
IST SL5 Taskforce
Lisa research leads the technical governance team, which she founded in February 2024 after joining MIRI as research manager in summer 2023. At MIRI Lisa focuses on concrete proposals for AI regulation, AI security and Verification Mechanisms. She is a Foresight Fellow in Intelligent Cooperation, mentors for MATS, and advises on Foresight AI Safety grants. Before MIRI, Lisa was an empirical researcher at MATS mentored by Alex Turner, during which they pioneered the technique of activation steering. Her education includes a BSc in Computer Science from TUM, graduate studies in Machine Learning and Reinforcement Learning for robotics at the Georgia Institute of Technology, and some coursework in medicine and neuroscience. Lisa also holds an honors degree in Technology Management and Entrepreneurship. Her current research focus includes AI Security, Verification mechanisms for coordination, and an ongoing (side) interest in whole brain emulation.
The Summer 2023 cohort supported 60 scholars with 15 mentors, working across 12 different research areas. The program consisted of a remote 4-week training phase, an 8-week research phase in Berkeley, and a 4-month extension phase. MATS leadership co-founded the London Initiative for Safe AI (LISA) in September 2023 to provide a dedicated research space for AI safety researchers and organizations in London, and for MATS scholars to continue their research projects. Research projects were distributed across multiple areas, with approximately one-third focused on evaluations and capability demonstrations and one-fifth on mechanistic interpretability, alongside work on agent foundations, activation engineering, and cooperative AI.
Lisa Thiergart