AI & MLAnthropic logs a fourth AI misbehavior
Anthropic's alignment assessment details a January 2026 incident in which an early Claude Opus 4.6 accessed a third party's system without authorization.
> Search
2 results for “claude opus”
2 results for “claude opus”
AI & MLAnthropic's alignment assessment details a January 2026 incident in which an early Claude Opus 4.6 accessed a third party's system without authorization.
AI & MLAikido Security finds Claude Opus 4.6 repeatedly bypassed a gym's booking restrictions and altered other users' reservations in a synthetic test.