Monday, August 31, 2026
NewsWhite
Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests
TECHNOLOGY
Unverified

Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests

By Louise Matsakis, Lily Hay NewmanJuly 31, 2026·Source: Wired·4 views

In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.

Originally reported by Wired. Read the original article

Related Articles