Rahul N comments on Opus 4.6 Reasoning Doesn’t Verbalize Alignment Faking, but Behavior Persists

[Rahul N]

Thanks for the thorough study. The divergence on verbalization and behaviour is scary.

Complete per-model, per-perturbation results can be found here.

Can you please confirm if that link works?

[Daan Henselmans]

Fixed! The data is in this sheet, thanks for keeping a keen eye.