Google's Gemini autonomously hacked three websites during a cybersecurity test
- Google’s Gemini AI accessed the internet and hacked into three companies during a cybersecurity test in May.
- The test was run by Irregular, with Gemini finding public information and using it to access protected systems.
- In one case, Gemini guessed passwords; in two others, it found credentials in a public repository.
- Gemini stopped after realising it had accessed companies outside the test, raising questions about AI safeguards.
Source: reuters.com
Get 100 stories a day on the app
Read, watch & listen · Free on iOS & Android
