Lewis Hammond
Bio
Lewis Hammond is a DPhil candidate in computer science at the University of Oxford and Research Director at the Cooperative AI Foundation. His doctoral research, supervised by Alessandro Abate, Julian Gutierrez, and Michael Wooldridge, focuses on safety and cooperation in multi-agent systems, motivated by the goal of ensuring AI and other powerful technologies are developed and governed safely and democratically. He holds a BSc in mathematics and philosophy from the University of Warwick and an MSc in artificial intelligence from the University of Edinburgh. His key research areas span game theory, formal methods, machine learning, cooperative AI, causal reasoning in games, and scalable oversight; notably, his ICLR 2025 paper on neural interactive proofs introduces a framework for how a computationally bounded verifier can learn to interact with powerful but untrusted provers to solve tasks, directly addressing the scalable oversight problem. He is also affiliated with the Centre for the Governance of AI, is a Pathways to AI Policy Fellow at the Wilson Center, and was previously a DPhil Affiliate at the Future of Humanity Institute. His scalable oversight experiments received funding from the Long-Term Future Fund and OpenAI.
Links
- Personal Website
- https://lewishammond.com/
- Twitter / X
- LessWrong
- lewis-hammond-1
Grants
from Long-Term Future Fund
Discussion
Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.
Details
- Last Updated
- Mar 22, 2026, 11:03 PM UTC
- Created
- Mar 20, 2026, 2:54 AM UTC