Deep dives into trustworthy & secure AI

ControlConf is a conference dedicated to the emerging field of AI control: the study of techniques that mitigate security risks from AI even if the AI itself is trying to subvert them.

FAR.AI, in collaboration with leading think tanks, is organizing the second annual Technical Innovations in AI Policy Conference to connect policymakers with leading AI technical experts.

FAR.AI, in collaboration with the Tarbell Center for AI Journalism, is organizing an inaugural workshop to connect journalists with leading AI experts.

FAR.AI, in collaboration with FAI, CNAS and RAND, is organizing the inaugural Technical Innovations for AI Policy Conference.

ControlConf is a conference dedicated to the emerging field of AI control: the study of techniques that mitigate security risks from AI even if the AI itself is trying to subvert them.

The Paris AI Security Forum brought together experts in AI development, cybersecurity, and policy to dramatically accelerate the security of powerful AI models, aiming to prevent potential catastrophes while fast-tracking scientific and economic breakthroughs.

We held a workshop bringing together a set of leading AI scientists who had independently converged on a family of approaches which shared a central ambition of developing quantitative safety guarantees for AI systems, resulting in a position paper documenting the key principles of "Guaranteed Safe AI" agendas.