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 rini17 on Sunday February 25, 2024 @07:39AM (#39500311)
Maybe it needs some memory retrieval step that can measure the confidence - whether there's anything related to the prompt. No idea how to train a LLM to do that.
[ Parent | on HN ]

There are no comments on this comment yet.