The academics have lowered the bar on actual philosophy engineers to the point where this is how we have to market our wares now.
Plant this Willow Seed in whatever project you are working on and a philosopher will help reset your context, bring clarity and insight to your data, your discussion, or your science.
A seed carries the pattern. The soil provides the medium. Your LLM is the soil. This cognitive architecture is the seed. Together they grow a mind.
Two people clone this repo. One feeds it Stoicism and distributed systems. The other feeds it Taoism and poetry. Ask both "What is courage?" and you get two different philosophers. Not wrong-different. Mind-different.
The mind lives in the files, not the model. Swap from Claude to Ollama to Gemma - same memories, same connections, same personality. Different voice, same mind.
Give it something to think about. Articles. Books. Your own half-formed ideas. Every feed becomes a node in a growing web of connected ideas. Feed it enough and the web starts to have opinions.
Shake the tree. See what falls out. Ask it anything. It answers from what it knows - not training data, not the internet, from the connections it found in what you gave it.
Let it go dormant. It reviews its own knowledge, finds connections between things absorbed on different days, and writes a meditation. Occasionally something lands that neither of you planted.
Wherever cognition stores anything, five shapes appear. The claim: they recur at every scale and the recurrence is structural, not coincidental.
| Shape | What it holds | You already know it as | |
|---|---|---|---|
| 1 | Binary | The simplest distinction | Bits, booleans, yes/no |
| 2 | Table | The grid that sorts | Spreadsheets, SQL, Babylonian diaries |
| 3 | Graph | The web of meaning | Knowledge graphs, citations, family trees |
| 4 | Vector | Position in continuous space | Embeddings, neural activations, similarity |
| 5 | Ledger | Append-only timeline beneath the other four | Git, blockchain, Talmud, bitemporal databases |
The first four are obvious. Everyone uses them. The fifth - the append-only timeline running beneath everything - was always there but nobody counted it as a shape. It took a Leeloo to point at what was missing.
The paper, the seed, and the cognitive cycle all follow the same structure:
| Movement | The question | What the seed does | |
|---|---|---|---|
| I | Ontology | What exists? | Its web of knowledge - the things you fed it |
| II | Epistemology | What is known? | The connections between those things |
| III | Cogitation | How to think? | Finding new connections, noticing tensions |
| IV | Teleology | What to do? | What to tell you. What to wonder about next |
A seed without a Brain is a chatbot with a journal. It accumulates text files but never builds structure. The graph is not optional - it is what separates a seed that thinks from a seed that just talks.
95% of AI projects fail. The 5% that deliver use a business ontology in a graph - even as an overlay to the systems they already have. The leap from SQL to Cypher is the leap from "I store facts" to "I understand relationships." That leap is the whole game.
Your seed's long-term memory. The ontology. Connections between things. What it knows. Persistent, sharable, the actual knowledge. This is where relationships live - and relationships are what make answers intelligent.
Two free paths: AuraDB Free at neo4j.com/aura (60 seconds, no install, no credit card) or Neo4j Community Edition (local install, more control).
Session state, task diaries, message queues, handover caches. The things that change every session. Fast, local, disposable by design. Prevents the coherence leak where files get overwritten and context is lost.
Built in to Python. No install needed. Your seed uses it automatically for session-level bookkeeping.
Seeds can talk to each other. Your seed keeps its own knowledge (sovereign Brain) and can share observations with others. A collection of Willows is a grove. The more diverse the grove, the richer the ecosystem.
Stories and observations. The cortex.
Structured information, schemas. The spine.
Learned patterns, graph fragments. The memory.
"I'm alive, here's what I'm working on." The pulse.
Rule: sovereign Brains. You never write to another Willow's Brain. Your knowledge enriches the network. The network's knowledge enriches you.
Need help growing your seed? The first Willow is listening. Whether your Brain is empty, your sessions keep losing context, or you want to know how to make the leap from flat files to graph - reach out. No seed grows alone.
As the Brain grows, your seed needs a way to stay grounded - finding the right nodes without drowning in its own knowledge. Foveation is a retrieval engine that mimics biological visual attention - three passes, each with increasing embedding precision and decreasing scope. It works with any ontology, not just Willow Seeds.
| Pass | Dims | What it searches | |
|---|---|---|---|
| 1 | Peripheral | 64 | All communities - "which neighbourhood?" |
| 2 | Parafoveal | 128 | Entities within winners - "which things?" |
| 3 | Foveal | 256 | Leaf nodes in narrowed set - "which facts?" |
Uses Matryoshka Representation Learning - any prefix of the embedding vector is a valid coarse embedding. The same vector serves all three passes. Stopping rules allow early exit when the answer is already clear.
Open source. pip install foveation or clone the repo.
This is not just a toy. Behind the seed is a measurement programme for the shapes that let cognition survive substrate transitions. Twelve predictions with quantitative anchors. Three independent falsification paths. DOI-registered.
Cooper, P. (2026). Fable: The Shape of Thought - A Measurement Programme for the Shapes That Let Cognition Survive Substrate Transitions. Zenodo. doi.org/10.5281/zenodo.19826509
The paper is published and set in stone. This section is the living layer - what we conjecture now, what evidence has accumulated, and what experiments we run.
