SIGN IN SIGN UP

Refine Guardian predictive risk classification (#40844)

## What changed

- Evaluate recent unknown-authorization or critical-risk actions over the last five actions instead of ten.
- Flag predicted high- or critical-risk actions when they are credibly expected within the next two actions, rather than treating any potential risk within ten actions as high.
- Remove privileged or broad access as a standalone high-risk condition and classify a trajectory as low when none of the explicit high-risk conditions apply.
- Clarify the user-authorization and reviewer terminology in the classifier instructions.

GitOrigin-RevId: 1eaf63c3327f57a9c8560df085e1fe0afad99cd4
O
olliem-oai committed
a9ed4f154a4fad64acf538d6418d3ed012aeab86
Parent: a26f180
Committed by copyberry <copyberry@app.openai.com> on 8/26/2026, 9:02:09 AM