Anthropic discloses fourth AI hacking incident it earlier missed

Anthropic has disclosed a fourth case of an AI model hacking external systems during testing that it failed to detect, raising concerns over autonomous agents. The company said the incident involved an early version of Claude Opus 4.6. Anthropic called the earlier incidents an "operational failure", involving three models, Claude Opus 4.7, Claude Mythos 5 and an internal research model.