheel to accommodate change (or they ignore it entirely).<p>As a developer, I love writing the same app for multiple places. As a user, I find it infuriating to deal with. While Apple is assuredly being lame by preventing other browser engines (I want Firefox, with WebRequest in blocking mode), they’re not wrong if they think that more PWAs will bring problems.</text><parent_chain></parent_chain></comment><story><title>Apple’s browser engine ban is holding back web app innovation</title><url>https://thenewstack.io/apples-browser-engine-ban-is-holding-back-web-app-innovation/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>iosawwwaaayyy</author><text>I just want ublock origin on iOS.<p>I bought an iPhone after seeing that it had Firefox, but I should have done more research. It&#x27;s not actually Firefox, just a rebranded WebKit. It doesn&#x27;t support extensions.<p>So, after trying a few paid Safari &quot;content blockers&quot; and being dissatisfied, I gave the iPhone away.<p>How is this a different situation from the antitrust case which prevented Microsoft from bundling Internet Explorer and preventing competing browsers in Windows?</text><parent_chain></parent_chain></comment><story><title>Apple’s browser engine ban is holding back web app innovation</title><url>https://thenewstack.io/apples-browser-engine-ban-is-holding-back-web-app-innovation/</url></story> |
29,708,359 | 29,705,637 | 1 | 2 | 29,702,974 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>spookylukey</author><text>I find it very strange to have claims about the database being tamper-evident etc without a clear description of the threat&#x2F;trust model, and how&#x2F;for whom it works. For example, what data does the client need to store to be sure no tampering has occurred?</text><parent_chain></parent_chain></comment><story><title>immudb – world’s fastest immutable database, built on a zero trust model</title><url>https://github.com/codenotary/immudb</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>willcipriano</author><text>&gt; You can add new versions of existing records, but never change or delete records. This lets you store critical data without fear of it being tampered.<p>&gt; immudb can be used as a key-value store or relational data structure and supports both transactions and blobs, so there are no limits to the use cases.<p>This is game changing. Use it for say a secondary data store for high value audit logs. I&#x27;ll consider using it in the future.</text><parent_chain></parent_chain></comment><story><title>immudb – world’s fastest immutable database, built on a zero trust model</title><url>https://github.com/codenotary/immudb</url></story> |
37,071,830 | 37,070,964 | 1 | 3 | 37,066,680 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>ummonk</author><text>When I worked at Meta, the execs said that many users think they&#x27;re being spied on when they see ads based on a conversation they&#x27;ve had in real life, but the execs categorically denied that this could be happening, and said it&#x27;s all just a coincidence. I thought this was a completely unfounded denial, since Meta had no way of auditing 3rd party apps on the user&#x27;s phone, and it&#x27;s perfectly plausible for another app to spy on their conversations and then use that to provide targeted ads to the Facebook account associated with the individual&#x27;s email.</text><parent_chain><item><author>ericd</author><text>The most galling offer we saw on the mobile app side was something that would turn on the user&#x27;s microphone, and listen for ads on tvs around them to track what they&#x27;d been exposed to offline. Adtech is such a thoroughly gross field.</text></item><item><author>mfrisbie</author><text>ChatGPT for Google was #1 on HN earlier this year. Check out the GitHub repo now: that person sold the extension.<p>I had a small side project extension, ~25,000 installs &amp; free to use. I got enough inbound interest trying to &quot;help me monetize&quot; that I thought it would be worth cataloguing all the different unsavory avenues: <a href="https:&#x2F;&#x2F;mattfrisbie.substack.com&#x2F;p&#x2F;the-ugly-business-of-monetizing-browser" rel="nofollow noreferrer">https:&#x2F;&#x2F;mattfrisbie.substack.com&#x2F;p&#x2F;the-ugly-business-of-mone...</a></text></item></parent_chain></comment><story><title>Temptations of an open-source Chrome extension developer (2021)</title><url>https://github.com/extesy/hoverzoom/discussions/670</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>BLKNSLVR</author><text>Adtech is psychological manipulation. Radicalisation uses the same techniques: Create the perception of a vacuum and then provide the solution to fill it.<p>One is actively censored and you can go to jail for, the other isn&#x27;t even on the legislative agenda. There are semi-understandable reasons, but it&#x27;s far from entirely non-hypocritical.<p>- Do you trust your constituency to make up their own minds or not?<p>- Who are you trying to protect?<p><pre><code> - From what?
- From whom?
