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.

heiso

[include mainsail.cfg]

[gcode_macro _CLIENT_VARIABLE]
variable_use_custom_pos   : False ; use custom park coordinates for x,y [True/False]
variable_custom_park_x    : 0.0   ; custom x position; value must be within your defined min and max of X
variable_custom_park_y    : 0.0   ; custom y position; value must be within your defined min and max of Y
variable_custom_park_dz   : 2.0   ; custom dz value; the value in mm to lift the nozzle when move to park position
variable_retract          : 1.0   ; the value to retract while PAUSE
variable_cancel_retract   : 5.0   ; the value to retract while CANCEL_PRINT
variable_speed_retract    : 35.0  ; retract speed in mm/s

dsmith73

Installing homebrew / Linuxbrew on Ubuntu-18.04 wsl for Windows 10

---

open wsl command line

type -

sh -c "$(curl -fsSL https://raw.githubusercontent.com/Linuxbrew/install/master/install.sh)"  

tomhicks

/*
Copy this into the console of any web page that is interactive and doesn't
do hard reloads. You will hear your DOM changes as different pitches of
audio.

I have found this interesting for debugging, but also fun to hear web pages
render like UIs do in movies.
*/

const audioCtx = new (window.AudioContext || window.webkitAudioContext)()

manuelbl

ESP32 as Bluetooth Keyboard

With its built-in Bluetooth capabilities, the ESP32 can act as a Bluetooth keyboard. The below code is a minimal example of how to achieve it. It will generate the key strokes for a message whenever a button attached to the ESP32 is pressed.

For the example setup, a momentary button should be connected to pin 2 and to ground. Pin 2 will be configured as an input with pull-up.

In order to receive the message, add the ESP32 as a Bluetooth keyboard of your computer or mobile phone:

1. Go to your computers/phones settings
2. Ensure Bluetooth is turned on

kevbost

Ubuntu

Windows Subsystem for Linux [Very Easy Installation]

1. https://msdn.microsoft.com/commandline/wsl/install_guide
   • [Follow instructions carefully and remember your password]
   • [it will prompt for password]
   • [password will not appear while you type, just push enter when finished]
2. Open "Bash on Ubuntu on Windows"
3. Run the commands formatted as code separately

• (they will take a while to complete)

kitze

import React from 'react';

const ConditionalWrap = ({condition, wrap, children}) => condition ? wrap(children) : children;

const Header = ({shouldLinkToHome}) => (
  <div>
    <ConditionalWrap
      condition={shouldLinkToHome}
      wrap={children => <a href="/">{children}</a>}
    >

kidGodzilla

// The following example POSTS data to mailthis.to, redirects the user to a confirmation page, and then sends an email (upon the successful completion of Recaptcha verification)

$.post('https://mailthis.to/test@example.com', {
  email: 'foo@bar.co',
  _subject: 'hi!',
  message: 'Test'
}).then(function () {
  location.href = 'https://mailthis.to/confirm'
});

chrisveness

/**
 * Encrypts plaintext using AES-GCM with supplied password, for decryption with aesGcmDecrypt().
 *                                                                      (c) Chris Veness MIT Licence
 *
 * @param   {String} plaintext - Plaintext to be encrypted.
 * @param   {String} password - Password to use to encrypt plaintext.
 * @returns {String} Encrypted ciphertext.
 *
 * @example
 *   const ciphertext = await aesGcmEncrypt('my secret text', 'pw');

AndiDittrich

// SPDX-License-Identifier: MPL-2.0

// AES Encryption/Decryption with AES-256-GCM using random Initialization Vector + Salt
// ----------------------------------------------------------------------------------------
// the encrypted datablock is base64 encoded for easy data exchange. 
// if you have the option to store data binary save consider to remove the encoding to reduce storage size
// ----------------------------------------------------------------------------------------
// format of encrypted data - used by this example. not an official format
//
// +--------------------+-----------------------+----------------+----------------+