Language Models Learn to Mislead Humans via RLHF

Posted by Anon84 on Friday November 01, 2024 @09:07PM
from the arxiv.org dept.

( 1 comment | 3 points | on HN )

Re:Language Models Learn to Mislead Humans via RLHF by mentalically on Friday November 01, 2024 @11:20PM (#42023817)

Anticipated by Stanislaw Lem in his History of Intellectronics.

[ Parent | on HN ]