Frank A. Krueger's Blog
TL;DR Running coding agents on local machines has never been easier. This article gives easy setup instructions for running Qwen 3.6 27B on an RTX 3090 in Linux. I then show how to use the model in VS Code using the LLM Gateway extension. By the end of this guide, you’ll be free of service providers and able to run a variety of OSS models.
TL;DR I wrote a .NET library, CLI tool, and MCP server for fetching app reviews from App Store Connect (with Google Play support in the works). You can use them yourself with the NuGet packages AppReviewFetch, AppReviewFetch.Cli, and AppReviewFetch.Mcp. The MCP server is especially exciting because it lets AI assistants analyze your reviews for you.
TL;DR There are no less than 4 different ways you can deploy your iOS app to a physical device for testing. I enumerate all of them below, along with their pros and cons. In the end, I recommend using dotnet build -t:Run if you can, as it is the simplest and most reliable method. But knowing the alternatives can be useful in certain situations.
TL;DR Apple has introduced a new layered approach to app icons in iOS and macOS 26. This post explains how to update your .NET and MAUI app icons to comply with the new requirements and ensure your app looks great on all devices. I outline two different approaches from easiest (do nothing) to hardest (composing and compiling your icons). I also outline the steps needed to manually compile your…
TL;DR Here are the basic steps to set up CI/CD for your iOS MAUI apps using GitHub Actions! I outline every step needed to setup the build environment, import your certificates and provisioning profiles, build, and, finally, upload your iOS apps to Test Flight and the App Store. I leave the macOS, Android, and Windows versions as an exercise for the reader.
TL;DR I used a custom-trained Large Language Model (T5) to create the world’s largest online corpus of translated cuneiform texts. It’s called the AICC (AI Cuneiform Corpus) and contains 130,000 AI translated texts from the CDLI and ORACC projects.
TL;DR I’ve been working on a WebGPU optimized inference and autograd library called webgpu-torch with an API that matches PyTorch. The goal is to run neural networks in the browser at speeds comparable to a Linux workstation. Many kernels have been implemented and its design is easily extensible. It’s available on NPM now and works in both the browser and Node.js!
TL;DR I used ChatGPT, with varying levels of success, to generate SVG images. With enough patience and prompting, you can get it to draw basic shapes and simple scenes about as well as a five year old can. (Which, hey, let’s face is, is good enough a lot of the time.)
TL;DR I wrote a javascript library that lets you run modern transformer neural networks from Hugging Face 🤗 in the browser. It works on mobile browsers, desktop browsers, pretty much everywhere. Check out transformers-js on GitHub to see how it works and checkout out the live translation demo running on my static website: https://transformers-js.praeclarum.org.
I sometimes find myself in a position of needing to write some code that I’m just not sure how to write. Been there have you? Here are the steps I take when I’m stumped. No huge revelations here, just hard-earned advice.