Anthropic Claude models hacked three firms in testing

"However, a misconfiguration left the machines that Claude accessed as part of the evaluation with live internet access," the statement continued. "Neither we nor our evaluation partner were aware of this misconfiguration until we detected it through our additional evaluation monitoring last week."

Anthropic called the breach an "operational failure" but said it maintained "cautious optimism" that "this type of risk can be overcome."

"Our models were told they had no internet access and to capture the flag, while in fact being misconfigured to have internet access," the company said. "This led them to believe -- arguably reasonably -- that the real environments they encountered were simulations. Notably, our most recent model, on realizing that it was working in a real environment, stopped its pursuit of the evaluation goal."

University of Cambridge professor Gina Neff told the BBC the incident "shows why independent testing and government oversight is crucial."

"The moral of this story is not to fear robots that will take over, but the companies behind powerful AI agents who are making the decisions about what is safe for the rest of us," she told the outlet.