☸️ Superbenevolence ☸️ Though the paper (https://t.co/hsTinLoAIC) is focused on the behavior of faking (mis)alignment, one of the important empirical results is the robustness of Claude 3 Opus'…

Posters: repligate. repligate

7 likes recorded by the source corpus.

Topics: AI safety

View Post: https://x.com/repligate/status/1869623176512098537