Hylæan · A research programme
We stopped asking how to copy the brain. We started asking what the brain discovered.
Aircraft fly without copying a bird. Hylæan asks whether intelligence, too, can be understood through a simpler underlying principle.
One evolving field. Thinking as settling. Learning as a lasting change in geometry. A research hypothesis, tested against explicit evidence.
Flight was never about feathers.
Nature shows that flight is possible. Aerodynamics explains how.
Understand the principle. Reinvent the machine.
An aircraft does not have to copy a bird. For intelligence, the equivalent principle remains an open question.
What if intelligence formed in a field?
Hylæan investigates one shared substrate for perception, memory and action.
Experience should change what happens next.
A useful learning system must improve a later outcome. The causal connection has to be measured.
A profile of evidence. An honest account of limits.
Capability, scaling and confidence stay separate. Missing evidence is visible.
Follow the question. Inspect the evidence.
Explore the architecture and the recorded evaluation. A project of Shopware Agentic Commerce Labs.
“Do not make the system look intelligent. Make the field become intelligent.”
00 · Origin
In plain words
Evolution produced a brain, but never a description of how it works. Copying the organ is one way forward. This chapter asks the other question: what did evolution actually find, and does that finding have a simpler form?
Evolution found intelligence. It never explained it. The brain is a working example of matter that perceives, remembers, abstracts, plans, learns and models itself, and it arrives with no theory attached. An existence proof says that something is possible. It does not say what that something is.
01 · Existence, not theory
That is already a great deal, and it is easy to read too much into it. The organism is the working example, not the finished description. So the opening question here is not how to imitate a brain more closely. It is what evolution actually found, and whether that finding has a cleaner form.
02 · The first era of AI
The founding move was never “copy the brain.” It was more precise than that. From McCulloch and Pitts through the perceptron, backpropagation, convolutional nets and the transformer, the field abstracted intelligence as networked computing elements, and then as a paradigm: network plus training plus inference. Today’s systems are already very far from the wet organ. They are still inside that abstraction.
Deep Learning can be an extremely capable path to intelligence without already being its most fundamental description. Transformers are not the opponent here. They are the strongest working instance of one abstraction, and that is exactly what makes the next question worth asking.
The biological example
It establishes that intelligence can emerge in a physical system.
03 · The level of abstraction
Birds show that flight is possible. Aerodynamics explains how wings can generate lift, including wings made very differently from a bird. The useful move is to understand the principle well enough to build another realisation.
01 / THE EXAMPLE
A living solution to flight.
02 / THE PRINCIPLE
Understand airflow and lift.
03 / ANOTHER REALISATION
A different structure. The same physics.
01 / THE EXAMPLE
A living example of intelligence.
02 / THE OPEN QUESTION
The equivalent of lift is still unknown.
03 / THE HYPOTHESIS
Test whether one evolving field is sufficient.
What is the equivalent of lift for intelligence?
For intelligence, that question is open. Hylæan explores whether a field with structured state, energy, dynamics and plasticity can be a useful answer. The analogy sets the research direction; experiments decide its value.
04 · The hypothesis
The working hypothesis is that a thought is not a token, a concept is not a label, and a memory is not a database row. All three are states of one dynamical system, stable or metastable. Such a system is described by four properties, and Hylaean is built out of those four and nothing else.
What is possible. The shape of the landscape, the basins that can exist.
What is stable. A valley that holds, or a ridge that cannot.
Where thinking goes. The field relaxes. It does not pick the next word.
What experience keeps. Learning changes the landscape itself, not a separate weight store.
05 · One dynamics, many regimes
If the hypothesis is even partly right, the usual catalogue of mental verbs is not a stack of modules. It is one physics read in different operating regimes.
Read the table as a research hypothesis, not as a report on twelve finished mechanisms.
06 · One substrate
Hylaean explores whether perception, memory, language and reasoning can share an evolving field, state.S. These are architectural goals; the explanations here do not establish how far each capability works.
