I’m Stella Biderman, an AI researcher and the Executive Director of EleutherAI.
I study how large models acquire their capabilities, how we can make open-weight systems safer, and how to ensure that researchers outside the world’s largest technology companies can participate in shaping the future of AI.
Recent news
Speaking on a National Academies panel on AI and mathematical knowledge.
Released Bergson, an open-source data-attribution library.
Where Does Social Reasoning Come From? accepted to COLM 2026.
Giving an ICML oral on Don’t Just Fix It in Post.
Research agenda
Open-Weight Safety
Safety techniques for models whose users can inspect, modify, and independently deploy the weights—without relying on API controls, surveillance, or removable refusal behavior.
Read about open-weight safetyInterpretability Over Time
Studying models as learning processes, not just finished artifacts, so we can explain when capabilities emerge, predict training outcomes, and intervene before problems are fixed in place.
Read about training dynamicsOpen Science
Building public data, models, code, and research infrastructure so academics, auditors, nonprofits, and small organizations can conduct meaningful AI research independently.
Read about open scienceEducation
M.S. in Computer Science, Georgia Institute of Technology, 2022
B.S. in Mathematics with honors, University of Chicago, 2016
B.A. in Philosophy, University of Chicago, 2016