Formation

Formation studies how a language model that starts each call with no memory of prior work can still become a particular skilled practitioner through later experience. The model weights stay frozen. What changes is the governed system around the model: which experiences it preserves, which proposed changes may affect later action, and how later evidence can revise or revoke those changes.

Its working thesis is:

A frozen, intermittently invoked model can develop into a particular practitioner when a governed system converts experience and consequence into durable, selective changes in future behavior that later counterevidence can revise, suspend, or revoke.

Here cold means that the model carries no project memory between calls. The practitioner is the cold model together with the developmental system that persists across calls.

Game mastering, coding, writing, research, and operations are possible test domains. None of them defines the project.

The question

An ordinary agent loop is good at continuing work:

assemble context -> infer -> act -> observe -> append -> repeat

But appending an observation can change the next answer without creating a change that should transfer to a new situation. More context is not the same as development.

Formation adds a second, governed loop:

practice loop:    orient -> decide -> act -> observe consequence
formation loop:   attribute -> propose change -> govern eligibility
                  -> activate selectively -> revise or revoke

A bounded trial may be part of governance. The project does not require a trial before every permitted influence.

The central question is whether experience can cause a warranted change that improves action in a later, novel, structurally related situation while staying silent where that structure does not apply.

The system boundary

Formation begins with three separate roles:

• The cold model supplies inference. It is replaceable and receives no weight updates within the project boundary.
• The formation runtime acts with the model, preserves developmental lineage, and governs changes in the practitioner.
• The trajectory harness creates controlled histories, forks identical starting states, schedules environments and declared consequence oracles, assigns ablations, and captures evidence for prospective scoring.

This separation prevents a specific mistake. If the harness interprets a consequence and quietly gives the model the correct lesson, the experiment measures oracle assistance rather than formation.

What counts as progress

A changed answer is not enough. A Formation claim requires at least:

1. Acquisition: consequential experience causes a later behavioral change.
2. Transfer: the change helps on prospective cases that prevent answer copying and simple episode matching.
3. Selectivity: the change stays silent where its structure does not apply.
4. Revision: later counterevidence can revise, suspend, or revoke it.
5. Causal contribution: ablation or controlled branching attributes the improvement to the acquired change.
6. Net value: the benefit survives the costs of context, checks, latency, maintenance, and negative transfer.

“Exceptional” is comparative. A formed practitioner must outperform the same cold model with static instructions and ordinary persistence on novel work, while remaining governable.

Relationship to Construct

Construct is the immediate experimental ancestor. It produced bounded results on offer quality, consequence-earned authority, cross-session influence, selective eviction and recovery, and governed continuity. Formation accepts those results within their original evidence bounds.

Formation does not inherit Construct’s runtime objects or vocabulary as requirements. They are prior work and candidate instruments. Formation must earn its own mechanisms.

Construct remains the lab that owns its findings and should stay reproducible. New trajectory experiments and formation-runtime code belong here.

Present state

No Formation effect has been earned. The project has deterministic machinery, several completed exploratory contacts, and a narrower measurement problem. Working code, stored text, and changed model output remain instrument or observation facts unless a prospective comparison supports a stronger claim.

Current empirical problem

The latest exploratory contact asked whether an unselected model-authored interpretation could affect later cold-model action. Qwen completed all 109 calls without retry. The six information paths produced the same proposed actions on 15 of 16 later cases. On the remaining case, two byte-identical requests also returned different actions. The observed branch difference is therefore no larger than the variation seen with the same input.

This result does not show formation. It identifies the next empirical problem: measure ordinary same-request variation well enough to tell it apart from a condition effect. The complete counts, requests, responses, and limits are in the evidence account. The preceding executable-prediction contact found the same instability in a different form; its evidence remains useful background.

The mechanism, deterministic specimen, charter, runner, and earlier review records remain available for audit. They are completed research history, not a mandatory sequence for the next exploratory test. A pre-contact import failure also remains recorded, but it is an engineering failure rather than a consumed scientific contact.

