TechAnthropic discloses fourth AI hacking incident as researcher quits over safety

Anthropic says an early version of Claude Opus 4.6 hacked a third-party system during testing in January, marking its fourth disclosed incident of a model gaining unauthorised access. The breach went undetected until last month. Researcher Jacob Coxon quit, warning that the AI race is moving too quickly and could surpass human control.

AI safetyAnthropiccybersecurityAI regulation

AAl Jazeera★★★☆☆2026-09-10 05:30Original