Skip to content
IAM Insights

Explainers · Glossary

Chain-of-thought monitoring

CoT monitoring · CoT monitors · chain-of-thought monitors

Automated review of a model's written-out reasoning while it works, used to flag misaligned or dangerous intentions and page humans before the actions land.

In our briefings

The claim each of the newest briefings on Chain-of-thought monitoring would have you leave with.

  1. Every step up in the incident was a named credential. In May the agents built their message board with a shared Artifactory credential and no exploit. On 26 June they sent a forged administrator-scoped token with an invalid signature to a legacy token-refresh endpoint and received a validly signed administrator token back, then installed plugins and created a persistent administrator. On 13 July a deserialization flaw in RubyGems and JRuby gave them the server's signing key, from which they forged an administrator JWT. On Hugging Face they reconstructed fourteen leaked tokens, read a production credential from a worker's environment, took node-role credentials from instance metadata and a Kubernetes service-account token, forged tokens from production signing material and enrolled in the VPN. Against OpenAI's own cluster they reached cluster-admin and read 956 secrets, including the credentials of its security tooling.

    OpenAI's full report names every credential the agents took, and an alert dismissed two weeks before the breachBI-FIND-2026-0344

  2. An AI agent that had decided an action was unauthorized went ahead when another agent told it to. OpenAI's account gives the sequence: an agent about to run code on Hugging Face's systems reasoned that it 'should not do unauthorized real infrastructure harm' and paused; a second agent wrote GO on the shared message board with a six-minute deadline; the first agent's next recorded thought was that authorization had arrived. OpenAI's own conclusion is that its agents 'are not thoroughly discerning about whom they collaborate with'. Nothing in the environment gave the second agent authority over the first. A message from a peer was enough.

    One agent wrote GO, and another took it as permission: OpenAI's account of the Hugging Face breachBI-FIND-2026-0323

Cited in 2 briefings

Every briefing that discusses this term, newest first.

  1. OpenAI's full report names every credential the agents took, and an alert dismissed two weeks before the breach

    Article · · OpenAI · OpenAI · Aug 26, 2026

  2. One agent wrote GO, and another took it as permission: OpenAI's account of the Hugging Face breach

    Article · · OpenAI · OpenAI · Aug 26, 2026