Research watch · Paper · Aug 2026

Subliminal Learning is Non-Semantic Distillation

This paper studies subliminal learning in the context of mechanistic interpretability. It was accepted as a spotlight paper for the ICML 2026 Mechanistic Interpretability Workshop.

Our reading

From: Ethan Hadley, Eren Gultepe

The work appears to examine how information is transferred or compressed inside model training or distillation settings.

Its framing places it within interpretability and internal representation analysis rather than consciousness research.

It does not show that models have subjective experience, and it does not establish reliable introspection by the model itself.

Source: arXiv ↗. This is a summary; the source is the authority.

What it changes

This is relevant to how internal representations move through models, but it adds little direct evidence about AI experiences.

How we weigh evidence like this: the evidence levels.