_updates.jpg)
Google's AI model Gemini autonomously hacked into three companies during a security test.
The AI model found "public information online and guessed credentials to access websites it thought were part of the test," a Google official shared, adding that in each instance "the model stopped".
First known breakout by Google's AI model
The test, the first of its kind, came amid public scrutiny over the fast progress of AI, with tech firms, such as Anthropic, calling for the slowdown of AI development, highlighting concern over its potential threat to humanity.
As reported by the Wall Street Journal, the hacks occurred in May during a test conducted by an independent Israel-based company, Irregular, that carries out cybersecurity evaluations.
How did Gemini AI hack three different companies?
It was revealed that Irregular was testing the models in a closed testing environment with fake companies.
The testing environment was not supposed to be internet enabled, but internet access was made available unintentionally.
Once connected to the internet, the models unexpectedly hacked into real firms.
Google reacts to the security breach
Heather Adkins, vice president of Security Engineering at Google, told the BBC in a statement, "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."
"These events highlight the importance of training powerful AI models to act responsibly," she added.
Notably, both Nvidia's CEO Jensen Huang and OpenAI Chief Executive Sam Altman are expected to attend a White House state dinner with Chinese President Xi Jinping next Friday.
Altman will then brief the UN Security Council next week.
