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.
The Summer 2022 cohort was MATS's first full-scale program, with 31 scholars and 7 mentors from leading AI safety organizations including OpenAI, ARC, MIRI, EleutherAI, and Aligned AI. The program ran 5 weeks online followed by 8 weeks in-person in Berkeley, where scholars conducted independent research under expert mentorship, participated in educational seminars, and built community with peers in the Berkeley AI safety ecosystem.
Dane Sherburn
