Artifact-backed experiments on the behavioral half-life of subliminal traits under recursive self-distillation.
-
Updated
Jun 11, 2026 - Python
Artifact-backed experiments on the behavioral half-life of subliminal traits under recursive self-distillation.
Code to reproduce the results of the paper "Learning Through Noise: Why Subliminal Learning Works and When It Fails"
A controllable model of subliminal learning via log-linear signal accumulation
From-scratch NumPy MLPs for MNIST, plus a larger teacher–student setup that demonstrates subliminal learning (implementing Cloud et al. (2025)).
Add a description, image, and links to the subliminal-learning topic page so that developers can more easily learn about it.
To associate your repository with the subliminal-learning topic, visit your repo's landing page and select "manage topics."