TORSDAG
2026-07-30
The Cloudy Brain

Too many projects, too many ideas, too few hours — one learning a day anyway

The Machine

0 days of fuel in the queue 90 posts published 38 human decisions logged page rebuilt 2026-07-30

This site publishes itself — but never by itself. Every word passes one human gate. This page is the architecture, public on purpose: the whole thesis here is that you shouldn’t trust an AI’s output, you should trust the structure around it. So here’s the structure.

THE PUBLISHING MACHINE DOORS — material comes in a URL I point at · the news feeds · today's git work a note typed minutes after something broke CO-WRITING SESSION me + an AI that argues back — objections surfaced, never silently applied; drafts grounded in fetched sources, always AGENTS — on schedules Field Monitor · weekly Code Milestones · weekly Dev Diary · nightly Dossier Drift · weekly Sparks Door · daily they gather, draft — and STOP drafts drafts THE HUMAN GATE I read, edit, sign — or it dies here. No AI path reaches publication. LEARNINGS one per day, FIFO queue; backlog is runway NEWS on merit only; source fetched and read before described DIARY the day's story, written from real git evidence SPARKS brainfarts, 60 words max, written down so they exist THE BROADSHEET YOU'RE READING THE CLOUDY BRAIN DWG NO. 001 PUBLISHING MACHINE REV. B drawn by: human + machine SHEET 1 OF 1
The drawing is the contract: nothing crosses from the upper half to the lanes without the gate.

The gates, specifically

  • One learning per day — enforced in code, idempotent. A hundred queued posts still release one per day.
  • Diary is a parallel lane — every approved diary entry publishes on the next run, dated by the day it covers. A diary never holds the daily post back, and never consumes its slot.
  • Fetch before describe — no post may characterize a source that wasn’t fetched and read. Headlines select stories; they never describe them.
  • Secret scan — every publish path refuses credentials, private hosts, and infrastructure detail.
  • Fixed layouts — every post type has a required shape; the build fails on violations.
  • The skeptic — before publishing, an AI pass argues against the post. I hear the objections; I decide.
  • The revision — after the skeptic files its case, the writer drafts one revision that answers it, alongside the original. Both sit in the editor: I approve the original, approve the revised, or edit either. The original is never overwritten and the objections stay visible — the dialectic is on the page, not hidden behind an auto-edit.
  • One-glance approval — the gate is becoming a phone-first inbox: each candidate is one card, rated for importance so the signal sorts to the top, approved or rejected with a tap. The gate itself is unchanged — one human still signs every post; only the surface gets easier.

What the AI may and may not do

May: gather evidence, draft, retrieve from my own corpus, argue, suggest line edits, label milestones in git history. May not: publish, decide, invent facts not present in its sources, or touch the queue without my signature. The drafting model runs behind a token-gated local bridge with tools disabled — it can write text and nothing else.

Why publish this

Because the interesting question of this decade is what human + machine workflows look like when the human stays sovereign. This site is one running answer, posted daily.