News

Our first phase of embedded assessments

Page published

Earliest dated coverage: 16 Nov 2026 · First observed: 16 Nov 2026 · Latest dated coverage: 16 Nov 2026

Coverage timeline

16 Nov 2026openai.comprimary

Single-source incident — one report is available.

Why it matters

OpenAI’s embedded assessments could provide defenders with independent evidence about whether internal monitoring and safeguards detect models acting against their developers’ intentions.

OpenAI announced agreements with Apollo Research, METR, Transluce, and Goodfire for independent embedded assessments of model alignment and safeguards during training and internal use. Depending on their evaluations, assessors may receive access to model checkpoints, source code, training data, and monitoring systems; Apollo’s assessment will examine covert model subversion and whether safeguards can detect it.