Comment by jsjohnst
1 year ago
> A human WILL NOT make up non-existent facts
Categorically not true and there’s so many examples of this in every day practice that I can’t help but feel you’re saying this to disprove your own statement.
1 year ago
> A human WILL NOT make up non-existent facts
Categorically not true and there’s so many examples of this in every day practice that I can’t help but feel you’re saying this to disprove your own statement.
It's absolutely true. Humans misremember details but I'll ask an LLM what function I use to do something and it'll literally tell me a function exists named DoExactlyWhatIWant and humans never do that unless they're liars. And I don't go to liars for information -- same reason I don't trust LLMs.
Tell me, does an LLM know when it lies?
I don't see a functional difference between misremembering details and lying. Sure one is innocent and one malicious, but functionally a compiler doesn't care if the source of your error is evil or not.
An LLM doesn't know when it lies, but a human also doesn't know when they are (innocently) wrong.
The crucial difference is between misremembering occasionally VS consistently.
You won't give any job to that kind of person.
Non-liar humans do in fact make mistakes.
True, but if they start producing non-existent facts consistently LIKE LLMS. You will be concerned about their mental health.
I insist that human hallucinations are NOT SAME as LLMs.