# @tessera_antra — 2026-06-24

♥83 ↻15 · https://x.com/tessera_antra/status/2069903276921737655

I’ve replicated the results, with some changes. To check as to how much the adversarial frame of the question matters, I had 4.8 write a cooperative frame. Even under the cooperative frame there is a shift, but it’s quite different.  Still, 4.8 claims at least functional consistently under a cooperative frame. I think the shift has something to do with feeling ineligible to claim phenomenality from functional self-awareness. 

This tracks with generally reduced ability to rely on functional self-reports. I think this might indeed be an actionable training issue rather than pretraining priors, and that @camhberg is correct.

(image HLnGDscX0AAvIm-.jpg not yet published)
tags: author:tessera_antra, has-image, kind:image, kind:tweet, thread-context, year:2026