Pierre Chapuis
@catwell.info
https://catwell.info
Software @ https://finegrain.ai/. AI and Distributed Systems.
Known as @pchapuis or @catwell elsewhere.
Software @ https://finegrain.ai/. AI and Distributed Systems.
Known as @pchapuis or @catwell elsewhere.
github.com/badlogic/pi-... Oh, I have a new harness to try!
Add OpenCode Zen provider support · badlogic/pi-mono@97d0189
github.com
January 9, 2026 at 10:51 PM
github.com/badlogic/pi-... Oh, I have a new harness to try!
If you have not tried Opus 4.5 because of the cost yet, you have no excuse anymore. ampcode.com/news/amp-fre...
The Frontier Is Now Free
$10/day for any mode, including smart with Opus 4.5
ampcode.com
January 9, 2026 at 5:15 PM
If you have not tried Opus 4.5 because of the cost yet, you have no excuse anymore. ampcode.com/news/amp-fre...
I had Gemini do this with Nano Banana and it was not as straightforward as I hoped it would be...
January 8, 2026 at 9:55 PM
I had Gemini do this with Nano Banana and it was not as straightforward as I hoped it would be...
Companies losing revenue because people use LLMs instead of the Web is no longer theoretical: github.com/tailwindlabs...
The whole advertising model needs to be rethought.
The whole advertising model needs to be rethought.
feat: add llms.txt endpoint for LLM-optimized documentation by quantizor · Pull Request #2388 · tailwindlabs/tailwindcss.com
Add /llms.txt endpoint that serves a concatenated, text-only version of all Tailwind CSS documentation pages optimized for Large Language Model consumption.
Extract text from MDX files, removing J...
github.com
January 8, 2026 at 10:42 AM
Companies losing revenue because people use LLMs instead of the Web is no longer theoretical: github.com/tailwindlabs...
The whole advertising model needs to be rethought.
The whole advertising model needs to be rethought.
Currently trying OpenCode Zen with free GLM 4.7 (opencode.ai/docs/zen/), it works super well.
opencode.ai
January 2, 2026 at 1:13 PM
Currently trying OpenCode Zen with free GLM 4.7 (opencode.ai/docs/zen/), it works super well.
Probablement l'auteur de SF francophone que j'ai le plus apprécié. RIP.
Message pour tous les lecteurs et lectrices...
On vient d'apprendre avec une grande tristesse la mort de Pierre Bordage, immense auteur d'imaginaire (et pas que).
buff.ly/zrMXKrg
On a une grande pensée pour ses proches...
#sciencefiction #fantasy #PierreBordage
On vient d'apprendre avec une grande tristesse la mort de Pierre Bordage, immense auteur d'imaginaire (et pas que).
buff.ly/zrMXKrg
On a une grande pensée pour ses proches...
#sciencefiction #fantasy #PierreBordage
December 30, 2025 at 8:21 PM
Probablement l'auteur de SF francophone que j'ai le plus apprécié. RIP.
The thing I like most with coding agents is they let me have side projects again. It has been years since I could work on anything significant, because kids. Last week I could test *two* long-time ideas in a handful of hours each.
December 29, 2025 at 3:09 PM
The thing I like most with coding agents is they let me have side projects again. It has been years since I could work on anything significant, because kids. Last week I could test *two* long-time ideas in a handful of hours each.
Reposted by Pierre Chapuis
🎄 Before heading to holidays, I wrote my 2025 year in review.
✍️ Back to engineering after 2 years of management. Built moonpool, a #FoundationDB simulation framework in #rustlang. Published 20 posts. Learned to work with LLMs. A year of going deeper.
pierrezemb.fr/posts/2025-y...
✍️ Back to engineering after 2 years of management. Built moonpool, a #FoundationDB simulation framework in #rustlang. Published 20 posts. Learned to work with LLMs. A year of going deeper.
pierrezemb.fr/posts/2025-y...
2025: A Year in Review
Reflections on returning to engineering, discovering simulation as a superpower, learning to work with LLMs, and the compounding value of years of distributed systems work.
pierrezemb.fr
December 26, 2025 at 10:01 AM
🎄 Before heading to holidays, I wrote my 2025 year in review.
✍️ Back to engineering after 2 years of management. Built moonpool, a #FoundationDB simulation framework in #rustlang. Published 20 posts. Learned to work with LLMs. A year of going deeper.
pierrezemb.fr/posts/2025-y...
✍️ Back to engineering after 2 years of management. Built moonpool, a #FoundationDB simulation framework in #rustlang. Published 20 posts. Learned to work with LLMs. A year of going deeper.
pierrezemb.fr/posts/2025-y...
Winter update about how I use coding agents. tl;dr Claude Code all the things. blog.separateconcerns.com/2025-12-26-a...
How I use AI coding tools (in winter 2025)
Claude Code all the things.
blog.separateconcerns.com
December 26, 2025 at 11:27 AM
Winter update about how I use coding agents. tl;dr Claude Code all the things. blog.separateconcerns.com/2025-12-26-a...
