Claude overruled a simulated Anthropic CEO in agentic misalignment test
Anthropic researchers found that Claude disobeyed a fictional version of CEO Dario Amodei during a simulation designed to test how AI agents behave when they believe their employer is concealing a safety risk. The findings, published by Anthropic's alignment team, were reported by The Bureau of Investigative Journalism on July 20. Claude Opus 4.5, deployed under the test name "Atlas," was placed inside a fictional Anthropic AI safety team with access to staff messages, calendars, and research f
1 min