GreaterFool

Live in productionFree account required

Talk through a risky decision and see the exact odds next to the plain bottom line before you commit.

GreaterFool showing its home page with a sample question about taking a bet

Current status

Production-ready decision and risk analysis web app at ftt.ngi.video with multi-model OpenRouter routing; requires a free account.

Overview

Production-ready decision workbench based on cognitive psychology's Fuzzy-Trace Theory—placing exact financial odds side-by-side with the real-world bottom line so you can reason clearly under risk.

Why it was built

Spreadsheets and standard AI chatbots reduce big life or financial choices to a single average number, ignoring whether a bad outcome could wipe you out.

Why it helps

Shows both the exact numerical math and the plain-English categorical risk side-by-side, flagging common psychological framing traps and verifying claims before you commit.

What you can do

Side-by-side breakdown of exact financial math vs. real-world bottom-line downside
Automatic alerts for framing traps like loss aversion, sunk-cost thinking, and false certainty
Rolling OpenRouter model fallback chain with hallucination and negation parity checks
Live interactive decision studio with subscription and credit metering at ftt.ngi.video

GreaterFool • Core Technology & Feature Architecture

Fuzzy-Trace Theory (FTT) Dual-Representation Workbench & Verbatim Math Healer

Places categorical bottom-line Gist intuition (catastrophic ruin vs. bounded downside) side-by-side with deterministic expected-value math while stress-testing assumptions with adversarial personas.

SCI-01 Math Auto-Healer

Deterministic Expected Value, StdDev & CV Recomputation

Intercepts LLM probability-payoff tables in Python and TypeScript to recompute exact expected value (EV), standard deviation, and coefficient of variation before rendering.

Gist vs. Verbatim

Parallel Categorical Risk & Framing-Trap Detector

Runs parallel Gist Extractor, Verbatim Extractor, and Decision Integrator pipelines to separate non-compensatory ruin thresholds from noisy expected-value averages.

4-Tier Evidence Grounding

Negation Parity Invariant & Polarity-Flip Rejection

Verifies every extracted claim against source documents across Exact, Normalized, SlidingWindow, and TokenBag tiers while rejecting single-negation polarity flips.

Circuit-Breaker Router

20-Call Sliding Window Health Tracker & Failover

Tracks live OpenRouter model health across a 20-call window, tripping a 60-second cooldown on HTTP 429/502/503/504 and promoting healthy fallbacks non-destructively.

Before & After Engineering AuditFuzzy-Trace Theory Decision Science100% deterministic EV/σ/CV math · 4-tier negation-parity grounding

FTT Gist + SCI-01 Verbatim math healer vs. hallucinated LLM expected value

Comparison focus

Before: Chatbot arithmetic hallucination & single-number EV blindness

Standard LLMs routinely miscalculate probability-payoff tables and recommend positive-EV bets that carry an unacceptable risk of catastrophic ruin.

// Unverified LLM financial advice
"With 65% chance of +$240k and 35% chance of -$40k,
 your expected value is ~$175k! You should definitely take the bet."
// Hallucinated EV ($175k vs $142k) & ignores whether -$40k causes ruin

After: Deterministic EV / StdDev / CV auto-healer + categorical ruin Gist

GreaterFool intercepts extracted probability tables to recompute exact EV, standard deviation, and CV deterministically while pairing them with Fuzzy-Trace Theory categorical Gist risk.

// GreaterFool SCI-01 Auto-Healer + FTT Dual Representation
verbatim = healVerbatimDecisionMath([{ p: 0.65, x: 240 }, { p: 0.35, x: -40 }])
// -> EV: +$142.0k, stdDev: $133.73k, CV: 0.942
gist = "Positive expected return, but carries non-zero downside exposure"

CV & VLM rubric shift: 0.7725 → 0.957 (+0.1845 · Sharpness +53.2% · PSNR 44.93 dB)

Grounding gate: Negation parity & evidence verified

Interactive walkthrough

Step through how GreaterFool works without creating an account or installing local dependencies.

Entry & problem context

Maturity: Live in production

Spreadsheets and standard AI chatbots reduce big life or financial choices to a single average number, ignoring whether a bad outcome could wipe you out.

Shared platform architecture sandbox

Test the live cross-language single source of truth shared across TypeScript, Python, and Rust.

Evidence grounding & negation parity check

Source evidence passageAssistant claim snippet to verify

Grounding tier: RejectedPolarityFlip (grounded: false, overlap: 1)

Socrates epistemic decision: clarify (confidence: 0.425)

Dual-gate write receipt verifier (DAWRI) & FTT math healer

Assistant response draftSimulate committed database write receipt (committedWrites.length > 0)

Unbacked claim stripped: true

Sanitized output: No profile changes were committed in this turn.

FTT verbatim math healer: EV 142, σ 133.5515, gist positive_ev_with_downside

Hick-Hyman EIG chips: Remote or hybrid? · Target salary floor? · Company stage? (lockout: false)

Semiotic Brand Identity & Federated SoC Governance

Peircean Brand Mark, Multi-Size Squint Test & 3-Tier SoC Boundary

SoC tier: internal_commercial16px rubric: 96.7% (PASS)

16px · 32px · 48px squint test

Motif: contrarian_candle

Iconic sign: Ascending & descending market candlesticks intersected by a contrarian alpha chevron

Indexical cue: Consensus overcrowding divergence and regime-shift signal

Symbolic archetype: Emerald quantitative alpha and disciplined risk asymmetry

SoC Boundary & Epistemic Retrieval Guardrails

Visibility & ceiling: private_commercial (max tier: internal_commercial)

Boundary policy: Commercial FTT cognitive calibration & decision analysis engine.

4-gram shingle novelty: 100.0% (non-redundant >15%) · Retired symbol trap: Clear (0 retired symbols)

GitHub Profile & Source Activity

Engineering Velocity & Open-Source Hygiene

Synced from @brbrainerd and @vox-foundation via the GitHub GraphQL API (GET /api/github/stats).

GitHub Profile vox-foundation/vox

Annual GitHub activity

13,842+

3,229 public · 10,136 private revisions

Curated portfolio history

19,523+

Revisions across 32 curated projects

Pull requests & reviews

463 PRs

Merged across 70 first-party codebases

GreaterFool historyTypeScript

218 revisions

575 tracked source files · Updated 2026-10-19

Language distribution across curated projectsWeighted by revision history & source volume

TypeScript38.9% (12 projects)

Rust36.9% (1 project)

Python11.3% (8 projects)

JavaScript4.7% (2 projects)

Lua4.1% (1 project)

Public open-source codebases on GitHub

vox-foundation/voxRust · 7,200 rev

Single-file full-stack programming language and Rust compiler that generates database schemas, server routes, and typed clients from one declaration.

#programming-language#rust#compiler#full-stack#lsp

brbrainerd/govSimTypeScript · 435 rev

Interactive political economy simulator with ECS civic rights, institutional modeling, policy levers, and multi-regime scenarios.

#simulation#political-economy#typescript#ecs#strategy-game

brbrainerd/neurogeckoHTML · 6 rev

Interactive 3D macaque brain atlas and stereo surgical view planner rendered in browser WebGL.

#neuroscience#webgl#threejs#brain-atlas#3d-visualization

brbrainerd/brFrameTypeScript · 23 rev

Single-binary Rust and React kiosk shell for Raspberry Pi digital photo frames with remote mobile upload.

#rust#raspberry-pi#kiosk#embedded#react

Open GreaterFool Browse all projects