Skip to content

Instantly share code, notes, and snippets.

View hcoona's full-sized avatar

Shuai Zhang hcoona

View GitHub Profile

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.

@nero120
nero120 / index.js
Last active January 20, 2023 17:26
A Node.js script to decrypt xBrowserSync sync data.
const crypto = require('crypto');
const lzutf8 = require('lzutf8');
const util = require('util');
const pbkdf2 = util.promisify(crypto.pbkdf2);
async function getPasswordHash(password, syncId) {
// Generate pbkdf2 key and return as base64 string
const encoder = new util.TextEncoder('utf-8');
const keyData = encoder.encode(password);
const salt = encoder.encode(syncId);
#!/usr/bin/ruby
# Create display override file to force Mac OS X to use RGB mode for Display
# see http://embdev.net/topic/284710
require 'base64'
data=`ioreg -l -d0 -w 0 -r -c AppleDisplay`
edids=data.scan(/IODisplayEDID.*?<([a-z0-9]+)>/i).flatten
vendorids=data.scan(/DisplayVendorID.*?([0-9]+)/i).flatten