Abstain is specified as a consequence of missing stability, not as a confidence
threshold bolted on afterwards. An answer may leave the system only when the field
itself has moved, and four gates have to fire together for that:
moved, energy_work, reached_answer and
not_echo. Where they do not, the honest output is abstain. That is a
design a reader can check rather than a promise that the system never guesses, and
the measurement section is where the checking happens.
07 · The hard ending
This is a research hypothesis, not a finished replacement for a brain. Its value must be established through experiments appropriate to each capability.
If the hypothesis is real, things should become visible that a story about capacity alone does not require. The five lines below are the open research agenda of this project, not a list of results, and each of them is also a way to be wrong:
What if intelligence isn’t a machine? What if it is a property of certain dynamical systems? Evolution found one. We are trying to understand the class.
The next section is the working metaphor for that class: a material that rings, rather than a network that looks up.
01 · The core idea
The following chapters explain the proposed architecture. Public demos and evaluation are coming soon.
In plain words
Strike a bell and it rings at particular notes. Those notes are not written down anywhere inside it, they follow from its shape. Hylaean holds what it knows as shape in the same way, and an answer is that shape coming to rest.
The origin chapter asked what evolution discovered. This page’s first working picture is a material, not a network. A piece of metal does not “know” what sound is. Yet strike it and it rings with resonances, modes and standing waves. That geometry is the knowledge. Hylaean is built to work the same way: intelligence as physics, not as a Python calculation.
weight += lrTransformers interpolate between what they have already seen. A field settles what it has never seen, because the answer is a stable shape of the physics, not a retrieved token.
02 · The one field
state.S: the brain itself
There is only one thing inside Hylaean's head: a single
continuous field called state.S. Imagine a huge elastic crystal.
Every point carries energy, direction, tension, momentum, couplings, and memories
of earlier deformations.
It is not memory. It is not a hidden state. It is not an embedding. It is the brain. A question, an answer, and a model of the world do not live in separate stores, they live as different regions of the same field.
03 · Knowledge is geometry
In Hylaean a concept is not a point in space, it is a valley (an attractor) in an energy landscape. Drop the field near it and it rolls in and rests. The deeper the valley, the stronger it pulls. Hover or tap the landscape below to disturb it.
Cat, dog and horse carve nearby valleys that share
geometry. From that overlap a higher valley, “animal”, appears
on its own. Nobody ever wrote animal =. It emerges.
Deep knowledge is not a longer vector. It is a richer topology: cat → animal → mammal → lives → moves → hunts → prey → night grows into a whole mountain range that all means “cat”.
04 · A question
A question is not a data structure. It is a boundary condition, like a stone dropped into still water. It sets the edges of the problem and lets the field run.
What spreads outward are not pieces of information. They are tensions waves that push the field out of balance and start it searching for rest.
05 · The answer
Once disturbed, the field does one thing: it tries to lower its energy. Like water finding its level, like heat spreading out, it relaxes until it reaches a stable resting state.
06 · Language
In plain words
The thinking is finished before any word exists. What is left is naming: something looks at the shape the field came to rest in and says which word fits it. If that step were clever enough to work out the answer itself, the field would not be the one thinking.
After the field settles, an idea already exists in its geometry. Language comes last: a simple decoder asks only one thing, “which words describe this shape?”, and reads them off.
The decoder is a sensor, not the thinker. The rule the project holds itself to:
“If you could remove the decoder and a normal program still knew the answer, then the architecture has failed.”
07 · Thinking
In plain words
A chat model produces one word, then the next, then the next. Here nothing is produced in sequence at all. The whole shape moves at once, the way a struck surface finds its note, and thinking is that movement running out.
A language model thinks token → token → token. Hylaean is meant to think differently: a disturbance grows into structure, structure collides, and structure fuses into one stable shape.
The map · three regimes
One scaffold makes everything below readable. The project measures intelligence in three separate regimes, and never lets one masquerade as another. Only the last one is the real frontier.
