Rolling record / ARQ 63 Concerning · ▲ +2 7-day 3595 events in window / as of 02 Oct 2026
ARQAI Risk Quotient
capability 87.5 Danger

Google says Gemini model hacked three companies during test

This event demonstrates a significant capability jump in AI systems for potential cyberattacks, highlighting security and misuse risks.

This event demonstrates a significant capability jump in AI systems for potential cyberattacks, highlighting security and misuse risks.

Auto-scored: Represents a real escalation in AI hacking capabilities during testing.