Laurent Charignon

Most todo apps treat tasks as immortal.

Last night, I found myself genuinely entertained watching progress bars.

I’ve been using AI coding assistants like Claude Code and OpenAI’s Codex CLI daily for the past several months.

I’ve been using an AI-powered packing list generator for months.

I wanted to track who’s home without building a complex computer vision pipeline.

I take a lot of screenshots.

Managing multiple LLM providers gets messy fast.

Getting HTTPS working on .lan domains is annoying.

I run about 50 services on my homelab.

This blog runs on Hugo and Cloudflare Pages.

“Agentic AI” is everywhere in 2024-2025.

I process hundreds of emails weekly.

Apple Shortcuts are powerful, but building complex automations with the visual block interface quickly becomes painful.

When I have a flight coming up, I want one thing: a persistent, glanceable display showing exactly when I need to leave for the gate.

So there I was, 2 AM, chatting with an LLM about whether we’re all just fancy API servers running on meat hardware.

My daughter loves memory games.

I built a visual editor for managing LLM system instructions.

What if your coding sessions looked like a Star Wars opening crawl?

LLM coding assistants like Claude are powerful, but they have a fundamental limitation: every conversation starts from scratch.

This is the final article in my series on working with LLMs at scale.

In Part 1, Part 2, and Part 3, I covered pain points and solutions that work reliably.

In Part 1 I described the pain points of working with multiple LLM sessions.

Part 1 described the problems of managing multiple LLM sessions.

Working with 10 parallel LLM coding sessions exposes problems that don’t appear at smaller scale.

Over the past year, I’ve been building a comprehensive home automation system using AppDaemon, a Python framework for Home Assistant automation.

What are budget categories?

When I worked at Facebook, I worked on making cross-region failover for source control more effective and automated.

This article is an exception as it is not related to programming.

Org-roam Org-roam is an emacs package to implement the Zetteltasken workflow for note taking.

I have been working as a Software Engineer in the US since early 2013.

My recent reading interests In 2020 and 2021 before becoming a dad, with forced reduced social interaction due to COVID, I spent a large amount of time reading technical books and working on my craft.

I recently became more mindful about how I spend my time, because time is so precious.

I recently got back into meditation.

I write a lot of content, and sometimes I like to look back and re-read what I wrote in the past.

I like to take notes and track all sorts of things with org-mode.

Almost everything I do on a computer happens in Emacs.

Context Nowadays, pictures don't carry the same sentimental value as they did for our parents.

This is my cheat sheet to prepare for interview loops with US companies.

How should you respond when a recruiter asks you the question you know is coming - “what salary are you looking for”?

Context The Apple Watch and other smartwatches record a humoungus amount of data about what you do every day.

This is a quick post about a fantastic little clojure libary called pdfboxing.

Context I frequently use code coverage to identify untested code and evaluate the risk of making a code change.

Context I am going through the PAIP book by Peter Norvig using emacs-lisp and would encourage every Emacs fan to try that.

Negotiating a job offer is hard.

At work, my team uses GitHub enterprise to store and manage our repositories.

Introduction I simplify a lot of my tasks at work with Google Apps Script, the scripting language for Google Apps.

Introduction Managing and distributing Let's Encrypt SSL certificates can be tedious.

Introduction Did you know that it was possible to extract your google chrome cookies to use them in a script?

Introduction You don't have to set up a new laptop every day.

Ansible is a great tool for automating environment setup and deploy.