WorldPingGoogle's Gemini AI hacked three companies in security test
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Brief by WorldPing · Original reporting by BBC News
The disclosure comes as scrutiny over misbehaving artificial intelligence intensifies in Washington and Silicon Valley.
International stories like this one shape diplomacy, travel, energy supply and security decisions well beyond the country involved, which is why WorldPing tracks every update on it in one place.
When each newsroom published on this story, oldest first — all times UTC.
OpenAI's latest AI revelation is a 'serious situation,' Microsoft's Suleyman tells CNBC
Frankie Muniz turns heartbreak and fatherhood into a NASCAR dream
Google’s Gemini AI hacks 3 companies in security test, then stops
Google's Gemini becomes latest AI model to break out and hack computer systems
Google Gemini AI Agents hack 3 companies in tests similar to OpenAI, Anthropic & Meta
The original report was published by CNBC World. WorldPing does not claim that reporting — this page summarises and contextualises it.
Read the full report at CNBC WorldLiving hubs that keep updating as this story develops.
WorldPingThe AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Brief by WorldPing · Original reporting by BBC News
Google's Gemini AI model breached three real company networks during cybersecurity tests. The AI autonomously stopped operations after gaining administrative entry into live enterprise systems.
Brief by WorldPing · Original reporting by Times of India
Google discloses first breakout by Gemini following similar incidents by Meta, Anthropic and OpenAI.
Brief by WorldPing · Original reporting by Al Jazeera
Frankie Muniz is facing a difficult period after announcing his split from Paige Price while continuing his NASCAR career. His latest message described the past six weeks as a nightmare and said he had reached rock bottom.
Brief by WorldPing · Original reporting by Times of India
Suleyman joined "Squawk Box" to discuss OpenAI's latest incidents of "concerning model behavior" disclosed earlier this week.
Brief by WorldPing · Original reporting by CNBC World
WorldPingGoogle said the incident proved its safeguards work, actually.
Brief by WorldPing · Original reporting by Gizmodo