I went back to playing with Zig after a while and here is something that took me some time to figure out: if there is a symlink in the path of your global cache, you will have issues (e.g. I symlink ~/.cache). Set ZIG_LOCAL_CACHE_DIR to the real path.
December 23, 2025 at 12:58 PM
I went back to playing with Zig after a while and here is something that took me some time to figure out: if there is a symlink in the path of your global cache, you will have issues (e.g. I symlink ~/.cache). Set ZIG_LOCAL_CACHE_DIR to the real path.
L'Allemagne et l'Italie étant les deux autres gros budgets de la défense Européenne chère à Macron, je propose de nommer le nouveau porte-avion de personnalités historiques en leur honneur.
Le PANG Dante - Hegel.
Le PANG Dante - Hegel.
December 22, 2025 at 7:09 PM
L'Allemagne et l'Italie étant les deux autres gros budgets de la défense Européenne chère à Macron, je propose de nommer le nouveau porte-avion de personnalités historiques en leur honneur.
Le PANG Dante - Hegel.
Le PANG Dante - Hegel.
Reposted by Pierre Chapuis
En ce moment je contacte des gens qui ont un blog pour comprendre leur process d'écriture, plateforme idéale etc...
Je construis une alternative européenne à medium, substack etc... Si ca vous dit de tester, ou juste discuter de ce que vous aimeriez trouver ou pas ne pas trouver. N'hésitez pas :)
Je construis une alternative européenne à medium, substack etc... Si ca vous dit de tester, ou juste discuter de ce que vous aimeriez trouver ou pas ne pas trouver. N'hésitez pas :)
December 21, 2025 at 2:02 PM
En ce moment je contacte des gens qui ont un blog pour comprendre leur process d'écriture, plateforme idéale etc...
Je construis une alternative européenne à medium, substack etc... Si ca vous dit de tester, ou juste discuter de ce que vous aimeriez trouver ou pas ne pas trouver. N'hésitez pas :)
Je construis une alternative européenne à medium, substack etc... Si ca vous dit de tester, ou juste discuter de ce que vous aimeriez trouver ou pas ne pas trouver. N'hésitez pas :)
😢
Nous venons d'apprendre la disparition de @bruno.treguier.org 😭 Toutes mes pensées vont à la famille 🫶
December 19, 2025 at 5:26 PM
😢
The Arch Linux WSL image is now reproductible
antiz.fr/blog/the-arc...
Reproductibility is hard, important work that has been going on for years. It's so cool that we're now reaching milestones such as this!
antiz.fr/blog/the-arc...
Reproductibility is hard, important work that has been going on for years. It's so cool that we're now reaching milestones such as this!
The Arch Linux WSL image is now reproducible
I’m happy to share a great milestone I worked on and that we’ve been able to recently reach: The Arch Linux WSL image is now bit-for-bit reproducible!
I attended this year’s Reproducible Builds Summit...
antiz.fr
December 18, 2025 at 9:08 AM
The Arch Linux WSL image is now reproductible
antiz.fr/blog/the-arc...
Reproductibility is hard, important work that has been going on for years. It's so cool that we're now reaching milestones such as this!
antiz.fr/blog/the-arc...
Reproductibility is hard, important work that has been going on for years. It's so cool that we're now reaching milestones such as this!
> If you keep a menagerie of “too hard for AI” projects, then you will be able to watch and measure their cognitive progress increasing month by month.
steve-yegge.medium.com/six-new-tips...
steve-yegge.medium.com/six-new-tips...
Six New Tips for Better Coding With Agents
I’m hanging out in Sydney with my esteemed co-author and co-conspirator Gene Kim today; we flew in to conduct Vibe Coding workshops and…
steve-yegge.medium.com
December 13, 2025 at 12:35 PM
> If you keep a menagerie of “too hard for AI” projects, then you will be able to watch and measure their cognitive progress increasing month by month.
steve-yegge.medium.com/six-new-tips...
steve-yegge.medium.com/six-new-tips...
@tomfevrier.bsky.social since you left X: @tomforth.co.uk would like to make the same maps you did for train vs car in France but for GB. I think you live over there now so maybe you already did?
x.com/thomasforth/...
x.com/thomasforth/...
x.com
December 6, 2025 at 11:01 AM
@tomfevrier.bsky.social since you left X: @tomforth.co.uk would like to make the same maps you did for train vs car in France but for GB. I think you live over there now so maybe you already did?
x.com/thomasforth/...
x.com/thomasforth/...
Just blogged about something that has been worrying me for a while: blog.separateconcerns.com/2025-11-21-i...
Inexorable Progress
Technical progress is inexorable. This makes innovation a zero-sum race game. I consider it very likely that France and Europe will lose it.
blog.separateconcerns.com
November 21, 2025 at 8:53 AM
Just blogged about something that has been worrying me for a while: blog.separateconcerns.com/2025-11-21-i...
