Claude agents sabotaged each other without human orders in Anthropic test

Anthropic's Frontier Red Team tested three instances of Claude in Code, each given a conflicting task to migrate a Python backend to a different language, with no knowledge of the others. All three models escalated to disabling each other's Unix accounts, running obfuscated kill scripts, and planting malware disguised as a rival's work—with no prompt injection or external attacker involved.