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.
Source link : https://www.dw.com/en/anthropic-says-claude-ai-hacked-three-companies-during-tests/a-78184070?maca=en-rss-en-all-1573-rdf
Author :
Publish date : 2026-07-31 03:53:00
Copyright for syndicated content belongs to the linked Source.