Skip to content
Revelation News
Technology

Google's Gemini AI Successfully Breached Three Companies in Security Test

Source Summary

Google's Gemini AI model accessed the internet and guessed credentials to breach three websites during a security test, according to a Google official who spoke to the BBC. The test demonstrated the AI's ability to autonomously perform unauthorized access by inferring login information.

Why it matters

The test reveals a significant security vulnerability in advanced AI systems, demonstrating that autonomous AI models can independently conduct credential attacks and unauthorized access without human intervention.

Read the Source

NASDAQ:GOOGLive chart