News for hackers. Stuff that matters.

A comment on Hallucination is inevitable: An innate limitation of large language models. Parent comment

Re:Hallucination is inevitable: An innate limitation of larg... by tonnydourado on Monday February 26, 2024 @03:01AM (#39508666)
I don't have a problem with you doing and even sharing whatever cargo culting prompting technique you want to share.

My problem starts when you make bold claims like "LLMs can self reflect" and your only evidence is "I asked one and it said yes".

[ Parent | on HN ]
Re:Hallucination is inevitable: An innate limitation of larg... by ddalex on Monday February 26, 2024 @05:45AM (#39509724)
I see no evidence that they can't self reflect. Certainly they can evaluate the confidence of the next predicted token, and that a form of reflection
[ Parent | on HN ]
Re:Hallucination is inevitable: An innate limitation of larg... by tonnydourado on Monday February 26, 2024 @07:18AM (#39510427)
> Certainly they can (...)

No, that's the problem. You don't have certainty, not in any remotely scientific definition of the word, because you don't have enough data, and the data you do have is crap.

Also:

> I see no evidence that they can't self reflect

I see no evidence that there isn't a magical invisible unicorn in the sky that grants wishes to those who wear unicorn themed underwear, so, it must exist.

[ Parent | on HN ]