# debate
標記為「debate」的 2 篇文章
Scalable Oversight Challenges
How oversight breaks down as AI systems become more capable: the scalable oversight problem, recursive reward modeling, debate, market-making, and implications for red teaming increasingly capable models.
scalable-oversightalignmentdebatereward-modelingcapability-gap
Scalable Oversight Challenges
How oversight breaks down as AI systems become more capable: the scalable oversight problem, recursive reward modeling, debate, market-making, and implications for red teaming increasingly capable models.
scalable-oversightalignmentdebatereward-modelingcapability-gap