[jerrac]

> Almost everyone who comes to SO, in my experience, has a fundamentally wrong idea about how the site is intended to work.

True. I quit trying to do anything there once I realized that SO was fundamentally not useful to me. It advertised as a gamified Q&A platform, but was actually a knowledge base psudeo wiki thing structured in way that didn't lend itself to answering the questions I needed answered.

So, I think a lot of the negative reactions are deserved, because SO looks like something it isn't.

People want a place to get help. SO looks like a place to get help. But SO is a place to ask for help only if your problem fits a specific set of requirements. And since most problems will never meet said requirements, most people can never actually get help on SO.

I post this in part because I'm still saltly about how much time I wasted trying to get help only to get downvoted, but also because if SO actually wants to do what they say, they really need to restructure into something that actually looks like what they want to be.

My suggestion would be to have two sites, one that is actually a general Q&A site like what everyone is after, the other is the kind of knowledge repository that SO wants to be. Then you just promote the really good questions from the Q&A site into the other site.

I'd also recommend ending the whole "downvote" idea. I have yet to see it not result in cliques and in discriminating against viewpoints the people with downvote permissions don't like. Let a lack of upvotes cause poor content to drop to the bottom.

[zahlman]

We would love to change how SO gets advertised. But we aren't in control of it, and the truth seems to be counterproductive to having a site that makes money from ad revenue.

I recommend looking for alternatives, because this problem can't really be fixed and the site owners seem intent on making it worse. I personally use and recommend (and am a moderator at, full disclosure) Codidact Software: https://software.codidact.com/ . But at Codidact we're still fundamentally using the same "Q&A site" (I don't think this means the same thing you appear to think it means) model . We just have proper community involvement (the site is owned by a non-profit foundation and committed to community sovereignty; see https://codidact.org/), new site software, and newly conceived site scope.

> My suggestion would be to have two sites, one that is actually a general Q&A site like what everyone is after, the other is the kind of knowledge repository that SO wants to be.

The problem is that there are already countless sites "like what everyone is after". If you try to split a Q&A site like Stack Overflow that way without changing the actual UI, the problem just repeats itself: people try to use the knowledge repository part as if it were yet another traditional forum.

And it turns out, people often think they're after that model, then get fed up with it over time.

I think an idea like yours can be done, but it would require radically different site software. (In early 2023 - I think - I kept myself busy with contemplating a design for exactly this, but I didn't really write anything down.)

[socalgal2]

Don't use S.O. Ask an LLM. It's a vastly superior experience. Better answers. no closures. No down votes.

[kyralis]

Honestly, this is one of the few places where I agree with this sentiment. I have roughly the same trust in an LLM answer as in a SO answer anyway, so it's not like I'm buying any particular additional verification cost - I have to treat the response as only vaguely trustworthy in either case, and the LLM experience is certainly nicer.

[klooney]

Sure, but where does the LLM get its answers?

[zahlman]

So here's the fun part.

I'm all over this thread explaining how Stack Overflow is supposed to work, and how almost everyone who comes to it has broad misconceptions, and about how we're very deliberately gatekeeping in a specific way for a specific purpose, and why I think that purpose is legitimate.

I've also expressed quite a bit of AI skepticism on HN before.

And I absolutely agree with you - assuming that by "use Stack Overflow" you mean "post a new question".

Most questions are fundamentally simple, even if they're tedious. If you're implementing something "complex", usually it really just involves following a straightforward series of steps, and it just takes a little bit of experience to see what the steps are. That breakdown is probably not useful to anyone else, and is hard to turn into a searchable artifact for others. If you're tearing out your hair troubleshooting something, most of the time one of the "standard" fixes really will work, and you just need to be talked through them.

If you like reading professional/academic sounding prose extensively trained to be inoffensive (even if it isn't always to the point), you have much better odds now with an LLM than with a random person who happens to be an expert on whatever it is you're trying to do.

If you're trying to figure out a thorny problem and it would benefit you to have a back-and-forth communication - or ask multiple questions on a theme and get all the responses from the same place - Stack Overflow can't do that for you. In fact, traditional forums can't, either, except accidentally (because they're too small to expose you to more voices). But the Stack Exchange Q&A model is explicitly about preventing back-and-forth communication, because it degrades the experience for third parties.

If you take downvotes personally (they aren't meant personally) or expect that your questions should be answered simply because you ask them, then of course you should prefer a system that doesn't rate what you say (unless you explicitly ask) and is directly tasked with responding (even if you prompt with complete nonsense).

And if you want a system that tries to adapt code to your personal circumstances and minimize the editing you need to do, then you obviously shouldn't use one that specifically tries to show demonstration code relevant to everyone with the same problem.

----

But the LLM is trained in part on Stack Overflow content. And if everyone using Stack Overflow used it as intended (and as took years to properly figure out, and is taking much longer to communicate), the LLM would be trained on much better Stack Overflow content. And would also not need the LLM a lot of the time, because a traditional search engine would find you high-quality Stack Overflow content directly.

(Actually, despite everything that's gone wrong, traditional search engines still do a reasonable job a lot of the time. Granted, it's extremely frustrating when they fail. I know because I've experienced this failure when trying to find a good target to close an obvious duplicate.)

And sometimes the LLM will be wrong; and it will be absolutely abysmal at introspecting whether it's wrong.