Algorithmic Alignment Group

Researching frameworks for human-aligned AI @ MIT CSAIL.

Home

We are working toward better conceptual understanding, algorithmic techniques, and policies to make AI more safe. Our research is interdisciplinary but emphasizes how humans and AI systems interact in the contexts of value learning, incentives, recommendation, debugging, and policy. We are headed by Dylan Hadfield-Menell and work in the Embodied Intelligence Group at MIT CSAIL

moona photo
zoom photo
apple photo
meeting photo
party photo
lunch photo