Glossary · Term

cross-entropy

← all terms

Definition

Plain language

The standard score for how surprised a model is by the next word — lower means it predicted better.

As stated in the literature

The expected negative log-likelihood a model assigns to target tokens; the default training loss for language models and the basis for derived metrics like perplexity and bits-per-byte. Also reused as ECHO's auxiliary loss on environment tokens.

Why it matters: It's the core signal that tells a language model how wrong it was, driving nearly all of its learning during training.

For example, if a model confidently expects 'cat' but the real next word is 'dog,' its cross-entropy score goes up to reflect that surprise.

Heard on the show

“So the visit count is doing the opposite of the cross-entropy rule.”
Episode 163 — Why Training Only on Perfect Solutions Cripples a Model's Reasoning

Mentioned in 3 episodes

  1. 163
    Why Training Only on Perfect Solutions Cripples a Model's Reasoning
  2. 084
    Terminal Agents Get Free Supervision From The Tokens We've Been Throwing Away
  3. 053
    An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script

Related terms