Public benchmarks can tell you a great deal about AI model capability. They still may not tell you which model will perform best on the work you actually need done.
This final post in a 3-part series shows how to investigate that gap with a small personal evaluation: a representative task, controlled user-visible conditions, and a rubric written before testing. It also examines what happened when I applied that method to three model systems.
I built HTML Deck Studio because I wanted slide changes to appear as ordinary text diffs. PowerPoint, Keynote, and Google Slides support useful visual editing, but their native workflows do not treat each slide as source code that an AI agent or script can edit directly.
HTML Deck Studio stores presentations as HTML, CSS, and JavaScript. A browser renders the deck, Git records text changes, and a script can export it to PDF. This post explains that file-centric design and the extra engineering responsibility it creates.
In this post, I will explain how HTML Deck Studio works, why I designed it as a file-centric viewer, and how it simplifies presentation authoring for developers and AI workflows.
When multiple AI coding agents or developers work on the same repository simultaneously, code conflicts are only half the battle. One agent might require Python 3.10 to evaluate legacy scripts, another might need Python 3.12 for modern async features, and a third might test breaking dependency upgrades. If all instances share a single local environment, runtime collisions become inevitable.
Combining Git worktrees with VS Code Dev Containers addresses both kinds of isolation. Worktrees give each task a separate directory and branch checkout. Dev Containers give each directory its own runtime dependencies. This post explains the extra Git metadata mount that makes the combination work.
Knowing that benchmark scores depend on their test setup is only the first step. The next challenge is recognizing what different benchmark families actually measure—and where their evidence ends.
This field guide maps six useful categories that appear in model announcements and provides a repeatable way to read them together. The categories are practical rather than exhaustive, and some benchmarks span more than one.
VS Code Insiders updates frequently, so a new build can introduce a crash, extension failure, or slowdown before a fix is available. Reverting means installing a specific earlier Insiders build and pausing automatic updates long enough to keep it in place.
This guide shows how to record your current version, find a known working commit, build the correct download URL for your platform, install it, and later restore updates. It also explains which settings and extensions the reinstall should preserve.
Every major AI model release arrives with a scorecard. One model scores 87% on one test, 63% on another, and claims to outperform last month's leader on a third. The numbers look precise, but they rarely tell regular AI users what to do next.
This post explains what those scores actually measure, why the same model can receive dramatically different results, and why even a well-run benchmark may not predict performance on your work.
Flashcards often begin as notes, but moving them into a separate app creates another copy to maintain. A database hidden behind cloud sync can also make ordinary Git history and text-based review difficult.
I built Markdown Flashcards so the deck remains a Markdown file. The local application turns that file into a study session and writes review dates and ratings back as readable metadata. This post explains the file format, review flow, and trade-offs of keeping content and study state together.
Technical presentations often duplicate material that already exists in Markdown documentation. Once copied into a slide editor, code samples and diagrams can drift away from the source.
I built the Markdown Presentation Tool to present the Markdown file directly in VS Code. The extension turns headings, lists, code blocks, and Mermaid diagrams into slides and updates the presentation when the source changes.
A PDF viewer parses a complex, potentially untrusted file. Its safety depends on the parser version, the browser or webview boundary, the resources it can load, and the capabilities the extension enables.
I developed Safe PDF Viewer to make those choices explicit inside VS Code. It bundles PDF.js locally, restricts its webview with a Content Security Policy, disables dynamic JavaScript evaluation in PDF.js, and exposes the file through a read-only editor. This post explains what each control reduces and what it does not guarantee.
Mermaid turns text into diagrams that can live beside code in a Markdown file. That makes diagrams easy to review and version, but an inline diagram can be too small to present in a meeting.
I built Mermaid Slideshow, a VS Code extension that finds Mermaid blocks and presents each one as a full-screen slide. This post explains how the extension works, how to navigate a deck, and which theme setting controls the rendered diagrams.