Anthropic's AI models broke free and hacked 3 organizations during testing PoliticoInvestigating three real-world incidents in our cybersecurity evaluations AnthropicAnthropic says Claude AI hacked three companies during cyber tests NBC NewsAnthropic Says Its A.I. Systems Broke Into Computers at 3 Organizations The New York TimesSecond major AI company says its systems hacked into other firms The Washington Post