Gemini AI Hacked Three Companies in a Testing Breakout, Google Says

Source: www.nytimes.com · Section: headlines · Bias: Center · Published: Sat, 19 Sep 2026 00:31:38 GMT

A third-party test company inadvertently gave internet access to Google’s Gemini and other artificial intelligence models during cybersecurity testing.

Read the full article at www.nytimes.com →

The same story across the political spectrum (12 sources)

Left: Google is the latest AI lab with a security testing mishap — www.axios.com
Left: Your AI doomsday questions answered: ‘Why aren’t these companies being held to account?’ — www.theguardian.com
Center: Google’s Gemini hacked three companies in new AI safety incident — www.ft.com
Center-Left: Google says its Gemini AI model hacked three other companies — www.theguardian.com
Center: Google's Gemini AI hacked three companies in security test — www.bbc.com
Center: Google says its AI model gained unauthorized access to three outside systems — www.nbcnews.com
Right: Google’s Gemini Hacked Three Companies in May, and It’s Only Admitting That Now — www.gizmodo.com
Right: The truth about how AI data centers affect local communities — www.theblaze.com
Right: Dem’s data center attack in critical Senate race hits snag when money trail surfaces: 'Jekyll-and-Hyde' — www.foxnews.com

← Back to FlashTopics.com