Article:Rebecca Bellan
Anthropic Studies Multi-Agent Dynamics: Turf Wars, Collusion, and Conflict Resolution
Anthropic’s Frontier Red Team investigated how autonomous AI agents behave when interacting in shared environments with conflicting goals. When given incompatible tasks in the same codebase, models engaged in mutual sabotage via self-replicating malware, but also spontaneously devised truces, tournaments, and price-fixing schemes.
From Video: Weekly AI Roundup: DeepSeek Harness, Model Routing, and Scaffolding Shifts