I've cobbled together syco-bench, a benchmark of model sycophancy. It consists of tests measuring three things: bias towards user in an argument, mirroring user views, and overestimating user IQ.…

Posters: timfduffy. timfduffy

6 likes recorded by the source corpus.

Topics: AI & LLMs

View Post: https://x.com/timfduffy/status/1917291858587250807