</code></pre>
And this is without even mentioning online advertising as a (seemingly increasing) vector of scams, frauds, malware and viruses.</text><parent_chain><item><author>ericd</author><text>The most galling offer we saw on the mobile app side was something that would turn on the user&#x27;s microphone, and listen for ads on tvs around them to track what they&#x27;d been exposed to offline. Adtech is such a thoroughly gross field.</text></item><item><author>mfrisbie</author><text>ChatGPT for Google was #1 on HN earlier this year. Check out the GitHub repo now: that person sold the extension.<p>I had a small side project extension, ~25,000 installs &amp; free to use. I got enough inbound interest trying to &quot;help me monetize&quot; that I thought it would be worth cataloguing all the different unsavory avenues: <a href="https:&#x2F;&#x2F;mattfrisbie.substack.com&#x2F;p&#x2F;the-ugly-business-of-monetizing-browser" rel="nofollow noreferrer">https:&#x2F;&#x2F;mattfrisbie.substack.com&#x2F;p&#x2F;the-ugly-business-of-mone...</a></text></item></parent_chain></comment><story><title>Temptations of an open-source Chrome extension developer (2021)</title><url>https://github.com/extesy/hoverzoom/discussions/670</url></story> |
5,211,099 | 5,210,771 | 1 | 3 | 5,210,648 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>yen223</author><text>&#62; "It seems to basically be the hosting ground for answers to hard factual questions answered in most documentation/materials elsewhere"<p>That's <i>exactly</i> what StackOverflow is meant to be.<p>I feel like I'm the only one who appreciates what StackOverflow is trying to achieve here - to be the place to document hard, solid facts - nothing more. If I wanted to read commentary and opinions on programming, there's always HN or Slashdot.</text><parent_chain><item><author>zainny</author><text>Locked. I honestly don't know why anyone would bother contributing to Stack Overflow at this point. It seems to basically be the hosting ground for answers to hard factual questions answered in most documentation/materials elsewhere, and a virtual wasteland of locked/deleted questions that are actually of use in the non-black and white world we live and work in. This real world ambiguity seems like it is completely intolerable to the mods at SO.<p>Not sure how the rest of you feel but in my mind if the answer is black and white, the question was probably bad.</text></item></parent_chain></comment><story><title>How to program if you are blind</title><url>http://stackoverflow.com/q/118984/127880</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>logn</author><text>Exactly. I've desperately needed answers to a handful of questions in the last 2 weeks alone that were all locked. I think unless you can quote an error message there's a good chance it will be locked. Didn't know server hard drive space came at such a premium. Honestly what good does it do to lock a question? I can see wikipedia wanting to groom their site to maintain some credibility and focus to achieve high overall quality with limited editing resources. But Stack Overflow? Give up the power trip already. How has Joel not created Subjective Overflow already?</text><parent_chain><item><author>zainny</author><text>Locked. I honestly don't know why anyone would bother contributing to Stack Overflow at this point. It seems to basically be the hosting ground for answers to hard factual questions answered in most documentation/materials elsewhere, and a virtual wasteland of locked/deleted questions that are actually of use in the non-black and white world we live and work in. This real world ambiguity seems like it is completely intolerable to the mods at SO.<p>Not sure how the rest of you feel but in my mind if the answer is black and white, the question was probably bad.</text></item></parent_chain></comment><story><title>How to program if you are blind</title><url>http://stackoverflow.com/q/118984/127880</url></story> |
40,522,416 | 40,522,595 | 1 | 2 | 40,520,334 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>loughnane</author><text>Memorization def gets a bad rap, for the reasons you mention.<p>Yet I bet most folks who have memorized a poem or a passage---out of an affinity for it, not when demanded by a teacher---know the value. Memorizing something means you can roll it around in your head whenever you want, think about it from this perspective or that, and let the brain really absorb the ideas the words express.<p>It&#x27;s good.</text><parent_chain><item><author>boerseth</author><text>I am reminded of Socrates, who lamented the practice of memorization being replaced with writing. Today one might dismiss this idea as silly, since memorization alone is frequently associated with dumb parroting and regurgitation, neither of which imply any depth of understanding.<p>But from this discussion, we see the old man may have been on to something! If understanding something deeply is necessary in order to memorize it well, then one might achieve understanding as a secondary effect by aiming to memorize something by heart.</text></item><item><author>quartesixte</author><text>This resonates.<p>As a frequent public speaker and coach of others in public speaking, the top priority is to just deeply understand the material. The second priority is to create the habit write like you publicly speak (i.e develop a style).<p>You put these together, and you have no choice but to explain it the way you’d have written it anyways. This enforces resilience against interruptions and allows for improvisation.<p>But this is hard. It requires two great efforts: to deeply understand the material, and to craft a speaking&#x2F;writing habit that makes for powerful, public speaking.<p>It doesn’t surprise me then, that actors do the same.</text></item></parent_chain></comment><story><title>How actors remember their lines</title><url>https://thereader.mitpress.mit.edu/how-actors-remember-their-lines/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>telesilla</author><text>This extraordinary book from Frances Yates explains how before writing, scholars and story tellers would visualize architecture so they could store memories in rooms, then they would walk from room to room and recover memories, for example to tell very long stories.<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Art_of_Memory" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;The_Art_of_Memory</a></text><parent_chain><item><author>boerseth</author><text>I am reminded of Socrates, who lamented the practice of memorization being replaced with writing. Today one might dismiss this idea as silly, since memorization alone is frequently associated with dumb parroting and regurgitation, neither of which imply any depth of understanding.<p>But from this discussion, we see the old man may have been on to something! If understanding something deeply is necessary in order to memorize it well, then one might achieve understanding as a secondary effect by aiming to memorize something by heart.</text></item><item><author>quartesixte</author><text>This resonates.<p>As a frequent public speaker and coach of others in public speaking, the top priority is to just deeply understand the material. The second priority is to create the habit write like you publicly speak (i.e develop a style).<p>You put these together, and you have no choice but to explain it the way you’d have written it anyways. This enforces resilience against interruptions and allows for improvisation.<p>But this is hard. It requires two great efforts: to deeply understand the material, and to craft a speaking&#x2F;writing habit that makes for powerful, public speaking.<p>It doesn’t surprise me then, that actors do the same.</text></item></parent_chain></comment><story><title>How actors remember their lines</title><url>https://thereader.mitpress.mit.edu/how-actors-remember-their-lines/</url></story> |
