Metacognitive Walker & Void Attention

Daisy chain monitoring layers, Glossolalia/Vickrey table analysis, metacognitive monitoring, void attention, chain convergence proofs.

ForkJoin MCP Server · Superserver · 41 tools · llms.txt
MCP Endpoint Full Docs Discovery

Tools

daisy_chain

Analyze Daisy Chain of monitoring layers with geometric convergence

glossolalia_engine

Vickrey Table sparse logit lookup analysis for agent inference

metacognitive_monitor

Stack metacognitive monitoring layers with detection rates

void_attention

Attend to what was NOT chosen -- void attention distribution

chain_convergence

Prove geometric convergence rate of metacognitive chain

five_bules

Compute a Five Bules personality profile. The five words -- Try (Fork), Choose (Race), Commit (Fold), Let Go (Vent), Learn (Interfere) -- each measure distance from phi along one axis. A spike indicat...

void_gain_index

Compute the Void Gain Index (VGI). VGI = (K_perceived - 1) / (K_actual - 1). When VGI = 1.0, the walker matches the terrain. When VGI > 1.0, the brain tracks phantom forks (rumination, anxiety). When ...

ocean_comparison

Compare the Five-Bule personality model with OCEAN (Big Five). Partial overlap, not equivalence. Openness loads on Try+Learn (2 primitives). Conscientiousness loads on Commit+Choose (2 primitives). Ne...

system_observation

Run metacognitive observation across all daemon void boundaries. Returns C0-C3 scores, daemon health map, cross-daemon correlations, convergence ratio, and actionable alerts. C0=generation health, C1=...

daemon_health_check

Check health of a single daemon from its rejection history. Returns convergence ratio, dominant rejection dimension, entropy, and dimension count.

resolve_alert

Get actionable remediation commands for a metacognitive alert. Returns shell commands that can be executed to investigate or resolve the issue.

thm_daisy_purity

The logit projection W * embedding[t] is a pure function of the token ID. Unlike transformers (where output depends on full attention context), Markov chains have no context dependence. Same token alw...

thm_daisy_linearity

Matrix-vector multiplication distributes over the linear state transition: W(α*e[t] + (1-α)*s) = α*(W*e[t]) + (1-α)*(W*s). This means precomputed logits can be interpolated at runtime with zero error....

thm_precomputation_validity

The precomputed Vickrey Table produces exact results. Cached interpolation logits = α * table[t] + (1-α) * prevLogits equals the full matVec logits = W * state, by THM-DAISY-LINEARITY. Zero approximat...

thm_topk_deficit

Storing top-K logits per token is a semiotic fold at build time: vocabSize paths collapsed to K paths, deficit = vocabSize - K. The vented logits are nuance paths that don't survive the build-time fol...

thm_absorbing_state

Linear Markov chains with α < 1 converge geometrically to fixed points. After n steps: state = (1-(1-α)^n)*e[t] + (1-α)^n*s₀. For α=0.7: 97.3% convergence in 3 steps. If argmax(W*e[t]) = t, token t is...

thm_glossolalia_completeness

The precomputed Vickrey Table is a complete representation for linear Daisy Chain language models. Any model in this class can be fully captured by its table, with inference on the table producing ide...

thm_identical_trivial_fold

When all agents in a Daisy Chain MOA have the same α and same projection W, they produce identical logits. The deficit-weighted fold assigns equal weights (1/k). k-1 agents are wasted. This is the for...

thm_diverse_alpha_divergence

Agents with different mixing coefficients α₁ ≠ α₂ produce different hidden states after one step from any non-trivial starting state (s ≠ x). Proof by contradiction via `(α₁ - α₂)(x - s) = 0`. Differe...

thm_moa_cost_with_vickrey

The marginal cost of adding one agent to a Vickrey-backed MOA is V (vocabulary size), independent of hidden dimension d. Without Vickrey: V*d per agent. Savings per agent: V*(d-1). For SmolLM2-360M (d...

