Rubi Hudson

I am a 5th year PhD student at the University of Toronto, supervised by Gabriel Carroll. My research focuses on AI alignment, using tools from microeconomic theory to model the incentives of AI agents.

I organize the Principled Agents research group, you can read about our research agenda here. Previously, I received a BMath degree from the University of Waterloo, was an early participant in the MATS program.

If you have thoughts or questions about my research and related topics, please reach out to chat!