MATS mentors are advancing the frontiers of AI alignment, transparency, and security

Toby Webster is a program director at Sentinel Bio, leading work on risks at the intersection of AI and engineering biology. Previously, Webster studied biological AI model security at RAND Europe.

David Demitri Africa is a research scientist at Resolution, where he works on understanding the character and motivations of AI systems in ways that scale to superintelligence.

Alfie is the founder and research lead at Formation Research, a startup research organisation focusing on lock-in and power concentration risks from AI systems. He works on AI-enabled totalitarianism, coups, and extreme power concentration. He claims that AI systems can make future versions of these phenomena much more stable, long-term, harmful, and widespread, and is focusing on developing and implementing governance-informed interventions for these problems leveraging technical methods of verification and cooperation.

Jan worked as a software developer for over a decade before shifting to AI safety in 2023. He is an ARENA and Astra Fellowship alumni, interested in anything related to out-of-context reasoning in LLMs.

Caspar Oesterheld is a researcher at Redwood Research where he works on improving models' conceptual reasoning capabilities, i.e., their reasoning about questions where we cannot verify the answer and the best way to make progress is through argumentation. Much of this work has been done in collaboration with Anthropic.

​

Previously, he completed his computer science PhD at Carnegie Mellon University where he was assistant director of the Foundations of Cooperative AI Lab. Caspar has published about multi-agent AI interactions, decision theory in Newcomb-like decision problems, and, informally, about how models reason about conceptual questions. He has served as a research mentor for MATS, PIBBSS, CLR and astra (incoming).

Neil Chowdhury is a member of technical staff at Transluce, a research lab building tools for understanding AI systems. Chowdhury previously worked on safety at OpenAI.

McKenna Fitzgerald most recently served as Manager of Development and External Affairs at Americans for Responsible Innovation (ARI), where she led Bay Area AI safety political engagement while helping translate technical and policy developments for federal audiences. She previously worked at MATS, supporting and managing AI safety research programs, and at the Global Catastrophic Risk Institute, where she served as Deputy Director. She holds a B.A. in philosophy from UC Berkeley.

I have founded three successful businesses and sold two, and now I've turned to investing in AI Safety.

​

Over the years I've learned a lot about what it takes to actually manage and run an organization, focus on what matters and scale the things that are important.

Alex Kleinman is a co-founder of Active Site. Previously, Kleinman worked on broad-spectrum vaccines at Alvea.

Sunishchal Dev is an AI safety researcher working pre deployment testing with a focus on biosecurity at the U.S. AI Safety Institute within NIST’s Center for AI Standards and Innovation (CAISI). Previously, he was an AI Evaluations Research Scientist at RAND, where he led machine learning engineering efforts focused on evaluating frontier AI systems, including building biological capability benchmarks, assessing risks from open-weight models, and developing methods to make LLM-based evaluations more reliable. He was a fellow during MATS 6.0 under the mentorship of Marius Hobbhahn. Before moving into AI safety, Dev spent nearly a decade as a data scientist, machine learning engineer, and management consultant.