Adi adisetiawan

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.

A non-exhaustive list of WebGL and WebGPU frameworks and libraries. It is mostly for learning purposes as some of the libraries listed are wip/outdated/not maintained anymore.

Engines and libraries ⚙️

Name	Stars	Last Commit	Description
three.js	![GitHub

Configuring Gammu for Mac OSX 10.11

Requirements

Disconnect modem first
Download and Install Driver USB Prolific for PL2303 Mac OS X
Reboot Mac
Install Homebrew

Step by step:

Type below command :

TERUSLAH BERSAHABAT SAMPAI WAKTUNYA PULANG

Ketika ada kesempatan, pergilah bersama teman teman lama. Berkumpul - kumpul, bukan sekadar makan, minum dan bersenang, senang tetapi ingat, Waktu hidup kita semakin singkat. Maka dari itu, bangunkanlah Persaudaraan

Mungkin lain waktu kita Tidak akan bertemu lagi.

Mungkin lain waktu kita sudah semakin Susah untuk berjalan.

Umur itu Seperti es batu, Dipakai atau tidak akan tetap mencair dan berakhir.

	const ALPHAPET = '234567abcdefghijklmnopqrstuvwxyz'

	function encode (i) {
	let s = ''
	while (i) {
	const c = i % 32
	i = Math.floor(i / 32)
	s = ALPHAPET.charAt(c) + s
	}
	return s

	/**
	* Wraps a function with caching functionality.
	* Allows for caching of expensive functions like paginated API calls that rarely change.
	*
	* @param fn - The function to cache results from
	* @param options - Optional configuration for the cache behavior
	* @param options.maxAge - Maximum age of cached data in milliseconds
	* @returns A function that returns the result of the function, either from cache or fresh execution
	*
	* @example

	"""Async and await example using subprocesses

	Note:
	Requires Python 3.6.
	"""

	import sys
	import time
	import platform
	import asyncio

	DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
	Version 2, December 2004

	Copyright (C) 2020 Adi Setiawan <adisetiawan@gmail.com>

	Everyone is permitted to copy and distribute verbatim or modified
	copies of this license document, and changing it is allowed as long
	as the name is changed.

	DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE

	<!DOCTYPE html>
	<html>
	<body>
	<!-- 1. The <iframe> (and video player) will replace this <div> tag. -->
	<div id="player"></div>
	<div>Current Time: <span id="time"></span></div>

	<script>
	// 2. This code loads the IFrame Player API code asynchronously.
	var tag = document.createElement('script');