The project owner approved the eight proposed clarifications of the pre-registered criteria on 2026-11-12, as recommended, after the parameter freeze and before any code or result exists. They are entered under «Presiseringer» with a dated entry and the reason for each under «Endringer». Three wordings in the criteria text are aligned with them. The specification now refers to them as clarifications instead of proposals, and the rule for conditions uses the 10th to 90th percentile. Equations and parameters are unchanged; modell/parametere.json keeps its checksum. Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
4.2 KiB
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 (01–12 first round, 13–21 targeted second round). 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–S47).modell/parametere.json: the frozen parameters (value, range, distribution, source entries); its checksum is recorded in the pre-registration. The table in chapter 14 of the specification is generated from that file.modell/fagfellevurdering-*.md: review findings per draft and what was done.PLAN.mdandSTATE.md: local working files (gitignored).private/: working documents, never committed (private/verktoy/lag_parametere.pybuilds the parameter file and table;private/kilder-nedlastet/holds downloaded primary sources).- 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 confirmedKontrollline may not feed a model parameter. - Pre-registration: the criteria in
FORHANDSREGISTRERING.mdare 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. - Frozen parameters:
modell/parametere.jsonis not edited after the freeze. A change is a deviation: new commit, new checksum, and a dated entry with the reason under «Endringer» in the pre-registration. - 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 underktg/until the repo-standard gate is green; visibility and the move toopen/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.