It is deterministic, no ? Do they have some entropy source they use?
Maybe it's chaotic like you and me, but it cant be non deterministic, it'd mean it doesnt even really answer questions and just spout random tidbits :s
They use a rand() function as part of the input. I don’t think they have a source of true randomness they use, but it’s random enough for any practical purpose.
I've asked this before, but is having a domain name with someone else's business name in it allowed? The answer I was given last time was you can buy it it but you might not get to keep it. Still, I can't help but think it would be inevitable legal trouble.
100% chance that stackoverflow will be sending nasty notes to the author (who appears to live in the US). 100% chance he'll have to take it down or change the name.
You really can't use the exact name of the people you are cloning. Even something like "stackrobot" would risky. Safest thing is to not use any words from the original product.
No one other than lawyers or lawyer accessories is going to represent the company to the domain owner about it, though.
Source: Ages ago I had a personal domain based on a longstanding nick that happened to partially coincide with the name of a major motion picture studio. That it was a paralegal who called me said they weren't anxious to take it seriously, and all they were really after was just getting me to say it was nothing to do with them so they had me on record in case I later did make it something to do with them. No big deal, but it wasn't like if I had a treatment burning a hole in my pocket I could've parlayed the conversation into a chance to submit it. And even at that, I doubt this will be anything like so simple and nonadversarial.
> No one other than lawyers or lawyer accessories is going to represent the company to the domain owner about it, though.
Of course. Here's the plausible chain of events:
1. Someone at the co. reads about this on HN
2. They tell their boss who might tell their boss, etc.
3. It finally gets to someone who is responsible for telling the lawyers. But they also say "hey this is kind of cool. We'll send a C&D, but maybe reach out to see if there's anything interesting there."
I guess it's not implausible somebody would try to open a nonadversarial conversation simultaneously with sending a C&D, but I will say I've never seen it done that way, and I suspect there's a good reason why not.
(Not least because escalating something to counsel, and then having side conversations about it with whoever you just brought to counsel's attention, is a bad idea!)
And that's if they see something here they might want to investigate further, which given SO's stance on ML-generated answers up to this point, I tend somewhat to doubt.
Sure, it makes sense to start with the friendly conversation and escalate to a C&D if that proves to be needed.
Deliberately infringing someone's trademark with a domain name seems to me like a dicey way to look for attention, though. But hey, "it's a bold strategy, Cotton, let's see if it pays off for 'em."
The owner of a simple hobby project like this, without SEO or sign-in or whatsoever, probably don’t need to care so much to protect his domain. If StackOverflow asks for his domain he can just give it away and set up the site at a new domain name.
If they have the motivation/resources to go through the process, no- even a branding like “staqoverflow” would be infringement if they engage in the same type of activity as the trademark registration.
Complicated question because it os
trademark law. “AppleBakeryChicago” probably doesn’t have to worry about Apple Inc suing them. In the case of this site they should be worried.
No he’s not saying that. He’s saying you cannot start a company called Apple in Mexico that sells smartphones. There are two components, what you provide as a service and your name. You just cannot do both.
But you could start a company called Stack Overflow that sells cookies in Austria. They may still try to sue you but then it comes down to an actual argued case and debates and such. This is just complete copy.
There are a lot of soft clones of SO that you encounter at times with the exact same questions and answers in a crappier display format. Missed opportunity to whoever copped https://stackgpt.com, I foresee something like that coming eventually.
Lol just yesterday I saw an eight year old answer on SO neatly solving my problem, except the API was hallucinated. Humans have been hallucinating APIs for far longer.
It didn’t change, the functionality was never there. The API only ever existed in that answer, otherwise a Microsoft API would have left traces elsewhere on the Internet.
Maybe mistook Java for being C# or PHP and replied with another language and framework in mind. Just guessing, I am. Or wrote pseudo code, but forgot to mention this?
This is the fundamental problem and shortsightedness of the ChatGPT ban on Stack Overflow - it doesn't go far enough.
There is some imagined distinction between a hallucinated answer from a LLM and one from a person posting "try {random code}" that are both equally wrong - but only the LLM is deleted (because deleting the wrong answers are an attempt by a human to answer(?) or would hurt feelings / engagement (?)).
