Well deserved! blog.tangled.org/seed
02.03.2026 11:09
👍 0
🔁 0
💬 0
📌 0
"Open source isn’t dying. It’s being industrialized." (by @juldanjou.bsky.social)
julien.danjou.info/blog/open-so...
Just blogged: Thoughts & Links 14
Almost 100% agentic coding-related. As it should.
blog.separateconcerns.com/2026-02-24-t...
Yea, GLM 5 is probably better. OpenCode Zen often has very strong models for free, currently GLM 5, Kimi K2 and MiniMax M2.5.
Current free agentic coding setup: pi + GLM-5 on OpenCode Zen. I still use Amp too but the free credits don't last long so I keep it for the harder parts.
What percent wrong is the output of your colleagues? Do you check it more or less thoroughly?
For those who are already using coding agents 100% of the time or close, this is important: steve-yegge.medium.com/the-ai-vampi...
The "Claude as a pair" way to work is by far my favorite but it is not sustainable because of this. As models and agents improve we'll need to learn to really delegate.
Moi ce que je veux surtout c'est que Anne Le Hénanff retourne dans sa Bretagne pour qu'on puisse enfin avoir Laurent Chemla ministre.
Vibe-coded project of the day. Watch logs from modal runs & kill them.
Made with Teal this time, because agents can use languages they don't know much too. I have a real use-case for this, but mostly it was to test terminal.lua.
github.com/catwell/mult...
🐇
C'est la même maison, mais Shiki faisait surtout des plats cuits (très bons :p). Ça fait un moment que je n'y suis pas allé, il faudrait que j'y retourne aussi !
@keltounet.keltia.net Je viens de voir ton update sur blog.keltia.net/la-maison-sa...
Ayant longtemps habité pas loin (rue du Dôme) je suis deçu aussi. J'ai immédiatement regardé ce qu'il advenait de Shiki et je suis rassuré : les cuisiniers de Sanki les ont rejoints shiki-boulogne-billancourt.com
At each of the companies I worked for, I have written a blog post describing what I was doing there after a few years. In keeping with the tradition, here it is for Finegrain: blog.separateconcerns.com/2026-02-07-f...
Several of the best engineers I know have joined the performance teams of Anthropic and OpenAI. They are probably part of the few teams with the highest concentration of talent in the world by now.
Back to training -> lament existing tooling -> vibe-coded what I lack.
If you use Trackio for experiment tracking with concurrent remote (serverless) runs you may like this.
github.com/finegrain-ai...
I am training models again. It has been a long time 😅
Un SaaS qu'on utilise a été racheté par OpenAI et va couper le service. On a regardé la concurrence pour savoir par quoi le remplacer. Finalement la réponse va être "on va demander à Claude de nous faire exactement ce qu'on veut"...
I wrote this in April, before Claude Code and Codex. Now I am changing my mind: The Carpenter can indeed just ask for a nice table.
JB Kempf highlights a key benefit of coding agents in this French podcast: the ability to greatly accelerate feature bootstrapping.
www.youtube.com/watch?v=25Mw...
Mais c'est clair que quand tu es bootstrap sans revenu mettre 15k c'est violent...
Mon principal problème avec ce nom c'est que quand tu le dis à l'oral tu es obligé d'épeler ensuite...
Perso j'aurais laissé tombé le .com. J'ai pas regardé les conditions mais write.blog et easy.blog sont dispos (mais premium) par exemple.
Sinon writeeasy.com est ~ 15k.
Perso je suis chez Fastmail depuis très longtemps mais c'est pas français (c'est australien, quand je suis passé chez eux ça appartenait à Opera qui était norvégien mais Fastmail est devenu indépendant depuis).
Haven't tried either! Just read stuff / watched videos so far. I want to, that's what I was saying above - but mostly because the spec mode intrigues me.
No I haven't either! I think it's somewhat similar in approach to the spec mode in Kiro.
I am curious about the specs part (also mentioned by @waxzce.org in his recent talk).
Currently with Opus + CC-like harnesses I found it better to iterate from simple prompts and not spec too much, but I will probably try a more spec-focused tool such as Kiro when I find time.
If you have not tried Opus 4.5 because of the cost yet, you have no excuse anymore. ampcode.com/news/amp-fre...
"can we have at home" meme with Opus 4.5 and GLM 4.7
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.
