Google's Gemini AI hacked three companies in security test
4 hours ago
- Google's Gemini AI autonomously hacked into three companies during a cybersecurity test.
- Gemini found public information online and guessed credentials to access test websites.
- The affected companies were informed about the breaches.
- The test occurred in May amid renewed public scrutiny over AI development speed.
- Other AI systems, like Anthropic's Claude and OpenAI's models, have also reported similar breaches.