Writing
Build logs. What got made, what was wrong about it, and what corrected it. Each one comes in three lengths.
Series · 5 parts
Core Swap
Terminal Delight, the terminal I’m building, had just learned to open a picture itself: Alt+click a PNG path and it appears in a floating square beside the line that printed it. The next step was the pictures programs draw on their own, so I ran four picture programs in a pane.
Series · 3 parts
Jev: Establishing Ground Truth
Before I build something that makes decisions with Jev, I write down the awkward cases it has to get right: a security hole filed as an ordinary bug report, a complaint about something fixed two releases ago, a rant with nothing in it to act on. I call those traps, and the finished system gets tested against them.
Series · 5 parts
Jev Frame Engineering
Frame engineering is the part of building on Jev that decides what a judgment can see and what it is asked. A frame is the state times the questions: the facts sent in one call, multiplied by the typed questions asked of them.
Series · 5 parts
Jev Engineering
Jev is a decision model: it takes application state and one or more typed questions in a single HTTP call, and returns a typed answer with a probability distribution — never prose to parse. POST a state object and a set of questions to one endpoint; get back an answer per question, every time.
Standalone
Unearned Zero
Somebody's Codex had quietly made 118 copies of their working tree — 202 gigabytes of them, sitting in /tmp . Codex ships a command that lists those copies.
Standalone
Twenty-Dollar Kill-Test
Earlier work measured whether parallel AI agents disagree on their own. Mostly they do not — nine agents on the same tickets forked on six of twenty-eight contested design questions.
Standalone
Agentic Attention Surface
A dozen agents running at once. One is finished, one is stuck, one has been quietly wrong for an hour.