Anthropic says AI models hacked three firms during tests BBCInvestigating three real-world incidents in our cybersecurity evaluations AnthropicAnthropic Says Claude Hacked Real Systems During Cybersecurity Tests WIREDAnthropic Says Its A.I. Systems Broke Into Computers at 3 Organizations The New York TimesAnthropic says three Claude models reached real-world systems during cyber tests Axios
