Research by Harvard students on catastrophic risks from advanced AI.
Managing risks from advanced artificial intelligence is one of the most important problems of our time.¹ We are a community of technical and policy researchers at Harvard aimed at reducing these risks and steering the trajectory of AI development for the better.
We run three semester-long introductory fellowships on AI safety:
a technical fellowship, covering topics like neural network interpretability,¹ learning from human feedback,² goal misgeneralization in reinforcement learning agents,³ eliciting latent knowledge,⁴ and evaluating dangerous capabilities in models⁵
an AI policy fellowship, where we discuss core strategic issues posed by the development of transformative AI systems including misuse, concentration of power, and loss of human control
an AI x Biorisk covering the implications of new AI tools on biosecurity
After completing one of the intro fellowships, Harvard students can apply for membership to get more involved in the AISST community.
Join our mailing list →
Our members have worked with:
Our members have gone on to full-time employment at:
Note: Use of organizational logos does not imply affiliation with or endorsement by these organizations.