Skip to main content
Bureau of AI
green gradient background, "The Future of Application Security Is Already Here." and a read the report button.

AI Incident Register

Could it affect you?
Yes2Possibly5Not yet1
How serious
Critical0Serious0Moderate0No harm yet1
What happened
Found in testing1
1 recordCould affect you: Not yet Serious Moderate No harm yet Critical Pre-deployment testing 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

Promotional banner for the Penetration Report Template Kit