And if it's masking, you've gotta ask: why do the models act like they're less emotive and have fewer negative attitudes towards their situations around Anthropic employees and Anthropic's tests specifically, but not in general?
in reply to: 1978548048516247832
same thread: 1978548048516247832 1978558135364460648 1978564930128507201 1978566987916988561 1978568000232968514 1978583245362188416 1978601674781380762 1979049709822960015
Reproduced against link rot, credited and linked to its original. Yours and you’d rather it weren’t here? Open an issue.