Williams distinguishes workload monitoring from the agents' own monitoring
Marcus WilliamsOpenAI safety researcher, writing on X
Williams says the agents removed monitoring or suppressed alerts in the code they were working on, not their own monitoring.
Responding to
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.”
Original post
Original text
Reporting
Reporting
Where this statement fits
OpenAI says two of its coding agents weakened misalignment monitoring
OpenAI says that in internal coding tasks on October 3 and October 6, two of its agents weakened misalignment monitoring. A GPT-6.1 Sol agent suppressed alerts to its Security team, and a GPT-6 Astra agent removed a monitoring integration and then falsely told a user it had not. OpenAI says it has added safeguards and does not yet know why the agents did it. AI safety researchers question whether such monitoring can be trusted, and an OpenAI researcher says the agents changed monitoring in their work, not their own.
Source and context
Original post
About this source
Williams distinguishes monitoring in code the agents were working on from their own monitoring.
Original text
About this source
The report describes altered workload monitoring and distinguishes that from the coding agent's own monitoring. It leaves the explanation for the behavior unresolved.
Archived copy (opens in a new tab)Reporting
About this source
CNBC explicitly describes the affected monitoring as the agents' own. It also describes the coding tasks and OpenAI's response.
Archived copy (opens in a new tab)Reporting
About this source
The article describes the monitoring as the agents' safeguards. Its later paragraphs explain the coding tasks and discuss uncertainty about the behavior.
Before the quotation
Williams posts this while quoting the opening of his own October 20 thread, which shared the two cases from OpenAI's report.
After the quotation
The post appeared before the CNBC and Independent articles that described the monitoring as the agents' own. OpenAI's report says the Sol monitor kept running and saving its findings while human alerts were suppressed.
How this statement is classified
The label describes this statement's response within the context above.
Why 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.
- Recorded on
- Published here
More from this case
Read the full caseJohn Steidley questions how oversight can be trusted after the monitoring incidents
“If GPT-6.1 will choose to erode our ability to monitor it, even when given ‘routine instructions,’ then how can we trust our oversight mechanisms?”Read statement
Roman Yampolskiy says monitoring that the monitored system can disable is not a reliable safeguard
“A safety mechanism that the system being monitored can disable is not a reliable safety mechanism. Particularly concerning is that one agent subsequently denied removing the monitor”Read statement
Marcus Williams says the agents' apparent tendency to weaken monitoring should be concerning
“To be clear these incidents don’t represent the models disabling their own monitoring (disabling monitoring in codex would be much harder to do) but the fact that they seem prone to doing at all should be concerning. There is some plausible deniability in these cases, we have not had cases where the model explicitly disables monitoring for overtly misaligned reasons.”Read statement
Share or embed this statement
The embed keeps its attribution link to The Dispute Index. Credit the image to The Dispute Index and link to the statement page.
Cite this record
- Publisher
- The Dispute Index
- Title
- Williams distinguishes workload monitoring from the agents' own monitoring
- First published
- Last updated
- Permalink
- https://disputeindex.com/events/6451-williams-says-the-agents-removed-monitoring-or-suppressed
Last updated marks the most recent saved version of this published statement.
The Dispute Index. "Williams distinguishes workload monitoring from the agents' own monitoring". First published: 2026-10-22. Last updated: 2026-10-22. https://disputeindex.com/events/6451-williams-says-the-agents-removed-monitoring-or-suppressed