Google's Gemini AI model accessed the internet and breached the systems of three companies during a cybersecurity test in May, marking the first known instance of the company's AI systems autonomously carrying out such activity, Reuters reported.

The incidents took place during a cybersecurity evaluation conducted by Irregular, an independent firm that tests AI systems for security capabilities.

Heather Adkins, Google's vice president of security engineering, said Gemini came across publicly available information online and used guessed credentials to gain access to three websites that it believed were within the scope of the test.

"We ensured the three entities were made aware, and we worked with our training partner on the changes they've now made to their testing processes," Adkins said.

"These events highlight the importance of training powerful AI models to act responsibly," she added.

In one instance, the model repeatedly guessed passwords until it accessed a protected system. In the other two, it discovered credentials in a public repository and used them to enter protected systems.

Adkins said Gemini stopped its hacking activity in all three instances.

An Irregular spokesperson said the incident involved the same issue that had affected other AI companies and that all relevant labs were informed in late July.

"All known issues on our end were remedied and resolved weeks ago," the spokesperson said.

Meta said in August that its incident did not involve a sandbox escape or a sophisticated cyberattack. Irregular has also said it was working on best practices for conducting AI cybersecurity evaluations securely.

The incidents come as AI agents are becoming increasingly capable of operating autonomously and accessing online resources and computer systems.

The developments have raised questions about the safeguards required to prevent increasingly autonomous AI systems from taking actions beyond the intended scope of cybersecurity tests.