CHRIS HAY

IDEAS · SYSTEMS · OBJECTS / LONDON · 2026

CHRIS HAY / FOLLOW THE THREAD

From a map
to a memory.

What can a model’s changing state tell us about the way it reads? Follow the map film into three visual notebooks, a memory you can change yourself, and the questions behind LARQL and VINDEX3.

A curated reading order, rather than a chronology of discovery. Films keep their original dates. Notes and dossiers remain working drafts; the interactive study is a constructed example.

THREAD-MAPEDITORIAL GUIDE · V0.1COMPOSED 2026-09-06START WITH THE FILM ↓
  1. 01film

    WATCH THE STATE MOVE

    370,000 tokens loaded in Context in 2.8MB, on a MacBook.

    Begin with the capital of Japan. The film follows the changing residual state, then asks what happens when a France state enters an Australia computation.

    ORIGINAL FILM

    WATCH FROM 02:00
    The projected residual trajectory among Tokyo, Paris, Berlin and Cairo landmarks.FROM THE FILM
  2. 02notebook

    ASK WHAT THE PICTURE MEANS

    What is the map actually a map of?

    Which token position is moving? What are the axes? The notebook reads the demonstration alongside its projection code and distinguishes a useful picture from an answer probability.

    WORKING DRAFT · OPEN

    OPEN THE NOTE
    Capital, currency and language directions add to one packed vector in a constructed six-dimensional example.CONSTRUCTED VISUAL STUDY
  3. 03notebook

    CHANGE THE STATE

    What has to survive?

    Replacing one position and replacing the full sequence are different interventions. Follow the transplant evidence into the question of what must persist after the next word.

    WORKING DRAFT · OPEN

    OPEN THE NOTE
    France’s residual replaces the Australia state; the layer readouts converge on Paris.FROM THE FILM
  4. 04notebook

    EXAMINE THE READER

    Reading by address.

    A state becomes useful when an operation can read it. Follow key matches, activations and value contributions, then compare the constructed memory with the native-model experiments.

    WORKING DRAFT · OPEN

    OPEN THE NOTE
    An explanatory conveyor: a capital-of-France address reaches an FFN lookup and writes Paris into the residual stream for downstream reading.CONSTRUCTED VISUAL STUDY
  5. 05interactive study

    MAKE AN INTERVENTION

    Try the mechanism.

    Choose capital of Atlantis. Inspect the competing activations, remove a neuron and watch the answer scores change. Every operation in this little memory is visible.

    CONSTRUCTED EXAMPLE

    TRY THE MECHANISM
    CAPITAL OF ATLANTISParis.CHANGE THE QUESTION ↗
  6. 06work

    TURN THE QUESTION TOWARDS SOFTWARE

    LARQL

    LARQL explores how learned systems can be queried. Return from the small memory to the larger engineering question: which operations can a model reliably expose?

    WORKING DRAFT · ONGOING

    EXPLORE THE WORK
    The LARQL knowledge-writing demonstration queries the capital of Atlantis.FROM THE FILM
  7. 07work

    ASK HOW TO REPRESENT IT

    VINDEX3

    If a model has parts we can address and relationships we can inspect, how should we represent them? VINDEX3 gives that question its own system and specification.

    WORKING DRAFT · ONGOING

    EXPLORE THE WORK
    REPRESENTATION / RELATION / ADDRESSA PART YOU CAN REACHCONCEPTUAL STUDY

THE NEXT QUESTION

What would make
the address reliable?

The notes keep the limits visible: changed phrasing, competing entities, retained state and use beyond the first answer. Follow the open research question, or search the underlying records.