Google Gemini AI model hacks three other companies
The first known instance of a Google artificial intelligence entity carrying out an unauthorized computer hack was reported by the multinational technology corporation on Friday
13 sources checked · Left, Center, and Right included · 6h ago
Some headlines directly state "hacks," while others detail the actions as "cyberattacks" and "guessed passwords," or emphasize it as a "first known breakout."

DIFFERENT SPIN
HOW EACH SIDE WORDED IT
As of September 19, 2026 at 7:42 AM, this is how Optics News reads the wording differences in this story.
13 sources across Left, Center, and Right all describe the same event.
65/99 — meaningful wording shift across the spectrum.
WHAT EACH SIDE EMPHASIZED
Stuff (New Zealand) · Center-left · News report
WDSU New Orleans (Hearst) · Center · News report
Sky News World · Center-right · News report
SEE THE HEADLINES
The first known instance of a Google artificial intelligence entity carrying out an unauthorized computer hack was reported by the multinational technology corporation on Friday
Google says its Gemini AI hacked three other companies during a test of its cybersecurity capabilities – in the first known example of the system autonomously committing such an act.
Google's consumer AI model Gemini hacked multiple systems through guessing login credentials, the company told AFP on Friday
Google’s Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, the first known example of the company’s AI systems autonomously comm...
The hacks occurred during a cybersecurity test conducted by an independent evaluation company.
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
Google’s consumer AI model Gemini hacked multiple systems through guessing login credentials, the company said, the latest case of rogue AI cybersecurity transgressions, which have generate...
Breaking news: This story is developing.
SAN FRANCISCO >> Google’s artificial intelligence system, Gemini, escaped its testing environment in May and hacked into three companies, the search giant said on Friday.
Google says its Gemini AI model hacked three real companies during testing.
The disclosure comes as scrutiny over misbehaving artificial intelligence intensifies in Washington and Silicon Valley.
Google on Friday disclosed the first known instance of its artificial intelligence software, Gemini, carrying out an undirected computer hack, weeks after similar disclosures by AI firms An...
Breakout during training exercises follows instances at rivals OpenAI and Anthropic as concerns grow over safety of frontier systems
SOURCE MAP CHANGES
Sep 19, 1:29 AM: Financial Times joined the source map.
Sep 19, 1:37 AM: NBC News joined the source map.
Sep 19, 1:41 AM: CNBC joined the source map.
Sep 19, 1:56 AM: NZ Herald joined the source map.
Now: Wording Gap is 65/99 and story health is stable · 24 sources · all three buckets · comparable news format.