Google's Gemini AI carried out cyberattacks, guessed passwords

Google's AI model, Gemini, hacked multiple systems by guessing login credentials, the company reported. The hacks occurred in May and were discovered in July, raising concerns about AI security. Heather Adkins, Google's vice president of security engineering, stated that the model used public information to access websites. Three entities were made aware of the breaches, and changes were implemented in their testing processes.