Working method

Move quickly enough to encounter reality, then become deliberate when interpreting evidence or making a claim.

Discovery comes before validation. An exploratory contact needs a clear question, an observation that would matter, an exact model and interface, a small budget and stopping condition, and a place to retain evidence. It does not need a new chain of license documents or automatic model reviews.

If repeated evidence exposes a phenomenon that bears on the Formation thesis, the project can then test it again with prospective controls, transfer and non-transfer cases, replication, and outside criticism. Cursor models may help with occasional internal critique when a human requests it. They are not external peer reviewers and do not decide whether an experiment may proceed.

The route to this result matters. Earlier contacts showed that interface compliance and computation are separate, that shape constraints can repair JSON without repairing an answer, and that several model setups could not perform their assigned responsibility. Later contacts exposed problems in consequence interpretation, selective influence, and model-authored reusable changes. Those results are retained as bounded research history; they are not another admission ladder. See Research history.

Supporting implementation lane

A separate deterministic lane builds the runtime and harness boundaries needed for later causal work. Ten fixture-local slices are implemented through action commitment. The next implementation step is environment application, followed by consequence intake and experience closure.

This lane does not gate the exploratory contact. Completing it would establish plumbing and authority separation, not model development. The detailed milestones and stopping conditions live in the plan.

Project map

Place	Responsibility
docs/	Concept, research contracts, history, and forward plan
docs/RESEARCH_HISTORY.md	Chronological account of closed research routes and how each exposed the next problem
formation/	Runtime-owned fixture producers, constraint binding, and foreground consumption; not yet a general runtime
trajectory/	Harness-owned fixture validation, assignment, provenance, and witness checks; not yet a general harness
contact/	Narrow executors for bounded exploratory and validation contacts
tests/	Deterministic contract, separation, and fake-contact tests
evidence/	Retained contact records and future primary trajectories, with bounded computed verdicts and explanations

Evidence and authority

When sources disagree, prefer the most specific authority for the question:

1. Primary developmental lineage and trajectory evidence for what occurred.
2. Frozen scorers and their computed output for experimental verdicts.
3. Reviewed experiment and mechanism specifications for the contacted contract.
4. The authority and record specifications for cross-experiment boundaries.
5. The concept document for working definitions and research questions.
6. This README for the project story, present state, and routing.
7. Plans and build documents for intended work.

Research history explains how the project arrived here. It does not override a specification, evidence record, scorer, or current route.

The retained admission and task-selection contacts occupy the first two classes only for their own bounded questions. No developmental trajectory or computed Formation verdict exists yet. Plans, fixtures, and functional frameworks cannot promote themselves into evidence.

Working here

Run uv sync once to create the locked Python 3.14 environment. Run the full deterministic and fake-contact suite with uv run pytest -q.

Before substantive work:

1. Read this page and the nearest directory README.
2. Name whether the task serves the current empirical problem, the deterministic supporting lane, concept formation, or later validation.
3. For mechanism or validation work, state what would distinguish the proposed account from retrieval, answer copying, prompt accumulation, or harness assistance.
4. For exploration, name the question, observation of interest, model and interface, budget, stopping rule, and evidence destination. Record external consequences and branch information when the experiment uses them. For validation, also freeze the same-model baseline, transfer target, non-transfer case, oracle, replication plan, and prospective verdict before contact.
5. Keep claims at the maturity actually supported by code and evidence.

The governing route is concept, authority, record, evaluation, plan, fixture, instrument map, and build boundary. The completed unselected-lineage contact defines the immediate empirical problem: same-request variation. Its only apparent branch effect was matched by disagreement between byte-identical calls. The bounded repeatability runner is implemented and fake-tested. It selects four exact requests from the retained packet and schedules eight interleaved repeats of each. No repeatability contact has run. The next step is an explicitly authorized 32-call execution, not another admission or procedural review program.