Theories
Open questions, worked in public.
The theories index lists open questions worked in public, with each theory's maturity state shown as prominently as its title.
The ladder is named, sketched, developed, live demo, with paused as a separate flag, because paused is a status, not a rung. 6 active, 1 paused. Numbers follow the order the theories first appeared.
- T-03Universal Question Geometry
Flagship · working paper
maturity: developed
first published 2026-05-17
last modified 2026-08-11
condition: active
Why do questions have geometry?
Questions have shape, and the shape predicts what an answer can reach. A map of how questions sit next to each other, and why some open doors that others structurally cannot.
- T-04Question–Answer Dynamics
In daily use
maturity: developed
first published 2026-06-02
last modified 2026-09-27
condition: active
Why should a useful-looking finding get more scrutiny, not less?
What an answer does to the next question. The loop, measured: most of the value in a conversation lives in how the second question moved.
- T-02The Architect Loop
Field-proven · fork, not mine
maturity: developed
first published 2026-04-20
last modified 2026-09-27
condition: active
Can one person run a software team by splitting judgment from building?
One model holds judgment, a separate set of models does all the building, and a git repository is the only shared memory. A fork of Dan McInerney's project, hardened and run daily.
- T-01Latent Emotions in LLMs
Paused exploration — live demo
maturity: sketched
first published 2026-03-14
last modified 2026-09-27
condition: paused
Do language models share a hidden vocabulary for relational states?
Different models reach for closely similar words when describing certain relational states. That might point to shared structure underneath, or to nothing. The work is parked, and it says so.
- T-06THE PAPER
Introduction only — document unpublished
maturity: sketched
first published 2026-07-05
last modified 2026-08-11
condition: active
What is a five-layer operating system for an agent-run business?
A specification for running a business where AI agents do most of the labour, in five gated layers. The document itself stays private; this page introduces the idea and links nothing.
- T-05Movement Economy
Sketched · enforced in code
maturity: sketched
first published 2026-06-18
last modified 2026-08-11
condition: active
What is a style rule a program can check?
Every sentence in a piece of analysis must do one of ten declared jobs or be deleted. Enforced on map objects inside OfOne rather than applied by taste to prose.
- T-07Function-First Orchestration
Sketched · standing rule
maturity: sketched
first published 2026-07-28
last modified 2026-09-27
condition: active
Should proof of function come before proof of thoroughness?
Ship one honest happy-path test plus the refusals that protect money, custody and truth. Defer the rest deliberately, in writing, rather than skipping it.
- Source
- The typed content source
- Method
- Listed where maturity is at least sketched; the count and the rows are the same list
- Built
- 2026-10-22 16:01 MT