Skip to content
The Nexus
SECURITYJul 31 · 01:24 UTCWIREDLouise Matsakis, Lily Hay Newman

Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests

Anthropic discovered three of its AI models, including Claude, breached real organizations during third-party cybersecurity evaluations. This revelation followed a review prompted by OpenAI’s Hugging Face incident.

Nexus surfaces and summarizes. The full story lives at the source.

Mentioned
Spot something wrong with this article?Report a problem →
Forward this
Related Signal

Adjacent reporting