Journal

What’s top of mind

• Story Craft + Tsumugu companion — wing open (Condensed, Diagnosing a Character); apply layer and cast diagnosis in tsumugu-core/docs/companion/craft/. Story/cast authorship stays with Fable/Opus; core code fixes land separately.
• Tsumugu Encoding Dictionary — live at tsumugu-ed.com. Next build pass: handwriting layer, example sentences, or phonetic-family browse.
• Higher-Order Generativity vs. Judgment — which vault moves are generativity I can hand off versus judgment I must keep? Ties to Tsumugu lane assignments (stories = top-model judgment; cribs = cheap generativity with cross-check).
• The AI Industrial Revolution (2026-06-15) — planning-as-spec vs planning-as-ritual still open. Repeated vault moves (ingest, lint, cross-link) may become extracted skills.
• WNAC — parked; not driving.

Recent entries

• 2026-07-09 — Baldur’s Gate 3 as a lens on the cast — BG3 is the pinnacle of reactivity rather than of writing, most of its companion architecture is already in the Tsumugu canon, and running its two-axis test against our seven students found that only two of them pass.
• 2026-07-07 — The workspace a language model thinks in — A language model does its slow, step-by-step thinking in a small internal workspace. Anthropic found it, learned to read it, and even to read what the model is privately weighing.
• 2026-07-03 — Doctrine With a Half-Life — AI advice rots fast, but not evenly; splitting what you learn into invariants and dated tactics keeps the notes trustworthy as models improve.
• 2026-07-03 — The Floor Rose, the Ceiling Is the Job — Vibe coding raises the floor of who can build software; the ceiling, correctness, security, and judgment, is what stays a job.
• 2026-07-02 — 2026-07-02 — Tsumugu PRD set authored (core + ed) — Session: Cowork (Claude Fable). Wedge asked for a comprehensive set of Opus-executable PRDs improving tsumugu-core and tsumugu-ed, written to durable locations with a change index.

Full calendar →

Essays

Finished, stable pieces — the journal’s open questions, settled enough to stand alone.

• On Red Team’s Closure — what a leaner military should have kept from Red Team, and what was right to cut.
• Experiences — operating principles drawn from lived experience (Taiwan 2020, Red Team training).
• Story Cards as Memory Scenes — why the dictionary’s Story card becomes a single-character memory scene that encodes only the residue the Form card leaves.
• The First Principles of the Story Card — the residue rule and the two axes (character situations × memory levers) that generate every card.
• The Story-Card Catalog — every way a single-character memory scene can be generated; 34 archetypes, built to be extended.

Review prompts

• Which tsumugu-ed feature earns the next build pass — example sentences, phonetic-family browse, or the handwriting layer?
• What in the vault workflow is generativity I can hand off versus judgment I must keep?
• Where is verification cheap enough to “waste tokens, save time,” and where would parallel models just multiply confident slop?
• Is planning-as-ritual actually rotting on my tasks, or only on tasks where the spec is already tight?