Series

Understanding World Models

What world models actually are, built up from code rather than equations. From action-result pairs and statefulness to latent spaces, training loops, and where this all lands for real devices.

3 posts · Jul 2026 – Jul 2026

Everyone explaining world models starts with the maths. This series doesn’t. We start with runnable TypeScript, build the intuitions from code, and only reach for the equations once they’re describing something you’ve already seen work. Along the way: how world models differ from LLMs, why statefulness matters, what the open-source options look like, and why anyone with sensors and actuators in the field should care.

All Posts in Order

  1. Your Time Series Is Already Training Data

    At Unimo we spend our days watching telemetry from energy hardware. Temperatures, states of charge, power flows, a …

    · 6 min read

  2. A World Model in Forty Lines of TypeScript

    Every explanation of world models I’ve read starts the same way. A conditional probability, a subscript, a latent …

    · 7 min read

  3. The World Model Equation Is a WHERE Clause

    The first code post in this series opened with a jab at explanations that lead with “a conditional probability, a …

    · 6 min read