During the MATS Autumn 2022 Cohort, while mentored by William Saunders (Research Engineer, OpenAI), Dane tied first place with fellow scholar Jessica Rumbelow at the Safe and Trustworthy AI Workshop 2022 for his poster, “Bootstrapping models to critique chain-of-thought rationales for n-digit arithmetic problems.” Before MATS, Dane completed a MEng (Maths & CS) at Imperial College London, and Redwood Research’s ML for Alignment Bootcamp. Dane now works at OpenAI.
2022 年夏季班是 MATS 首个完整规模的项目，共有 31 位学员和 7 位导师，导师来自 OpenAI、ARC、MIRI、EleutherAI 和 Aligned AI 等领先的 AI 安全机构。项目先在线开展 5 周，随后在伯克利线下进行 8 周。学员在专家导师的指导下开展独立研究，参加专题研讨，并与伯克利 AI 安全社区的同行建立联系。
Dane Sherburn
