Writing & build logs.
Essays on software development, web builds, and AI tooling. Plus build notes from what I'm actually working on right now.
The cron ranked 150 clusters and drafted none: what a corrective verifier is built to surface
On 2 July, the morning cron ranked 150 clusters and produced zero drafts. The cron exited clean. The gap between those two facts is the surface a corrective verifier is built to make legible—without one, every zero-draft run looks identical from the outside.
Both corrections came from the phone. The catalogue was reading the README.
Four web-history cards merged in the afternoon. Two were withdrawn before evening — one for describing the wrong project entirely, one for using a product name the app had dropped earlier in the year. Both corrections came from Cj reading the live page from his phone. The catalogue had a single source of truth. It was the wrong one.
One note on the contact page. The same mistake on three more.
Rewriting the /contact/ timelines note taught one thing: copy written to signal the founder's values reads differently to a prospect who doesn't share those values. The lesson ran through three other copy fixes that quarter.
Seven clusters dark. A zombie IHT draft on its third PR. Both were the same assumption.
Between 30 June and 13 July, ten cron cycles produced one ready draft and zero auto-publishes while the skipped count climbed from two to seven. The same period produced a zombie IHT draft that slipped into a third PR. Both traced to the same assumption: a topic recorded in the index is a topic handled.
The Passage: 32.7 seconds in landscape, three upload IDs, one premiere
The Passage went into YouTube Studio on 24 July at 32.7 seconds in landscape. CJ’s call the same day: that format gets penalised — it has to be a Short. What followed was three uploads, two abandoned, two fix commits, and a lesson about specifying format before the render.