nerdCopter nerdCopter

LLM Wiki: Universal Blueprint (The Knowledge Compiler)

Adapted from the original pattern by Andrej Karpathy: gist.github.com/karpathy/442a6bf555914893e9891c11519de94f

1. The Core Philosophy: From RAG to Knowledge Compilation

The Knowledge Compiler pattern represents a fundamental shift in how Large Language Models (LLMs) interact with information. Traditional Retrieval-Augmented Generation (RAG) is a stateless operation; it treats the LLM as a sophisticated search engine that "rediscovers" knowledge on every query, re-processing raw documents through a vector database to find relevant chunks. This approach is prone to "context drift," hallucination under pressure, and the loss of subtle inter-document connections.

In contrast, the LLM Wiki is a stateful intelligence engine. It treats the LLM as a compiler and the wiki as a persistent codebase of knowledge.

	#!/bin/bash

	if [ $# -lt 3 ]
	then
	echo "Usage: ${0##*/} <filename> <fromtime [HH:]mm:ss> <totime [HH:]mm:ss> [suffix]"
	echo " Ex: ${0##*/} INPUT.mp4 0:20 9:40 snip001"
	echo " requires: gpac (MP4Box) and ffmpeg"
	else
	function to_sec() { echo "$1" \| awk -F':' '{if (NF == 2) {print $1 * 60 + $2} else {print $1 * 60 * 60 + $2 * 60 + $3}}';}