Writing
Notes on software architecture, self-hosted infrastructure, and designing so the bill stays small.
Can a cheaper model review code like Fable?
Nine AI reviewers replayed four changes on which Fable caught a real bug. One open model matched it change for change at about a tenth of the cost, and a small one I already run at home caught what models fifteen times its size missed.
October 2026
Two AI reviewers, by the numbers
Seven weeks of every pull request reviewed by two Claude models: how often the review loop clears a blocking finding, what each model caught that the other never mentioned, and what it cost.
October 2026
Madness, genius, dealing with grief, or just a way to get more done
Running a fleet of AI coding agents the way I once ran parallel teams of new developers, and why I open-sourced the fleet but not the judgment behind it.
September 2026
Plan dispatch, drawn
One feature plan, traced from a draft to a merge. A human merge arms the work, a watcher spawns one run per plan, and it comes back as a pull request a human merges again. The colours are the honest part: what is built, and what is only specified.
September 2026
Lab token usage, 2026
What a year of agentic coding at home actually consumed — measured from transcripts, cross-checked against the subscription's own meters. Two volume conventions exist and both are true, so both are quoted.
September 2026
Six things I got wrong
A governance practice is only worth as much as its correction record. Six claims my own adversarial review pipeline caught — a cost figure several times too low, a reversed conclusion, one that was never measured at all, a safety rule blind to its own incident — three of them already published, all corrected with changelog entries, and the ISO 42001 gap list underneath.
September 2026
Merge is ignition
I wanted one answer to "what authorised this?" that software cannot write, so a human's reviewed merge became the only thing that starts automated work — with the diagram, the refusals, and the parts that are specified but not yet wired.
September 2026
Ten runs, one lever
I re-ran the same AI code review ten ways to find out what actually makes a second reviewer worth paying for — then my own reviewers found three errors in it, one in the scoring, one in a flag that was never connected, and one in a cost figure, taking two of the three conclusions with them.
September 2026
Nine rounds with a machine reviewer
What nine adversarial review rounds on a single pull request taught me about where AI code review actually stops — including three defects in fixes the reviewer itself asked for, and why the loop ended on budget rather than on approval.
August 2026
The basement cloud
How a home lab became a working miniature of enterprise AI infrastructure — a model gateway, zero-trust ingress, agentic CI with human review gates, and an eval harness — with no cloud bill.
July 2026
The app checks itself
Shipping a zero-backend app: give the client a static set of public links, let every install do its own fetching — and know exactly where that pattern stops working.
July 2026
Where the tokens actually go
Running a two-model coding loop at home — a frontier model to plan, a local model to execute — and designing it so the bill stays small.
July 2026