Explaining
Explaining
5 topics × 10 subjects video-explainer arc. Janet narrates animated cards + D3.js / Cytoscape.js graphics over a HeyGen → Remotion → DaVinci Resolve pipeline. Scripts only here; rendering downstream.
version outline-v1
source explaining/outline.md
built 2026-05-24T20:33:04.165Z
NOT YET LIVE Stage 1–6 pipeline
Script (here) → Claude Design bundle → HeyGen narration → Remotion B-roll → DaVinci Resolve composition → S3 publish.
| ID | Subject | Profile | Script | Design | Record | Render |
|---|---|---|---|---|---|---|
| Topic 1 — Why theorem provers… instead of semantic searches | ||||||
1.1 | The hallucination tax — where LLMs lose at high stakes. | P1 | ✓ | ✓ | ✓ | — |
1.2 | What semantic search actually does (and doesn't). | P1, P5 | — | — | — | — |
1.3 | The Lean4 kernel — a 10kloc oracle for proof correctness. | P1 | — | — | — | — |
1.4 | Predicates as the LLM-Lean bridge — where judgment lives. | P1 | — | — | — | — |
1.5 | Negative verification — when the kernel says "no, that's not RICO." | P1, P2 | ✓ | ✓ | ✓ | — |
1.6 | Axioms vs. evidence — why we don't trust the LLM with everything. | P1 | — | — | — | — |
1.7 | Civil RICO walkthrough — predicate, sub-axioms, verdict. | P1, P2 | ✓ | ✓ | — | — |
1.8 | Title VI walkthrough — discriminatory intent has structure. | P1, P2 | — | — | — | — |
1.9 | Why this scales to financial contracts (and on to TREND/MOMENTUM). | P1, P3 | — | — | — | — |
1.10 | The cost — latency, surface area, and auditability as a feature. | P1, P5 | — | — | — | — |
| Topic 2 — Why narrative analysis… or Qnarre | ||||||
2.1 | The Family Court that ate the file — a real narrative-analysis use case. | P2 | ✓ | ✓ | ✓ | — |
2.2 | What is a "narrative" formally? — predicates over named entities. | P1, P2 | — | — | — | — |
2.3 | Three-zone Qnarre — input, kernel, witness. | P2, P5 | — | — | — | — |
2.4 | SSE event streaming — watching a proof elaborate live. | P2, P5 | — | — | — | — |
2.5 | From DOCX to Lean — how a complaint becomes a claim object. | P2 | — | — | — | — |
2.6 | RAv:p record citations — when the appendix is the source of truth. | P2 | — | — | — | — |
2.7 | Pro se on appeal — why ordinary people need this. | P2 | — | — | — | — |
2.8 | Counterfactual narratives — what a defense story has to deny. | P1, P2 | — | — | — | — |
2.9 | Federal civil RICO + § 1983 — stacking predicates. | P1, P2 | — | — | — | — |
2.10 | What Qnarre never does — write your brief for you. | P2, P5 | — | — | — | — |
| Topic 3 — Why result evaluations… or Qresev | ||||||
3.1 | Backtests lie — the survivorship + look-ahead industry. | P3 | — | — | — | — |
3.2 | Six defined-risk strategies, hard refusal of everything else. | P3 | — | — | — | — |
3.3 | TREND, MOMENTUM, OPTIONS-RISK, SECTOR, DRAWDOWN — five frameworks. | P3, P1 | — | — | — | — |
3.4 | Why sector-cap claims need a kernel, not a spreadsheet. | P3 | — | — | — | — |
3.5 | OHLCV parquet hub — the same bars feed every framework. | P3, P4 | — | — | — | — |
3.6 | Live evaluator walkthrough — portfolio in, verdict + witness out. | P3 | — | — | — | — |
3.7 | Drawdown as a theorem — the conservative PM's mandate. | P3 | — | — | — | — |
3.8 | Where the LLM lives — predicate judgments over price action. | P1, P3 | — | — | — | — |
3.9 | Aggressive vs. conservative — same kernel, different axioms. | P3 | — | — | — | — |
3.10 | What Qresev refuses — naked options, leverage, look-ahead. | P3 | — | — | — | — |
| Topic 4 — Why rigorous debates about… technical analysis | ||||||
4.1 | The TA bestiary — 117 indicators, mostly redundant. | P4 | — | — | — | — |
4.2 | TA-Lib as ground truth — the MACD EMA-realignment quirk. | P4 | — | — | — | — |
4.3 | DuckDB + Parquet — why columnar beats row-store for bars. | P4, P5 | — | — | — | — |
4.4 | Lightweight-charts v5 — rendering 10y of bars at 60fps. | P4 | — | — | — | — |
4.5 | Aggregators — small-multiples, heatmaps, Three.js surfaces. | P4 | — | — | — | — |
4.6 | Three competing PMs on the same feed — where disagreements live. | P3, P4 | — | — | — | — |
4.7 | The defined-risk options floor — why analyzing/ enforces it too. | P3, P4 | — | — | — | — |
4.8 | Alpaca IEX live + yfinance/Stooq — data sourcing tradeoffs. | P4 | — | — | — | — |
4.9 | GICS as the only acceptable "sector" referent. | P3, P4 | — | — | — | — |
4.10 | What an indicator is, formally — turning TA into testable predicates. | P1, P4 | — | — | — | — |
| Topic 5 — About Quantapix… the Jack and Janet startup | ||||||
5.1 | Two people, one repo — what "Jack and Janet" means. | P5 | — | — | — | — |
5.2 | The qagents monorepo tour — 12 subprojects, one venv, one workspace. | P5 | — | — | — | — |
5.3 | Claude Code as the third teammate — agents you can fire. | P5 | — | — | — | — |
5.4 | CLAUDE.md — writing instructions for the colleague who never reads twice. | P5 | — | — | — | — |
5.5 | memsearch — how Janet remembers what Jack told Claude last Tuesday. | P5 | — | — | — | — |
5.6 | The 5×10 video plan — made by Claude, for Claude to make. | P5 | — | — | — | — |
5.7 | Verifying/ + Evaluating/ — shipping two products from one kernel. | P1, P5 | — | — | — | — |
5.8 | The legal arc — from pro-se filings to a verifier product. | P2, P5 | — | — | — | — |
5.9 | The financial arc — from analyzing TA to evaluating portfolios. | P3, P5 | — | — | — | — |
5.10 | What Quantapix is betting on — kernels under everything. | P1, P5 | — | — | — | — |
| 4/50 scripted · 4/50 designed · 3/50 recorded · 0/50 rendered | ||||||
Metrics
- topicCount
- 5
- subjectsPerTopic
- 10
- totalScripts
- 50
- scripted
- 4
- designed
- 4
- recorded
- 3
- rendered
- 0