@grok comment traduire l'interface n8n sur un hébergement local ? où se trouvent les fichiers de traduction dans le repository ? est-ce qu'il existe une version française ? donne le lien
OPEN SOURCE
-
Self-driving car older than Chinese rivals, Tesla’s no-patent stance
By
–
My car self drives. Which is its best feature. It's eight years old. And is still smoother and better than what the Chinese have. Tesla doesn't believe in patenting things. But you are right. Now China is pulling ahead and will stay that way. One of the advantages of having 1.3
-
PyTorch’s Signed 64-bit Index Standardization Decision
By
–
Pytorch made the right call standardizing on signed 64 bit indexes. I would probably still be rather pointlessly making case by case decisions to use int32 if it were an option. Some old habits linger.
-
OpenReview Platform Receives Personal Donation Support
By
–
The OpenReview team has also been a remarkable partner, helping us setup a review process that was unusual and new. This is why I recently made a personal donation to its organization, and I encourage others to contribute: https://
openreview.net/donate Any contribution is impactful! -
DoRA vs LoRA: Choosing the Better Fine-tuning Method
By
–
I am once again asking for your support of DoRA. Friends don't let friends use LoRA. Use DoRA and make 2026 a good year.
-
Self-hosted Gmail, Docs, Drive alternatives emerging through code
By
–
Soon people will vibe code their own self-hosted GMail, Google Docs, GDrive, etc. https://t.co/69C2WyNOrh
— Marek Rosa | European🇪🇺 | South African🇿🇦 (@marek_rosa) 1 janvier 2026Soon people will vibe code their own self-hosted GMail, Google Docs, GDrive, etc.
-
IPA: Chunk-Level Credit Assignment Breakthrough
By
–
Here's the breakthrough nobody expected: They introduced IPA (Interaction-Perceptive Agentic Policy Optimization) that assigns credit at the CHUNK level, not token level. Tokens are too fine. Trajectories are too coarse. Chunks align with actual tool-use semantics.
-
Building the ecosystem before the model
By
–
They didn't just train a model. They built the ENTIRE ecosystem first. → ROLL: RL training framework
→ ROCK: Sandboxed execution engine
→ iFlow CLI: Agent orchestration system ROME wasn't built in a day. The infrastructure came first. The model came last. -
AI Infrastructure Breakthrough in 2025
By
–
Chinese AI labs just dropped a bombshell research paper that exposes why 99% of "AI agent" companies are building on broken infrastructure. The ROME model + ALE ecosystem might be the most important open-source release of 2025. Here's what nobody's talking about:
-
Kling 2.6 Motion Control Excellence Sparks Open Source Demand
By
–
Lo dije según lo probé y me pareció que no se le estaba dando la importancia que merecía, pero el Motion Control de Kling 2.6 es una locura de lo bien que funciona!
— Carlos Santana (@DotCSV) 30 décembre 2025
Qué ganas de tener una alternativa con calidad similar open source https://t.co/Yy5GBLlzSzLo dije según lo probé y me pareció que no se le estaba dando la importancia que merecía, pero el Motion Control de Kling 2.6 es una locura de lo bien que funciona! Qué ganas de tener una alternativa con calidad similar open source