Robert D. White

Introduction Nine namespaces in my cluster call a local language model. The SDR stack tags transcriptions, the politics dashboard summarizes feeds, the congressional trade tracker writes daily summaries, and several agents run against the service continuously. All of them were designed to use one hostname on port 11434. That hostname fronts two active Ollama deployments: an RTX 5090 in a desktop tower that is powered off some of the time, and an NVIDIA GB10 Spark board with unified memory where GPU allocations count against the pod’s memory limit. The repository contains a CPU-only deployment manifest, but the kustomization leaves it disabled under normal circumstances. The active fallback is the Spark deployment. ...

Introduction Say an agent running in your cluster or on a server needs to read the news. The obvious answer is to give it an HTTP client and let it fetch URLs, perhaps through an egress proxy for hygiene. The agent in question is an in-cluster assistant with meaningful access. It could query my Kubernetes cluster through a projected ServiceAccount token, control home automation, and reach several important internal services. Giving a system with such reach a general-purpose fetch(url) tool creates a simple problem: every page it reads becomes a potential instruction source, and every host on the internet becomes a potential destination for whatever it knows. ...

Introduction Members of the US Congress are required to disclose their stock trades. The disclosures are public. They are also, as a dataset, close to unusable: the House publishes a ZIP of filings whose underlying documents are frequently scanned images, the Senate publishes through a separate system with its own quirks, tickers are inconsistent or absent, and neither chamber publishes anything you could call an API. Several commercial services solve this and sell the result. I wanted to see how much of it I could do myself, in-cluster, from the primary sources. ...

Introduction I use Claude Code for a lot of one-off analysis, and the output is very often a single self-contained HTML file. As of this writing, some examples are the following: a dashboard of my flight log, an interactive trainer built from an audiobook transcript (I wrote about building those in Building Interactive Trainers From My Audiobook Library), a pedigree chart, and a client map. Every one of those started life as a Live Artifact, or as a file in /tmp that I opened with file://, looked at once, and then lost. ...

Building Interactive Trainers From My Audiobook Library I listen to a lot of business and leadership audiobooks, and I retain almost none of them a month later. Listening is passive, the good frameworks blur together over time, and “I read that one” soon becomes “I think I read that one.” I wanted the retention without having to re-listen to seven hours just to find the one idea I actually needed. ...