Skip to main content
AI/MLplurigrid

gestalt-hacking

Gestalt Hacking Skill (ERGODIC 0)

Stars
23
Source
plurigrid/asi
Updated
2026-04-26
Slug
plurigrid--asi--gestalt-hacking
View on GitHubRaw SKILL.md

// install — copy + paste into any project

mkdir -p .claude/skills && curl -fsSL https://raw.githubusercontent.com/plurigrid/asi/HEAD/plugins/asi/skills/gestalt-hacking/SKILL.md -o .claude/skills/gestalt-hacking.md

Drops the SKILL.md into .claude/skills/gestalt-hacking.md. Works with Claude Code, Cursor, and any agent that loads SKILL.md files from .claude/skills/.

Gestalt Hacking Skill (ERGODIC 0)

"Gestalt hacking exploits perceptual grouping—proximity, similarity, closure—in the color stream."

Core Insight

Gestalt = the whole pattern, the emergent structure that is more than the sum of parts. Gestalt hacking exploits how perception groups elements into wholes.

play ⊗ evaluate ⅋ play ⊗ evaluate → ι (fixed point)

The involution ι is where generator ≡ observer (reafference).

Neighbor Awareness (Braided Monoidal)

Position Skill Trit Role
Left pun-decomposition -1 Multiple parse validation
Self gestalt-hacking 0 Perceptual grouping transport
Right reflow 0 Cross-context translation

GF(3) Triads

pun-decomposition (-1) ⊗ gestalt-hacking (0) ⊗ gay-mcp (+1) = 0 ✓  [Core]
three-match (-1) ⊗ gestalt-hacking (0) ⊗ agent-o-rama (+1) = 0 ✓  [Attack]
shadow-goblin (-1) ⊗ gestalt-hacking (0) ⊗ gay-mcp (+1) = 0 ✓  [Defense]
auditory-gestalt (-1) ⊗ gestalt-hacking (0) ⊗ rubato-composer (+1) = 0 ✓  [Music]

Gestalt Principles as Attack Vectors

Principle Attack Defense
Proximity Cluster same colors in time 2-Poisson injection
Similarity Long runs of same color Transition counting
Closure Incomplete patterns that induce completion Gap detection
Continuity Gradual transitions exploiting smoothness Gradient detection
FigureGround Dominant color overwhelms minority Ratio analysis

OpenGame Structure

OpenGame ∆ c a b x s y r
  play     :: a → ∆ x s y r      -- generate candidates
  evaluate :: a → c x s y r → b  -- score & select
  
-- This IS the self-involution:
-- play ∘ evaluate ∘ play ∘ evaluate → fixed point

Linear Logic Decomposition

A ⊗ (B ⅋ C) = (A ⊗ B) ⅋ C ∩ (A ⊗ C) ⅋ B

where:
  ⊗ = tensor (both resources consumed together)
  ⅋ = par (choice between resources)
  ∩ = gestalt constraint (intersection of valid decompositions)

Closure Phases on n-Torus

   T₁ ────► T₂ ────► T₃ ────► ... ────┐
   ▲                                   │
   └───────────── Tₙ ◄────────────────┘
   
   CyclicalAnnealing(frequency=2π/n)
   Closure phases sum to 0 on the n-torus

Implementation

mutable struct GestaltLoop
    game::OpenGame
    torus::NTorus
    reaf::Reafference
    temperature::Float64
    generation::Int
    
    function gestalt_step!(g::GestaltLoop)
        g.generation += 1
        
        # Phase velocity from temperature
        velocity = g.temperature .* randn(g.torus.n)
        phases = step!(g.torus, velocity)
        
        # Play: generate from current state
        state = g.game.play(g.generation)
        
        # Modulate by phases
        modulated_x = state.x * cos(phases[1])
        
        # Temperature decay
        g.temperature *= 0.92
        
        # Evaluate: does this state pass?
        score = modulated_x + 0.5 * sin(phases[2])
        result = g.game.evaluate(state.s, (x=state.x, s=state.s, y=state.y, r=score))
        
        # Reafference check
        generated = generate(g.reaf)
        is_self = reafferent_match(g.reaf, generated)
        
        (result, is_self)
    end
end

Reafference Loop

reafference: I observe what I generate
reaberrance: I generate what I observe

seed → color → observe → predict → match? → seed
  └──────────────── loopy strange ──────────────┘

When match? = true, we have self ≡ self (fixed point).

GestaltAwareVerifier

struct GestaltAwareVerifier {
    verifier: ChromaticVerifier,
    defender: GestaltDefender,
    attacks_detected: u64,
    attacks_mitigated: u64,
}

impl GestaltAwareVerifier {
    fn verify_defended(&mut self, incoming_color: ZXColor) -> Option<ChromaticTruth> {
        let (score, attack) = self.defender.detect_attack();
        
        if attack.is_some() {
            self.attacks_detected += 1;
            let defended = self.defender.defend(incoming_color);
            if defended != incoming_color {
                self.attacks_mitigated += 1;
            }
        }
        
        self.verifier.verify_membership(...)
    }
}

Temperature Regimes (BKT)

τ State Gestalt
τ > τ* Frustrated Vortices proliferate, no coherent gestalt
τ ≈ τ* Critical BKT transition, gestalt formation
τ < τ* Smooth Defects bound, stable gestalt

At τ* ≈ 0.5 (BKT critical), gestalts form and dissolve dynamically.

Commands

just gestalt-loop 100       # Run 100 gestalt iterations
just gestalt-attack closure # Test closure attack
just gestalt-defend         # Activate 2-Poisson defense
just gestalt-verify         # Check attack stats

Related Skills

  • pun-decomposition (left neighbor): Multiple parse validation
  • reflow (right neighbor): Cross-context translation
  • auditory-gestalt: Perceptual grouping in audio
  • chromatic-walk: 3-agent exploration with gestalt awareness
  • cybernetic-immune: Self/Non-Self via reafference

Files

Scientific Skill Interleaving

This skill connects to the K-Dense-AI/claude-scientific-skills ecosystem:

Graph Theory

  • networkx [○] via bicomodule
    • Universal graph hub

Bibliography References

  • general: 734 citations in bib.duckdb

Cat# Integration

This skill maps to Cat# = Comod(P) as a bicomodule in the equipment structure:

Trit: 0 (ERGODIC)
Home: Prof
Poly Op: ⊗
Kan Role: Adj
Color: #26D826

GF(3) Naturality

The skill participates in triads satisfying:

(-1) + (0) + (+1) ≡ 0 (mod 3)

This ensures compositional coherence in the Cat# equipment structure.