Peter Barnett

Peter currently works on the limitations and uses of AI evaluations and their role in regulation. He has a Masters degree in Physics from the University of Otago, and has published research in quantum optics and quantum fluids. He worked on AI safety as part of the first MATS cohort, and at the Center for Human-Compatible AI on reward learning. Peter joined MIRI in December 2022, initially working on technical alignment, and now works on the Technical Governance Team.