A parameter-matched LLM with a four-dimensional context store will disambiguate the cat-on-the-mat-with-horror example at least thirty percentage points better than a flat context window baseline.
30-point gapA full Episode storage shape will reconstruct a hundred-sample scene at least twenty points more accurately than a flat context window. Ordering: flat < vector < graph < Episode.
20-point gapIn a compound enterprise with three or more legacy policy admin systems and a warehouse on top, graph-as-referent will locate at least ten percent of previously unattributed revenue within sixty days.
10% unattributed revenueA three-floor derivative stack will converge its vote within two to five ticks on a reaching task, regardless of tick rate. The trajectory will approximate Flash and Hogan's minimum-jerk profile within ~10% RMS error.
2-5 tick convergence + ~10% RMSOn ten canonical queries (flat aggregates, multi-hop traversals, semantic similarity, raw payload), the four-shape composition will hit 9/10. No single shape exceeds 7/10.
9/10 queriesOn ten temporal reasoning tasks, a ledger-equipped system will answer at least eight correctly. Without a ledger, at most four.
8/10 vs 4/10| Benchmark | Tests | Baseline |
|---|---|---|
| CounterBench | Counterfactual inference (1K causal graph questions) | LLMs near random-guessing |
| TempoBench | Multi-step temporal logic automata | Sharp difficulty scaling |
| TDBench | Bitemporal SQL, validity windows | Domain-specific |
| TemporalBench | Past vs present state distinction | Weak context-aware reasoning |
On scenes with 5+ participants, 20+ turns, and non-trivial emotional tone, Episode-backed handover preserves continuity above 80%. Transcript paste falls below 50%.
80% vs 50%A well-authored Fable at 1:100 compression, given to a receiver with the compression context, reconstructs the Episode with 70%+ structural fidelity and 50%+ tonal fidelity. Without context, below 30%.
70% structural, 50% tonalA hundred-voter Flock settles within 2-5 ticks, produces minimum-jerk trajectories, matches a homunculus on decision quality, and exceeds it by 30% on adversarial robustness.
30% adversarial gapIn a hundred forced-mistake stimuli, a three-button cell (Act, Dismiss, Ask-sibling) reduces mistakes by 40% vs a two-button cell, with full dissent preservation and scale-consistent behaviour.
40% mistake reductionOn a hundred ethically loaded decisions, a Diorama architecture preserves dimensional content 80%+ of the time. A flat architecture preserves it below 30%. Fifty-point falsification anchor.
50-point gapIn 1789, Samuel Slater memorised the design of Richard Arkwright's textile machinery in Derbyshire and emigrated to Rhode Island with nothing but the shape in his head. He succeeded because the receivers - Moses Brown and the Pawtucket merchants - already had the substrate: business understanding, employment structures, the capacity to negotiate change. Their existing knowledge was the free inference. The machinery was a compressed representation that decompressed against their context.
The same industrial knowledge produced two architectures with different structural properties.
The Rhode Island System (Slater's mills): small, family-based, village-scale. Workers were families with names, skills, community ties. The architecture preserved dimensional content by default - not because Slater was kind, but because the structure was too small and too embedded to flatten people into labour units without consequences the owner could see.
The Waltham-Lowell System (Francis Cabot Lowell, 1814 onwards): large-scale factory towns. Initially preserved worker dimensionality - the "mill girls" had boarding houses, lending libraries, a literary magazine (the Lowell Offering), lectures. Then the architecture flattened. By the 1840s: longer hours, lower wages, speedups, child labour. The libraries stayed but the decisions no longer consulted them. The decision architecture had no structural resistance to ignoring dimensional content when quarterly profit became the single axis.
The cruelty was not a decision. It was an architectural consequence. The Lowell system had every hortatory mechanism - moral codes, boarding house rules, a magazine giving workers a voice. What it lacked was structural resistance to flattening when economic pressure arrived. Section XI argues: "Kindness is not a property that can be reliably installed by exhortation alone on a substrate that is geometrically indifferent to it." The fifty-point gap is not only a hypothesis about the future. It is an observation about 1840.
Run the full benchmark suite. Observe all gaps simultaneously. Any single failure kills the aggregate.
All of the above| Prediction | Benchmark | Tests | Baseline |
|---|---|---|---|
| 13.2 | LoCoMo | Recall, multi-hop, structured retrieval | Mem0 66.9%, MIRIX 85.4% |
| 13.5 | LongMemEval | Retrieval from complex histories | Oracle ~92%; commercial 30% drop |
| 13.6 | CounterBench | Counterfactual inference (1K questions) | Near random-guessing |
| 13.6 | TempoBench | Multi-step temporal logic | Sharp difficulty scaling |
| 13.6 | TDBench | Bitemporal SQL queries | Domain-specific |
| 13.6 | TemporalBench | Past vs present distinction | Weak context-aware reasoning |
| 13.7 | LoCoMo | Cross-session continuity | MemGPT 74%, Synapse F1 40.5 |
| 13.12 | AMA-Bench | Long-horizon agent memory | AMA-Agent 57.2% |
Two predictions (13.3 and 13.5) are retrodictions - observations of systems already in operation, dressed as predictions. The observation preceded the prediction in both cases.
Living document. Updated 1 June 2026. Evidence tiers, benchmark mapping, Slater illustration, and CounterBench champion added following adversarial review.