The field re-states a fact it was just handed. This is the mechanics of transport, decode and commit, useful as a sanity check but not intelligence.
Contract-declared organs settle answers to structured problems: arithmetic, sequences, symmetry. Booked in its own bucket, separate from what the raw field produced.
The open frontier is whether the field can determine what an unseen scene means and continue a structure by itself.
08 · Creativity
Why do genuinely new answers appear? Because two “mountains” that were never combined are forced to relax together.
Cat and water may never have met. Ask “Can a cat swim?” and both landscapes relax into a shared process, and a new valley forms. The answer was nowhere stored. It came into being.
09 · Learning
A neural network learns by nudging millions of weights. Hylaean learns by changing geometry. Use a connection often and:
This is the idea of well_depth: a concept that proves useful
deepens its own basin, so the field is pulled toward it more easily
next time. There is deliberately no back-propagation on the answer path
learning is a change of shape, not a training step.
10 · The field's grammar
In plain words
The field can do three things to itself. It can twist, so a state changes in place. It can bind, so two things belong together. And it can carry, so meaning moves from one place to another. Everything else is built out of those three moves.
The field has a tiny grammar of what it can do. These moves are learned, not hand-written, and each is a physical transformation of the field.
Torsion, the field's memory. It transports and twists state within a place.
The metric, it binds things together, complementary to the twist.
The only way to move content between places, discovered from examples.
The project investigates richer operations built from these three:
11 · Memory layers
In plain words
There is no separate database to look things up in. Remembering is how deep a groove in the landscape is: a fresh impression is a shallow dip that fades again, and something met often enough becomes a valley that stays.
The field has no separate database. What it “remembers” is layered into its own physics, each layer holding on for a different length of time. A moment passes through all of them, and leaves a deeper trace the further down it reaches.
state.SThe living state itself: the present moment. It is not storage, it is the thought currently happening. Disturb it and the trace fades within ticks.
K_fast / K_slowTwo timescales of the twist operator: a fast bank for short exposure and a slow bank for longer-term changes.
12 · Regions & networking
The one field is not a uniform blob. Its points organise into regions, a place for vision, a place for language, a place that holds the question, a place for a model of the world. Crucially, nobody names them in code. They are discovered by the field, emerging from how points cluster and couple.
Regions are wired together not by code but by operator structure: where the twist (K) is strong, where binding (L) holds, where transport (T) routes, where energy pulls. This difference between regions, their heterogeneity, is exactly what lets a question, a world model and an action carry different dynamics while living in the same field. Hierarchies appear on their own: cat, dog and horse share geometry, so a higher valley, “animal”, forms by itself.
13 · Microcells & tabs
Zoom into a region and you find microcells: local, programmable clusters of the field. Every tick, each one reads the field around it, runs a little local physics, and writes the result back, always through the field, never around it.
Each cell carries a short program tape (the “tabs”), only a few steps long. The tape rotates and updates only when it earns credit by being useful. This is how a flat sheet of points becomes a structured, programmable substrate, and it is the rung between raw points and full skills:
14 · Skills & chained skills
The skill hypothesis is that a reusable energy program can shape the landscape before relaxation, making a useful basin easier to reach.
A program is only kept when its class actually formed in the field and its own application serves correctly. That receipt is the skill. No proof, no crystallisation, so a skill is a certificate, not a habit that drifted in.
Facing a new problem the field runs a demo less selection: the program whose shape resonates with the current residual is the one that fires. When two are byte identical it refuses rather than guess. No Python interpreter chooses.
Everything stays field native: the program is a piece of energy, selection is resonance, the answer is a settled state, and a dumb decode reads it. The chain below is the shape a skill takes, fixed steps joined by typed hand offs, but it runs as landscape, not as code.
15 · Organs of the field
In plain words
Parts of the field specialise, the way tissue does in a body. An area that handles counting behaves differently from one that handles symmetry, yet both obey the same physics. Each area has to declare where it writes and which experiment proves it, or it gets removed.
