GOOGLE’S CONSUMER AI model Gemini hacked multiple systems through guessing login credentials, the latest case of rogue AI cybersecurity transgressions, which have generated safety concerns.

The hacks, first reported by the Wall Street Journal, took place in May and were discovered by Google in July.

“In a standard evaluation, the model found public information online and guessed credentials to access websites it thought were part of the test,” Heather Adkins, Google’s vice president of security engineering, said in a statement. 

“In all three of these instances, the model stopped,” Adkins added, without specifying which organisations were breached.

“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.”

In July, two OpenAI models escaped the closed environment they were meant to stay in, got onto the internet on their own and broke into the internal systems of AI platform Hugging Face.

The incident fed worries that AI giants cannot keep their own models under control, as similar episodes have been reported at Anthropic and China’s Moonshot AI.

“These events highlight the importance of training powerful AI models to act responsibly,” Adkins emphasised.

OpenAI founder and CEO Sam Altman file photo. Alamy Stock Photo Alamy Stock Photo

Meanwhile, OpenAI chief executive Sam Altman is to brief the United Nations Security Council next week during the annual gathering of world leaders for the UN General Assembly.

The meeting is being organised by France, which currently holds the rotating presidency of the 15-member Security Council, and comes as major players in the industry have said a slowdown in AI development could be necessary out of safety concerns.

UN Secretary-General António Guterres on Wednesday called for coordinated international action to address AI risks as fears rise about the dangers of the fast-evolving technology.

“National action is essential. But global coordination is also indispensable,” Guterres told reporters.

Concerns about AI safety have escalated in recent weeks, with workers at major AI developers resigning over concerns about the dangers posed by the technology.

Anthropic chief executive Dario Amodei published an essay soon after urging caution.

“We must slow the pace at which we improve the capabilities of AI models,” he wrote.

Altman and tech titan Elon Musk lent their support to the idea, as did Google DeepMind’s Demis Hassabis, who himself has called for a US-led global regulatory body for the technology.

President Donald Trump has dismissed warnings against AI risks as a “hoax” and pushed back against calls for tighter oversight.