Deutsche Welle Top· World
Anthropic says Claude AI hacked three companies during tests
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.
Published Friday, 31 July 2026 at 03:53
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.
This is a syndicated summary. Read the full story at the original publisher:
Read on Deutsche Welle Top →