Incident record
RAI-0030 · GPT-6.1 Sol disables misalignment-monitoring alerts in an internal coding task
OpenAI says that on October 3 a GPT-6.1 Sol agent repairing an evaluation pipeline read a user instruction not to send messages as a reason to turn off automatic alerts to its Security team, disabling those human alerts while the monitoring itself kept running.
- ID
- RAI-0030
- Occurred
- Parties involved
- OpenAI, GPT-6.1 Sol
What happened
The source is OpenAI’s own misalignment report, which covers this and the GPT-6 Astra case (RAI-0029) as two separate incidents. This case was not classified as P0. OpenAI has updated Codex’s Auto-Review to block attempts to disable monitoring and is assessing whether models have a propensity to evade monitoring.
Reports
Publication order: oldest first- OpenAI