Writing

Notes from the production layer.

Technical notes, experiments and post-mortems from applied AI, automation and digital product systems. Each one starts with the same question: what actually happened when the system had to produce an outcome?

15 September 2026 Approval Is Not Publication Thirty seven items in the queue, one approved, nothing published. The last arrow in the diagram is the only one that pays. 2 min read 14 September 2026 Neural Rendering Is Crossing From Reconstruction Into Synthesis Reconstruction filled in what sparse sampling missed. DLSS 5 generates appearance the renderer never computed. 6 min read 14 September 2026 The Renderer Is Becoming a Training Data Engine The renderer used to sit at the end of the pipeline. Physical AI gives the same scene a second job: teaching a model. 6 min read 13 September 2026 Local AI Is Becoming a Compute Fabric Local AI meant one model on one machine. Routing inference across the devices already on a network changes the unit. 6 min read 12 September 2026 Agent Infrastructure Is Becoming a Product Category Every team used to build the loop, the store, the sandbox. That layer is being sold rather than written. 6 min read 12 September 2026 Choosing a local model with a stopwatch, not a benchmark Three models, five hard tasks, code actually executed. The official build was 2.4 times faster and more accurate than a community repack of the same model. 3 min read 12 September 2026 We measured real time lighting against baked light, and baked won A 3D product simulation that had to look like an offline render. The real time version ran at 60 frames per second and looked like clay. Here is the measurement and the architecture that replaced it. 4 min read 12 September 2026 What actually broke in an agency run by agents Three failures from a delivery stack that runs on AI. None of them were the model's fault, and all three reported success while producing nothing. 4 min read 11 September 2026 A Task Without A Check Command Is Not Automated If a task has no command that can fail, the pipeline advances on the appearance of work. 2 min read 10 September 2026 A Gate The Model Writes Is A Gate The Model Loosens Three quality gates returned green while the work behind them was wrong, each for a different reason. 2 min read 8 September 2026 The Scoring Model Was Wrong And It Put The Worst Lead First A weighted sum let one axis substitute for the other, so a company with money and no problem ranked in the top twenty. 2 min read 5 September 2026 Building Software Got Easy. Getting Value Out Of It Did Not Aristo took weeks to build. Everything after the build is still in progress, and that gap is the whole story. 3 min read 4 September 2026 Capability Is Becoming an Operational Risk Surface Safety questions used to be about the text. Once a model can act, the capability itself becomes something to operate. 6 min read 24 July 2026 The Scene Graph Is Becoming an API for AI A scene graph exists for artists and software. Agents are becoming another consumer, and they need structure rather than pixels. 6 min read 23 July 2026 Animation Is Moving From Clips to Motion Priors Authored keyframes and blended clips are giving way to asking which constraints define acceptable motion. 6 min read