We are a very ambitious but friendly group interested in building a community of people collaborating together to mitigate the risks that increasingly capable AI brings to the world. We refine each other's mental models of the risks and build the skills to solve them through AI Alignment and AI Governance.

We have two main programs 1) Cambridge AGI Safety Fundamentals Program conceptually teaching you the in and outs of AI Alignment and why it's the problem of our time. 2) Machine Learning for Alignment Bootcamp program where you learn the technical skills.

Throughout both, we look for promising students to invite into our top Safety Scholars Program to collaborate together on exciting new research agendas and projects.

We also host weekly discussions, speaker events, or hackathons on these topics.

Join our discord here: https://discord.gg/KNEGe2gB7S