“Astra and Sol can take low probability actions with no CoT” by Zephaniah Roe

LessWrong (30+ Karma) · Oct 16, 2026 · 16m

This is a research update from a replication of Serrano et al., 2026. I’m releasing these results now because I hope it inspires others to run similar / followup experiments.

tl;dr:

If a model wants to subvert evaluation safeguards, it may choose to take misaligned actions very rarely. Because evaluation is much shorter than deployment, this could be an effective strategy for a model to avoid taking misaligned actions during evaluation, but have a high probability of defecting during deployment.

Serrano et al., 2026 found frontier models can take actions at low, calibrated rates, but their…