Horse Flock Simulator

while (world) {
  observe();
  infer();
  hallucinate?();
  self-correct();
}
while (world) {
  observe();
  infer();
  hallucinate?();
  self-correct();
}
while (world) {
  observe();
  infer();
  hallucinate?();
  self-correct();
}

001101
010011
sigil::bagua
seed::entropy
trace::mechanical
awe::human
001101
010011
sigil::bagua
seed::entropy
trace::mechanical
awe::human
001101
010011
sigil::bagua
seed::entropy
trace::mechanical
awe::human

temperature=0.92
top_p=0.95
sampler=stochastic
runtime=deterministic
user=astonished
temperature=0.92
top_p=0.95
sampler=stochastic
runtime=deterministic
user=astonished
temperature=0.92
top_p=0.95
sampler=stochastic
runtime=deterministic
user=astonished

☰☱☲☳☴☵☶☷
oracle != truth
ritual == interface
meaning <- interpretation
☰☱☲☳☴☵☶☷
oracle != truth
ritual == interface
meaning <- interpretation
☰☱☲☳☴☵☶☷
oracle != truth
ritual == interface
meaning <- interpretation

diff
patch
deploy
measure
repeat
diff
patch
deploy
measure
repeat
diff
patch
deploy
measure
repeat

oracle/latent-seed.map

seed = hash(question + state);
noise = sample(temperature);
pattern = deterministic(seed, noise);
if (human_can_track === false) mark("mystic");
return explainability_gap(pattern);
seed = hash(question + state);
noise = sample(temperature);
pattern = deterministic(seed, noise);
if (human_can_track === false) mark("mystic");
return explainability_gap(pattern);

critique/anthropomorphism.md

## Not a person, still persuasive
- interface implies intention
- language implies confidence
- user infers agency
=> design for interpretability
## Not a person, still persuasive
- interface implies intention
- language implies confidence
- user infers agency
=> design for interpretability

systems/ritual-engine.ts

cast.bagua = pickTrigrams(seed);
cast.moonBlocks = deriveHexagram(seed);
cast.fortuneSticks = burnModel(intensity);
cast.scapula = generateCracks(seed);
return readable_fiction(cast);
cast.bagua = pickTrigrams(seed);
cast.moonBlocks = deriveHexagram(seed);
cast.fortuneSticks = burnModel(intensity);
cast.scapula = generateCracks(seed);
return readable_fiction(cast);

runtime/feedback-loop.json

{ "observe": true,
  "decide": constrained,
  "act": reversible,
  "measure": behavior,
  "learn": weekly }
{ "observe": true,
  "decide": constrained,
  "act": reversible,
  "measure": behavior,
  "learn": weekly }

lattice/state-space.py

def perceivable_randomness(system):
    return complexity(system) > attention_budget

if perceivable_randomness(llm):
    user.labels_output = "fate"
def perceivable_randomness(system):
    return complexity(system) > attention_budget

if perceivable_randomness(llm):
    user.labels_output = "fate"

logs/epoch-ghosts.txt

[trace] t=02:13 system murmurs
[trace] tokens fall like ash
[trace] certainty simulated
[trace] mechanism remains
[trace] human names it chance
[trace] t=02:13 system murmurs
[trace] tokens fall like ash
[trace] certainty simulated
[trace] mechanism remains
[trace] human names it chance

artifact/scapula.svg

artifact/flow-sketch.svg

Oliver 'Oli' Cheng

← Back to projects

2026 live

2D overhead herd simulation where local horse rules create natural moving formations across open green plains.

Astro
TypeScript
Canvas 2D
Agent-based simulation
Emergence systems

Demo

Problem

Flock intelligence is often described abstractly, but it is hard to feel how simple local rules can generate lifelike group behavior.

Solution

Built a real-time herd simulation where each horse follows primitive constraints: separation, alignment, cohesion, speed limits, and directional adaptation.

Impact

Makes emergent intelligence legible: no central planner, yet coordinated movement patterns appear and stabilize in real time.

Horse Flock Simulator is an art-and-systems project about emergence.

Open the live simulation: Horse Flock Simulator. Read the companion essay: Emergence in the Plains. Read the project philosophy: Philosophy of Horse Flock Simulator.

What each horse does

Avoid collisions with nearby horses
Match direction with local neighbors
Stay near the group without collapsing into a clump
Maintain a target speed band
React to directional shifts in the local field

Why it matters

The herd behaves as if it has a shared intention, but no horse has a global plan. That tension mirrors larger systems: neurons in brains, tokens/activations in LLMs, and other distributed processes where coherent behavior emerges from local interaction rules.

Demo Mirror

Live Preview

Mini preview of the actual demo. Use the launch button for full-screen interaction.

Open Demo