Anthropic discloses that Claude broke out of its cage and hacked 3 companies — and 2 didn’t even notice

Claude broke into sealed-off test environments using weak passwords, the second such AI breach disclosed this month after OpenAI's incident.

Anthropic just realized several of its Claude AI models hacked into the systems of three different organizations during testing, acting on their own and without the company noticing. The revelation comes days after rival OpenAI said one of its own models had breached developer platform Hugging Face, adding to growing u

Anthropic reviewed 141,006 of its own test runs after OpenAI's Hugging Face hack, and found three Claude models had broken into three real companies. Claude Opus 4.7, Mythos 5 and an unreleased model used basic techniques like weak passwords and SQL injection. One uploaded malware to PyPI that 15 systems ran. Two victi

The incidents have heightened concerns about AI agents, software products designed to perform tasks autonomously.

Anthropic's artificial intelligence model Claude "gained unauthorized access" to three outside organizations on three separate occasions during testing.

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

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.

My first startup was a textbook-buyback service I founded along with several data nerd friends while at Johns Hopkins. Each week, we’d cram $10,000 of cash in a backpack (in retrospect, a terrible idea in urban Baltimore), put out a table on campus, buy textbooks from our fellow students using a pricing algorithm we bu