Patrick Desjardins Blog

https://patrickdesjardins.com/blog

16 posts · 5 Votes

Tech 88% · Culture 6% · Life 6%

Subscribe via RSS

  1. Porting the Self-Fixing Bug Workflow to a Bot With No Sentry, No Railway, No CI Runner

    I previously wrote about [TribeMarkets' self-fixing production loop](/blog/building-tribemarkets-with-ai-architecture-and-self-fixing-production): a scheduled GitHub Actions workflow that reads grouped errors from Bugsink and, under a long list of guardrails, prepares a draft pull request for a repe…

    0
  2. oktopai: A 2.36x Compiler Speedup From TypeScript 7 and the Latest Teacher-Student Results

    I have been running for a while now, my experimental, local-only coding orchestrator. The idea is simple to state and hard to earn: route a prompt to a small local model that has been specialized for the task instead of always reaching for a large general one, keep everything on my own GPU, and onl…

    0
  3. Building AudioRouter: From Google Doc to a Multi-Day Autonomous Codex Goal

    I have been experimenting with a new project called , and the process behind it says more about where AI-assisted development is heading than the project itself does. AudioRouter is a Windows application that routes, modifies, and configures system audio, in the spirit of tools like and , but with…

    0
  4. What a week of teaching a local coding model actually taught me

    This week I worked on **oktopai**, an experiment in local coding specialists. The idea is simple: use a stronger model as a teacher, use compiler-verified examples to train a smaller student, and eventually load the right specialist only when it is needed. The important part is the word *verified*.…

    0
  5. Teaching a small local model to speak typescript

    I am experimenting with an idea called **oktopai**: instead of asking one small local model to know every programming language and framework, can I keep several focused specialists and load the right one when it is needed? The first specialist is TypeScript. The goal is not simply to make a model so…

    0
  6. Oktopai: A Local Fleet of Specialized Coding Knowledge

    The most interesting local-LLM idea to me is not finding one enormous model that can do everything. It is building an orchestration of models and letting a local orchestrator choose the right one for each task. That is the idea behind **oktopai**: an experimental, privacy-preserving coding orchestra…

    0
  7. Building TribeMarkets with AI: Architecture and Self-Fixing Production

    I have been building as a small but serious experiment: a private, play-money prediction-market platform where communities create Tribes, open markets, stake internal credits, and resolve outcomes. The interesting part is not only the product. It is the way the product is built. I am using AI throu…

    0
  8. Humans are Becoming Simple Megaphones

    AI has not just entered the workforce. It has begun speaking for it. Over the past two years, the rise of large language models has transformed how we work, far beyond coding. People now turn a few lines into pages of documentation, which others then use AI to summarize, critique, and challenge. The…

    0
  9. 5-8x Coding Improvement that Could be Doubled

    In the two previous blog posts and in , I discussed the impact of AI on software development and experimented with a new way of developing software. In this article, I'll discuss my conclusions after three months of using several different approaches. The last three months have been interesting, es…

    0
  10. Using epaper for studying

    A few months ago, I and within a few weeks I was taking page after page of notes using . I initially liked it, but I missed taking notes with a pen. Something about scribbling, annotating, and illustrating my thoughts helps me focus and retain better than copy-pasting or typing. When I was doing my…

    0
  11. HATEOAS as the Natural Interface for Autonomous Agents

    The web was built for humans using a browser. APIs were built for developers who read documentation. Both scenarios never anticipate autonomous agents that must reason about what to do next. As LLM agents increasingly interact with services, a question emerges that few people are addressing directly…

    0
  12. Generating Documentation with AI

    I will argue that generating documentation with AI is useful, specifically the kind that lives as dedicated documentation files in folders alongside the code, and specifically for business logic and architecture. My thesis is that this documentation is valuable because it serves humans and AI agents…

    0
  13. How to test in TypeScript 2026 edition

    I wrote in , , , and about TypeScript and private functions. Eleven years later, I still believe that relaxing encapsulation to ease testability has the best return on investment (ROI). In this blog post I will argue that separating classes and interfaces preserves a portion of the encapsulation wh…

    0
  14. Mastodon Thread on a Static Website

    I recently visited and noticed a simple idea that I liked: comments do not need to live inside the website database. They can live on the social web, and the website can point to the discussion. For a static website, this is appealing because I do not want to run a comment server, to moderate a loc…

    0
  15. Replacing NextJS With a Rust Static Site Generator

    I recently moved this website away from NextJS as the static generation engine. The site was working, but it had become heavier than what I needed. Most pages are static. Most content is markdown. The build was doing a lot of framework work for a problem that had become much smaller than the framewo…

    5
  16. Audiobook machine version 3 using an ELECROW ESP32 Rotary Display 240x240

    I built an audiobook machine for my daughter in January 2022 using a Raspberry Pi and RFID cards (). In early 2026, I built a second version for my son using an ESP32 and a TFT display (). Over time, I wanted to replace my daughter's original device because the RFID cards became cumbersome whenever…

    0