[duxup]

ChatGPT at least seems like it is trying to help me.

The meta games going on in SO are a whole lot more of a mess and ChatGPT is more than happy to hear my question a 3rd time and spit out the same answer as before but change a few things. SO, not so much.

[coffeebeqn]

I use chatgpt as a rubber duck who I’m suspicious of. Way too often it just comes up with fictional features

[s_dev]

I really don't get this dependence problem. People want information to be 100% accurate?

This is the internet -- lies and false claims are the standard. It's up to individuals to corroborate that the info they're looking at is reliable. Google provides a list of relevant results to a keyword search -- every one of those results can be bogus and no one bats an eye. ChatGPT provides text output based on a text input and the text can be bogus. Why should ChatGPT be held to a higher standard than Google?

[SV_BubbleTime]

Is entirely possible to hit some search result for a real human had a code hallucination. And to the topic, on stackoverflow that would have been deleted, downvoted or corrected.

GPT will tell you it’s right… well, it’ll apologize, offer another solution that could also be wrong and now you are in a loop.

[s_dev]

Only a computer can get stuck in a loop or a person who is insane. It's not like if you ask a person to divide by zero they will fall in to a coma or sit there computing.

I 100% believe that ChatGPT can output absolute garbage but for the same reason you don't cite Wikipedia/Google you won't be citing ChatGPT. Just like Wikipedia or Google It's just an excellent starting point to rapidly get a working draft going.

[duxup]

I get wrong answers too, but they're pretty easy to figure out fast and if I rephrase I get what I need.

It's not like I'm not validating SO answers, there's not any extra steps from my SO experience. Also SO likes to give oddly, technically correct, but also hard to work with code sometimes to the point of being unusable and I take someone else's example anyway. ChatGPT is really good at making super generic answers and quick iterations / alterations.

ChatGPT's power is often in the "conversation" where I add or take things away or change things "I need to break out X,Y,Z before I render it because..." and blamo I get new code. SO has none of that.

[SV_BubbleTime]

I’m going to steal that.

I’ve been trying to explain to people that GPT is good for subjective things, not object of things. But that didn’t really jive with the programming part that works OK for certain tasks.

Then I realized it does and programming is just subjective a lot of the time. You need a right answer but how you get there is open.

Using it as a spring board is good advice.

[tomrod]

Aye. It's a scaffold or first draft at best.

[nirvdrum]

I've found it refreshing to be able to ask a performance-related question and not get a trite reply about premature optimization. It's frustrating reading a well-researched, obviously informed question about a specific thing and the top reply is "Why do you need this? Did you profile it?". Nothing new is learned and the cynical part of me thinks it's just a race to get free Stack Overflow points.

[dotnet00]

Similarly with questions about doing X with Y where the top answer just pushes some library, a different language or outright changes X to something else (without answering the original question).

I feel like the people writing those answers should also be well aware that often you can't just change the problem or just add in a library to solve one specific problem on a whim. It's kind of demeaning to push those kinds of answers anyway rather than maybe question the task but provide a solution anyway.

[bluetomcat]

The SO community culture rewards precise, concise and direct answers to simple and popular questions like "how do you subtract 2 dates in Python". In the first years, those were the low-hanging fruit and a source of big reputation points for some people. Unpopular questions regarding an obscure bug in the user's code or perhaps a misunderstanding of the OP aren't seen as "pretty" - they require answerers to understand the context of the particular problem and will not gain them many reputation points, even if they provide a useful answer to the OP.