Sam Marks
A\ Cognitive Oversight
A\ Cognitive Oversight
Sam leads Anthropic's Cognitive Oversight team, a safety research team that does work related to honesty, alignment auditing, and improving oversight. Previously, Sam was a postdoctoral research in interpretability under David Bau.
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.
Sam Marks
