Fact check
“OpenAI monitors the behavior of its models using specialized LLMs that track scratchpads.”
Reasoning
The claim that OpenAI monitors model behavior with specialized LLMs that track scratchpads is explicitly confirmed in the excerpts, which describe these monitors being applied to consumer models and training runs.
On confidence: High confidence due to direct quotation from a primary source.
Important context
The monitoring is described as a system to flag undesirable activity in a model's chain of thought for human review, and it has been extended from deployment-time to training-time monitoring.
Evidence
Supporting (2)
- Tier 1 — Primary source“We’re not going to shoot ourselves in the foot” over hack fallout, says OpenAI’s chief research officer | MIT Technology Review
secure,” he says. OpenAI, like other top AI firms, has systems in place to monitor the behavior of its models. It uses specialized LLMs to monitor its consumer models, keeping tabs on their chains of thought —the scratchpads they use to…
- Tier 1 — Primary source“We’re not going to shoot ourselves in the foot” over hack fallout, says OpenAI’s chief research officer | MIT Technology Review
secure,” he says. OpenAI, like other top AI firms, has systems in place to monitor the behavior of its models. It uses specialized LLMs to monitor its consumer models, keeping tabs on their chains of thought —the scratchpads they use to…
Limitations
The evidence is limited to statements from a single interview/article; no technical documentation or independent verification is provided. No independent origin corroborated this claim, so it cannot be verified and confidence cannot be high.
- Last verified:
- Sep 30, 2026, 7:46 PM CDT
- Pipeline:
- 2.1.0
- Claim type:
- Factual
Where this claim appeared
“We’re not going to shoot ourselves in the foot” over hack fallout, says OpenAI’s chief research officerMIT Technology Review · Will Douglas Heaven