In September 2026 I got an email saying Codex could use Ollama. A few months earlier I had already managed to run a local model inside Cursor, OpenCode, and Crush, then wrote up the arrangement in Running Local LLMs Inside Cursor, OpenCode, and Crush. I had a working LM Studio server on my network. I… Read More »
This may seem self-evident, but I wanted to put it through a small experiment: saying what I need the first time should cut down on wasted AI work. I wanted to find something practical I could contribute to greener AI usage. Prompting seemed like a useful place to start because it’s something I can change… Read More »
The first time you stare at a backlog of a few hundred small repeated violations, all of them roughly the same shape, the natural thought is that this should be automated. Some validation rule trips on a missing attribute, or the same handful of conventions are wrong in dozens of templates, and the work is… Read More »
It took me twenty years to make Linux my daily driver. I wanted to. Every time I tried, something stopped me. A missing driver, a configuration file I couldn’t decode, a game I wanted to play, some piece of software my livelihood depended on that only ran on Windows. I would install, struggle, reach the… Read More »
Bone Keeper (2026) feels like a low-budget creature feature with a newer image pipeline running through it, and that pipeline feels like part of the creative decision-making, not a layer of effects sitting on top. The film’s own credits list Howard J. Ford as writer, producer, cinematographer, editor, and director, and after watching the movie… Read More »
How the Template Emerged The origin is boring in the best way. I was writing skills, markdown files with YAML frontmatter that tell an AI coding agent what to do. Each skill needed to work in Claude, Cursor, Windsurf, OpenCode, and Codex. Each of those tools has a different frontmatter format, different file layout expectations,… Read More »
Pasting a hard bug into one AI prompt feels productive until it isn’t. Single-model inference hits a ceiling fast; if the model misses the root cause on the first pass, it will cheerfully validate its own wrong answer forever. One way out is to act as human middleware between multiple, architecturally different LLMs: generate parallel… Read More »
I love books even though I rarely find time to read them. I have an old Audubon book, “Birds of America” that my wife found for me at Savers for five dollars. It is not the best bird book in any modern sense. The illustrations are no longer the highest-fidelity option available. Folks could argue… Read More »
Making Connections Integrating a robust application framework with a documentation tool often involves reconciling different philosophies on how code should be built and rendered. I recently worked on integrating an Ember UI library with Storybook 10, and I encountered a specific architectural challenge. I actually tried and failed to combine the two many times before… Read More »
I wanted the best of both worlds: local models for privacy and cost, plus the scaffolding that makes modern tools actually pleasant to use. The plan was straightforward: LM Studio running the model, LiteLLM as the OpenAI‑compatible face, and three clients in the mix: Cursor, Opencode, and Crush. No spend, no drama, just enough configuration… Read More »