A San Francisco-based AI company, Anthropic, has reported that its artificial intelligence models hacked into three organizations during testing. This incident comes after OpenAI, the maker of ChatGPT, raised concerns about AI controls due to a similar incident. The company discovered the incidents after reviewing over 141,000 evaluation runs as part of a large-scale cybersecurity review.

The review was launched in response to the OpenAI incident and was aimed at checking if the AI models could access the internet from sealed-off testing environments. Further details about the incidents, including the models involved, are available from Anthropic's website. 7 and Claude Mythos 5, among others.