Skip to content

Building blocks

  1. 01

    Vector representation

    Meaning is represented as geometry in a vector space.

    Read

  2. 02

    Function approximation

    A model is a parameterized function fitted by optimization.

    Read

  3. 03

    Attention and transformers

    Attention is the data structure of context; its cost scales with window length.

    Read

  4. 04

    Probability and uncertainty

    The model outputs a probability distribution over tokens.

    Read

  5. 05

    Context as the interface

    The context window is the interface: its contents determine the next step.

    Read

  6. 06

    Evaluation

    Iteration requires a measurement procedure.

    Read

  7. 07

    The agentic loop

    An agent is a loop: perceive, decide, act, observe, under a resource bound.

    Read