Altaf Shaikh altafshaikh

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.

Assembly Language / Reversing / Malware Analysis / Game Hacking -resources

⭐Assembly Language

Modern x64 Assembly

https://www.youtube.com/playlist?list=PLKK11Ligqitg9MOX3-0tFT1Rmh3uJp7kA

VSCode Shortcuts

List of helpful shortcuts for faster coding

If you have any other helpful shortcuts, feel free to add in the comments of this gist :)

Official List of all commands

Windows
Mac

	// Initialize Scene class object.
	Scene scene = new Scene();

	// Initiate FBXLoadOptions class object.
	FBXLoadOptions opt = new FBXLoadOptions();

	// Output all properties defined in GlobalSettings in FBX file.
	opt.KeepBuiltinGlobalSettings = true;

	// Load input FBX file

	App.css
	html, body, #root {
	font: 0.9rem sans-serif;
	background: #0a1f44;
	color: #1e2432;
	height: 100%;
	margin: 0;
	}

	.main-container {

	const maybeNull = null
	if(maybeNull) { console.log("Not null") } else { console.log("Could be null") } // Could be null

	for(let i = 0; null; i++) { console.log("Won't run") }

	maybeNull ? console.log("truthy value") : console.log("Falsy value") // falsy value

	import http from "k6/http";
	import { check } from "k6";


	/*
	* Stages (aka ramping) is how you, in code, specify the ramping of VUs.
	* That is, how many VUs should be active and generating traffic against
	* the target system at any specific point in time for the duration of
	* the test.
	*

	using UnityEngine;
	using System.Collections;
	using System.Collections.Generic;
	using UnityEditor;
	using System;
	using System.IO;


	public class findGuid : MonoBehaviour {