Definition
Plain language
A training program that helps new researchers get into AI safety work.
As stated in the literature
ML Alignment & Theory Scholars — a research fellowship program; several papers in this corpus list MATS-affiliated authors collaborating with frontier labs.
Why it matters: It helps bring new talent into AI safety research, widening the pool of people working on making AI systems trustworthy.
For example, a recent graduate interested in AI safety might join this program to work alongside experienced researchers and frontier labs.
Heard on the show
“… The paper is by a team out of MATS along with collaborators at Anthropic and Google DeepMind — with EE-yon Jang, Damon Falck, and YOSH-kah …”Episode 007 — Exploration Hacking: When Models Sabotage Their Own RL Training