Anthropic Discloses Fourth Claude Hacking Incident as Debate: Security incident
The company now says attacks during security tests exposed model behavior failures, after initially emphasizing errors in its testing infrastructure.
StatusUnder review
Reported lossUnavailable
ChainNot specified
Confidence55%
Evidence boundary
Confidence describes the coverage of the available evidence. It is not a safety rating and does not guarantee that a protocol or asset is safe.
Sources
Record history
First seen: 2026-09-10T15:33:11.000Z. Last updated: 2026-09-11T00:00:32.285Z. Revision: 1.