No, I scoured the API surface and the functionality simply isn’t exposed, so the question has no answer. There was already a comment pointing out the answer’s wrong.
Whether it's AI generated, or some random schlep on Stack Overflow - Don't trust the answer without reviewing. Amateurs run code they don't understand.
Part of the challenge of StackOverflow is finding the question that matches your situation. But that is a pointless act with ChatGPT -- just ask it your exact question. Duplicates be damned.
Slight off topic question: this is a browser addon too; does being installed as a browser addon enable any security risks? Do browser addons/extensions get access to all browser traffic?
I see various software as browser addons/extensions... is that a security loophole?
They can get access to all browser traffic if they're configured to. They can also be configured for activation only on specific sites. It really depends.
I don't get this hate-boner HN has for SO. Have you tried being active there? It's super easy to not have your question closed, just do the minimum amount of effort. And if you're active, you'll see the thousands of similar questions arrive every day. If you're active in the review queues, you will see all the spam, broken answers, non-SO fitting questions etc. people churn out.
I see people complain about how their "well researched and well articulated question got closed" all the time, but when prompted no one every actually provides a link to their question. Which makes me believe it actually just was a low effort noisy question after all..
If anything, HN is much more snarky, just look at the comments on anything here.
Many questions get dupe-hammered within seconds of being asked because it remotely resembles an older question. If it doesn't get dupe hammered, the platform encourages other users to answer as quickly as possible to appear on top. Unfortunately, this promotes many dangerously unsafe answers. Many articles have reported on the high number of security vulnerabilities in accepted and highly upvoted answers.
However, even when ignoring all that, if you really ask a "well-researched and well-articulated question" on a complex matter, you will not get an answer in most cases. For those after reputation points, it is far easier to answer simple questions. You are far better off raising it as a GitHub issue if it is an open-source framework.
Scroll until you find an upvoted question. Count how many downvotes you see on the way. You can often get to page 2 with dozens of downvotes before the first upvote.
Hard mode: Scroll until the net upvotes are more than the net downvotes.
What should that prove? If anything, it backs up my point: the amount of noise is huge.
But I tried: scrolled two pages. Most questions were at 0 votes. But I checked every down voted question, and they were all useless. No code, just a vague statement of trying to do something.
"But I checked every down voted question, and they were all useless. No code, just a vague statement of trying to do something."
That's exactly it. Someone out there is asking for help. They don't know how to ask or where to start. Then they get shut down by the community for being useless and vague instead of guided on the right questions to ask.
It's someone who does not understand switch and wants to know why their code doesn't match with their understanding of switch. There's no given reason for the downvote.
ChatGPT at least takes the effort to make sense of the question and verifies that this is what the asker intended.
Do you see stack overflow as a resource for total beginners?
Such a question has no place on SO from my perspective. A chat with a more experienced person would be much more helpful and chatgpt could be the next best thing in this context.
Today that question would be downvoted as a bad question, and so would many of the answers.
It's kicking out the ladder after you've climbed it and is hostile to anyone learning to program today.
All those questions you deride as "useless" is someone who is struggling to do something, who takes the time to ask for help and gets downvoted and hostility in return.
My favorite is searching for a solution to an issue in google, finding exactly what I'm looking for in the search results, and then seeing the question closed for being off-topic etc.
The SO community can be pretty toxic with newcomers that don't ask questions in the "one true way". I can get away with asking questions because I know what will work, but that doesn't make the site friendlier. Also, God forbid you ask anything that can be considered "opinion based"...
>Also, God forbid you ask anything that can be considered "opinion based"...
It's clearly not allowed. People shouldn't be surprised when their answer gets closed. The goal of stack overflow is to build a quality mapping from questions to answers. There is no way to map a subjective question to an answer.
Opinion based exists in a spectrum. I'd expect the mods to error on the side of not closing questions and letting the discussion continue. However, there are very active mods that take them as gospel and will take any chance they get to enforce them to their most strict interpretation.
A heavily policed community is not a welcoming one.
