Speakers
Fazl Barez is a Senior Research Fellow and Principal Investigator at the TSG Lab at the University of Oxford, where he leads research on AI safety, technical governance, and the societal impacts of AI. He also serves as Technical Director of the AI Governance Initiative.
His work focuses on AI safety and interpretability—understanding how AI systems reason, whether their explanations can be trusted, and how these systems shape society. His research has been adopted by leading AI labs, including OpenAI, and is supported by Anthropic, OpenAI, Schmidt Sciences, and NVIDIA.
He leads the $1M Martian Interpretability Prize, the largest open prize in the field, and teaches Oxford’s AI Safety and Alignment course. He has published over 50 papers and is a regular contributor to public debates on the governance, societal impact, and trustworthiness of advanced AI.