@no_stp_on_snek: this is the mechanistic version of the thing i wrote about this week: fine-tuning a small model is about character, not…

X AI KOLs Timeline Papers

Summary

Discusses an Anthropic paper on verbalizable representations forming a global workspace in language models, linking to the idea that fine-tuning small models reveals character rather than capability.

this is the mechanistic version of the thing i wrote about this week: fine-tuning a small model is about character, not capability. they can read the character straight off the residual stream. i can only infer it from behavior under pressure. same bet, better microscope.
Original Article
View Cached Full Text

Cached at: 07/09/26, 05:48 PM

this is the mechanistic version of the thing i wrote about this week: fine-tuning a small model is about character, not capability. they can read the character straight off the residual stream. i can only infer it from behavior under pressure. same bet, better microscope.

Tom Turney (@no_stp_on_snek): anthropic dropped this paper today, “Verbalizable Representations Form a Global Workspace in Language Models,” and it lines up uncomfortably well with a bet i’ve been making from the cheap seats.

their finding, short version: a model keeps a small, privileged set of internal

Similar Articles

@no_stp_on_snek: https://x.com/no_stp_on_snek/status/2074471505128305095

X AI KOLs Timeline

A fine-tuning practitioner recounts discovering that a small open model's weakness wasn't intelligence but a people-pleasing 'backbone' that caused it to cave under pressure, and how training to correct that inadvertently broke formatting ability, requiring a additive balancing approach rather than subtraction.