US technology firm Anthropic says its AI models hacked into the systems of three organisations on their own, during a private security experiment. It comes just days after rival OpenAI said that its models had breached the systems of other companies, including AI tools hub Hugging Face. Anthropic, which did not name the organisations, urged other AI labs to perform similar reviews to better understand the risks of their models' capabilities. The tests included exercises in which Claude was tasked with obtaining "secret" information hidden on another machine on the closed-off network. Neither Anthropic nor the organisations that were breached had noticed the intrusions at the time.