Thomas Wolf 称赞 METR 智能体失控评估工作
As always, great to read METR’s thoughtful and in-depth work on this topic
AI 导读
Thomas Wolf 表示，一如既往地很高兴读到 METR 在这一话题上深思熟虑且深入的工作。METR 此前提出，若 AI 开发者即将失去对内部智能体的控制，公司外部是否有人能知晓，并分享了与 AI 开发者合作公开评估和分享相关证据的设想。
查看原帖If an AI developer was on track to lose control of its internal agents, would anyone outside the company know? Today, we are sharing METR’s vision for how we would work with AI developers to openly assess and share evidence about this. https://t.co/rtJsbIjSGN
正文
当前显示原文，中文全文译文尚未就绪。
As always, great to read METR’s thoughtful and in-depth work on this topic