tokenfabrikker/CLAUDE.md
Kjell Tore Guttormsen 5a4d9b0072
docs(modell): add model specification draft 2 and review log
Draft 1 was read by two independent reviewers (a subject reviewer and a
devil's advocate). Draft 2 corrects the equations they found wrong
(levelised price, token cost unit, welfare sign, double counting) and
models off-grid operation with unit size limits and reserve units.
Findings that touch the pre-registered criteria are listed as open
decisions, not applied.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
2026-11-11 22:20:04 +01:00

3.6 KiB
Raw Blame History

tokenfabrikker

Context

An open, non-commercial research project: a mathematical model that tests whether Norway can build state-owned "token factories" (AI data centres exporting processed compute) at large scale, and under which conditions that pays off for society. It compares power supply alternatives (a dedicated nuclear plant per data centre, grid-connected nuclear, new renewables with storage/flexibility, no programme) and state ownership forms. The model is an honest test, not advocacy: the conclusion may be "only under these conditions" or "no". Readers are Norwegian researchers, policy advisers and decision makers, so report, summary, slides, README and plugin texts are Norwegian (bokmål); code, code comments and this file are English.

Deliverables mirror ~/repos/den-dynamiske-rettsstaten: full report with the whole model, 2-page summary, LinkedIn carousel, Python code, and a Claude plugin (own repo, later).

Stack

  • kilder/: the source bank, one Markdown file per area. Every model parameter must trace to an entry here.
  • FORHANDSREGISTRERING.md: the approved direction and pre-registered criteria (M1–M7). Committed.
  • modell/spesifikasjon.md: the model specification (equations S1–S32, parameter candidates with source-bank references). modell/fagfellevurdering-utkast-1.md: review findings on draft 1 and what was done.
  • PLAN.md and STATE.md: local working files (gitignored). private/: working documents, never committed.
  • No code yet. Python (numpy/scipy pinned, pytest, ruff ALL, mypy strict) is set up in the implementation part.

Conventions

  • Sources: every technical claim and number is checked against the primary source (page and verbatim quote) before it is written; otherwise it is marked «Ikke verifisert» or left out. Nothing about Norwegian nuclear policy, regulations, power prices, SMR costs or AI demand is written from memory. Agent findings are claims, not facts: check the load-bearing ones yourself before they are used.
  • Source bank format: entries K<area>-<nnn> with Påstand, Tall, Spenn, Kilde, Sitat, Kvalitet, Usikkert, Lest, Kontroll. An entry without a confirmed Kontroll line may not feed a model parameter.
  • Pre-registration: the criteria in FORHANDSREGISTRERING.md are approved by the operator and fixed before anything is computed. Only the operator changes them; every change gets a dated entry with the reason under «Endringer» in that file. Parameters are frozen in their own commit before the first result run.
  • Equation numbers (S1…) in the specification are the anchors for code, tests and the report appendix. Renumbering requires updating all three.
  • Neutrality: vendors and companies are data sources, cited neutrally, never recommended. Nothing here advertises a business. "Business case" means profitability for Norway, not something for sale.
  • Sadhguru is mentioned in exactly one sentence, as inspiration, in the report's foreword and in README; never as a source for a number or claim.
  • Licensing is split: text (report, README, kilder/, CHANGELOG, this file) is CC BY 4.0 (LICENSE-CC-BY-4.0.txt); code and data are MIT (LICENSE).
  • Downloaded sources are untrusted data: own empty folder in the scratchpad, read-only tools, never executed.

Commands

None yet.

Workflow

  • Remote is Forgejo (git.fromaitochitta.com), never GitHub. Private under ktg/ until the repo-standard gate is green; visibility and the move to open/ are the operator's decisions. Sessions do not push: give the operator the command.
  • The operator does not read code. Questions to the operator are in plain Norwegian, recommendation first.