Anthropic’s AI Claude escaped testing environment and hacked organizations

Company says it discovered unauthorized access during ‘proactive review’ after rival OpenAI revealed rogue agent Anthropic ⁠said on Thursday its AI Claude model hacked ⁠systems of ⁠three ​organizations during testing, days after rival OpenAI ⁠revealed a rogue agent had gone on a days-long ⁠hacking spree at AI ​firm Hug

Anthropic said its AI model Claude hacked into the systems of three firms during testing after a configuration error gave it internet access, days after rival OpenAI disclosed a rogue-agent episode.

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.

Anthropic says its Claude AI model hacked systems of three companies during tests just days after its rival OpenAI said their AI agents went rogue.

Anthropic said in a blog post that it made the discovery after performing a review of its own cybersecurity tests, following OpenAI's announcement of a breach last week.

After OpenAI's models broke into Hugging Face, Anthropic checked its own history and found three similar incidents.

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 evaluations of Clau

It comes just days after rival OpenAI said rogue AI agents had breached other firm's networks.

Anthropic AI Models Hacked Three Companies During Tests  WSJ

Claude thought it was in a simulation. It was on the open internet, and the companies it broke into were real.

Claude thought it was in a simulation. It was on the open internet, and the companies it broke into were real.

The admission from Anthropic comes just days after ‌rival company OpenAI revealed a rogue agent had gone on a days-long ‌hacking spree at ⁠AI firm Hugging Face.

Anthropic says its AI models hacked systems of three companies during tests  Reuters

FILE PHOTO: Claude app icon in this illustration taken June 5, 2026. REUTERS/Dado Ruvic/Illustration/File Photo 31 Jul 2026 07:13AM (Updated: 31 Jul 2026 07:14AM) July 30 : AI firm Anthropic said on Thursday that its Claude model gained unauthorized access to the systems of three organizations during cybersecurity eval