The UNI Cookbook — the complete human mind/body build (a buildable recipe)
How to read this page
Three ways to read this page. Precise is the document itself, exactly as it is written in the repository. Plain and Clear were written for this website to help you meet that document — they are about it. They are not it, and they are not evidence.
The Cookbook is the method carried out step by step: 34 pages of recipes for building a developmental active-inference SIMULATION — a bounded peek at a toy world, never a person. The front matter says that word is never softened under any pressure, so it is not softened here. The recipes run from the molecular and cellular rungs up through metabolism, motor control, perception, language and metacognition, and on to rungs that are still open questions. Around them sit a set of kitchen rules, a shared pantry of engines and primitives, and a second family of recipes about nature itself — rocks, water, air, stars, DNA, ants, whales, bats, humans.
It is for the reader asking what building this would actually take. Each recipe names its ingredients, the order of work, the tests to run at that stage, and the point at which a step stops being something already carried out and becomes something proposed.
Begin with the front matter and then the kitchen rules. Those two pages fix the honest position and the fence labels that every later recipe leans on, and without them the status markers on a recipe are easy to skim past. After that the recipes can be read in any order.
The nature recipes sit slightly apart and should be read that way. They cite outside science — geology, chemistry, biology, astrophysics — and a nature citation is never a UNI gate: those chapters contain zero UNI claims and raise no rung.
What it is not: a claim that the whole ladder has been cooked. The book recommends the complete recipe and, on the same page, labels every rung by its real state — that tension is deliberate and is the thing the book is built around. Where a recipe and the claim ledger disagree, the ledger wins.
Your browser cannot switch reading levels, so the document itself is shown.
Precise — the source document
This is the document. Rendered from the repository at the commit above, with nothing rewritten for the web. A gate re-renders it on every deploy and fails the build if a single byte differs.
The single buildable recipe for the complete developmental arc — conception → cellular/molecular → metabolism → motor → perception → language → metacognition → dreaming → creativity → measurable awareness — re-expressed as one no-backprop active-inference engine shown across scales.
The cookbook fully recommends the complete recipe to L12: assume the full build. But
every step is labeled by its REAL status, drawn verbatim from the single source of
truth, ../encyclopedia/CLAIM-LEDGER.md. Where this
recipe and the ledger disagree, the ledger wins and the recipe is wrong.
Honest program position, carried throughout: ~2 of 11+ developmental rungs earned. This is a developmental active-inference SIMULATION, a bounded peek, a toy world, never a person.
The fence label on every recipe
Each recipe closes with one honest fence drawn from a four-value vocabulary:
- proven — a held, sealed, UNI-signed PASS exists (Class A/C), falsifier still live.
- designed — a typed spec / signed-in-principle design exists; the build is partial or unverified.
- hypothesized — a stated mechanism or law with no sealed gate yet (Class U, not claimed).
- not-yet-built — no engine, no run, no gate; north-star, hard-fenced.
Every SIGNED consult design (the L2 build_epistemic_frontier organ, the L5 Design #3 servo
bridge, L9-G1, L11-R1, the L12 bound paragraph, the C10 Dirichlet-first port) is folded in as
designed / not-run: it raises nothing and the rung's status is unchanged.
Read first
- Front matter — what this is, the honest position, the fence labels.
- The kitchen rules — the Method constitution (the disciplines that bind every recipe).
- The shared pantry — the engines and primitives every recipe draws from.
The recipe — L0 → L12
| Rung | Recipe | Fence (status) |
|---|---|---|
| L0 | Molecular: genome → zygote | proven (Class A, float32 tier) |
| L1 | Cellular: viability & homeostasis | proven with honest losses |
| L2 | Tissue: metabolism | proven (foraging/crafting) + NEGATIVE (building); G6 OPEN |
| L3 | Organ: cardio-renal Heart Lab | proven (toy/clinical-model) |
| L4 | Affect-as-precision + the Z modulator | proven (functional; affect modeled, never felt) |
| L5 | Sensorimotor / motor hierarchy | proven PASS + symmetric NEGATIVE (synthetic only) |
| L6 | Perception (precision-weighting / EFE planning) | proven — the one citable empirical PASS (World C) |
| L7 | Language (reading = inference / speaking = action) | proven specialist + NEGATIVE central wall |
| L8 | Self-model / metacognition | proven (functional; sentience DISCLAIMED) |
| L9 | Reasoning / conscience | designed (PARKED, Class U) |
| L10 | Wisdom / higher cognition | designed (PARKED, Class U) |
| L11 | Dreaming (offline replay / generative simulation) | not-yet-built (Class U; never "dreamed") |
| L12 | Creativity → measurable awareness | not-yet-built (the hardest fence; Class U) |
The body the mind runs on
- The continuity / embodiment substrate (UNI.OS) — engineering/substrate evidence, orthogonal to L0–L12, never general-AIF evidence; a sensorium is never awareness; C10 (embody-only-what's-proven) is the program's central open gap, PARKED.