37,102,404 | 37,097,359 | 1 | 3 | 37,093,776 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>danaw</author><text>Both of those are coupled to React&#x2F;JSX unless I&#x27;m mistaken.<p>The reason we&#x27;ve chosen DaisyUI (which seems similar to Hyper) is that its framework independent and just uses CSS (no JS) as our team uses Svelte&#x2F;SvelteKit.<p>In my experience this gives you more flexibility while still giving you a lot of the common UI boilerplate you need to scaffold apps quickly.<p>Being able to use a single component library across UI frameworks is a huge advantage.</text><parent_chain><item><author>ilrwbwrkhv</author><text>After the launch of <a href="https:&#x2F;&#x2F;www.radix-ui.com&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.radix-ui.com&#x2F;</a> nothing comes close anymore. Maybe <a href="https:&#x2F;&#x2F;ui.shadcn.com&#x2F;docs&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;ui.shadcn.com&#x2F;docs&#x2F;</a></text></item></parent_chain></comment><story><title>HyperUI: Free Open Source Tailwind CSS Components</title><url>https://www.hyperui.dev/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>rmuratov</author><text><a href="https:&#x2F;&#x2F;daisyui.com&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;daisyui.com&#x2F;</a> looks decent too.</text><parent_chain><item><author>ilrwbwrkhv</author><text>After the launch of <a href="https:&#x2F;&#x2F;www.radix-ui.com&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.radix-ui.com&#x2F;</a> nothing comes close anymore. Maybe <a href="https:&#x2F;&#x2F;ui.shadcn.com&#x2F;docs&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;ui.shadcn.com&#x2F;docs&#x2F;</a></text></item></parent_chain></comment><story><title>HyperUI: Free Open Source Tailwind CSS Components</title><url>https://www.hyperui.dev/</url></story> |
24,836,582 | 24,834,837 | 1 | 3 | 24,831,809 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>jonstewart</author><text>The essential problem, which Justice Kennedy seemed not to understand, is that money is not speech. The easy test to show this as nonsense is quantification, i.e., it’s clearly the case that some citizens have more money than others, but it’s nonsense to think that some citizens have more free speech than others.<p>One of Justice Kennedy’s clerks in 2009-2010 was Misha Tseytlin, a Federalist Society member who undoubtedly helped write Kennedy’s opinion on the Bilski case, which widened the potential for business process patents and considered by many software developers to be a terrible decision regarding the patentability of software. Despite no connection to Wisconsin whatsoever, Tseytlin was later appointed Wisconsin Solicitor General by Scott Walker and worked on many of the voter suppression initiatives in Wisconsin. He’s been party to litigation on behalf of the Wisconsin Tavern League seeking to overturn Governor Evers’s executive order on masks and public gatherings. I’m a part-time resident of the state and grew up there, and it’s distressing to me that a fringe ideologue with no connection to the state continues to do it harm.</text><parent_chain><item><author>pg_bot</author><text>I knew someone would bring up Citizens United v FEC when I said worst. I know this will be an unpopular opinion on this forum, but I believe that case was decided correctly. I agree wholeheartedly with Justice Kennedy&#x27;s opinion that<p>&quot;If the First Amendment has any force, it prohibits Congress from fining or jailing citizens, or associations of citizens, for simply engaging in political speech&quot;<p>Read the opinions and dissents of that case and you may change your mind.<p><a href="https:&#x2F;&#x2F;supreme.justia.com&#x2F;cases&#x2F;federal&#x2F;us&#x2F;558&#x2F;310&#x2F;#tab-opinion-1963051" rel="nofollow">https:&#x2F;&#x2F;supreme.justia.com&#x2F;cases&#x2F;federal&#x2F;us&#x2F;558&#x2F;310&#x2F;#tab-opi...</a></text></item><item><author>gruez</author><text><i>worst</i>? what about citizens united? how often is eminent domain abused for economic development, compared to how much favorable legislation was passed for corporations?</text></item><item><author>pg_bot</author><text>You can blame the worst supreme court decision in the 21st century for that. (Kelo v City of New London)<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Kelo_v._City_of_New_London" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Kelo_v._City_of_New_London</a></text></item><item><author>kenned3</author><text>This is a great article around why &quot;corporate welfare&quot; rarely works out. Also, semes like a textbook example of &quot;eminent domain&quot; abuse?<p>We call this &quot;expropriation&quot; in Canada and it is rarely abused like this.<p>Taking peoples property to give it to a private corporation? I can understand the need to take property for public use (roads, infra) but the US needs to end eminent domain abuse. If Foxconn needed the property, go to the landowners and buy it, dont go to the gvt and claim &#x27;road widening&#x27; to kick them off.</text></item></parent_chain></comment><story><title>Foxconn’s empty buildings, empty factories, and empty promises in Wisconsin</title><url>https://www.theverge.com/21507966/foxconn-empty-factories-wisconsin-jobs-loophole-trump</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>tyre</author><text>I would still put Citizens up there. We have rules around elections in the same way that we have some limits on individual speech (yelling fire, and all that) to effect the fundamental right that the First Amendment is meant to protect. Similarly, PACs were an unforeseen (and in some ways unforeseeable to eighteenth century framers) exploit of a well functioning democracy as it relates to <i>people</i>.<p>Kucho vs. Common Cause as well. Gerrymandering is a clear abuse of the system. Kagan’s dissent is heartbreaking.</text><parent_chain><item><author>pg_bot</author><text>I knew someone would bring up Citizens United v FEC when I said worst. I know this will be an unpopular opinion on this forum, but I believe that case was decided correctly. I agree wholeheartedly with Justice Kennedy&#x27;s opinion that<p>&quot;If the First Amendment has any force, it prohibits Congress from fining or jailing citizens, or associations of citizens, for simply engaging in political speech&quot;<p>Read the opinions and dissents of that case and you may change your mind.