[FergusArgyll]

Subliminal Learning: language models transmit behavioral traits via hidden signals in data

https://arxiv.org/html/2507.14805v1

"In our main experiments, a “teacher” model with some trait T (such as liking owls or being misaligned) generates a dataset consisting solely of number sequences. Remarkably, a “student” model trained on this dataset learns T. This occurs even when the data is filtered to remove references to T."

[aesthesia]

In those experiments, the effect only happened between models from the same family (and likely the same weight initialization).