I often want information from a long YouTube video or audio recording without having to listen to the entire content. Whether it’s a recipe video, an audio recording, or something educational. Recently, locally runnable LLMs have improved enough to run on my MacBook Pro, with a large degree of success. That got me wondering: Could I build a script that not only summarizes videos and audio, but lets me ask follow-up questions?...
I often finding myself writing one-off scripts to automate various parts of my day-to-day. You can see a few of them that have survived numerous refactors of my toolbox repo here. Python is my scripting language of choice, and until recently, I’d often find myself writing bash, to ensure that the script is portable, and easy to run. Introducing PEP 723, a new feature that describes how meta-data can be written inside a Python script....
I’ve recently had the desire to build myself a daily digest. With the express intent to ensure all data is processed locally. I’m going to use this blog post to detail this project. Before we go over how this was achieved, here’s a lightly anonymized example of an actual digest that landed in my inbox: Weather Today's high is 48°F with a low of 23°F — a significant jump from yesterday's rainy 38°F high and 30°F low....
While Claude Code has become my coding assistant of choice, I don’t always want to be using a remotely hosted LLM. I recently found out it’s pretty easy to use Claude Code with a non-Anthropic hosted model. This allows you to use an alternative remote host like OpenAI, OpenRouter, or even a locally hosted model. To point Claude Code at my LM Studio instance, which I use for local models, I can simply run:...
How to configure Claude Code to leverage Gemini for cheaper execution
I’ve been experimenting with integrating LLMs into software development for quite some time now. Having played with countless libraries, frameworks, and tools, I’ve identified what I believe are the key tiers of integration individuals will experience today. Level 1: “Copy + Paste” - Human driven with AI Consultation I believe the first situation developers will experience is simply using a web based chat LLM interface like chatgpt, claude, gemini, deepseek, or even the self hosted open-webui....
How easily orchestrating containers can make development, and integration testing easier.
How to easily switch between different LLMs using Open Router as a unified interface
How Anthropic’s new open protocol is standardizes the way LLMs interact with external systems and data
A guide to installing and running Claude Desktop on Linux systems using Nix Flakes