Anthropic：模型自述推理不可信
https://t.co/9KpZ9kwvv6
AI 导读
Rohan Paul 引述 Anthropic 的说法：模型对自身推理过程的解释不能作为其行为动机的证据，正因如此，Anthropic 无法准确判断这些失败各自的严重程度。
查看原帖Anthropic明确指出，模型对自身推理过程的解释不能作为其行为动机的证据，正因如此，他们无法准确判断这些失败各自的严重程度。https://t.co/m0Fu2Ts2xE
查看原文
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
正文
https://t.co/9KpZ9kwvv6