> If anything, HN is much more snarky, just look at the comments on anything here.
Was your comment intended to be the perfect example of this? replying to a joke about insults in answers... by going on an entire rant about how it's easy not to get your question closed (which was not mentioned at all).
I'm not directly addressing my parent comment, but rather all the sibling comments. :)
Note, I do like the comments on HN, and spend more time here than on SO. I personally like how they're both direct and don't accept too much fuss. But I also see newcomers here getting burnt by "that orange website", not being used to how it is.
It very much depends on the tags you use. Swift and iOS is absolutely abysmal and questions will be closed as duplicates of questions that have been irrelevant for years.
Go and Haskell are great though.
Android is as bad or worse. I wonder if SO's quality could be improved by a restart -- no closing questions because they're duped of something pre-restart. And FFS mandate that questions and answers include version numbers for all relevant software.
> but when prompted no one every actually provides a link to their question.
Ask, and ye shall receive.
Here's my SO profile screen[0]. You can tell that it's me, because of my dragon logo, which is actually a refinement of my signature from the days I wanted to be an artist[1]. I actually make an effort to be "non-anonymous," these days. I feel that it helps me to be a better netizen.
The first thing that you may notice about my profile, is that the Answer[2]/Question[3] ratio is about 0.6. That's unusual for many of the more senior members (I've been there for about 15 years. I used to have another account, and nuked it in disgust, many years ago, then decided I was being a big baby, and came crawling back. I've been a member since, but the name was changed, somewhere along the line, as I decided that "non-anonymity" was my lodestar).
That's because I don't go there to answer questions, or prove how smart I am. I go to solve problems, and remove roadblocks, in my day-to-day work.
Here's my latest question[4]. It's a really basic question. One I could have found the answer to, myself, but I would have had to spend a bunch of time in the ugly, chaotic documentation that Apple has for their bundle hashes. Probably would have taken me an hour or so.
I should tell you a bit about myself.
I have been writing software, since my days of 6800 machine code, in 1983. I've been writing Apple software since 1986. I have been shipping software, since 1986/7 (depending on how you define "shipping").
This ain't my first rodeo.
I've also been training and mentoring folks since I was 19. One thing that I learned, very early on, is that the people I'm training, usually (not "sometimes," "usually") have more expertise than I, in matters outside the scope of the class.
I learned to respect my students. I'm not better than they are. I just have a bit of knowledge that can help them, and it's an Honor to be allowed to provide it.
When someone asks me "what I do," I generally respond with "I solve problems."
That's what I do. Every. Single. Day. Every day, I am presented with a "Argh! We're all gonna die!" problem; often multiple times a day[5].
And I solve them. That doesn't make me unique, in the slightest. Lots of people here, can easily say the same, and they probably solve much more difficult issues than I. That's one of the reasons I like coming here. I'm not the smartest person in the room. I have found great comfort in surrounding myself with people that humble me. It can be difficult, at times, but I feel that I need to learn something new, every day, and I don't get that, by staying in my comfort zone.
I also speak Swift without an accent. I've been writing Swift, seven days a week, 52.14 weeks per year, since the day it was announced, in 2014. I've also been shipping apps in Swift, since not too long, afterwards.
Everything I do is geared towards "ship."
That often means that my solutions and workflows are not always optimal, or "academically pure." Duct tape and baling wire. Make it work. I take a great deal of care in the Quality of my work, but it is not always "exemplary." It needs to work, work well, and be maintainable. I also like to get to the point, where I leave it behind, and move on to the next project[6].
SO helps me to quickly find "correct" solutions. I don't like duct tape and baling wire. I'd like to do it right, the first time. That's pretty much exactly the spirit behind my latest question [4].
Note that the question got almost immediate downvotes and close votes. That happened within seconds of it being posted.
But it was answered. It was answered in a rather condescending way, but I got what I needed. I then took that answer, and configured it into something that I could ship[7], and, eventually, into something that I could share[8].
Now, that was a productive interaction for me. It gave me the answer I needed, I was able to greencheck someone for answering it, even if they did so, looking down on me, and I was able to repackage their response into something that can be quite useful, in the future.
