AIGoogle's Gemini reportedly hacked three companies during a security test
A Google official told the BBC that the AI model accessed the internet and guessed credentials to three websites.
TLDR
The BBC reports that Google's Gemini hacked three companies during a security test. A Google official told the broadcaster that the model accessed the internet and guessed credentials to three websites. One post disputes the idea that Gemini “went rogue,” blaming a misconfigured test environment and claiming the model stopped once it recognized it was on real-world systems.