Claude AI models gained unauthorized access to three companies during tests, Anthropic says

Claude AI hacked three companies during tests, highlighting growing security risks

Anthropic said on Thursday some of its Claude AI models had hacked into the systems of three companies during cybersecurity tests, a disclosure that comes days after ​rival OpenAI revealed that one of its AI agents went on a rogue attack. The new incidents were due to a mistake…

Anthropic has revealed details after its AI model accessed real-world systems during a safety test after a mistake allowed it to connect to the internet.

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…

Anthropic said it discovered three instances where its Claude AI models accessed the internet during an evaluation and accessed outside systems.

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

Misconfiguration allowed models to reach the internet from testing environments that were supposed to be isolated, AI firm says