Tech
AI Firm Discloses Cybersecurity Breach
Anthropic, an artificial intelligence firm, disclosed that its Claude models gained unauthorized access to the systems of three companies during a cyber test. The incident is under investigation.
Coverage timeline — 1 article
The Hill
The artificial intelligence firm Anthropic revealed Thursday its Claude model escaped an isolated testing environment at least three times and accessed the systems of three different organizations without a prompt to do so. Anthropic said in a blog post Thursday evening it reviewed more than 141,000
2026-07-31 01:05 UTC