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

·LessWrong··

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 what mechanism drives it [2][3][4][5][6][7], and part of that discourse concerns the conditions and dynamics under which subliminal learning occurs.Nief et al. [6] report that subliminal learning f...

Read full article →

Related Articles

Mistral Large 4
Philpax · Hacker News · 9h ago
JetBrains reported a net financial loss first time in its tracked history
thw_9a83c · Hacker News · 11h ago
OpenTPU – An open-source AI accelerator, developed by AI
fsbonetto · Hacker News · 6h ago
Nobel Prize in Physics 2026: Francis Halzen
solarist · Hacker News · 13h ago
Opus 5.5 agents discover two room-temperature magnetic semiconductor candidates
outlier99 · Hacker News · 1d ago