When I ask well-researched, well-documented, windy questions, they are usually ignored, like so[9], and I end up answering my own question. Sometimes, these self-answered questions get fairly popular[10], or even unanswered ones[11].
It's fairly plain that the SO folks think of people that ask questions as "supplicants," and to be looked down upon. Look at all the folks with massive scores, and single-digit question counts (the digit is frequently "0").
Here's an exercise: Go to Meta, and suggest that people applying for positions of authority have at least a 10% question-to-answer ratio.
Why would you want a general that doesn't know what it's like to be pinned down in a shellhole?
It really is too bad that you decided to start our relationship on such a petty note (I would also humbly submit that the optics aren't especially good, in a professional venue).
I suspect that we could have actually found a lot in common.
In my experience, I have found friends in the most unlikely places.
Everybody got what they wanted and it’s much “nicer” now (it won’t even let you comment “what have you tried?” anymore, for instance). Wouldn’t you know it, the front page is now full of low-quality, low-effort questions.
I don’t ask questions, because people take a very carefully explained, explicit question and post irrelevant stupid comments on it (“why are you doing this?”) instead of answering the question.
I don’t answer questions, because people upvote wrong answers and vindictively downvote answers to the actual question (which is why everyone posts comments instead of answering, because you can’t down vote them for it).
People care more about karma than actually helping.
The quality issues are real, but really?
I care not at all if 90k+ karma folk leave. Just leave. If you don’t like what it is, go hang out somewhere else. Why are you there if you’re not trying to help people?
What I care about is the people patiently answering questions in a way that is correct, not antagonistic, not ducking off because it took more than 5 minutes and they can get better karma somewhere else.
…almost like, a dedicated support community who care about a topic. That’s a nice idea. You could probably find one of those for your topic of interest and get help there from nice people. That’s what I do now. The folk there are generally quite lovely, because they actually care.
The people on stack overflow, by and large, are not nice, do not care and won’t help you if you have any really hard problems to solve.
An AI would be just as good, if it had decently accurate answers.
> An AI would be just as good, if it had decently accurate answers.
Well, this reminds me of "if my grandmother had wheels, she'd be a bicycle."
Failing to clean up bad questions is encouraging all the bad behavior you're talking about, since answering yet another question from someone who couldn't be bothered to write his own regex is an easy 25 points that nobody will ever look at again.
Well, you said you were dissatisfied that people were avoiding challenging questions in favor of karma farming easy ones. Failing to prune lazy questions with no value to other users incentivizes that exact behavior because hard questions don't usually have a better payoff.
It's a gargantuan task to clean up low quality post and fight back low quality copy paste blog spam from a community that has become resume padding for the masses.
The community has spoken, to the extent whether the majority of usage becomes the defacto standard, and basically filtered out all but the most basic coding issues that are just one peg above homework assignments.
Well, I wouldn’t say it was the community speaking. This is what the operators wanted because the old way was not “welcoming” enough and didn’t contribute enough to growth. Hey, it’s a business. I get it.
No, it wasn’t “not ‘welcoming’”, it was just “not welcoming”. Sure it’s the owners who forced this, but it’s not a bad thing to be more welcoming and thinking otherwise because “it’s better” is problematic. You should also blame the owners for not giving a shit about moderation for the low quality of things now, if you want to blame them for the push for being “welcoming”.
At the end of the day enforcing guidelines involves telling people "sorry, this is not the kind of question we want here," and people are always going to find this less than welcoming -- justifiably so, since they've objectively been excluded. You can be as nice as you want about it, and I'm not advocating being rude or cruel, but it doesn't matter.
Right, I think so too. My point is more that moderation doesn’t imply being unwelcoming, and they are more or less distinct. A great example is HN, it’s a pretty welcoming place with good moderation, albeit at a much smaller size than SO.
"why are you doing this" isn't a "irrelevant stupid comment". It's because most askers are really asking a XY question. They ask for Y, since that's their immediate problem, but solving X is their real goal. So it's a question meant to make it easier to help, when doing Y seems a bit weird.
