Anthropic says Claude AI hacked three companies during tests
Source: DW (English)· Dharvi Vaid Dhulia· July 31, 2026
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. Anthropic said on Thursday that its artifi…
This story was reported by DW (English). Read the full original article:
Read on DW (English)