Henry Papadatos

Henry Papadatos is Executive Director of SaferAI, where he works on key aspects of the organisation’s work ranging from risk-management ratings and AI benchmark research to risk management and internal operations. He is a technical AI risk management expert focused on closing the gap between rapid AI advancement and society’s ability to manage associated risks, and previously conducted research on large-language-model alignment at the Center for Human-Compatible AI at UC Berkeley. In his role at SaferAI he develops AI governance strategies and technical solutions for managing risks from frontier AI systems.

No endorsements yet.

Personal Website

https://henrypapadatos.com/

LinkedIn

-

Twitter / X

-

LessWrong

-

EA Forum

-

No grants recorded.