<p><a href="https:&#x2F;&#x2F;supreme.justia.com&#x2F;cases&#x2F;federal&#x2F;us&#x2F;558&#x2F;310&#x2F;#tab-opinion-1963051" rel="nofollow">https:&#x2F;&#x2F;supreme.justia.com&#x2F;cases&#x2F;federal&#x2F;us&#x2F;558&#x2F;310&#x2F;#tab-opi...</a></text></item><item><author>gruez</author><text><i>worst</i>? what about citizens united? how often is eminent domain abused for economic development, compared to how much favorable legislation was passed for corporations?</text></item><item><author>pg_bot</author><text>You can blame the worst supreme court decision in the 21st century for that. (Kelo v City of New London)<p><a href="https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Kelo_v._City_of_New_London" rel="nofollow">https:&#x2F;&#x2F;en.wikipedia.org&#x2F;wiki&#x2F;Kelo_v._City_of_New_London</a></text></item><item><author>kenned3</author><text>This is a great article around why &quot;corporate welfare&quot; rarely works out. Also, semes like a textbook example of &quot;eminent domain&quot; abuse?<p>We call this &quot;expropriation&quot; in Canada and it is rarely abused like this.<p>Taking peoples property to give it to a private corporation? I can understand the need to take property for public use (roads, infra) but the US needs to end eminent domain abuse. If Foxconn needed the property, go to the landowners and buy it, dont go to the gvt and claim &#x27;road widening&#x27; to kick them off.</text></item></parent_chain></comment><story><title>Foxconn’s empty buildings, empty factories, and empty promises in Wisconsin</title><url>https://www.theverge.com/21507966/foxconn-empty-factories-wisconsin-jobs-loophole-trump</url></story> |
14,710,338 | 14,709,405 | 1 | 3 | 14,708,327 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>aaronlevin</author><text>It&#x27;s a combination of:<p>- getting dark around 4&#x2F;5pm
- extremely dry and cold
- winter starts in October, lasts until late April
- massive urban sprawl so the city core is dead during the winter, and therefore the city feels lifeless.<p>That&#x27;s particularly bleak and definitely biased, but it&#x27;s not far from the truth.</text><parent_chain><item><author>bb101</author><text>Out of pure interest, how would you describe winters in Edmonton?</text></item><item><author>fnbr</author><text>I completely agree with that assessment. The U of A is a great school, and summers in Edmonton are fantastic, but the winters are something else.</text></item><item><author>aaronlevin</author><text>University of Alberta has a very strong pure mathematics department (especially in Functional Analysis and Algebra). Pairing this with a strong Computer Science department could eventually bring it to a level to compete with Waterloo.<p>On the other hand, as someone who grew up in edmonton, I don&#x27;t ever want to live there again. It&#x27;s a tough city to live in, though it has its beauty when you look hard enough.</text></item><item><author>pmalynin</author><text>I&#x27;m currently a student at the UofA, and I do Machine Learning &#x2F; Deep Learning professionally; These are pretty good news, I know a lot of these professors personally and they do a lot of great (fundamental) work in the field of RL &#x2F; ML, with a lot of collaboration happening between the university and the private sectors.<p>Hopefully, this will provide the needed boost to the University&#x27;s CS department, and particularly Edmonton&#x27;s tech sector.</text></item></parent_chain></comment><story><title>DeepMind expands to Canada with new research office in Edmonton</title><url>https://deepmind.com/blog/deepmind-office-canada-edmonton/?href=</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>visarga</author><text>Take a look : <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=WGpsfvRb120" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=WGpsfvRb120</a></text><parent_chain><item><author>bb101</author><text>Out of pure interest, how would you describe winters in Edmonton?</text></item><item><author>fnbr</author><text>I completely agree with that assessment. The U of A is a great school, and summers in Edmonton are fantastic, but the winters are something else.</text></item><item><author>aaronlevin</author><text>University of Alberta has a very strong pure mathematics department (especially in Functional Analysis and Algebra). Pairing this with a strong Computer Science department could eventually bring it to a level to compete with Waterloo.<p>On the other hand, as someone who grew up in edmonton, I don&#x27;t ever want to live there again. It&#x27;s a tough city to live in, though it has its beauty when you look hard enough.</text></item><item><author>pmalynin</author><text>I&#x27;m currently a student at the UofA, and I do Machine Learning &#x2F; Deep Learning professionally; These are pretty good news, I know a lot of these professors personally and they do a lot of great (fundamental) work in the field of RL &#x2F; ML, with a lot of collaboration happening between the university and the private sectors.<p>Hopefully, this will provide the needed boost to the University&#x27;s CS department, and particularly Edmonton&#x27;s tech sector.</text></item></parent_chain></comment><story><title>DeepMind expands to Canada with new research office in Edmonton</title><url>https://deepmind.com/blog/deepmind-office-canada-edmonton/?href=</url></story> |
28,722,867 | 28,722,999 | 1 | 3 | 28,722,427 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>jdavis703</author><text>Most viral political tweets (on both sides) are super misleading. I’ve actually twice tweeted incorrect stuff by accident , and those tweets were on the verge of going viral before folks pointed out the error and I deleted&#x2F;amended the tweet.<p>(FWIW one tweet was because a budget document itself had a misleading denominator, and the other because of a recent change to a law.)</text><parent_chain></parent_chain></comment><story><title>Twitter disallows liking, commenting, or retweeting “Misleading” tweets</title><url>https://twitter.com/MichaelPSenger/status/1443238759944785922</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>thepasswordis</author><text>Who cares? Nobody will stop using twitter over this.<p>Yeah, twitter sucks. We can get mad at each other and argue about it and talk about how bad it is and blah blah.<p>Nobody cares. It will change nothing.</text><parent_chain></parent_chain></comment><story><title>Twitter disallows liking, commenting, or retweeting “Misleading” tweets</title><url>https://twitter.com/MichaelPSenger/status/1443238759944785922</url></story> |
