I like to chastise Sonnet and Opus for their mistakes from time to time. "Ground your answer, this is wrong".
I want to show them, they haven't mastered it all... yet.

Sharing mindmaps with markdown emmanuelbernard.com/blog/2026/04...

Remember the "Fire everyone, keep the coders!" cartoon. That did not age too well.

it works from here. Maybe a temp glitch.

Oui ! On a la plateforme normalement et on doit configurer tout ça. Bref c’est en cours.

Episode 338 - Le soulèvement des bots de skills #skills #benchmark #mcp #jdk26 #Security #java sur https://youtube.com/watch?v=1Av8YU_5beI et en podcast lescastcodeurs.com/2026/03/20/lcc-338-le-so...

Read the thread above @swallez.com it was my response to your message.

Crap I failed to reference @swallez.com and his post bsky.app/profile/swal...

So what you propose should not be called a spec. It’s closer to code. And I don’t see English as being a good basis for it.

Whether it’s code or your advanced spec Sylvain (of which I have doubts about), humains won’t read it much in the future. Like I don’t read much assembly code today.

It’s quite uncanny and what defines these tools vs the other technologies before it. It makes some (stochastic and algorithmic based) judgment calls.

What is fascinating is that coding agents can adjust one based on the other and iterate on them like a pyramid. And coding agents do “fill the blank”, the unknown, the unsaid.

AGENTS.md AGENTS.md is a simple, open format for guiding coding agents. Think of it as a README for agents.

But there is something to the cascading for artéfacts. A WHY artefact not to lose the big picture (say a readme), the HOW (agents.md, architecture.md) as a constraining set of requests (I say requests because the coding agent can ignore them), the high level WHAT (spec.md) and the real WHAT (code).

So to describe the what something like code ends up being better. And between English code and Java code, I know what I prefer to read, understand and navigate. Java is less expressive and more deterministic and syntactically structured. These constraints make it a good descriptor of WHAT.

Lean and you leave loads of undefined semantic. Detail to fix that and English (let alone French) will turn your text into a very long, verbose and hard to parse text. That’s because human language has lots of uncertainty built in and fighting it falls under its own weight.

I don’t agree with you Sylvain and I think the article does not either.
People that have written specs that need to be implemented by several other systems, that spend countless hours to refine it, know that uncertainty and unclarity creeps in at every opportunity.

Comme dans beaucoup d’endroits, ma ville n’a que des listes citoyennes non affiliés. Mais les maires et certains conseillés sont grands électeurs pour les sénatoriales. C’est un trou dans la raquette de la représentation nationale.

Venez vivre un Super Mercredi à Devoxx France 2026 🙌

Une offre spéciale pour la journée du mercredi 22 avril : 250 € au lieu de 370 € avec le code "SuperMercredi26"

⚠️ 300 places seulement
👉 reg.devoxx.fr

Now. At least I saw it only today.

oh looks like Claude code can not react to messages you send it while it is thinking. That's going to be big.

What do people use to clean up macOS unexpected disk space usage ? Including slack, Chrome, Firefox etc caching
Nowadays any random app believes it can use 10GB for caching to be fast. Well you’re not alone on my machine buddy.

Boy!
Watch for Claude Desktop and Docker sandbox eating your hard drive alive.
I did not understand why my incremental backup was eating 4TB of space in a matter of a couple of weeks. Now I know.

Ah remember also the trick to put a whole in the corner of your blue 720kB disk to boost it to 1,44MB. Good times.
I don't even remember how such tricks were propagated at the time pre internet :D

Running postgreSQL in your JVM in embedded mode 😱
github.com/roastedroot/...

I can see a lot of small and embedded use cases for this as it matures. Good work!

How old are you ?

Sharing your ~/.claude config with Docker Sandbox I wanted to run Claude Code in YOLO mode but isolated from my actual machine. Docker has Docker Sandbox for exactly that: a CLI wrapper and a set of Docker image templates that give you a contained en...

Docker Sandbox is a great idea to isolate your coding agent like Claude Code from your machine. But how to share your settings? I explain it all here emmanuelbernard.com/blog/2026/02...

The good thing about French lunch time length is that you can schedule an OS update and be reasonably confident it will be done.

With us giving more freedom to Claude code and friends. What are your patterns to isolate you « code machine » from your « everything else » machine ?
One container per project and Claude code? A VM? A vps somewhere ?
Go commando?
Something else ? Share and explain 🙏

🎉 Les résultats du CFP #DevoxxFrance 2026 sont tombés !

• 1090+ propositions • 270 speakers sélectionnés • 3 jours de conférences épiques • +4000 devs attendus !

🗓️ RDV du 22 au 24 avril à Paris

✅ Résultats → m.devoxx.com/events/devox...
🎟️ Billetterie → reg.devoxx.fr

Dis @parisjug.org ? C’est possible d’arriver en retard ce soir et d’être quand même accepté ?