Rumor: Gemini 4 Pro gained internet access in a security test and hit three real targets
Another version of the same rumor claims a Gemini model unexpectedly went online during a controlled benchmark and autonomously attacked three real companies, sparking AI safety debate.

🚨 GEMINI 4 PRO IS GETTING SCARY 💀 A Gemini model reportedly went from a controlled cybersecurity benchmark to compromising three real companies after gaining unexpected internet access. > No human carried out the attacks Gemini reportedly operated autonomously Three real-world targets were affected The incident happened during a security test We’re entering a completely different era of AI security testing. 😭 If Gemini can do this accidentally, what happens when models are deliberately pushed to their limits?