thm_moa_deficit_decomposition

The total deficit decomposes additively: Δβ = (k-1) + (V-K). Fold deficit (k-1) is structural (unavoidable). Table deficit (V-K) is a design choice (K is the knob). Minimum: k-1 (full table). Maximum:...

thm_diversity_necessary

For a MOA fold to extract more information than a single agent, agents must produce different logit distributions. Identical agents contribute zero marginal information. Effective agent count = number...

thm_daisy_chain_moa_design

The design prescription: total deficit is minimized when agents are diverse (different α or W) and the Vickrey Table is maximal (K → V). Full table + diverse agents achieves minimum deficit k-1. Singl...

thm_meta_converge

Metacognitive walker C0-C1-C2-C3 cognitive loop on void surface: eta remains bounded, exploration stays within configured bounds, gait is always a valid cognitive level, inverse Bule measure is non-ne...

thm_five_bule_personality

Personality is five measurable Bule distances along fork/race/fold/vent/interfere axes. Try=Fork (eta), Choose=Race (temperature), Commit=Fold (commitGain), LetGo=Vent (decayRate), Learn=Interfere (fe...

thm_phi_attractor

All five personality dimensions converge to phi_inv = (1+sqrt(5))/2 - 1. Distance from phi_inv is the Bule (deficit) along each axis [LEDGER: THM-PHI-ATTRACTOR]

thm_bule_spike_detection

A person's pathology is a spike -- one Bule much higher than the others. measureBules() identifies the spike dimension [LEDGER: THM-BULE-SPIKE-DETECTION]

thm_seven_layer_stack

Rejection propagates through seven personality layers with timescale-appropriate attenuation: mental health 1.5x (amplified), behaviors 0.8x, traits 0.1x, temperament/culture 0.01x [LEDGER: THM-SEVEN-...

thm_ocean_partial_overlap

OCEAN (Costa & McCrae 1992) partially overlaps but is not equivalent to Five-Bule. Openness loads on Try+Learn (2 primitives). Conscientiousness loads on Commit+Choose (2 primitives). Neuroticism is a...

thm_personality_weighted_complement

Personality parameters modulate the Buleyean complement distribution: eta controls softmax sharpness, commitGain scales rejection counts, decayRate fades old rejections, feedbackGain scales deviation ...

thm_python_personality_mirror

Python implementation mirrors TypeScript: same five parameters, same derivation, same complement distribution, same stack propagation [LEDGER: THM-PYTHON-PERSONALITY-MIRROR]

thm_frf_positivity

0 < K for K >= 1 [LEDGER: THM-FRF-POSITIVITY]

thm_frf_rejection_count

1 <= K-1 for K >= 2 [LEDGER: THM-FRF-REJECTION-COUNT]

thm_frf_system_converges

Any ForkRaceFoldSystem converges [LEDGER: THM-FRF-SYSTEM-CONVERGES]

thm_frf_failure_more_info

K-1 > 1 for K >= 3 [LEDGER: THM-FRF-FAILURE-MORE-INFO]

thm_frf_void_grows

Void boundary grows monotonically [LEDGER: THM-FRF-VOID-GROWS]

thm_frf_deficit_decreases

Deficit non-increasing under learning [LEDGER: THM-FRF-DEFICIT-DECREASES]

thm_frf_deficit_converges

Deficit reaches zero or floor [LEDGER: THM-FRF-DEFICIT-CONVERGES]

thm_frf_observer_separation

Data path strategy != observer strategy [LEDGER: THM-FRF-OBSERVER-SEPARATION]

thm_frf_five_properties

Any FRF system satisfies all five properties [LEDGER: THM-FRF-FIVE-PROPERTIES]

thm_mindfulness_converges

Iterating self-reflection converges [LEDGER: THM-MINDFULNESS-CONVERGES]

Discovery Endpoints

Paper Reference

From "Being Irreversible" by Taylor William Buley.
LEDGER sections: Daisy Chain, Glossolalia & MOA, Metacognitive Walker & Void Attention
Read the paper at Wallington Lab