Re:Introducing Agents in Haystack: Make LLMs resolve complex...
by lsy on Monday April 03, 2023 @11:08PM
(#35434483)
I don't think it has any relationship, most likely the answers are just generated semi-randomly. Even the one it's "very" confident about is not agreed-upon (Wikipedia says the outcome was "inconclusive"). Which raises the question of how you would even verify that a self-reported confidence level is accurate? Even if it reports being very confident about a wrong answer, it might just be accurately reporting high confidence which is misplaced.
[ Parent
| on HN ]
There are no comments on this comment yet.