Glossary · Term

state-space model

← all terms

Definition

Plain language

A sequence model that maintains a fixed-size running memory rather than attending to every previous token.

As stated in the literature

A class of sequence models that maintain a fixed-dimensional recurrent state, including Mamba and S4 variants, offering constant memory per step.

Also called: state-space models, SSM, state-space

Why it matters: Constant-memory recurrence offers a path to much longer effective contexts than attention can affordably handle, though typically at some quality cost on short tasks.

For example, a Mamba layer keeps a small hidden vector that gets updated as each new token arrives, with no need to look back at every prior token.

Heard on the show

“The whiteboard is a fixed-size matrix the authors call a "fast weight" — it lives in what's called a state-space model, or SSM.”
Episode 085 — Why Long-Context Models Might Need Compute, Not Capacity, Before Eviction

Mentioned in 4 episodes

  1. 085
    Why Long-Context Models Might Need Compute, Not Capacity, Before Eviction
  2. 053
    An AI Agent Swapped In Focal Loss And Beat A Human-Tuned Training Script
  3. 033
    Echo: The Paper Arguing You Never Needed a KV Cache for Retrieval
  4. 027
    When AI Agents Build the Serving Stack: A Bet on Bespoke Infrastructure

Related concepts

Related terms