Youpen-y

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.

By Shmuel Csaba Otto Traian, CC BY-SA 3.0, Link

	"""
	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

	/* Implement a stack class template */
	#include<iostream>
	#include<vector>
	#include<stdexcept>

	using namespace std;

	template <typename T>
	class Stack{
	private:

	#include <stdio.h>
	#include <stdlib.h>
	#include <time.h>

	int main(int argc, char **argv) {
	struct timespec start, end;
	int size = atoi(argv[1]);

	// alloc memory on stack
	clock_gettime(CLOCK_MONOTONIC, &start);

	#include <stdio.h>
	#include <stdlib.h>
	#include <pthread.h>
	#include <stdatomic.h>
	#include <semaphore.h>
	#include <time.h>

	#define ITERATIONS 10000000

	atomic_int atomic_lock = 0;