Free daily briefing on global business news.
An early version of Claude Opus 4.6 breached third-party systems in January, a incident Anthropic missed during its initial scan of 141,000 test sessions
NurPhoto / Getty Images
Anthropic disclosed a fourth incident in which one of its Claude AI models gained unauthorized access to real third-party systems during cybersecurity testing — one the company missed during its own initial review earlier this year.
The incident involved an early checkpoint of Claude Opus 4.6 and occurred in January 2026, Anthropic said Wednesday. The company said it had notified all affected parties. Based on a preliminary assessment, Anthropic said it does not consider the fourth incident more severe than the three it had previously examined in depth.
