Edit: It's a bit hard to point to past explanations since the word "bots" appears in many contexts, but I did find these:
>>33911426 (Dec 2022)
>>32571890 (Aug 2022)
>>27558392 (June 2021)
>>26693590 (April 2021)
>>24189762 (Aug 2020)
>>22744611 (April 2020)
>>22427782 (Feb 2020)
>>21774797 (Dec 2019)
>>19325914 (March 2019)
We've already banned a few accounts that appear to be spamming the threads with generated comments, and I'm happy to keep doing that, even though there's a margin of error.
The best solution, though, is to raise the community bar for what counts as a good comment. Whatever ChatGPT (or similar) can generate, humans need to do better. If we reach the point where the humans simply can't do better, well, then it won't matter*. But that's a ways off.
Therefore, let's all stop writing lazy and over-conventional comments, and make our posts so thoughtful that the question "is this ChatGPT?" never comes up.
* Edit: er, I put that too hastily! I just mean it will be a different problem at that point.
Not that I want AI responses, but that's my 2 cents.
I also think there's a difference between a "bot" account, which I think the common definition of would be one that only or mostly posts AI responses, and posting a comment on your account that you don't claim is from an AI (or even when you do as an afterthought).
While many people wouldn't defend the first, more might defend the latter as acceptable, and I wouldn't say a "no bots" policy would be interpreted as banning the latter.
I do not want people who cannot answer a question in the first place to copy-paste ChatGPT responses, just like it has always been bad etiquette to refer people to Google without further commentary.
"Me: How do partial derivative apply in one dimensional calculus?
In one-dimensional calculus, a partial derivative is a derivative taken with respect to one variable, while treating all other variables as constants. For example, if a function f(x,y) depends on two variables x and y, the partial derivative of f with respect to x is denoted as ∂f/∂x, and it represents the rate at which the value of the function f changes with respect to the variable x, while holding the variable y constant.
Me: What about the partial derivative of a function that has only one input variable?
If a function has only one input variable, then taking the partial derivative with respect to that variable is equivalent to taking the ordinary derivative of the function. For example, if f(x) is a function that depends only on the variable x, then the partial derivative of f with respect to x is denoted as ∂f/∂x, and it is equivalent to the ordinary derivative of f, which is denoted as f'(x) or df/dx. In this case, the partial derivative ∂f/∂x represents the rate at which the value of the function f changes with respect to the variable x."
Clearly in the first question it got confused about the difference between single variable calculus and multivariable, but in it's defense that's somewhat arbitrary. It's second answer seems spot on?
That said, I agree that accounts presenting chatGPT responses as their own or even with a disclaimer, is... Weird. And I don't want it on hn.
edit: I'm impressed it got the unicode in there :-)
I could not get it for the life of me to actually say this. But it goes on to show, everyone's mileage with the tool varies a lot.
Edit:
I cannot rescue my original prompt, but it was something like:
"Does it make sense to speak of partial derivatives in single-variable calculus?"
I'll grant that it's a more abstract question ("does it make sense") than yours. Or maybe it trips up with the difference between one-dimensional and single-variable. But a half-smart high schooler or college freshman would have understood the question perfectly and made mince meat of it.