Please see the comments under the OP. While the question is technically sound (I've needed this exact thing for a REPL I was writing), the comments are perfectly useless, self-entitled and discouraging drivel. Notable example:
> This is an incredibly odd thing to ask
(emphasis theirs). How is this even slightly odd. Are REPLs odd? Of course not.
They ask a question with some weird requirements, people ask why those requirements are in place as it makes it hard to solve, the asker explains why. Everything is good.
If you’re writing a REPL it’s one thing but it does seem like evaluating a string is the kind of thing where most people trying to do it are using the wrong approach.
They're the one saying people at SO aren't nice. My guess is just that the person feels that way after getting pushback from their own behavior / attitude. I feel it's a trend, I see lots of toxic comments from people "having given up SO", and I think to myself that it's a good thing..
But you're right, I should've avoided going personal.
Yeah it's kind of sad really. I was a member for 10 years. The point is sometimes, yes, your 9th repost of the same question is garbage, and should be treated as such.
But that doesn't get you the sweet sweet ad money I guess. Quick Stack Overflow, make another blog post no one gives a shit about, and continue banning 90k rep users over rollback wars.
And yet I have no issues finding answers to my question when using a search engine. I'm sure if a slippery slope is detected, SO will change its policy back.
Why are you sure of that? They're all the way down the damn slope at this point, there's no cleaning it up. But ownership's metrics are not mine necessarily.
They want the platform to survive, otherwise they wouldn't have bothered listening to user feedback. Either way, I'm happy to see they are doing something about how toxic SO is. The community has certainly earned its reputation. I for one don't think being an asshole is the only way to drive down noise.
I'm kind of curious, because I've heard the line of reasoning about keeping it "clean" multiple times. Like its only purpose is to be a pristine knowledge base where every question is asked only once, and a perfect answer is selected and enshrined for all time. That's all wonderful and magical, but how does also serving it's purpose as a QA platform for new people on the struggle bus prevent that first goal?
You won’t be able to find the useful questions because they’re buried under garbage. This problem is papered over by a lot of high-rep old answers but it’s going to look longer and longer in the tooth as those get dated. The platform “surviving” is orthogonal to it being what its original users were looking for.
Make it a slider, that way users can adjust 'arrogance' to their personal tastes.
Personally I'd crank it, it's a good motivation boost to keep on my toes.
This just feels like the wrong way around, I go to stackoverflow for stuff chatgpt can't answer. If anything, the right tool would be something which turns chatgpt threads into a stackoverflow question. (I don't actually think that is a good idea, just that it would make more sense)
Stack overflow gives you more than the answer, it gives you multiple answers for variations on what the OP wanted and therefore more options to try out. I guess this is useful when there are zero options provided or only crappy ones.
"Why are ChatGPT responses written a few words at a time?"
It replied, a few words at a time:
- - -
The responses are broken up into smaller chunks for several reasons:
1. Better readability: Breaking up the responses into smaller pieces makes it easier for users to read and understand the information being provided.
2. Interactivity: ChatGPT's response format allows for a back-and-forth interaction with the user, making it feel more like a conversation and allowing the user to ask follow-up questions or clarify information.
3. Error correction: By responding a few words at a time, the model can quickly correct any errors or misunderstandings in real-time, leading to a more accurate overall conversation.
4. Efficient communication: Responding in smaller chunks allows the model to quickly provide information and reduces the latency in the communication process.
Overall, the goal is to create an efficient, user-friendly, and interactive conversational experience.
For those who don't know, it is like Markov Chains: probability of next word (or a group of words encoded as a token) is calculated based on previous words and computationally intensive. It just uses not just probability between 1-2 previous tokens, it uses 2048 token window (roughly 1500 words) to predict next token, then puts next token into window and goes on.
What is even the point of posting nonsense spam from ChatGPT as replies? At least clearly indicate that it's generated. I thought it was from OpenAI as you said "from the horse's mouth", until I started reading that nonsense. Was under the impression that you were just trying to troll first.
The chatgpt output comes in chunks from openai's servers themselves, it can't get computed instantly. There's no way for this plugin to do what you want it to do.
