Our work spans the technical, strategic, and governance dimensions of AI safety. Active research concentrates in three areas:
Studying the attack surface of advanced AI systems — including model weights, training pipelines, deployment infrastructure, and the information-security posture of frontier labs. Check out our Security Guide.
Mapping AI development trajectories, identifying high-leverage interventions, and analyzing how transformative AI will reshape institutions, economies, and global risk.
Examining regulatory frameworks, compliance and verification mechanisms, compute governance, and the international coordination challenges posed by frontier AI development.
