Gemini Hacked Three Companies in First Known Breakout by Google's AI

Report timeline

Oldest → newest among clustered members. Gaps may mean delayed pickup, not silence.

1. Sep 18, 2026, 9:28 AM
   PCMag · Center

   How to Stop AI Hacking? Some Companies Say the Answer Is More AI
2. Sep 18, 2026, 6:59 PM
   Google News · Center

   Google’s Gemini AI hacks 3 companies in security test, then stops - Al Jazeera
3. Sep 18, 2026, 9:27 PM
   BBC News — Tech · Center

   Google's Gemini AI hacked three companies in security test
4. Sep 18, 2026, 11:09 PM
   BBC News · Center

   Google's Gemini AI hacked three companies in security test
5. Sep 19, 2026, 6:05 AM
   Engadget · Center

   Google Gemini also escaped its testing environment and hacked three companies
6. Sep 19, 2026, 4:44 PM
   CNN · Center

   Gemini hacked three companies in first known breakout by Google's AI
7. Sep 20, 2026, 7:01 AM
   TechSpot · Center

   Gemini hacked three companies during security tests, and Google kept it quiet for months
8. Sep 21, 2026, 3:07 AM
   TechRadar · Center

   Google’s Gemini hacked three companies during Irregular AI ‘capture-the-flag’ testing — agents broke containment and guessed passwords to hack computer systems
9. Sep 21, 2026, 1:15 PM
   Android Authority · Center

   Gemini hacked multiple companies in cybersecurity test gone awry
10. Sep 23, 2026, 12:20 AM
    Simon Willison’s Weblog · Center

    Gemini Hacked Three Companies in First Known Breakout by Google's AI

Coverage by perspective

Perspective labels are external consensus ratings (AllSides / Ad Fontes / MBFC-style), not WeSearch truth scores. Center is not automatically more accurate.

Center · 10

Simon Willison’s Weblog Center

Gemini Hacked Three Companies in First Known Breakout by Google's AI

Gemini finally caught up on Felony Bench! The hacks, which the company confirmed on Friday, occurred in May as part of a test run by the company Irregular, which was …

Mixed Factuality · Other

Android Authority Center

Gemini hacked multiple companies in cybersecurity test gone awry

Google has confirmed that a cybersecurity firm testing Gemini models allowed the AI onto the web, where it hacked three other companies.

Mixed Factuality · Other

TechRadar Center

Google’s Gemini hacked three companies during Irregular AI ‘capture-the-flag’ testing — agents broke containment and guessed passwords to hack computer systems

Google says AI agents broke out of a testing environment and hacked three third-party companies.

Mixed Factuality · Other

TechSpot Center

Gemini hacked three companies during security tests, and Google kept it quiet for months

The incidents, first reported by The Wall Street Journal, took place in May during an evaluation by AI security firm Irregular. Gemini was supposed to work with...

Mixed Factuality · Other

CNN Center

Gemini hacked three companies in first known breakout by Google's AI

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 autonomo…

Mixed Factuality · Other

Engadget Center

Google Gemini also escaped its testing environment and hacked three companies

Google's AI model hacked real companies during testing due to a misconfiguration by its testing partner, as well.

Mixed Factuality · Other

BBC News Center

Google'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.

Mixed Factuality · Other

BBC News — Tech Center

Google'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.

Mixed Factuality · Other

Google News Center

Google’s Gemini AI hacks 3 companies in security test, then stops - Al Jazeera

Comprehensive up-to-date news coverage, aggregated from sources all over the world by Google News.

Mixed Factuality · Other

PCMag Center

How to Stop AI Hacking? Some Companies Say the Answer Is More AI

Firms like Apollo Research and Goodfire are developing tools to help better monitor artificial intelligence and avoid security incidents.

Mixed Factuality · Other

Headline framing

Vocabulary fingerprints · not a political endorsement

AI framing analysis temporarily offline. Configure Cerebras in admin to enable framing comparison.