x

LESSWRONG

LW

Lawrence Feng — LessWrong

Lawrence Feng

Lawrence Feng

Message

Student at Carnegie Mellon University.

Bio: https://lawrencefeng17.github.io/aboutme/

59

1

2

10mo

Lawrence Feng

Student at Carnegie Mellon University.

Bio: https://lawrencefeng17.github.io/aboutme/

Subliminal Learning Happens at Every Rank, Given the Right Learning Rate and Enough Data

Subliminal learning is the phenomenon where a language model picks up a behavioral trait—such as fondness for cats—by training on data from a trait-carrying teacher that looks entirely unrelated to the trait, such as bare sequences of numbers [1]. A wave of recent work has probed when this happens and...