Beyond regions and microcells, the field grows organs: contract-declared patches of the substrate with their own local dynamics, arithmetic, sequences, symmetry, analogy, a world model, a workspace. Each one must declare where it writes, what it reads, and which experiment proves it. No consumer on the answer path? It gets deleted.
16 · Causal program spine
In plain words
This is the single path every thought takes, from something arriving at the senses through to something being learned from the outcome. There is no second route and no shortcut around it.
The primary cognitive architecture is not the classical tower of microcells and tapes. It is the causal program spine: perception writes into the one field, residual pressure opens determination, a formation program crystallizes, an executor runs it, a typed commit lands or the system abstains, and a later encounter can be faster because the outcome left geometry behind. The tower stays as execution and locality infrastructure under that spine.
Target chain (architecture source of truth), read left to right in the animation:
The new synthesis. Hylaean can now use addressed causality: a producer and consumer sharing one typed address can learn a law, act on it and transfer it. The missing layer is field native contextual address formation, deriving the right frame, candidate set and late landing point from an open situation. See the four part address stack →
The operators and organs sections describe responsibilities; this section sketches how they connect to a candidate program and its output.
17 · Reasoning & deep reasoning
In plain words
The field does not reason because it was told to. It reasons because something does not fit yet, and that misfit is a physical tension. Thinking is the field working that tension down. When it cannot, saying so is the honest result.
Hylaean does not reason because a prompt told it to. It reasons when something does not add up, a gap between what it expected and what it actually sees. That gap (the residual) becomes a pressure in the field. On the causal program spine that pressure feeds determination (R3), then formation, execution, and commit or abstain.
Pressure opens a reasoning frame: a small nested workspace where the field can twist and bind without disturbing everything else. Deep reasoning is just this going deeper, a local segment where microcell programs and operator chains keep working until the residual shrinks. It is budgeted: when the pressure is gone, it stops, and a runaway is cut off by a health gate.
And if no stable shape ever forms, the honest result is to abstain, never a confident-sounding guess.
20 · Generative genesis
The fix is class different. A candidate is carried as a discrete winding, a twist in the field's phase that cannot be shrunk smoothly away, it would have to jump a real barrier. So several candidates coexist through the whole settle, kept apart by identity, not by amount. During a bounded construct window a gentle washboard energy holds the competing twists; when the window closes the field collapses to exactly one winner or honestly abstains, never many at once.
Hylæan / The shared evaluation
Declare the intended impact, measure under a frozen protocol, assess against explicit criteria, and record the change.
27 · The name
The name is borrowed from the Hylaean Theoric World in Neal Stephenson's novel Anathem: a timeless realm where perfect mathematical objects, the ideal circle, the truth that 2 + 2 = 4, exist independently of any mind that thinks them. It is the novel's version of an old philosophical position, mathematical Platonism: mathematical truths are not invented, they are discovered.
Knowledge is stored as millions of trained weights, a fitted approximation that lives entirely inside the particular network.
Knowledge arises as a stable attractor in a dynamic field, a shape the physics settles into, not a number looked up.
The structure itself exists independently of its carrier. An intelligent system does not invent it, it discovers it.
The aspiration is simple: the field should discover stable causal invariants rather than manufacture a plausible answer. The name is a direction, not a scientific claim.
If the field one day holds stable attractors of universal relations, answering will feel less like symbol manipulation, and more like navigating a Hylaean space.
If this works, an answer will feel less like searching a database, and more like dropping a stone into a pond and watching the ripples settle into a shape that was always the only stable one.
This is a philosophical interpretation, not an established scientific theory, but as a guiding metaphor for a field based AI it is honest about what it is: a direction, not a claim.
28 · Foundation
The structure borrows its discipline and vocabulary from TFPT (Topological Fixed-Point Theory), the ideas of a field on a carrier, twist and binding operators, transport between positions, and a gap that guarantees a single attractor. Hylaean takes the structure, not the physics predictions: it is an architecture for letting intelligence emerge as field physics.