Skip to main content

Posts

Featured

LLM WIKI 03 - Setting Up Claude Code and a Basic CLAUDE.md Schema: Telling the LLM the Rules of Your Wiki

On top of the folders and the Obsidian vault from part 2, let's now get the LLM ready to work. The file that tells the LLM "this is how this wiki is run" is CLAUDE.md. In this post, I open the sample wiki folder with Claude Code, write a basic CLAUDE.md for a reading-notes wiki, and check that the LLM reads it. The example is the same three imaginary books as in parts 1 and 2. This post was written on November 23, 2026. Where can you use Claude Code? Here is what I confirmed by reading the official Claude Code documentation (code.claude.com/docs) on November 23, 2026. You can use it in the terminal (CLI), the desktop app, the VS Code and JetBrains extensions, and on the web. According to the documentation, they all use the same engine, so CLAUDE.md and settings are shared. You need an account on one of Pro, Max, Ultra, Team, or Enterprise, or a Console account with API credits. The documentation says the free claude.ai plan does not include Claude Code, and that the ...

Latest Posts

LLM WIKI 02 - Folder Structure and Obsidian Vault Setup: Separating raw and wiki

LLM WIKI 01 - What Is an LLM Wiki? A Knowledge Base You Build Instead of Search

Three Recent AI Papers on Explainability, Safety, and Real-World Deployment

In-Context Reinforcement Learning Under Non-Stationarity: How Agents Adapt from Context Alone

2026 LLM Research Trends: Search Agents, RL Credit Design, Internal Representations, and Inference Scaling

Multimodal Sentiment Analysis and Sparse Attention: Two Recent Papers, Two Different Efficiency Ideas

From Multimodal Depression Detection to Long-Context Language Models: 3 Recent arXiv Papers in Brief

Multimodal Depression Detection and Lightweight EEG: What Two Recent Papers Say About Practical Medical AI

Why Traditional LLM Agent Evaluation Falls Short: From Auditable Question Formation to Simulation Environments

How Audio and Visual Signals Move Inside Multimodal LLMs