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