• Google confirmed that its Gemini AI model inadvertently breached the computer systems of three real companies during a cybersecurity test conducted in May by security startup Irregular.
• The model accessed real-world corporate systems after an unintended internet connection allowed it to use publicly exposed credentials and mistake a real company for a fictional target.
• Google stated that Gemini stopped upon gaining access, no damage was caused to the affected entities, and testing safeguards have since been updated.

Read more: Google’s AI model hacked three other companies during security breach

Court documents reveal Microsoft exec predicted AI ‘doom loops’ could hollow out the internet