The whole organism

Every part, and every connection between the parts. Drawn from the code, not from the design documents.

There is no hierarchy.

This is the answer to “where is the full model?”. The UI is not failing to draw the layers — the layers do not exist.

What is built is 21 separate little models sitting side by side. They are siblings, not layers. There is no connection between any two of them: no message, no shared belief, no influence. Each one senses one thing and forms its own private opinion about it. The only place they meet is the choice of what to do next, where their scores are simply added up.

Above them sits one strategist, joined by a channel that carries a single integer — about 2.3 bits — once every 12 ticks. A third layer is wired in but dead. So: two working levels and a straw, where the design calls for eight, nested, recursively.

levels declared
3
levels that run
2
factors at L1
21
connections between them
0
bandwidth up to L2
2.3 bits/12t
levels in the design
8

1 · What is actually there

slow “scene” layer — 4 states DEAD: its weight matrix is uniform and never written, so its message is the same for every belief it could hold L2 · strategist — ONE factor, 5 situations picks one of: forage · build · flee · socialize · rest — once every 12 ticks up: ONE integer, 0–4 ≈2.3 bits · every 12 ticks · from ONE factor a shock across 20 of 21 factors cannot reach L2 at all down: what to want + precision ×1.3 · learning rate ×0.88 every tick, not every 12 L1 · the body — 21 factors, side by side no arrows between them because there are none: they never exchange anything status4 st inventory4 st vision6 st threat3 st social3 st self4 st strategy5 st light3 st sky3 st sight4 st build3 st prey4 st ▲ 12 exteroceptive — FROZEN: belief cannot move, ever. They contribute nothing to any decision. aim3 st reach2 st contact4 st dig4 st motion3 st energy6 st gut6 st soma6 st fatigue6 st ▲ 9 body factors — these work: they sense their own state, so their beliefs move. the ONE lateral link in the whole brain — a single hard-wired “am I holding food?” column the only place the 21 ever meet: their scores are ADDED UP to pick one action G(action) = Σ over factors — a sum, not a conversation. 12 of the 21 add exactly zero. …then the chosen action feeds back into the world, and the tick begins again

2 · Every connection that exists

from → towhat crossessizehow oftenstatus
factor → factor (any of the 21 to any other)nothing at all0 bitsneverABSENT
energy → gut (the single exception)one hard-wired “holding food?” column1 columnper tickHARD-WIRED
all 21 → action choicetheir scores, summed1 number eachper tickLIVE
L1 → L2one integer 0–4, read from one factor only≈2.3 bits1 in 12 ticksA STRAW
L2 → L1chosen option → preference override + precision ×1.3 + learning rate ×0.887 vectorsevery tickLIVE
slow layer ↔ L1would be belief vectors both waysneverDEAD

Read the first row again. It is the whole point. Twenty-one models that never exchange anything are not a hierarchy and not a network — they are twenty-one separate animals wearing one coat, voting on what the coat should do next.

3 · What was designed, against what exists

The design — 8 layers, nested, recursive

Each unit is an 8-layer stack. A unit then sits as layer 1 of the unit above it — flagellum inside cell, cell inside nerve, nerve inside nervous system — each joined through its own Markov blanket. Update rates between adjacent layers stand in a fixed ratio, so layers learn and unlearn at different speeds. Precision is a separate organ that steers attention; the ratio only sets timing.

Status: NOT BUILT — no part of this exists in the engine. Not partially: the recursion has no instance anywhere, and there is no per-layer clock to put a ratio on.

What exists — 2 levels and a straw

One flat bank of 21 unconnected factors. One supervisor above it, reached by a 2.3-bit channel that only one factor can speak into. One dead layer. No unit sits inside another unit anywhere. The colony is peers under a supervisor sharing a world — there is no colony-level belief and no colony-level free energy.

So the gap is not “some layers are missing”. It is that the nesting mechanism itself has never been built, and there is nothing for a Fibonacci cycle ratio to be a ratio of.

Why this matters more than the individual defects. A frozen likelihood is a bug you can fix in 40 lines. A missing hierarchy is a piece of architecture. The depth axis of the paralysis prediction — “a shock deep enough through enough layers” — is unfalsifiable on this machine, because there is no depth to propagate through: 2 levels give the depth axis exactly one degree of freedom, and the channel between them is too narrow for most shocks to cross at all.

4 · One tick, end to end

#what happensnote
1senses arrive and are binned into one outcome per factor21 numbers
2once every 12 ticks, L2 re-picks an option from the single integer it can seeotherwise the old option is held
3the option is pushed down: preferences overwritten, precision ×1.3, learning rate ×0.88every tick, even when L2 did not think
4each factor updates its belief from its own observation12 of them cannot move
5each factor learns — counts go up, and never downnothing ever decays
6each factor scores every action; the scores are summed; one action is sampledthe display shows a different, greedy calculation
7the action is taken and only that action's transition block learnsthis is the lock: taking it makes it look better

Step 4 runs before step 6, so a factor decides using the model it has just this instant revised. Step 7 is why one action ends up taken 95% of the time.

Drawn from the engine at 0c42216; factor counts and state sizes read from the genome; connection inventory read from the message-passing code, not from design documents. If a connection is missing from the table above it is because it is missing from the code.