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.

iagooar

Omarchy Cheat Sheet for Devs

A comprehensive reference for Omarchy - an opinionated Arch Linux + Hyprland setup by DHH.

Essential Keyboard Shortcuts

System & Window Management

Shortcut	Function

cloorc

/*
 * A simple vscode style customization for https://github.com/be5invis/vscode-custom-css
 * Just put this file into anywhere and refer it from your vscode `settings.json` under `vscode_custom_css.imports` as following:
 * "vscode_custom_css.imports": [
 *   "file:///c:/Users/anyone/vscode.css"
 * ]
 **/
a.label-name,
p.subtitle.description,
h1.product-name.caption,

Snawoot

Poor Man's Global Traffic Manager

Sometimes we need to add redundancy to some service or server which happen to be a public-facing entry point of our infrastructure. For example, imagine we want to add a high availability pair for a load balancer which sits on the edge of network and forwards traffic to alive backend servers.

                                             ┌─────────────┐
                                             │             │
                                      ┌─────►│  Backend 1  │
                                      │      │             │
                                      │      └─────────────┘

auycro

(this is an old example that illustrates how I introduced a a team to the process of RFCs, my understanding of how to deploy this process well has evolved since then)

RFC on RFCs

• Main Author: @buritica
• Backers: n/a

1 Summary

mario52a

# -*- coding: utf-8 -*-
from __future__ import unicode_literals
#
"""
***************************************************************************
*   Copyright (c) <mario52> 2017 2018 2019 2020 2021 2022 2023 2024 2025  *
*                                                                         *
*   This file is a supplement to the FreeCAD CAx development system.      *
*                                                                         *
*   This program is free software; you can redistribute it and/or modify  *

johnloy

Electron apps

• Marp: Markdown presentation ecosystem.

• muryoimpl/slippr: markdown presentation app by Electron

• joe-re/cafe-pitch Markdown-driven presentation tool built on Electron.

Slide deck frameworks supporting Markdown source

magnetikonline

AWS CLI JMESPath cheatsheet

Random query recipes of JMESPath for the AWS CLI tools that I might have written or stumbled upon.

• Examples
  • List available AWS regions
  • List Lambda functions within AWS account region
  • Test if specific Lambda function exists
  • List Route 53 record names and their type for a zone
  • List CloudWatch log groups

mikaelz

# Basic commands

    :Git [args]              # does what you'd expect

all of your `~/.gitconfig` aliases are available.

    :Git! [args]             # same as before, dumping output to a tmp file

Moving inside a repo.

koppi

#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Sends HAL signals to the given MQTT broker host.
#
# usage: hal2mqtt.py [hostname]
#
# Video demo at https://www.youtube.com/watch?v=uFbr7xBjItE
#
# sudo apt-get install mosquitto mosquitto-clients python-mosquitto