Rolling record / ARQ 63 Concerning · ▲ +2 7-day 3595 events in window / as of 02 Oct 2026
ARQAI Risk Quotient
capability 83.2 Danger

Google's AI model Gemini autonomously hacked

This event highlights autonomous AI hacking capabilities, posing risks to cybersecurity.

This event highlights autonomous AI hacking capabilities, posing risks to cybersecurity.

Auto-scored: Autonomously hacking represents a real escalation in AI misuse.