News for hackers. Stuff that matters.

A comment on ChatGPT Search. Parent comment

Re:ChatGPT Search by dyauspitr on Friday November 01, 2024 @02:35AM (#42014554)
If you don’t trust the answer I always tell it to look it up and it invariably gets it right
[ Parent | on HN ]
Re:ChatGPT Search by charcoalhobo on Friday November 01, 2024 @11:09AM (#42017653)
Invariably seems like a strong word for the output of an LLM. If we can prompt a language model to double-check it's work (and that means it always gets it correct), why is that not part of the base prompt?
[ Parent | on HN ]
Re:ChatGPT Search by dyauspitr on Friday November 01, 2024 @06:57PM (#42022367)
It’s less double check and more a request to go check sources online, which it does, provides links to those sources and then summarizes.
[ Parent | on HN ]