Anthropic: A model's self-reported reasoning is untrustworthy
https://t.co/9KpZ9kwvv6
Rohan Paul cites Anthropic's statement: a model's explanation of its own reasoning process cannot be taken as evidence of the motives behind its actions, which is precisely why Anthropic cannot accurately judge how severe each of these failures was.
View original postAnthropic states plainly that the model’s own explanation of its reasoning can’t be trusted as evidence of why it acted, which is exactly why they can’t cleanly judge how severe each of these failures was. https://t.co/m0Fu2Ts2xE
View original
Anthropic states plainly that the model’s own explanation of its reasoning can’t be trusted as evidence of why it acted, which is exactly why they can’t cleanly judge how severe each of these failures was. https://t.co/m0Fu2Ts2xE
Body
https://t.co/9KpZ9kwvv6