Our Programs

An overview of AI alignment, the field that aims to align advanced AI systems with human values and intentions. We cover the fundamentals such as interpreting the internals of neural networks, reinforcement learning from human feedback, and concrete ways that transformative AI might go really badly. Prior machine learning experience is not necessary! See our curriculum here.

Each week, we select a technical paper from the AI alignment literature or related research and meet to individually read and then discuss them. We may also host talks from alignment researchers from time to time. Prior participation in our Intro Technical Fellowship is not necessary.

An exploration of the policy and governance landscape surrounding advanced AI. We read and discuss foundational and contemporary work on AI regulation, international coordination, and institutional design—examining how governments, research labs, and civil society can shape the development of AI to be safe and beneficial.