Top New Best Ask Show Jobs

Language Models Learn to Mislead Humans via RLHF | Hacker News Reader

Language Models Learn to Mislead Humans via RLHF

arxiv.org

3 points·Anon84··1 comment

Open articleView on HN

Anticipated by Stanislaw Lem in his History of Intellectronics.

Reply on news.ycombinator.com