karpathy

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.

khalidx

The experience of using Node.JS with TypeScript, ts-node, and ESM is horrible.

There are countless guides of how to integrate them, but none of them seem to work.

Here's what worked for me.

Just add the following files and run npm run dev. You'll be good to go!

package.json

gaearon

Next.js client-only SPA example

Made this example to show how to use Next.js router for a 100% SPA (no JS server) app.

You use Next.js router like normally, but don't define getStaticProps and such. Instead you do client-only fetching with swr, react-query, or similar methods.

You can generate HTML fallback for the page if there's something meaningful to show before you "know" the params. (Remember, HTML is static, so it can't respond to dynamic query. But it can be different per route.)

Don't like Next? Here's how to do the same in Gatsby.

DavidWells

/* Ultra lightweight Github REST Client */
// original inspiration via https://gist.github.com/v1vendi/75d5e5dad7a2d1ef3fcb48234e4528cb
const token = 'github-token-here'
const githubClient = generateAPI('https://api.github.com', {
  headers: {
    'User-Agent': 'xyz',
    'Authorization': `bearer ${token}`
  }
})

bmegli

Motivatation

• modern CMake is required for building a lot of new software
• CMake is dependency for many packages (e.g. ROS related)
• we don't want to remove CMake (which would remove packages that depend on it)
• we want safe procedure to update CMake that can be reversed easily

Current version in OS

Check current version

sindresorhus

Pure ESM package

The package that linked you here is now pure ESM. It cannot be require()'d from CommonJS.

This means you have the following choices:

1. Use ESM yourself. (preferred)
   Use import foo from 'foo' instead of const foo = require('foo') to import the package. You also need to put "type": "module" in your package.json and more. Follow the below guide.
2. If the package is used in an async context, you could use await import(…) from CommonJS instead of require(…).
3. Stay on the existing version of the package until you can move to ESM.

hugdru

diff --git a/node_modules/mongoose/lib/index.js b/node_modules/mongoose/lib/index.js
index 80a8ca5..cc3d2b4 100644
--- a/node_modules/mongoose/lib/index.js
+++ b/node_modules/mongoose/lib/index.js
@@ -4,16 +4,7 @@
  * Module dependencies.
  */
 
-if (global.MONGOOSE_DRIVER_PATH) {
-  const deprecationWarning = 'The `MONGOOSE_DRIVER_PATH` global property is ' +

jeb5

const channels = [...document.querySelectorAll("#main-link.channel-link")].map(e => {
	const [, a, b] = e.href.match("/((?:user)|(?:channel))/(.*)$");
	const feed = "https://www.youtube.com/feeds/videos.xml?" + (a === "user" ? "user=" : "channel_id=") + b;
	const channelName = e.querySelector("yt-formatted-string.ytd-channel-name").innerText;
	return [feed, channelName];
});
if (channels.length == 0) {
	alert("Couldn't find any subscriptions");
} else {
	console.log(channels.map(([feed, _]) => feed).join("\n"));

prologic

Learn Go in ~5mins

This is inspired by A half-hour to learn Rust and Zig in 30 minutes.

Basics

Your first Go program as a classical "Hello World" is pretty simple:

First we create a workspace for our project:

Arty2

// static/scripts/fixedsearch/fixedsearch.js
/*--------------------------------------------------------------
fixedsearch — Super fast, client side search for Hugo.io with Fusejs.io
based on https://gist.github.com/cmod/5410eae147e4318164258742dd053993
--------------------------------------------------------------*/

if (typeof variable !== 'undefined') {
	console.log('fixedsearch.js already loaded');
} else {
fixedsearch = function(){