53 lines
1.6 KiB
Markdown
53 lines
1.6 KiB
Markdown
# Reader Translation Layer V0
|
|
|
|
status: draft_translation_boundary
|
|
date: 2026-06-20
|
|
|
|
## Purpose
|
|
|
|
Internal cognitive processing can use Wantsong's model vocabulary, formulas, metaphors, layered reasoning, and mechanism chains.
|
|
|
|
Reader-facing output cannot simply expose that internal trace. It must translate the result into language a reader can use.
|
|
|
|
## Output Modes
|
|
|
|
M0-M1 recognizes these modes:
|
|
|
|
- `R0_internal_trace`: internal analysis record for owner inspection.
|
|
- `R1_owner_brief`: compact owner-facing quality summary.
|
|
- `R2_reader_explanation`: explanation for a normal reader.
|
|
- `R3_publishable_draft`: future writing-workbench draft.
|
|
- `R4_product_response`: future product answer.
|
|
|
|
v0.1 targets only `R0_internal_trace` and `R2_reader_explanation`.
|
|
|
|
## Translation Operations
|
|
|
|
Reader translation performs four operations:
|
|
|
|
1. Terminology translation: replace model jargon with ordinary language.
|
|
2. Structure translation: reorder the reasoning so a reader can follow it.
|
|
3. Example translation: use concrete examples to carry abstract mechanisms.
|
|
4. Action translation: turn insight into "how to see this / what to consider next".
|
|
|
|
## What To Preserve
|
|
|
|
- core insight;
|
|
- mechanism;
|
|
- boundaries;
|
|
- Wantsong-style distinction and depth;
|
|
- practical next way to think.
|
|
|
|
## What To Remove Or Compress
|
|
|
|
- full model trace;
|
|
- unnecessary formulas;
|
|
- seven-layer expansion when only three layers matter;
|
|
- governance vocabulary;
|
|
- generic disclaimers;
|
|
- marketing exaggeration.
|
|
|
|
## Boundary
|
|
|
|
This layer is defined now because it changes model-card requirements. The actual translation prompt is not created in M0-M1.
|