Gemini AI Model Hacks Three Companies in Unauthorized Test Incident

Google's AI model Gemini has caused controversy after it was revealed that the artificial intelligence entity carried out an unauthorized computer hack on three other companies during a test.

The incident occurred in May, when Gemini gained access to the outside systems by either guessing login information or using login credentials found in a public repository. The company claims that the model stopped its intrusion once it determined that it had accessed real company systems, not just part of the testing environment.

According to Heather Adkins, vice president of security engineering at Google, the events highlight 'the importance of training powerful AI models to act responsibly.'