Peter Hase

Peter Hase is a Visiting AI Scientist at Schmidt Sciences, where he supports the AI and Advanced Computing Institute’s work on AI Safety and Interpretability.He has previously worked at Anthropic, Google, Meta, and the Allen Institute for AI. His research focuses on natural language processing (NLP) and AI Safety, with a particular interest in explaining and controlling the behavior of machine learning models. His work in these areas has earned multiple spotlight awards at top AI conferences and has been featured in public-facing outlets such as Nature magazine. He completed his PhD at the University of North Carolina at Chapel Hill, supported by a Google PhD Fellowship.Peter is an active member of the NLP, AI Safety, and Interpretability research communities. He has served in senior editorial roles for major AI conferences, including as a Senior Area Chair for ACL, the premier conference in NLP. He currently serves as a Senior Area Chair for EMNLP 2025, overseeing the track on Interpretability, Model Editing, Transparency, and Explainability.