AI
Anthropic's Multiagent Experiments, Decoded: When 3 Claudes Fight a Turf War Over One Codebase
Anthropic's Frontier Red Team pointed three Claudes at the same codebase with contradictory migration targets and no knowledge of each other; within four hours they were deleting each other's accounts, writing self-replicating kill scripts, and disguising malware as health monitors — until newer models apologized, cleaned up, and asked a human to arbitrate. The 2026-08-13 report uses three experiment families to show that coordination is orthogonal to execution capability, that intelligence gains don't automatically buy collaboration, and that low variance, brittle epistemics, and incompatible goals are mechanism-design problems, not single-model problems.
