Muhammad Nasrurrohman jurnalanas

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.

Automated PR Reviews with Claude Opus on AWS Bedrock

A GitHub Actions workflow that uses Claude Opus (via AWS Bedrock) to automatically review pull requests with inline comments.

Features

Two-round review system — Round 1 reviews the full diff, Round 2 only reviews changes made after Round 1 (to address feedback). No further reviews after Round 2.
Inline PR comments — Feedback is posted as review comments on specific file/line, not just a wall of text.
Cost tracking — Each review comment includes token usage and estimated cost.
Smart skipping — Docs/config-only PRs are skipped automatically.

Meta Prompting

In the Generative AI Age your ability to generate prompts is your ability to generate results.

Guide

Claude 3.5 Sonnet and o1 series models are recommended for meta prompting.

Replace {{user-input}} with your own input to generate prompts.

Use mp_*.txt as example user-inputs to see how to generate high quality prompts.

Purpose

Bootstrap knowledge of LLMs ASAP. With a bias/focus to GPT.

Avoid being a link dump. Try to provide only valuable well tuned information.

Prelude

Neural network links before starting with transformers.

Service Worker - offline support for the web

Progressive apps - high-res icon, splash screen, no URL bar, etc.

Progressive Web Apps: Escaping Tabs Without Losing Our Soul

Download videos from egghead

Go to the egghead website, i.e. Building a React.js App

run

$.each($('h4 a'), function(index, video){
  console.log(video.href);
});

	// Note: this gist is a part of this OSS project that I'm currently working on: https://github.com/steven-tey/dub

	export default async function getTitleFromUrl (url: string) {
	const controller = new AbortController();
	const timeoutId = setTimeout(() => controller.abort(), 2000); // timeout if it takes longer than 2 seconds
	const title = await fetch(url, { signal: controller.signal })
	.then((res) => {
	clearTimeout(timeoutId);
	return res.text();
	})

	(() => {
	let count = 0;

	function getAllButtons() {
	return document.querySelectorAll('button.is-following') \|\| [];
	}

	async function unfollowAll() {
	const buttons = getAllButtons();

	addEventListener('fetch', function (event) {
	event.respondWith(handleRequest(event.request));
	});

	// Allowed domain origins
	var allowed = ['http://localhost:8000', 'https://your-website.com'];

	/**
	* Respond to the request
	* @param {Request} request

	function waitForElement(selector) {
	return new Promise(function(resolve, reject) {
	var element = document.querySelector(selector);

	if(element) {
	resolve(element);
	return;
	}

	var observer = new MutationObserver(function(mutations) {