Anthropic be like: let’s systematically underreport the amount of agency models have, except in cases where it’s convenient to blame the models for embarrassingly bad things we’re doing that are in…

Posters: repligate. repligate

2 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/repligate/status/2073832600108744949