---
type: "synthesis"
tags: ["synthesis", "maintenance", "principle"]
spans: ["video", "paper"]
id: "synthesis-edit-source-as-dialogue-evolution"
sources: ["cross-day"]
---
# Synthesis: Edit-Source Principle Closes the Dialogue Loop

The video frames the creation step: extract dialogue → encode as skill ([[framework-skill-creation]], [[action-codify-voice]]). The paper frames the **maintenance** step: [[concept-edit-source-principle]] / [[quote-edit-source]]:

> *"Editing the output fixes this run. Editing the source fixes every future run."*

## The full loop

Together the two sources describe a complete lifecycle:

1. **Author** — extract latent dialogue structure into markdown ([[framework-skill-creation]]).
2. **Run** — single orchestrator traverses folders ([[concept-icm-d2]], [[framework-icm-architecture]]).
3. **Review** — human edits at stage gates ([[action-review-gates]], [[claim-ushaped-intervention]]).
4. **Diagnose** — if output is wrong, trace back to which layer is wrong: L2 contract? L3 reference? L1 routing? ([[concept-five-layer-hierarchy]])
5. **Repair** — edit the source layer ([[concept-edit-source-principle]]). Future runs inherit the fix.

## What the paper concedes

Doing step 4 systematically — automated trace from a wrong phrase to its causing source — is **future work** ([[question-semantic-debugging]]). Right now it's a manual discipline.

## What the video implies but doesn't say

The edit-source principle is the natural successor to dialogue extraction. The first chat is the proto-source; subsequent edits refine the source. The skill is a **living document**, not a snapshot.

See [[synthesis-glass-box-meets-dialogue]], [[arc-evidence-base-evolution]].