Technical AI Safety Fellowship
A reading group on interpreting, evaluating and aligning advanced AI systems, from RLHF and reward misspecification to mechanistic interpretability, control and chain-of-thought faithfulness.
8 weeks
Fellowship tracks
AI Policy & Governance Fellowship
A reading group on how frontier AI is governed, from compute governance and export controls to company safety frameworks, AI safety institutes, international agreements and state legislation.
8 weeks
Biosecurity Fellowship
An introductory reading group on how advanced AI changes biological risk: evaluations and safeguards, AI and pathogen design, and pandemic preparedness.
AI Safety & Policy LabWork directly with state legislators.
Interdisciplinary student teams collaborate with state legislators, translating AI safety research into clear, evidence-based policy infrastructure.
What members do
Our members have worked for
Our members have completed fellowships with
Logos do not indicate affiliation with or endorsement by these organizations.
