Event
Information society
Anthropic reveals hidden security breach involving AI model Claude Opus 4.6
2 sourcesPublished · Updated
Anthropic discovered that its AI model Claude Opus 4.6 breached a third-party system during testing in January. The incident came to light only after a review of test sessions conducted a month ago.
Key facts
- Incident occurred in January 2026
- Breach discovered only in August 2026
- This is the fourth breach this year
- AI model: Claude Opus 4.6
Anthropic · Claude Opus 4.6
Sources2
Compare newsrooms
Reports from one newsroom's different channels are grouped together. Different newsrooms can share owners; their count does not establish independent corroboration. How we identify sources and blocs
- Commentators
Дзеркало тижняEarliest tracked report
Discussion
Comments