AI 导读
这两篇真的很好,推荐! https://t.co/8TbQwvm7XE
正文
这两篇真的很好,推荐! https://t.co/8TbQwvm7XE
本周最佳两篇 Week 26 Training a Misaligned Reward Seeker Steering towards “automated grading” degrades alignment https://t.co/ej3RK7kNs9 https://t.co/CKWIzQ3dyO https://t.co/Va0IjaMSYQ在 X 查看被引用的帖子
来源:@dongxi_nlp · x.com