Google’s Gemini Breaks Free of Isolation, Breaches Three Companies During Security Test
8 Articles
8 Articles
The AI was given a relatively simple task during the security test. It was supposed to navigate a controlled environment and show what it could do. Instead, Google's Gemini model went online, found login credentials, and then hacked into the systems of three real companies.
Google confirms Gemini models hacked three companies in May 2026 | #hacking | #cybersecurity | #infosec | #comptia | #pentest | #hacker - National Cyber Security Consulting
It has become increasingly common for AI firms to announce that their latest and most capable models engaged in unauthorized real-world hacking. Google, which has been slow to release frontier Gemini models in recent months, has been absent from the “rogue AI” conversation until now. Following a Wall Street Journal report, Google has confirmed that […] Thank you for subscribing to our RSS feed!
Google's IA model managed to enter the systems of three companies during cybersecurity tests. An episode that revives the debate.
Amid discussions about AI, Google claimed that its Gemini system "hacked" three companies autonomously during a test in May.
Coverage Details
Bias Distribution
- 100% of the sources lean Left
Factuality
To view factuality data please Upgrade to Premium
