OpenAI (@OpenAI) “Chain of thought monitors are a key layer of defense against AI agent misalignme” — TopicDigg
OpenAI
@OpenAI
OpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring:
加入 December 2015
4 正在关注 4.9M 粉丝
Chain of thought monitors are a key layer of defense against AI agent misalignment. To preserve monitorability, we avoid penalizing misaligned reasoning during RL.
We found a limited amount of accidental CoT grading which affected released models, and are sharing our analysis.
显示更多
