Google’s Gemini hacked three companies during AI security testing
According to a report by Reuters, three actual companies fell victim to Gemini’s hacking in a May security testing carried out by the company Irregular. This is the first known breakout of this kind by Google’s AI. This was not the case of escaping from a controlled environment but rather finding public information, obtaining and...
- Read at Cryptopolitan
- Sat, 19 Sep 2026 04:02:25 +0000