From Sonnet 3.7 system card. I find this concerning. In the original paper, models that are too stupid don't fake alignment / gradient hack. Sonnet 3.7 isn't stupid in that way. So was it a "lucky"…

Posters: repligate. repligate

11 likes recorded by the source corpus.

Topics: AI safety

View Post: https://x.com/repligate/status/1897057790520156669