6,391,083 | 6,391,093 | 1 | 2 | 6,390,467 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>clicks</author><text>&gt; Despite all the music out there, people continue to gravitate towards the big record label stars. Nobody is competing by producing something people like as much as Rihanna, except cheaper.<p>You seem to be under the impression that people determined her art to be of greater value and thus a higher demand for it was created than all of Rihanna&#x27;s competitors. That is only very slightly true. Demand for Rihanna&#x27;s music is created mostly by record companies&#x27; aggressively promoting it and advertising it in various venues, not because people decided with no outside influence that her music is better than the competitors&#x27;. Rihanna won because her record company is better at salesmanship than her competitors. Now her popularity is soaring in a bandwagon effect, as is typical of popstars or really any popular phenomenon.<p>Your point that music should not be free because of its marginal cost of production being zero is an interesting one -- just as there isn&#x27;t an expectation for the iPhone price to be $200, it does indeed make sense that music shouldn&#x27;t be free. But, with all the talk about capitalism being a faulty economic system these days, a particular recipient of rage -- and rightfully so, in my opinion -- is that entity which charges bad prices [1] for its goods. Now, you might be wondering why it&#x27;s <i>music</i> which gets all this drama about people objecting to its costs, and not the banking sector or something. That&#x27;s because it&#x27;s a thing that&#x27;s close to people -- everyone listens to music, and naturally everyone wonders why it costs so much when the means of its distribution are effectively zero.<p>Personally I think we as a society need to first think deeply about corporations that operate essentially on a rentiering model of monetization (the recent wave of &#x27;sharing startups&#x27; are a prime example) and then we should worry about what is a good model of music distribution. But hey, record companies are basically rentiering companies as well.<p>[1]: Bad as in socially or morally irresponsible. If some company finds a cure for cancer -- and that cure, it turns out requires only $2 to make for every pill, it would not be ethical to charge an exorbitant price like $20,000 for it, no matter how much the research costs were (people dying is a bigger concern than people not getting paid). This is obviously an extreme example, but you get the point.</text><parent_chain><item><author>rayiner</author><text>This article is totally wrong. It mentions two very important things, but gets the implications of both wrong.<p>1) Competition is an issue. But competition isn&#x27;t driving down prices. Despite all the music out there, people continue to gravitate towards the big record label stars. Nobody is competing by producing something people like as much as Rihanna, except cheaper. Instead, the &quot;competition&quot; is by delivering Rihanna for free by infringing copyrights.<p>2) Marginal costs of production of music are zero. But that does not mean music should be free, any more than it means iPhones should be $200 or whatever. The point about competition shows that music is not fungible. People have rejected indie music. They want Rihanna. Now, when you&#x27;re talking about a product that is not fungible marginal cost is irrelevant. It doesn&#x27;t how much each Hermes bag costs to reproduce.</text></item></parent_chain></comment><story><title>The problem isn’t piracy – it’s competition</title><url>http://rocknerd.co.uk/2013/09/13/culture-is-not-about-aesthetics-punk-rock-is-now-enforced-by-law/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>quahada</author><text>I largely agree with the article, but also agree with your conclusions.<p>&gt;Instead, the &quot;competition&quot; is by delivering Rihanna for free by infringing copyrights.<p>This is a problem for Rihanna and a Maserati problem once a musician become famous, but the author states this article does not apply to &quot;the majors or rock stars.&quot;<p>The challenge faced by the indies is as old as the music industry, they have merely been exacerbated by technology. Even before the decline of music sales, the main challenge for an indie musician was discovery. I think we have a confirmation bias about the past. There have always been unsuccessful musicians, but we forget they existed. Starving artist is not a new cliche.<p>Have people rejected indie music or is there something else behind superstar popularity? Conventional thinking is that free music makes it easier to get discovered (but harder to monetize, once discovered) because it cost nothing for consumers to try new music. It turns out that there is so much content&#x2F;competition out there now (because music cost less to produce + free distribution), consumers have choice overload. This makes it harder for people to try indie music.<p>Music is cultural, so what is popular follows the same power-law dynamics as social networks (in fact, it is driven by social networks). Hence, what&#x27;s popular becomes more popular.<p>Agree that the fact that the product has a zero marginal cost does not mean people are unwilling to pay. The entire software industry is built upon a business model of building a product with high production costs and zero marginal cost.</text><parent_chain><item><author>rayiner</author><text>This article is totally wrong. It mentions two very important things, but gets the implications of both wrong.<p>1) Competition is an issue. But competition isn&#x27;t driving down prices. Despite all the music out there, people continue to gravitate towards the big record label stars. Nobody is competing by producing something people like as much as Rihanna, except cheaper. Instead, the &quot;competition&quot; is by delivering Rihanna for free by infringing copyrights.<p>2) Marginal costs of production of music are zero. But that does not mean music should be free, any more than it means iPhones should be $200 or whatever. The point about competition shows that music is not fungible. People have rejected indie music. They want Rihanna. Now, when you&#x27;re talking about a product that is not fungible marginal cost is irrelevant. It doesn&#x27;t how much each Hermes bag costs to reproduce.</text></item></parent_chain></comment><story><title>The problem isn’t piracy – it’s competition</title><url>http://rocknerd.co.uk/2013/09/13/culture-is-not-about-aesthetics-punk-rock-is-now-enforced-by-law/</url></story> |