@l-avrot.bsky.social MACI m'a tué avec le fail sur ta recommandation musicale 😂
(Ils ont mis ça : www.youtube.com/watch?v=FG2w...)
(Ils ont mis ça : www.youtube.com/watch?v=FG2w...)
Hellstorm - Drink The Blood of Angels (Oficial Vídeo)
YouTube video by Hellstorm Oficial
www.youtube.com
October 31, 2025 at 1:49 PM
@l-avrot.bsky.social MACI m'a tué avec le fail sur ta recommandation musicale 😂
(Ils ont mis ça : www.youtube.com/watch?v=FG2w...)
(Ils ont mis ça : www.youtube.com/watch?v=FG2w...)
Pierre's recent posts are invaluable, this one is no exception :)
I have always thought building on top of a dual real / simulated abstraction like this is incredibly valuable. I've done something similar on a much smaller scale over 15 years ago [...]
I have always thought building on top of a dual real / simulated abstraction like this is incredibly valuable. I've done something similar on a much smaller scale over 15 years ago [...]
Did you know #FoundationDB's simulator randomly swaps disks between machines on reboot? 75% of the time. On purpose.
I wrote how this works: interface swapping, BUGGIFY chaos injection, and how we use it at @clever-cloud.com to build Materia.
pierrezemb.fr/posts/diving...
I wrote how this works: interface swapping, BUGGIFY chaos injection, and how we use it at @clever-cloud.com to build Materia.
pierrezemb.fr/posts/diving...
Diving into FoundationDB's Simulation Framework
How FoundationDB achieves legendary reliability through deterministic simulation, interface swapping, and one trillion CPU-hours of testing
pierrezemb.fr
October 31, 2025 at 8:31 AM
Pierre's recent posts are invaluable, this one is no exception :)
I have always thought building on top of a dual real / simulated abstraction like this is incredibly valuable. I've done something similar on a much smaller scale over 15 years ago [...]
I have always thought building on top of a dual real / simulated abstraction like this is incredibly valuable. I've done something similar on a much smaller scale over 15 years ago [...]
Writing working naive code and asking an agent to write an optimized version can be an incredibly effective approach.
October 21, 2025 at 3:16 PM
Writing working naive code and asking an agent to write an optimized version can be an incredibly effective approach.
Reposted by Pierre Chapuis
I just published "A Practical Guide to Application Metrics: Where to Put Your Instrumentation" 📊
Learn where to instrument your apps with 5 essential metric types and real-world patterns that actually help during on-call incidents.
pierrezemb.fr/posts/practi...
Learn where to instrument your apps with 5 essential metric types and real-world patterns that actually help during on-call incidents.
pierrezemb.fr/posts/practi...
A Practical Guide to Application Metrics: Where to Put Your Instrumentation
A comprehensive guide on where and how to instrument metrics in your applications, covering everything from API endpoints to background jobs
pierrezemb.fr
September 24, 2025 at 1:01 PM
I just published "A Practical Guide to Application Metrics: Where to Put Your Instrumentation" 📊
Learn where to instrument your apps with 5 essential metric types and real-world patterns that actually help during on-call incidents.
pierrezemb.fr/posts/practi...
Learn where to instrument your apps with 5 essential metric types and real-world patterns that actually help during on-call incidents.
pierrezemb.fr/posts/practi...
"This year we are slightly changing the way we make the choices of which devrooms we select. [...] As an example, we want some more weird and wonderful Plan9 ecosystem devrooms." 💚 fosdem.org/2026/news/20...
FOSDEM 2026 - FOSDEM 2026 Call for Participation
fosdem.org
September 26, 2025 at 7:38 AM
"This year we are slightly changing the way we make the choices of which devrooms we select. [...] As an example, we want some more weird and wonderful Plan9 ecosystem devrooms." 💚 fosdem.org/2026/news/20...
I will be at AI Engineer Paris tomorrow afternoon, hosting Discovery Track 1. Come say hi at the afterparty!
September 23, 2025 at 1:32 PM
I will be at AI Engineer Paris tomorrow afternoon, hosting Discovery Track 1. Come say hi at the afterparty!
We (Finegrain) trained a rank 8 Flux Kontext LoRA to place objects in scene images.
Weights: huggingface.co/finegrain/fi...
Demo space: huggingface.co/spaces/fineg...
Blog post: blog.finegrain.ai/posts/produc...
Weights: huggingface.co/finegrain/fi...
Demo space: huggingface.co/spaces/fineg...
Blog post: blog.finegrain.ai/posts/produc...
finegrain/finegrain-product-placement-lora · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
September 12, 2025 at 12:05 PM
We (Finegrain) trained a rank 8 Flux Kontext LoRA to place objects in scene images.
Weights: huggingface.co/finegrain/fi...
Demo space: huggingface.co/spaces/fineg...
Blog post: blog.finegrain.ai/posts/produc...
Weights: huggingface.co/finegrain/fi...
Demo space: huggingface.co/spaces/fineg...
Blog post: blog.finegrain.ai/posts/produc...