Essays
Arguments on staying capable when everything changes: why training doesn’t stick, how knowing actually moves, and what building in the open teaches about both. No magic. Just the work.
Latest
- Building in the open · July 2026 A skipped test protects nothing. An inverted one guards the absence. Deleting a feature is a one-line change. Deciding what to do with the dozen tests that now fail is the real question, and the obvious answer is the wrong one. A reverse-TDD pass that keeps the suite honest about what is now true, and why it matters more once a model is doing the deleting.
- Building in the open · July 2026 The bug is old. The way you drive the model through it is the new part. A mystery bounce on an OTP login, chased end to end: probing the error, building a mock to recreate it, red-bar tests, a two-layer fix, adversarial critic passes, and the CI gate. The three-line fix is the least of it. The discipline around the model is what actually solved it.
- Building in the open · July 2026 Without code journals, your AI will fail you. A test proves the code still works. Only the journal remembers why you built it that way, and the why is the part your AI, and next-week you, cannot reconstruct.
- Building in the open · July 2026 Prompting is just telling it enough of the story. The blank always fills with the most likely word. Prompt engineering is the plain act of telling a long enough story that the word you wanted becomes the likely one. You have done it since you learned to talk.
- Leading through change · June 2026 The Bottleneck Was Never the Machine Electrification took roughly forty years to show up in the productivity numbers, because the gain came from reorganizing the factory, not from the dynamo. AI is the same story. The bottleneck is how fast people adapt, and that part is a choice.
Browse by theme