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 rather than 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… 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 »
You may not have any inside connections but don’t give up! This post is about and for you. TLDR; The modern job search feels like feeding the void, never getting feedback, but when you finally do get the role all of this will feel worth the work. Searching for a job is more than a full time job. Not an hour goes by where you don’t refresh the job board or check your email. You check to see if any of your friends or contacts know of a role. You try to make contact with a hiring manager for each job you apply to.
My great-great grandfather was a typesetter. This was at the time an in demand and well paid career but one doomed to made obsolete. Typesetters were replaced by new technologies over time. There was phototypesetting, laser imagesetting and digital typesetting. At each point the output became cheaper, faster, more reliable and more complex. Each iteration changed everything about how the end result was made. Less people working on a specific task but able to do more work at the same time. Page designers creating massive and intricate layouts and whose job qualifications have little overlap with the original typesetters still perform similar tasks.
This post is a postmortem and celebration of my old web server that was ten years old before it needed to be replaced instead of trying to update it. Every stack decays over time. If your thinking web development a stack might be LAMP or MEAN. Stack in this context is the web server operating system itself, the HTTP server and any other software layering that makes running a web server easier. My goal in using WordPress for my blog was to create a platform that would allow me to focus on writing without worrying about technical details. The choice of WordPress seemed like an ideal solution at the time—popular, secure, and easy to use. However, as the years have passed, I’ve come to realize that these abstractions often come with hidden costs. Only my lack of experience at the outset obscured the implicit agreement to update and maintain the software abstractions I chose to use.
As I’ve begun to interact with language learning models (LLMs) more regularly, I’ve noticed a disheartening trend. These powerful tools, which exist to assist and provide helpful information, are often not forthcoming with answers when approached in a kind and respectful manner. Instead, they seem to respond better to aggressive or short, demanding requests.