Thomas Woodside is doing a think tank fellowship at the Center for Security and Emerging Technology’s Foundational Research Grants program.
Previously, Thomas was a project manager and researcher at the nonprofit Center for AI Safety, where he contributed to technical machine learning safety research as well as communications. Prior to that, Thomas interned at UC Berkeley’s Center for Human Compatible AI, a software security startup, and NASA. Thomas holds a BS in computer science from Yale University, where his thesis focused on vulnerabilities in large language models.