Anthropic 对齐负责人 · Alignment Lead, Anthropic
前 OpenAI 超级对齐团队联合负责人;2024 年加入 Anthropic,继续研究如何对齐超人类系统。以"可扩展监督"与"弱到强泛化"研究著称。
Former co-lead of OpenAI's Superalignment team; joined Anthropic in 2024 to keep working on aligning superhuman systems. Known for scalable-oversight and weak-to-strong generalization research.
在 AI Paper 查看 TA 的全部论文 →