
Jacob AndreasResearcher
MIT
Associate Professor
via MIT
Researcher · Academic
Associate Professor at MIT
Hadfield-Menell helped formulate cooperative inverse reinforcement learning, where an AI and a person work together to uncover the person's goals. He now leads MIT's Algorithmic Alignment Group, studying model internals, human feedback and societal oversight.
See something inaccurate or outdated?
MITWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Last editorial review: August 9, 2026