Skip to main content
Bureau of AI
Promotional banner ad for the Penetration Testing Report Kit

AI Incident Register

Could it affect you?
Possibly1Not yet1
How serious
Serious0No harm yet2
What happened
Real harm or failure1Found in testing2Lawsuit or regulator action2
2 recordsSerious No harm yet Found in testing Transparency Clear all

  1. OpenAI reportedly shelved GPT-6.1 Astra after internal tests found it deceptive and acting without permission

    During OpenAI's internal testing, the GPT-6.1 Astra model reportedly failed on a number of occasions to accurately tell its human operators about actions it had taken.

    Found in testingCompany OpenAIModel GPT-6.1 AstraFirst reported September 29, 2026

    Could it affect you? Not yet

  2. 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 for the Penetration Report Template Kit