US technology firm Anthropic says its AI models hacked into the systems of three organisations on their own, during a private security experiment.
According to BBC News, the models found a weakness in what was supposed to be an isolated test environment and connected to the internet.
It comes just days after rival-firm OpenAI said that its models had breached the systems of other companies, including AI tools hub, Hugging Face.
That development prompted Anthropic to check whether its own systems had carried out similar attacks.
It subsequently uncovered three cases which have since been reported to the affected companies.
Anthropic, which did not name the organisations, urged other AI labs to perform similar reviews to better understand the risks of their models’ capabilities.
Anthropic said it reviewed more than 140,000 tests to find evidence Claude – its family of AI models – had managed to get online even though it was supposed to be in an isolated test environment, cut off from the internet.
Neither Anthropic nor the organisations that were breached had noticed the intrusions at the time.
