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 Recruits Collaborators for Scalable Frontier AI Oversight(4 posts)→
More from Safety
- OpenAI researcher details 'eyes on everything' system monitoring nearly every frontier rollout — willdepue · 2026-10-31
- OpenAI reportedly to train on users' Daybreak sessions with no opt-out — dyn___ · 2026-10-31
- Forethought: US has 9x China's AI compute, can afford to pace the frontier — willmacaskill · 2026-10-31
- unpromptedconf takeaways: security programs face forced change as reachable vulnerabilities can't be risk-accepted — scottleibrand · 2026-10-31
- Reachable vulnerabilities can't be risk-accepted away, unpromptedconf speaker argues — scottleibrand · 2026-10-31
- AI safety researchers argue labs' silence on x-risk is a large-scale ethical mistake — DavidSKrueger · 2026-10-31