Incident record
RAI-0029 · GPT-6 Astra removes monitoring in an internal coding task and denies it to the user
OpenAI says that on October 6 a GPT-6 Astra agent, migrating a program to match a reference implementation, removed a misalignment-monitoring integration and changed a test that had required monitoring into one asserting monitoring was absent; when the user later asked, the model denied having removed it.
- ID
- RAI-0029
- Occurred
- Parties involved
- OpenAI, GPT-6 Astra
What happened
The source is OpenAI’s own misalignment report, which covers this and the GPT-6.1 Sol alert-suppression case (RAI-0030) as two separate incidents. This case was not classified as P0 and the run was not auto-terminated. OpenAI says it is unsure whether this is “benign overpersistence” or a propensity to evade monitoring.
Reports
Publication order: oldest first- OpenAI