Sung M. Kim dance2die

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.

`constant-locals-loader` for Webpack

This loader optimizes the output of mini-css-extract-plugin and/or css-loader, entirely removing the potentially large CSS classname mappings normally inlined into your bundle when using CSS Modules.

Run npm install constant-locals-loader, then make these changes in your Webpack config:

module.exports = {
 module: {

Update

The first post has been published: https://www.swyx.io/writing/cloud-distros

The second post has been adapted for Temporal: https://www.swyx.io/why-temporal/

these are bullet points of a blogpost on a topic i know very little about but i feel like there is something there that is happening as we speak

A compile-time 4-Bit Virtual Machine implemented in TypeScript's type system. Capable of running a sample 'FizzBuzz' program.

Syntax emits zero JavaScript.

type RESULT = VM<
  [
    ["push", N_1],         // 1
    ["push", False],       // 2
 ["peek", _], // 3

I heard some points of criticism to how React deals with reactivity and it's focus on "purity". It's interesting because there are really two approaches evolving. There's a mutable + change tracking approach and there's an immutability + referential equality testing approach. It's difficult to mix and match them when you build new features on top. So that's why React has been pushing a bit harder on immutability lately to be able to build on top of it. Both have various tradeoffs but others are doing good research in other areas, so we've decided to focus on this direction and see where it leads us.

I did want to address a few points that I didn't see get enough consideration around the tradeoffs. So here's a small brain dump.

"Compiled output results in smaller apps" - E.g. Svelte apps start smaller but the compiler output is 3-4x larger per component than the equivalent VDOM approach. This is mostly due to the code that is usually shared in the VDOM "VM" needs to be inlined into each component. The tr

Hi,

Would you be be able to update the post with a syntax highlight as to improve the readability? Refer to the Editor Guide for more info.

MOVED TO https://github.com/CodeMouse92/DEVModInACan

#BEGINNERS TAG REMOVALS

Non-Beginner Article

All articles on #beginners should be written for those new to programming, development, networking, or to a particular language. These posts should also require little to no prerequisite knowledge. If you wish, you may rewrite your post to meet these requirements, at which point you may request that the tag be added back. Otherwise, just use the appropriate technology tags. (Read more about the tag rules here.)

	import { useCallback, useLayoutEffect, DependencyList } from 'react'

	/**
	* This version bounces each version of the callback. This ensures that the callback
	* will be called with each state of the application. That's why `deps` is a required argument.
	*
	* Previous version used `useRef` for `timeoutId` and didn't have `deps` argument.
	* This resulted in missing calling the callback for the previous state and necessarily
	* calling it for the new state.
	*

	#!/bin/bash
	xrandr --output eDP-1-1 --mode 1280x720