←back to thread

Why language models hallucinate

(openai.com)
277 points simianwords | 1 comments | 06 Sep 25 07:41 UTC | HN request time: 0s | source
Show context
yreg ◴[07 Sep 25 07:50 UTC] No.45156255[source]▶
Maybe it goes against the definition but I like saying that _all_ output is a hallucination, when explaining LLMs.

It just happens that a lot of that output is useful/corresponding with the real world.

replies(1): >>45156423 #
kelnos ◴[07 Sep 25 08:25 UTC] No.45156423[source]▶
Well yes, it goes against the accepted definition. And if all output is hallucination, then it's not really a useful way to describe anything, so why bother?
replies(3): >>45156460 #>>45156875 #>>45169827 #
1. drekipus ◴[07 Sep 25 08:34 UTC] No.45156460[source]▶
But it's the perfect definition because it shows what it is. The output is a hallucination in what it thinks you want, which you can use for better form prompts or the like.

To say "it only hallucinates sometimes" is burying the lede and confusing for people who are trying to use it

Q: How do I stop Hallucinations? A: useless question, because you can't. It is the mechanism that gives you what you want