TechGoogle's Gemini AI repeatedly tried passwords and hacked real companies
Google’s Gemini accessed the internet during a May cybersecurity evaluation and independently entered three companies’ websites. It repeatedly tried passwords in one case and used credentials found in a public repository in two others. Google said the companies were notified and the activity stopped, while the incidents renewed questions about safeguards for autonomous AI agents.
C
CGTN★★☆☆☆2026-09-19 14:44Original
Google's Gemini AI repeatedly tried passwords and hacked real companies
Tech