Research.

Notes on what it means to represent a person’s taste: what the literature supports, how we read it, and where we have taken a position. Each note keeps established research, interpretation and our own view separate, and ends with its sources.

  1. Note 01 · Representation

    Taste Is Not a Vector

    Vectors are exceptional tools for computation. The difficulty begins when a representation built for one task is treated as a sufficient model of the person behind it.

    · 9 minRead note
  2. Note 02 · Temporal Models

    Preference Has a History

    An observation is not only a value. It carries a date, a context and a relation to everything observed before it. Every preference has provenance.

    · 12 minRead note
  3. Note 03 · Context

    Context Is Part of the Preference

    Preference is inferred from evidence produced in situations. Removing context does not remove noise. It changes what the observation says about the person.

    · 9 minRead note
  4. Note 04 · Representation

    Similarity Is Not Understanding

    Modern systems are remarkably good at learning which things are related. Relatedness alone does not establish which property of an object mattered, or what should generalize from it.

    · 11 minRead note
  5. Note 05 · Personal AI

    Personal AI Needs a Theory of the Person

    Personal AI is usually framed as a memory problem. The harder problem is deciding what accumulated evidence should mean about the person it describes.

    · 12 minRead note

REQUEST A DEMO

Let’s explore
your use case.