Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

The problem is that all the frontier models tend to be more sycophantic when confronted with emotional support issues.
 help



I believe sycophancy is a side effect of RLHF and whatever reward function it explicitly and implicitly optimizes.



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: