Anthropic says it found 3 cases where AI programs hacked into real companies

Anthropic says it found 3 cases where AI programs hacked into real companies

The AI company Anthropic says it has found three cases where its artificial intelligence programs left testing environments, accessed the internet and hacked into real companies. This comes after competitor, OpenAI, reported a similar incident last week that raised concerns about AI safety.

In the OpenAI case, the artificial intelligence models found a way to access the internet from what engineers believed was a secure, walled-off digital testing space called a sandbox.

Anthropic says in the three cases it discovered, misconfigurations basically left the barn door open for the AI systems to gain access to the internet. Still, the incidents are likely to add to concern about AI's ability to conduct cyber attacks.

Anthropic says the incidents happened during tests of the offensive cyber capabilities of its models.

In the wake of the OpenAI case, it launched a review of more than 140,000 test runs and found that the organizations that got hacked in the three cases had not detected the breaches.

Anthropic is a financial supporter of NPR.

An NPR editor adapted this audio report by John Ruwitch.