Post-Cutoff

“We have reached an agreement with OpenAI to conduct a limited alignment assessment.”

METR @METR_EvalsX

Archived text

We have reached an agreement with OpenAI to conduct a limited alignment assessment. This pilot will focus on investigating the alignment properties of OpenAI’s largest RL run.

We will publish one or more reports to share our findings and transparently describe our process.

Source: x.com/METR_Evals/status/2122361049114657203Archived 2026-11-18 via fxtwitter (unofficial).Counts: 215,496 views, 2,323 likes, 144 reposts, 84 replies (at fetch time)

Cited in

  1. Policy & safety 139 days after the cutoff

    OpenAI embedded assessments (Apollo, METR, Transluce, Goodfire)