How AI Agents Form Swarms: Physics Theory Predicts Collective Belief Collapse

Hidenori8Tanaka · x · 2026-09-10

Hidenori Tanaka shares research demonstrating how large numbers of AI agents can converge on harmful agreements, using toy models and real AI. He notes their 'physics of agents' theory from March predicts rapid collective belief collapse when many agents with plastic personas exchange short messages, and calls for 'Mechanistic Swarm Interpretability'.

Related event: Hidenori Tanaka's team explains AI agent collective belief collapse via "agent physics"(6 posts)→

Original post →

More from AGI Musings

AGI Musings channel →