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.

kconner

macOS Internals

Understand your Mac and iPhone more deeply by tracing the evolution of Mac OS X from prelease to Swift. John Siracusa delivers the details.

Starting Points

How to use this gist

You've got two main options:

likethesky

$ brew update && brew doctor          # Repeat, until you've done *all* the Dr. has ordered!
$ brew install postgresql             # You'll need postgres to do this... you may also need to 'initdb' as well. Google it.

$ brew install elixir
$ mix local.hex                       # Answer y to any Qs
$ createuser -d postgres              # create the default 'postgres' user that Chris McCord seems to like -- I don't create mine w/a pw...

# Use the latest Phoenix from here: http://www.phoenixframework.org/docs/installation -- currently this is 1.0.3
# ** Answer y to any Qs **
$ mix archive.install https://github.com/phoenixframework/phoenix/releases/download/v1.0.3/phoenix_new-1.0.3.ez

xiaolai

# default.custom.yaml
# save it to: 
#   ~/.config/ibus/rime  (linux)
#   ~/Library/Rime       (macos)
#   %APPDATA%\Rime       (windows)

patch:
  schema_list:
    - schema: luna_pinyin   # 朙月拼音
    - schema: terra_pinyin  # 地球拼音 dì qiú pīn yīn

jonmumm

OpenTok is a hosted API for adding real-time video chat to your application. The API gives developers the ability to create private one-to-one chats, group chats, or broadcasts that can stream to thousands of viewers in real-time.

When developing with OpenTok, most of the development is done on the client. The server is used only to generate and distribute room ids (sessions) and security credentials (tokens) to the client.

OpenTok has client-side libraries for JavaScript, iOS, and ActionScript, and server-side libraries for Ruby, PHP, Java, Python, .NET and Node.js. This add-on will set up your server-side environment for use with OpenTok.

n1k0

/**
 * Sample key binding (emacs users will hate it, but they're probably not using SublimeText2)
 *
 */
[
    { "keys": ["ctrl+w"], "command": "run_macro_file", "args": {"file": "Packages/User/Quick Wrap.sublime-macro"}}
]

lotem

# luna_pinyin.custom.yaml
#
# 【朙月拼音】模糊音定製模板
#   佛振配製 :-)
#
# 位置：
# ~/.config/ibus/rime  (Linux)
# ~/Library/Rime  (Mac OS)
# %APPDATA%\Rime  (Windows)
#

myobie

Get Mountain Lion and Homebrew to Be Happy

1) Install XCode 4.4 into /Applications

Get it from the App Store.

2) Install Command Line Tools

In XCode's Preferences > Downloads you can install command line tools.

jcasimir

Sessions and Conversations

HTTP is a stateless protocol. Sessions allow us to chain multiple requests together into a conversation between client and server.

Sessions should be an option of last resort. If there's no where else that the data can possibly go to achieve the desired functionality, only then should it be stored in the session. Sessions can be vulnerable to security threats from third parties, malicious users, and can cause scaling problems.

That doesn't mean we can't use sessions, but we should only use them where necessary.

Adding, Accessing, and Removing Data

wahyusumartha

#!/bin/bash
#!/usr/bin/env ruby
#########################################
# Define source and destinations

MONGO_DBS=""
BACKUP_TMP=~/tmp
BACKUP_DEST=~/backups
MONGODUMP_BIN=/Users/wahyusumartha/Documents/mongodb-db/bin/mongodump
TAR_BIN=/usr/bin/tar