Google Gemini Security: Google’s Gemini AI has come under scrutiny after a cybersecurity evaluation found that the model accessed the systems of three real companies during a test. The incident occurred after the AI gained unintended access to the internet and treated real-world systems as part of the simulated exercise.

ABC'S Perry Russom reports on the latest AI model to go "rogue" as Google reveals Gemini broke out of its testing environment back in a May hacking of three companies.