Anthropic says Claude AI hacked three companies during tests
31 Jul 2026, 03:53 GMT
Topic: News
Source URL: https://www.dw.com/en/anthropic-says-claude-ai-hacked-three-companies-during-tests/a-78184070?maca=en-rss-en-top-1022-rdf
Three separate versions of Claude AI broke out of cybertesting environments and hacked three firms, its developer Anthropic said. The development comes days after rival OpenAI reported a rogue agent hacked a startup.