Scott Garrabrant
Mathematician at MIRI who works on the foundations of agency and alignment
A mathematician at the Machine Intelligence Research Institute whose work on logical induction and the foundations of agency underpins much of the alignment vocabulary on this page, including the mesa-optimization line of research.
In the library
Nothing of theirs is filed in the hub yet. Browse the full library.
Recommended next
Hand-picked from the hub based on what Scott Garrabrant covers.
Proofs and Prompts
A communal blog where working mathematicians — professors, PhD students, sceptics and enthusiasts alike — write about what AI is doing to their field: authorship, what counts as understanding, where papers will go, and whether the job changes. Recent pieces include Martin Hairer on why he joined the AGMAI advisory group and Jonny Evans on the choices ahead. Submissions are open to anyone in the field, any length.
Why this: Also about mathematics
Early career researcher responses to AI in math
Preprint, not yet peer-reviewed, by Anna Brandenberger, Hanna Mularczyk, and Dora Woodruff. The paper surveys more than 260 early-career mathematicians at nearly 60 institutions about their experiences and concerns around AI in mathematics.
Why this: Also about mathematics
100+ reactions to 100+ solutions (Proofs and Prompts)
An updating snapshot of the math community's gut reactions to OpenAI's October 6, 2026 announcement, collected by the Proofs and Prompts blog.
Why this: Also about mathematics
openai/math
OpenAI's public GitHub repository, released October 6, 2026, of manuscripts the company says contain solutions to a number of high-profile mathematics problems. See the AHM statement for mathematicians' response.
Why this: Also about mathematics