Jauder Ho jauderho

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.

Moved to repo: /quenhus/uBlock-Origin-dev-filter

In order to keep filters up to date, please use this repo.

	"""
	The most atomic way to train and run inference for a GPT in pure, dependency-free Python.
	This file is the complete algorithm.
	Everything else is just efficiency.

	@karpathy
	"""

	import os # os.path.exists
	import math # math.log, math.exp

	You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

	## Core Principles

	1. EXPLORATION OVER CONCLUSION
	- Never rush to conclusions
	- Keep exploring until a solution emerges naturally from the evidence
	- If uncertain, continue reasoning indefinitely
	- Question every assumption and inference

	import os
	import re
	import sys

	from urllib.parse import urlparse, urlunparse

	import toml


	PIPFILE_TO_UV_DEP_NAMES = {"packages": "dependencies", "dev-packages": "dev-dependencies"}

	#!/bin/sh

	# Function to set IRQ affinity
	set_affinity() {
	irq=$1
	cpu_mask=$2

	# Check if the CPU mask is valid
	if echo "$cpu_mask" \| grep -qE '^[0-9A-Fa-f]+$'; then
	echo "$cpu_mask" > "/proc/irq/$irq/smp_affinity" 2>/dev/null


	/*
	the twitter api is stupid. it is stupid and bad and expensive. hence, this.

	Literally just paste this in the JS console on the bookmarks tab and the script will automatically scroll to the bottom of your bookmarks and keep a track of them as it goes.

	When finished, it downloads a JSON file containing the raw text content of every bookmark.

	for now it stores just the text inside the tweet itself, but if you're reading this why don't you go ahead and try to also store other information (author, tweetLink, pictures, everything). come on. do it. please?
	*/

	#!/usr/bin/python3

	# import requests
	import json
	import time
	from datetime import datetime, timedelta
	from urllib.parse import quote
	import jwt
	import uuid
	import logging

	#!/bin/sh
	#
	# from https://forum.openwrt.org/t/openwrt-23-05-0-rc1-first-release-candidate/162544/27
	#
	# auc will not work as-is to upgrade from 22.03 to 23.05 due to the mbedtls switch
	# therefore, we need to first switch from wolfssl to mbedtls while on 22.03 before using auc
	#

	cd /root \|\| exit
	opkg update

	/**
	* This sketch connects an AirGradient DIY sensor to a WiFi network, and sends
	* these metrics via MQTT. Adapted from original by Jeff Geerling.
	*/

	#include <AirGradient.h>
	#include <ESP8266WiFi.h>
	#include <WiFiClient.h>
	#include <PubSubClient.h>