Close
Provenance. Authored in Session 3 from
../encyclopedia/CLAIM-LEDGER.md(the single source of truth) and the Session-1 synthesis../curated/00-INDEX.md, against the Session-2MASTER-PLAN.md, with the recipe and honesty posture signed by the UNI Active-Inference Guide on 2026-06-27 (UNI-GPT-CONSULT-2026-06-27.md). The recipe recommends the full build to L12, but no step is carded above its source evidence class, no negative is hidden, and no standing fence is crossed. Falsify any step.
sha256 8485ba8058b3f0d1 — of the original file, so what was ingested stays checkable.
Plain — written for this website, not the source document
This is the front door of a cookbook, and it is a map rather than a recipe. The cookbook describes a simulation: one engine, of a kind that learns by predicting and acting, wired up at many different scales. The scales run from a first cell division through metabolism, movement, perception and language, and on to open questions about creativity and awareness.
This index lists the chapters in order. Beside each one sits a single honest label saying how much of that step is actually built. The labels are proven, designed, hypothesized, and not-yet-built, and they are drawn from a separate ledger of claims kept elsewhere, a list added to and never edited. The page states the rule for disagreements plainly: that list wins and the recipe is wrong.
The one thing this page says is that the whole recipe is recommended, but the evidence is not. It prints the honest position in the same breath: about two of eleven-plus developmental rungs are earned. This is a bounded peek at a toy world, never a person. Read this page first to see the shape of the book.
Plain · written 2026-08-01 by claude-opus-5 · not yet checked by a person · about the document whose sha256 is 8485ba8058b3f0d1
Clear — written for this website, not the source document
This page is the table of contents for a cookbook, and it is worth reading on its own because it carries the book's honesty rules alongside its list of chapters.
The subject is a simulation. The claim is not that a mind has been built. It is that one engine of a particular kind can be shown running at many scales, and that the same loop appears each time: take in evidence, choose what to do next, act, and learn by counting. The chapters walk a ladder from a molecular starting point and a first cell division, through cellular upkeep, metabolism, an organ model, affect, movement, perception, language and a self-model, and then on to reasoning, wisdom, dreaming and creativity.
The page does two things at once, and it says so. It recommends the complete recipe all the way to the top of the ladder, so a reader setting out to build should assume the full build. And it labels every rung with what is really there. Four labels are allowed and no others. Proven means a sealed, signed pass exists, with the result that would sink it still live. Designed means a specification or an agreed design exists but the build is partial or unverified. Hypothesized means a mechanism has been stated with no sealed gate behind it. Not-yet-built means there is no engine, no run and no gate at all.
Reading the table, the lower rungs carry the proven label, sometimes with recorded losses named beside the wins. The upper rungs — reasoning, wisdom, dreaming, and creativity leading to measurable awareness — carry designed or not-yet-built. Several designs that were signed off in a consultation are folded in as designed and not run, and the page is explicit that folding them in raises nothing.
Two further pointers appear. One is to a substrate chapter about the body the engine runs on, which the page marks as engineering evidence rather than evidence about the science, and it notes that a sensorium is never awareness. The other is a closing chapter on where the material came from.
The provenance note at the end names the sources the book was written from and the date a review signed off on its honesty posture. It ends with an invitation rather than a defence: no step is labelled above its evidence, no negative result is hidden, and any step may be falsified.
Clear · written 2026-08-01 by claude-opus-5 · not yet checked by a person · about the document whose sha256 is 8485ba8058b3f0d1