Simon Marache-Francisco

I have been trying to get more independent of third-party services. Over the years several of them have become unsuitable: too complex to use because they keep adding features I don’t want abandoned/bought adverts and dark patterns increased subscription fees I also worry about them getting hacked (or one of their suppliers), or just selling my data outright. I have been following the LLM space for some time now (book translation, RAG experiments, wiki of babel…), and I have found a very nice use case for Claude code as way to get more independent.

Given the recent events, I have been slowly migrating my internet presence to the EU and off the Big US Tech companies. As a secondary objective, I also wanted to get rid of subscriptions and have more control over my data. It has not been very hard, but it is a slow process given all the tools that have been experimenting with over the years. So far: email: Fastmail: I have been using them for years, without knowing that they had a strong EU presence.

Introduction I was talking with a friend about the library of babel (the book, and the online library). Inspired by my short experiments with RAG, I decided to see if I could make something similar: an infinite Wikipedia, where each keyword leads to a page, and pages have links between them. What is tricky is making sure that the wiki stays consistent. Description It’s a pretty simple service: every top-level URL is valid and will return a webpage with content generated by an LLM.

Over the weekend, I implemented a Retrieval-Augmented Generation (RAG) pipeline as an experiment. RAG is an AI-driven document search technique. While it is powerful and interesting, the fundamentals turned out to be a lot more basic than I expected. The source code of the pipeline is available in the microProjects repo. What does RAG or AI Search look like? From the point of view of the user, RAG is a sophisticated document search engine.

Recently, I’ve been working on a few small but fun projects. As usual it’s mostly about software, but there is a bit of (light) embedded too this time! These involve using MicroPython for a hardware project, creating a user-friendly interface for DALL-E, and setting up a self-hosted music streaming solution. USB Volume Knob with CircuitPython I created a volume/media key USB controller for my desktop using MicroPython and a ProMicro microcontroller.

Post in French Introduction I was talking to my father about the Lewis and Clark expedition of 1804. I found the original document (in the public domain) on the gutenberg project’s webpage. I translated a couple of entries for him and he looked interested. Unfortunately I couldn’t find any French translation of these work for him to read. Given the simple nature of the medium (cleanly separated entries with a title), we wondered if we could use ChatGPT to perform the translation.

[Français] Presentation Ceci est une traduction française du livre “The Journals of Lewis and Clark, 1804-1806” qui contient les récits de voyages de William Clark et Meriwether Lewis lors de leur expédition à travers l’Amérique. Je n’ai pas pu trouver de traduction de ce texte en français et j’ai donc décidé d’utiliser GPT-4 Turbo d’OpenAI pour réaliser une traduction automatique. Bien que le résultat soit de très bonne qualité, je ne peux faire aucune promesse quant à la fidélité de la traduction.

Over the year I have been using several platform to host my projects, from S3/cloudfront/ACM, docker-compose/VPS to k8s, back to docker-compose/VPS again. But I recently found out that github pages was supporting artifacts created by github actions and custom subdomains in the free tier. I then migrated most of my static projects: Scoring assistant for Archery: https://score.marache.net Simple hex/dec/binary converter: https://convert.marache.net This website: https://marache.net Recipe generator for Bread-making: https://pain.marache.net That was also a nice opportunity to clean up the remnant of the travis build pipelines, and replace them with github action pipelines.

I am a backend/DevOps, so I don’t have a lot of opportunities to work on any kind of GUI. But at the same time, I am always fascinated by image generation (See my voxel renderer, software rasterizer, and many fractal generators), and having a simple engineering UI makes life much easier for the developer. Since my last project was (another) fractal generator, written in rust/OpenGL this time, I decided to look for a simple UI component that I could use to provide the interface, and stumbled on egui (the UI) + glow (the OpenGL bindings).

I read about the gardner hype cycle a long time ago, but it is only in the last few years that I feel that I fully “got” it. And now, I see it everywhere. There’s always a new technology promising to revolutionize everything, change the world, only to fall short of the (often exaggerated) expectations. As I’ve grown older, I’ve come to realize that the most visible failures often thrive within a VC/media echo chamber, detached from the realities on the ground.