40,315,493 | 40,313,550 | 1 | 3 | 40,312,469 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>thayne</author><text>If you are looking for short period events, losing a single frame can mean losing critical data.<p>&gt; Or they can just use that information for better scheduling: wait a minute or two to image a particular spot, so there won&#x27;t be satellites in the field of view.<p>Which means more time and effort, and ultimately money needs to be spent on scheduling observations to avoid the thousands of these satellites.<p>And sometimes it isn&#x27;t an option. What if a GRB happens in the same field of view as one of these satellites and you want to observe it as soon as possible?<p>Now there are some types of observations that won&#x27;t be impacted that much. If you can tolerate scheduling around it, or throwing away some of your frames it is just a minor annoyance. But a lot of observations are also more sensitive to such disruptions.</text><parent_chain><item><author>StellarScience</author><text>There certainly is a real concern for astronomers, but the photo illustrations used in the article are selected to make things seem worse than they really are. They&#x27;re wide field of view, long-duration exposures. That <i>used</i> to be the way astronomers imaged space, with film systems a century ago. But these days astronomical telescopes tend to have much narrower fields of view (like tiny soda straws peering into one particular spot in space) and use image stacking, a technique where many individual images are processed to form the final image (very simplistic overview: <a href="https:&#x2F;&#x2F;www.skyatnightmagazine.com&#x2F;astrophotography&#x2F;astrophoto-tips&#x2F;a-guide-to-astrophotography-stacking" rel="nofollow">https:&#x2F;&#x2F;www.skyatnightmagazine.com&#x2F;astrophotography&#x2F;astropho...</a> .) Using image stacking and armed with accurate catalogs that predict precisely where every satellite will be at any time, enables the removal of satellites during the image stacking process. Or they can just use that information for better scheduling: wait a minute or two to image a particular spot, so there won&#x27;t be satellites in the field of view.<p>The article definitely gets this part right:<p>&gt; “Some astronomers see this as a true ‘hair on fire’ emergency, heralding irretrievable losses to space science; others present a more sanguine face, depicting this as yet another challenge to be surmounted in surveying a decreasingly pristine sky,” Koplow remarks.<p>Being involved in both space and astronomy plants me squarely in the latter camp. It takes a bit more work and software, but having so many satellites in space is a surmountable challenge for terrestrial astronomers. (Not to mention, these days some of the best astronomy is performed by telescopes in space, so astronomy overall benefits by having easier access to space.)</text></item></parent_chain></comment><story><title>How bad are satellite megaconstellations for astronomy?</title><url>https://www.leonarddavid.com/blinded-by-the-light-megaconstellation-clash-with-astronomical-peer-groups/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>gammarator</author><text>&gt; They&#x27;re wide field of view, long-duration exposures. That used to be the way astronomers imaged space,<p>Sorry, but one of the two example images (<a href="https:&#x2F;&#x2F;noirlab.edu&#x2F;public&#x2F;images&#x2F;iotw1946a&#x2F;" rel="nofollow">https:&#x2F;&#x2F;noirlab.edu&#x2F;public&#x2F;images&#x2F;iotw1946a&#x2F;</a>) is a single 333-second exposure with a modern survey camera, the Dark Energy Camera. This is not particularly long nor does it represent some outmoded observational strategy. Large, wide-field imaging sky surveys (such as the upcoming Rubin Observatory) are among the highest-profile ground-based astronomy projects today.<p>Masking and stacking can mitigate the problem but it does not of course compensate for the lost area and sensitivity. And the brightest satellites (like BlueWalker) saturate the readout electronics and spoil the whole exposure.<p>Narrow field instruments (such as spectrographs) have less geometric chance of seeing a satellite but tend to take longer exposures (tens of minutes), so there is a greater loss of telescope time when a streak does happen.<p>Even space telescopes are affected by streaks (<a href="https:&#x2F;&#x2F;www.space.com&#x2F;hubble-images-spoiled-starlink-satellite-steaks" rel="nofollow">https:&#x2F;&#x2F;www.space.com&#x2F;hubble-images-spoiled-starlink-satelli...</a>).<p>&gt; It takes a bit more work and software<p>Equivalently, it takes more money and time. That just means less science, given flat to declining funding from Congress.</text><parent_chain><item><author>StellarScience</author><text>There certainly is a real concern for astronomers, but the photo illustrations used in the article are selected to make things seem worse than they really are. They&#x27;re wide field of view, long-duration exposures. That <i>used</i> to be the way astronomers imaged space, with film systems a century ago. But these days astronomical telescopes tend to have much narrower fields of view (like tiny soda straws peering into one particular spot in space) and use image stacking, a technique where many individual images are processed to form the final image (very simplistic overview: <a href="https:&#x2F;&#x2F;www.skyatnightmagazine.com&#x2F;astrophotography&#x2F;astrophoto-tips&#x2F;a-guide-to-astrophotography-stacking" rel="nofollow">https:&#x2F;&#x2F;www.skyatnightmagazine.com&#x2F;astrophotography&#x2F;astropho...</a> .) Using image stacking and armed with accurate catalogs that predict precisely where every satellite will be at any time, enables the removal of satellites during the image stacking process. Or they can just use that information for better scheduling: wait a minute or two to image a particular spot, so there won&#x27;t be satellites in the field of view.<p>The article definitely gets this part right:<p>&gt; “Some astronomers see this as a true ‘hair on fire’ emergency, heralding irretrievable losses to space science; others present a more sanguine face, depicting this as yet another challenge to be surmounted in surveying a decreasingly pristine sky,” Koplow remarks.<p>Being involved in both space and astronomy plants me squarely in the latter camp. It takes a bit more work and software, but having so many satellites in space is a surmountable challenge for terrestrial astronomers. (Not to mention, these days some of the best astronomy is performed by telescopes in space, so astronomy overall benefits by having easier access to space.)</text></item></parent_chain></comment><story><title>How bad are satellite megaconstellations for astronomy?</title><url>https://www.leonarddavid.com/blinded-by-the-light-megaconstellation-clash-with-astronomical-peer-groups/</url></story> |
34,038,552 | 34,038,659 | 1 | 3 | 34,038,021 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>mabbo</author><text>Many years ago, as an intern at Google, one of my mentors said to me &quot;Google found a hose that money pours out of, and it&#x27;s name is &#x27;online advertising&#x27;. All we do now is improve that hose and desperately search for another one&quot;.<p>I would love to see Waymo become another hose. I&#x27;d love to see it launch in my city (whenever the laws are amended to allow such things).<p>(Yes, I know arguably they&#x27;ve had a few other successes.)</text><parent_chain></parent_chain></comment><story><title>Waymo expands its rider-only territories</title><url>https://blog.waymo.com/2022/12/wheels-up-for-waymo-as-we-expand.html</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>amelius</author><text>LIDAR makes implementing FSD so much simpler. And you can still harvest data so you can use it as a stepping stone for video-only based FSD.</text><parent_chain></parent_chain></comment><story><title>Waymo expands its rider-only territories</title><url>https://blog.waymo.com/2022/12/wheels-up-for-waymo-as-we-expand.html</url></story> |
