Apart Research Events

Henry is the Executive Director of SaferAI, where he works on risk modeling for AI cyber and loss-of-control risk, third-party evaluations of frontier models, and turning risk management practices into enforceable standards. He contributed to the EU AI Act's Codes of Practice as part of the expert working group on risk taxonomy and assessment, and helped draft the G7 Hiroshima AI Process reporting framework through the OECD task force.

His talk: an analysis of the Hugging Face breach, then what SaferAI proposes to do about the next one.

 15-30 min talk + 10-15 min Q&A. Online (Zoom); the Zoom link is shown once you RSVP.

, September 11-13, online. Co-organized by 

HackTalk: Henry Papadatos