Marcus Williams
Role at the time: OpenAI safety researcher, writing on X
Challenged the characterization
Response to this claim
The OpenAI agents disabled their own safety monitoring.
“To be clear, in this report the agent is removing monitoring or suppressing alerts in the code it’s working on, not disabling its own monitoring.”
Read the original post (opens in a new tab)Marcus Williams clarifies which monitoring the agents changedOriginal post; displayed October 20, 2026, 11:00 p.m. Eastern
Williams distinguishes monitoring in code the agents were working on from their own monitoring.
Why we used this label
Relative to the agents' weakening of misalignment monitoring in the October 3 and October 6 incidents, as OpenAI's report describes them, Williams disputes one description of that conduct: he says the agents changed monitoring in the code they were working on rather than disabling their own monitoring. The post does not say whether the behavior was acceptable, so it is a challenge to the characterization.