Writing

A served model can load at 96K context and still be useless past 64K. Loading is not the same as staying coherent. Here is how we mapped the exact cliff with a progressive needle-in-haystack bench — and why the limit was the model, not the GPU.

How I would roll out AI-assisted development on a team that has not standardized: what to do in week one, what to earn the right to argue about later, and what almost always goes wrong.

A short, adoptable AI usage policy for engineering teams: what to put on the page, what to leave off, and why the policy matters less than the habits it makes explicit.

What it took to get Gemma 4 E4B serving cleanly on Radeon through FlexInfer: a stable TRITON lane on a 7900 XTX, an experimental TurboQuant long-context lane on a second node, and the GPTQ pipeline work still underway.

AI-assisted development is useful leverage, but only if you convert borrowed competence into real judgment before the support becomes a dependency.

Field notes from building and operating a small private GPU platform with Harvester, K3s, and a GitLab -> Flux delivery loop.

A deep dive into optimizing Canvas 2D and Three.js visualizations for Kubernetes dashboards, covering algorithmic complexity, memory management, and GPU-efficient rendering patterns.

A real-world integration story from both sides of the table: supporting and consuming the same healthcare API.

What changed since Meaningful Use, and what still blocks plug-and-play healthcare apps.

A practical blueprint for scaling partner integrations without burning out engineering or support.