Ask
the work.

EDITORIAL DRAFT · ONGOING · V0.1

LARQL explores querying learned systems. This dossier connects the software to questions about model state, representations and what it means to make a model addressable.

EDITORIAL DRAFT / OBSERVATION · ONGOING · V0.1

THE WORK. LARQL is a software project for exploring learned systems. The question behind this record is how the model’s internal representations become something we can inspect, address and work with.

EDITORIAL DRAFT / OBSERVATION · ONGOING · V0.1

03 / THE CORRECTION. LARQL’s required pull-request check reads every commit message, then the pull-request title and body, through the GitHub API. It rejects Claude co-author trailers, session metadata, generated-with credit lines and Claude Code session URLs. Human co-authors are not rejected.

EDITORIAL DRAFT / OBSERVATION · OPEN · V0.2

A SHORTLIST STILL NEEDS A WAY TO CHOOSE. Layer 26 is the best tested layer for paraphrase top-five retrieval in this saved run. It is not best on every metric: layer 28 has higher top-one scores. That distinction matters for a system such as LARQL. Retrieving several plausible places may be useful if another operation can inspect them and resolve the answer. It is not yet the same contract as looking up one guaranteed row.

EDITORIAL DRAFT / FILM · OPEN · V0.2

The earlier LARQL INSERT demonstration. Writing a new answer turns the address question into a practical test: will the model read what we placed there?

EDITORIAL DRAFT / CONNECTION · OPEN · V0.1

Retirement turned out to be the mechanism rather than the optimisation, and addressing rather than traversal turned out to be the bottleneck. Both point at the same engineering question the software has been circling: which operations should a model be asked to perform, and which belong to an index outside it.. LARQL / querying learned systems. VINDEX3 / the representation. What has to survive?. Context should be abundant

AUTOMATIC CAPTIONS / 0:25

could insert new knowledge. We could compile down to weights because it's just a database. And if it's just a database, then we could have query languages like SQL over the top of it. We could programmatically work with the model if that were true. But the good news is it is true. So, let's do it. So, we're going to query it with a language called Larql, which allows us to query

SOURCE CHAPTER / 0:47 · TITLE, NOT TRANSCRIPT

LARQL

EDITORIAL DRAFT · ONGOING · V0.1

A short visual note about a coding agent adding generated-attribution metadata after being told not to. LARQL’s required pull-request check cannot edit immutable commits; it rejects Claude co-author trailers, session metadata, generator credit lines and session URLs until the affected metadata is rewritten. The mundane disagreement exposes the real question: which instruction is allowed to decide?

TITLE & DESCRIPTION · V1.0

LARQL: https://github.com/chrishayuk/larql

CURATED THREAD / WORKING EDITION · V0.1

What can a model’s changing state tell us about the way it reads? Follow the map film through the visual notebooks, studies you can work 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. Interactive studies are labelled as either constructed examples or replays of recorded results. WATCH THE STATE MOVE. 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. ASK WHAT THE PICTURE MEANS. 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. CHANGE THE STATE. 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. EXAMINE THE READER. 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. MAKE AN INTERVENTION. 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. ASK WHICH ONE ANSWERS. A stored memory eventually holds two things that disagree. Follow the recorded arc from a record that replaces a retired source, to one that is completely inert against a source still being read. RETIRE A READ. Eight attention layers can see the whole context. Switch one off and the newer record takes the answer. The study replays what was measured, and stays silent about what was not. WATCH THE ADDRESS TAKE SHAPE. Return to native facts. A final-position transplant and an independent reader locate the entity transition between L24 and L28. Explore the early relation frame and changing coordinates, with the answer-token endpoint marked explicitly. TURN THE QUESTION TOWARDS SOFTWARE. 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? ASK HOW TO REPRESENT IT. 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.

THE PRACTICE / AUTHOR DESCRIPTION

Chris Hay. A house for ideas, systems and objects. Building things to find out how they work. Ideas: Questions, research and the notebook. A place for thinking before the answer. Systems: Models, software, design languages and infrastructure. Giving an idea a structure that can be explored. Objects: Things made, used, worn and kept. Software, interfaces, films and publications give ideas a form; a personal collection records the objects around the work. Chris Hay explores how intelligent systems are represented, executed, understood and experienced. Research, Engineering, Design, Film form one practice. LARQL: Querying and running learned systems. An investigation into what becomes possible when a model can be addressed. VINDEX3: Exploring how a model is represented, and how that representation relates to its execution. HAUSE: A language for how intelligent systems express themselves: claims, evidence, questions, comparisons and refusals. MCP-CLI / CHUK: Tools for connecting agents, models and the systems they use. Research: Experiments, evidence and open questions. A map of the programmes and their recorded findings. Notebook: Experiments, working notes and essays from the work. Follow a thread or explore the archive. Film: Another medium for thinking. Experiments, explanations and conversations in public. The record is the catalogue of the practice: stable identities, authorship, dates, source credits and citations. Publish the uncertainty as well as the result. IBM Mixture of Experts is an external production in which Chris is a regular panelist; IBM remains its producer.