Call for Collaborators on Scalable Oversight: Verification, Collusion, Steganography, AI Control

timrudner · x · 2026-09-13

timrudner is recruiting collaborators to improve methods for effective frontier AI oversight, beyond just more evaluator organizations. Topics of interest include formal and runtime verification for agents and multi-agent systems, scalable oversight for very large multi-agent systems, statistical guarantees, mechanism design, collusion and emergent cooperative norms in multi-agent systems, covert communication (steganography), alternatives to CoT monitoring, and AI control. Interested parties are invited to fill out a form.

Related event: Researcher Calls for Collaboration on Scalable Frontier AI Oversight(2 posts)→

Original post →

More from Safety

Safety channel →