Live data from Hacker News

Ask HN: ChatGPT doesn't ackowledge being wrong?

news.ycombinator.com

21–23 of 23 posts

Re: Ask HN: ChatGPT doesn't ackowledge being wrong?

#21

It always acknowledged it to me. Something like: > AI: Answer that's clearly factually wrong (e.g. a function that doesn't exist or a completely wrong numerical figure). > Me: that's not right, the function doesn't exist (etc.) > AI: you are right, that function doesn't exist. The answer is blah And repeat, since if it didn't get it right first time, it seems unlikely to be able to get there at all (and you'd not kno…

I always wondered why it bothers returning the first result if it can tell it's wrong 30 seconds later if you ask it again "I think that's wrong". Why not do make the function that outputs answers also feed itself "is this actually right/are you sure/is this not wrong"? Too expensive? Giant loop?

> Why not do make the function that outputs answers also feed itself "is this actually right/are you sure/is this not wrong"? Too expensive? Giant loop?

They do this, with humans. Both during training (they use supervised and reinforcement learning), and now at a much greater scale: it's what the free public access period is for and why there's a thumbs up/down button next to the output.

Re: Ask HN: ChatGPT doesn't ackowledge being wrong?

#22
When ChatGPT gives me a wrong answer, and I point out that it is wrong, ChatGPT immediately apologizes, every time. I have not seen it argue that it's actually right.

I've also seen it give different answers when asked the same question in a different way. Usually, one of the answers will be correct.

It has no idea if it's answers are right or wrong. It only knows that it's putting words in a common order.

Re: Ask HN: ChatGPT doesn't ackowledge being wrong?

#23

Earlier quoted context omitted.

I always wondered why it bothers returning the first result if it can tell it's wrong 30 seconds later if you ask it again "I think that's wrong". Why not do make the function that outputs answers also feed itself "is this actually right/are you sure/is this not wrong"? Too expensive? Giant loop?

It's a language model trained to return the most likely answer given a specific prompt. The goal of the answer is, to simulate a conversation and to sound realistic. ChatGPT is not grounded in reality, it does not know where its "knowledge" comes from, nor does it know whether the things it is saying are correct or wrong. It can't tell it's wrong, it just reacts in a plausible well to you telling it it's wrong (ackno…

> It can't tell it's wrong

So you are saying the order of events if:

1. you ask it a question

2. it gives you an answer (in this case, it's wrong)

3. you ask it "are you sure? i think that's wrong"

4. it answers again "you are right, i think the answer i just gave you was wrong, here is what i think is the right answer this time" (and again, it's wrong)

and repeat forever?

Post reply on HN