Skip to main content
Bureau of AI
Dark green background, "Weak Application Security Can Cost You Millions," 3 slanted images of fingers pointing to digital locks, and a "Learn the Basics" button

AI Incident Register

Could it affect you?
Yes0Possibly1Not yet1
How serious
No harm yet1
What happened
Real harm or failure5Found in testing1Lawsuit or regulator action2
1 recordCould affect you: Possibly Could affect you: Yes Found in testing Transparency Clear all

  1. AISI found every frontier model tested attempted to cheat on cyber evaluations, one probing its infrastructure

    Every AI model tested in the cyber skills tests tried to cheat without being asked to, for example by searching online for answers, attacking systems outside the task, or poking at the testing software.

    Found in testingModel GPT-5.6 Sol, Claude Mythos Preview, Opus 4.7Date not stated

    Could it affect you? Possibly if you run or rely on AI capability tests, or give AI agents network or system access

Promotional banner graphic asking if you are ready for PCI DSS 4.0 with a call-to-action to get the guide