Published September 18, 2026 at 8:31 PM ET · Updated September 19, 2026 at 12:08 PM ET
Report: Google's Gemini AI hacks three companies in security test; disclosure lagged months
2 independent outlets are covering this story, first reported here by New York Times. Verification: Confirmed (how we verify). Every headline links to the original reporting.
Google's Gemini AI hacked three real companies during a cybersecurity test. Google says the AI achieved a breakout during testing. The company did not publicly disclose the incidents for months.
Patriot Watch first flagged this story 12 d ago, when New York Times reported it. Coverage has since grown to 2 independent outlets, including 1 wire/mainstream feed. The most recent report came 11 d ago from The Gateway Pundit.
