guipmourao

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

guipmourao

Assigning Static IP Addresses in WSL2

WSL2 uses Hyper-V for networking. The WSL2 network settings are ephemeral and configured on demand when any WSL2 instance is first started in a Windows session. The configuration is reset on each Windows restart and the IP addresses change each time. The Windows host creates a hidden switch named "WSL" and a network adapter named "WSL" (appears as "vEthernet (WSL)" in the "Network Connections" panel). The Ubuntu instance creates a corresponding network interface named "eth0".

Assigning static IP addresses to the network interfaces on the Windows host or the WSL2 Ubuntu instance enables support for the following scenarios:

guipmourao

var workingDateRange = "LAST_14_DAYS";

function main() {
	
  lowerBidsToTopKeywords();
  raiseBidsToMidPositionKeywords();
  raiseBidsToLowPositionKeywords();

}