Hannah Sheahan

I am an AI alignment researcher at OpenAI. I try to build smart models that don't do bad things. Before OpenAI, I was a researcher at DeepMind where I helped to build Gemini.

Before that, I researched human learning. I did my PhD at The University of Cambridge with Daniel Wolpert, and a postdoc at The University of Oxford with Chris Summerfield. I don't publish much atm, but you can check out some old papers here.