Sebastien Dubois

news

Git Worktree

`git worktree` is a built-in Git feature that lets a single repository check out multiple branches into multiple working directories at the same time. Instead of cloning the repo twice, you keep one `.git/` and attach extra working trees to it ; each tree on its own branch, sharing all objects, conf

news

Gemma 4

Gemma 4 is the fourth generation of Google's Gemma open-weight model family. Released April 2, 2026, it is purpose-built for advanced reasoning and agentic workflows. Licensed under Apache 2.0.

news

Obsidian Starter Kit - Foundation

🏠 User Guide / Foundation

news

Gemma 4 Gets Multi-Token Prediction Drafters: 3x Faster Inference Without Quality Loss

On 2026-05-05, Google released a companion line of small autoregressive drafter models for the Gemma 4 family, plus a Multi-Token Prediction (MTP) head. Available on Hugging Face and Kaggle. Supported in Transformers, MLX, vLLM, SGLang, and Ollama from day one. Apache 2.0.

news

Build in public: keeping the OSK v4 AI Assistant robust at 250+ skills

Build-in-public update on the AI Assistant Architecture inside OSK v4.

news

AI SDKs

An AI SDK is a programmatic library you embed in your application to talk to AI models, orchestrate tool use, and ; in the agent-runtime variants ; run a full plan-act-observe loop. Where a CLI like Claude Code or gh copilot is a user-facing product, an SDK is the same machinery exposed for another

news

Git 2.54: Config-Based Hooks Replace Husky and Pre-Commit

Git 2.54 ships config-based hooks — the single most practical improvement in years for teams that care about code quality gates. If you've been managing Husky config files, `pre-commit` YAML, or manually copying hook scripts across repos, this replaces all of it.

news

Claude Code via GitHub Copilot

How to route Claude Code through your GitHub Copilot subscription using a local LiteLLM proxy. This lets you use Claude Code without a direct Anthropic subscription, authenticated via GitHub OAuth.

news

Markdown-based Installation (MD Scripts)

Markdown-based installation replaces shell scripts (`install.sh`) with prose installation procedures (`install.md`) that an LLM) reads and executes against the local environment. Instead of writing brittle Bash that branches on OS, package manager, shell version, and existing state, you write the in

news

Kimi CLI

Kimi CLI (official name: Kimi Code CLI) is Moonshot AI's open-source terminal-native AI coding agent, the CLI surface of the Kimi Code product. It runs an agentic loop in the terminal, operating on code, files, and shell commands via natural language, backed by the Kimi K2 model line.

news

Browser-Provided Language Models

An emerging pattern where web browsers ship with or download trained language models, exposing them to web applications through standardized APIs. Enables developers to access LLM capabilities without managing model weights, infrastructure, or API keys.

news

On-Device Machine Learning

Running machine learning models locally on the user's device rather than sending data to a remote server for inference. Also called edge ML or client-side ML. Core value proposition of the WebMachineLearning initiative and the Prompt API.