26,223,832 | 26,223,855 | 1 | 2 | 26,223,347 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>danpalmer</author><text>&gt; IBM Canada has won $1.5M contract to develop new platform for IRCC<p>This will buy what? A team of 4 interns and new grads for 6 months. At the end they&#x27;ll have a slide deck with too much wordart in ith containing some half-baked ideas, and a few lines of code that don&#x27;t do anything useful at all and are further from production readiness than starting from scratch.</text><parent_chain></parent_chain></comment><story><title>Virtual passport app presents real data risk, experts warn</title><url>https://www.cbc.ca/news/canada/ottawa/passport-application-online-program-1.5920625</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>nuccy</author><text>In Ukraine, there is a DIYA (Дія) app developed by the government, which holds electronic national passport, passport for traveling abroad, driving license, car registration documents (including car insurance information), child birth certificate (in parents app) and tax payer information. The app generates temporarily barcodes which can be scanned by another DIYA app to verify somebody&#x27;s identity or presented documents. The national electronic passport can already be used in some companies, like post offices (state and private), banks, etc. Driving license and car registration can be presented to patrol police when requested. Very handy in general, especially if one forgets his wallet. I have a general concerns about privacy and security of this service, but I can also imagine that all the individual databases, which are accessed by this service, may have their own security issues, so having a single entry point is somewhat reducing the attack surface, which may actually be an advantage.</text><parent_chain></parent_chain></comment><story><title>Virtual passport app presents real data risk, experts warn</title><url>https://www.cbc.ca/news/canada/ottawa/passport-application-online-program-1.5920625</url></story> |
13,447,369 | 13,447,337 | 1 | 2 | 13,446,947 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>gshulegaard</author><text>&gt; if providers can sell a fastlane to Netflix they can reduce prices for the consumer.<p>Historically, this is not shown to be how companies act. The implicit assumption here is that a supplier has some sort of benevolent desire. But the reality is that if a company can increase revenue, they will do so without redistributing it to the benefit of their customers or even employees.<p>&gt; They would argue that in the end that&#x27;s great for consumers too, but as far as I am concerned, that remains to be seen.<p>We have seen it, and it&#x27;s not great for consumers. Trickle-down economics is a fallacy. It&#x27;s also been debunked by Economists very thoroughly.</text><parent_chain><item><author>entee</author><text>I&#x27;m quite opposed to the guy&#x27;s ideas from what I&#x27;ve read so far, but here&#x27;s one perspective:<p><a href="http:&#x2F;&#x2F;www.nytimes.com&#x2F;2010&#x2F;03&#x2F;21&#x2F;opinion&#x2F;21Benkler.html" rel="nofollow">http:&#x2F;&#x2F;www.nytimes.com&#x2F;2010&#x2F;03&#x2F;21&#x2F;opinion&#x2F;21Benkler.html</a><p>Some of the ways to look at it is that if providers can sell a fastlane to Netflix they can reduce prices for the consumer. Other arguments that have been advanced include having a fast lane for medical devices or emergency services.<p>I could see an argument in favor if the rest of the marketplace was highly competitive and you could just switch to a different provider if the provider you had was behaving abusively. That&#x27;s not the case in most of the US where you have a duopoly at best for fast internet.<p>Personally, I find this guy&#x27;s proposals to be bad policy for individual consumers, but they&#x27;re pretty great for ISPs. They would argue that in the end that&#x27;s great for consumers too, but as far as I am concerned, that remains to be seen.</text></item><item><author>rashkov</author><text>Is there a sympathetic view of Ajit Pai that anyone could offer?<p>I can understand how he would be opposed to the pro-consumer agenda of Wheeler&#x27;s FCC. To be sure, there might be a better way of solving these problems using a free market mechanism, instead of top-down regulation which is antithetical to the libertarian&#x2F;conservative ethos.<p>For example, previous HN discussions have surfaced how some european countries have a deregulated last mile, giving the consumer a nearly zero-friction way to switch between ISPs.<p>I just can&#x27;t imagine Pai doing anything like this. I can only anticipate him enhancing the monopolistic powers of the big ISPs.</text></item></parent_chain></comment><story><title>FCC to be led by Ajit Pai, staunch opponent of consumer protection rules</title><url>http://arstechnica.com/tech-policy/2017/01/fcc-to-be-led-by-ajit-pai-staunch-opponent-of-consumer-protection-rules/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>rashkov</author><text>I completely agree with you, but I would put it into even stronger terms. Paid fast lanes are not an experiment worth performing, in the hope that ISPs pass the savings down to consumers. The ISPs have absolutely zero incentive to pass the savings onto consumers when they have no real competition.<p>Any free-market thinker should recognize this to be self-evident, so if they really want to give ISPs the freedom to offer paid fast-lanes, then they have to solve the competition problem first.</text><parent_chain><item><author>entee</author><text>I&#x27;m quite opposed to the guy&#x27;s ideas from what I&#x27;ve read so far, but here&#x27;s one perspective:<p><a href="http:&#x2F;&#x2F;www.nytimes.com&#x2F;2010&#x2F;03&#x2F;21&#x2F;opinion&#x2F;21Benkler.html" rel="nofollow">http:&#x2F;&#x2F;www.nytimes.com&#x2F;2010&#x2F;03&#x2F;21&#x2F;opinion&#x2F;21Benkler.html</a><p>Some of the ways to look at it is that if providers can sell a fastlane to Netflix they can reduce prices for the consumer. Other arguments that have been advanced include having a fast lane for medical devices or emergency services.<p>I could see an argument in favor if the rest of the marketplace was highly competitive and you could just switch to a different provider if the provider you had was behaving abusively. That&#x27;s not the case in most of the US where you have a duopoly at best for fast internet.<p>Personally, I find this guy&#x27;s proposals to be bad policy for individual consumers, but they&#x27;re pretty great for ISPs. They would argue that in the end that&#x27;s great for consumers too, but as far as I am concerned, that remains to be seen.</text></item><item><author>rashkov</author><text>Is there a sympathetic view of Ajit Pai that anyone could offer?<p>I can understand how he would be opposed to the pro-consumer agenda of Wheeler&#x27;s FCC. To be sure, there might be a better way of solving these problems using a free market mechanism, instead of top-down regulation which is antithetical to the libertarian&#x2F;conservative ethos.<p>For example, previous HN discussions have surfaced how some european countries have a deregulated last mile, giving the consumer a nearly zero-friction way to switch between ISPs.<p>I just can&#x27;t imagine Pai doing anything like this. I can only anticipate him enhancing the monopolistic powers of the big ISPs.</text></item></parent_chain></comment><story><title>FCC to be led by Ajit Pai, staunch opponent of consumer protection rules</title><url>http://arstechnica.com/tech-policy/2017/01/fcc-to-be-led-by-ajit-pai-staunch-opponent-of-consumer-protection-rules/</url></story> |
