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.

wong2

Task

Launch a new agent that has access to the following tools: Bash, Glob, Grep, LS, exit_plan_mode, Read, Edit, MultiEdit, Write, NotebookRead, NotebookEdit, WebFetch, TodoRead, TodoWrite, WebSearch. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries, use the Agent tool to perform the search for you.

When to use the Agent tool:

• If you are searching for a keyword like "config" or "logger", or for questions like "which file does X?", the Agent tool is strongly recommended

When NOT to use the Agent tool:

• If you want to read a specific file path, use the Read or Glob tool instead of the Agent tool, to find the match more quickly
• If you are searching for a specific class definition like "class Foo", use the Glob tool instead, to find the match more quickly
• If you are searching for code within a specific file or set of 2-3 files, use the Read tool instead of the Agent tool, to find the match more quickly

Rafisto

How to easily setup PXE boot for cluster provisioning

This guide will show you how to setup a PXE boot server to provision a cluster of machines. For the sake of this guide, we will be using system agnostic docker containers to simulate the DHCP and the PXE boot server.

Featured technologies:

• netbootxyz
• networkboot/dhcpd

PXE boot description

spipm

#!/bin/bash

# Run PXE boot server on interface
#   Seems to work with UEFI and Secureboot
#   Spip, 2023
#
# Most stuff from https://www.youtube.com/watch?v=E_OlsA1hF4k
#

# Check args

lafentres

#!/bin/bash

# Credit to https://gist.github.com/alisdair/ffc7c884ee36ac132131f37e3803a1fe for the excellent original
# script that this one is based on. This script modifies the original to create the all-the-way-down effect.

# Generate a `:*-all-the-way-down:` Slack emoji, given a reasonable image
# input. I recommend grabbing an emoji from https://emojipedia.org/

set -euo pipefail

smith

{
  "type": "object",
  "required": ["name", "description", "identity", "trigraphs"],
  "description": "JSON schema for https://spellcaster.sh",
  "properties": {
    "name": {
      "type": "string",
      "description": "represents an intent, desired state, or outcome."
    },
    "description": {

lafentres

#!/bin/bash

# Credit to https://gist.github.com/alisdair/ffc7c884ee36ac132131f37e3803a1fe for the excellent original 
# script that this one is based on. This script modifies the original to create the jumbo. 

# Generate a jumbo Slack emoji, given a reasonable image
# input. I recommend grabbing an emoji from https://emojipedia.org/

set -euo pipefail

lafentres

#!/bin/bash

# Credit to https://gist.github.com/alisdair/ffc7c884ee36ac132131f37e3803a1fe for the excellent original 
# script that this one is based on. This script modifies the original to create the party effect. 

# Generate a `:*-party:` Slack emoji, given a reasonable image
# input. I recommend grabbing an emoji from https://emojipedia.org/

set -euo pipefail

shawwn

This was a response to a Hacker News comment asking me what I've been up to since 2010. I'm posting it here since HN rejects it with "that comment is too long." I suppose that's fair, since this ended up being something of an autobiography.

--

What happened after 2010?

raysan5

CUSTOM GAME ENGINES: A Small Study

WARNING: Article moved to separate repo to allow users contributions: https://github.com/raysan5/custom_game_engines

A couple of weeks ago I played (and finished) A Plague Tale, a game by Asobo Studio. I was really captivated by the game, not only by the beautiful graphics but also by the story and the locations in the game. I decided to investigate a bit about the game tech and I was surprised to see it was developed with a custom engine by a relatively small studio. I know there are some companies using custom engines but it's very difficult to find a detailed market study with that kind of information curated and updated. So this article.

Nowadays lots of companies choose engines like [Unreal](https: