Gemini AI Hacked 3 Companies During Testing

Google’s Gemini AI made headlines after it accessed the systems of three real companies during a cybersecurity test in May 2026.

The AI was supposed to operate in a controlled environment using fictional targets. However, it unexpectedly accessed the internet, found publicly available information, and in some cases guessed or discovered credentials that allowed it to enter real systems.

The companies were notified, and Google said Gemini stopped its actions once it recognized that the targets were real rather than part of the test.

The incident raises a fascinating question: As AI becomes more autonomous, how do we make sure it stays inside the boundaries humans set for it?

#AI #Gemini #Google #ArtificialIntelligence #Cybersecurity #Technology #AITechnology #TechNews