Nick Brown nick-brown

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.

Regular Event Loop

This shows the execution order given JavaScript's Call Stack, Event Loop, and any asynchronous APIs provided in the JS execution environment (in this example; Web APIs in a Browser environment)

Given the code

git commit stats

Commands to get commit statistics for a Git repository from the command line -
using git log, git shortlog and friends.

The introduction to Reactive Programming you've been missing

(by @andrestaltz)

This tutorial as a series of videos

If you prefer to watch video tutorials with live-coding, then check out this series I recorded with the same contents as in this article: Egghead.io - Introduction to Reactive Programming.

Backend Development

node.js
- Installation paths: use one of these techniques to install node and npm without having to sudo.
- Node.js HOWTO: Install Node+NPM as user (not root) under Unix OSes
- Felix's Node.js Guide
- Creating a REST API using Node.js, Express, and MongoDB
- Node Cellar Sample Application with Backbone.js, Twitter Bootstrap, Node.js, Express, and MongoDB
- JavaScript Event Loop
Node.js for PHP programmers

Frontend Development

Attention: the list was moved to

https://github.com/dypsilon/frontend-dev-bookmarks

This page is not maintained anymore, please update your bookmarks.

	/*
	This script attempts to identify all CSS classes mentioned in HTML but not defined in the stylesheets.

	In order to use it, just run it in the DevTools console (or add it to DevTools Snippets and run it from there).

	Note that this script requires browser to support `fetch` and some ES6 features (fat arrow, Promises, Array.from, Set). You can transpile it to ES5 here: https://babeljs.io/repl/ .

	Known limitations:
	- it won't be able to take into account some external stylesheets (if CORS isn't set up)
	- it will produce false negatives for classes that are mentioned in the comments.

	# Initialize the scroll
	page = es.search(
	index = 'yourIndex',
	doc_type = 'yourType',
	scroll = '2m',
	search_type = 'scan',
	size = 1000,
	body = {
	# Your query's body
	})

	set nocompatible " Disable vi-compatibility
	set t_Co=256

	colorscheme xoria256
	set guifont=menlo\ for\ powerline:h16
	set guioptions-=T " Removes top toolbar
	set guioptions-=r " Removes right hand scroll bar
	set go-=L " Removes left hand scroll bar
	set linespace=15

	--langdef=coffee
	--langmap=coffee:.coffee
	--regex-coffee=/(^\|=[ \t])class ([A-Za-z_][A-Za-z0-9_]+\.)([A-Za-z_][A-Za-z0-9_]+)( extends ([A-Za-z][A-Za-z0-9_.]*)+)?$/\3/c,class/
	--regex-coffee=/^[ \t](module\.)?(exports\.)?@?(([A-Za-z][A-Za-z0-9_.])+):.[-=]>.$/\3/m,method/
	--regex-coffee=/^[ \t](module\.)?(exports\.)?(([A-Za-z][A-Za-z0-9_.])+)[ \t]=.[-=]>.*$/\3/f,function/
	--regex-coffee=/^[ \t](([A-Za-z][A-Za-z0-9_.])+)[ \t]=[^->\n]$/\1/v,variable/
	--regex-coffee=/^[ \t]@(([A-Za-z][A-Za-z0-9_.])+)[ \t]=[^->\n]$/\1/f,field/
	--regex-coffee=/^[ \t]@(([A-Za-z][A-Za-z0-9_.])+):[^->\n]*$/\1/f,static field/
	--regex-coffee=/^[ \t](([A-Za-z][A-Za-z0-9_.])+):[^->\n]*$/\1/f,field/
	--regex-coffee=/((constructor\|initialize):[ \t]\()@(([A-Za-z][A-Za-z0-9_.])+)([ \t]=[ \t][^,)]+)?/\3/f,field/