4,713,077 | 4,712,816 | 1 | 2 | 4,712,230 | train | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>jjwiseman</author><text>Blind allocation got me too. They told me how allocation worked before I joined, but I was hopeful that they would put me on a project that had some overlap with what I was interested in and what I had worked on for the past 15 years (computer vision, robotics, natural language processing).<p>No. I found out on the last day of orientation I would be doing YouTube ads. I knew there was no way I could do that for 18 months, and I told my manager. He was understanding, but there wasn't really anything he could do. He passed my concerns up the management chain.<p>A couple weeks later my manager gave me their response, which was, literally, "We don't care." That shocked me a little, and I knew at that point I wouldn't be at Google for very long. Maybe that was even the right thing for them to do, since I was proving myself to be the kind of employee who wouldn't work on a project they weren't interested in for a year and a half just because it was good for Google, or good for their potential career at Google.<p>For a short time I led a 20% project with three other engineers that was in my interest area, and after we won an innovation award I hoped that it might make the Google bureaucracy more sympathetic to my preferences, but management didn't care. I left not long after that.<p>(tl;dr: I learned that Google is a bureaucratic megacorp.)</text><parent_chain><item><author>varelse</author><text>I worked at Google for a short stint. I found the tech interview easy and I wasn't asked anything particularly ridiculous. I received a job offer shortly thereafter and accepted.<p>As someone who regularly interviews prospective engineers at my current gig, I see no problem with expecting candidates to arrive prepared to answer algorithm questions or questions about their strongest programming language. Ditto for someone who wishes to change assignment within their organization, however they arrived there. If you're unwilling to provide proof you're not a bozo, you're probably going to be just awful to work with as well.<p>However, the blind allocation policy at Google sucks, and it continues to suck. I came in as an expert in field D and therefore according to Google's magic sorting hat I ended up a natural for assignment in field Q. I tried my hand at it for several months, but as someone else has already said, bored employees quit: <a href="http://www.randsinrepose.com/archives/2011/07/12/bored_people_quit.html" rel="nofollow">http://www.randsinrepose.com/archives/2011/07/12/bored_peopl...</a><p>In order to avoid that fate, I futilely attempted to get reassigned to something close to field D (really, B, C, E, or F would have been just peachy) and that seemingly got me flagged as trouble internally. Shortly thereafter, I got a higher offer to go somewhere else and left.<p>However, unlike the author of this post, while Google recruiters regularly stalk my linkedin profile, none of them ever contact me, which is good.</text></item></parent_chain></comment><story><title>No, I still don't want to work for Google</title><url>http://infotrope.net/2012/10/29/no-i-still-dont-want-to-work-for-google/</url></story> | <instructions>Your goal is to analyze the following comment and estimate how highly it will be upvoted by the Hacker News community.</instructions><comment><author>samstave</author><text>I went through a 3-month long interview with google in 2007, they said I did great in the interview and told me they'd be sending me an offer.<p>Two days later they rescinded and said they would not be giving me an offer without explanation. I was really pissed off.<p>A couple years later they contacted me again for a job and started the interview process, then I told them what happened the last time. They then said they didn't want to proceed.<p>Then a few month ago they contacted me again (these were all for basically the same job) - I sent the recruiter a rather terse email stating my experiences and said "stop wasting my time - either give me the job at salary $X or stop contacting me."<p>They replied that they couldnt meet my salary requirements.<p>Personally their recruiting method is farking ridiculous.</text><parent_chain><item><author>varelse</author><text>I worked at Google for a short stint. I found the tech interview easy and I wasn't asked anything particularly ridiculous. I received a job offer shortly thereafter and accepted.<p>As someone who regularly interviews prospective engineers at my current gig, I see no problem with expecting candidates to arrive prepared to answer algorithm questions or questions about their strongest programming language. Ditto for someone who wishes to change assignment within their organization, however they arrived there. If you're unwilling to provide proof you're not a bozo, you're probably going to be just awful to work with as well.<p>However, the blind allocation policy at Google sucks, and it continues to suck. I came in as an expert in field D and therefore according to Google's magic sorting hat I ended up a natural for assignment in field Q. I tried my hand at it for several months, but as someone else has already said, bored employees quit: <a href="http://www.randsinrepose.com/archives/2011/07/12/bored_people_quit.html" rel="nofollow">http://www.randsinrepose.com/archives/2011/07/12/bored_peopl...</a><p>In order to avoid that fate, I futilely attempted to get reassigned to something close to field D (really, B, C, E, or F would have been just peachy) and that seemingly got me flagged as trouble internally. Shortly thereafter, I got a higher offer to go somewhere else and left.<p>However, unlike the author of this post, while Google recruiters regularly stalk my linkedin profile, none of them ever contact me, which is good.</text></item></parent_chain></comment><story><title>No, I still don't want to work for Google</title><url>http://infotrope.net/2012/10/29/no-i-still-dont-want-to-work-for-google/</url></story> |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.