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.

inamiy

React & Elm inspired frameworks in Swift

This is a curated list of iOS (Swift & ObjC) frameworks which are inspired by React and Elm.

Swift frameworks

React-inspired

• ReactSwift by @ColinEberhardt
• https://github.com/ColinEberhardt/ReactSwift

toddhopkinson

// You have a very very large video file you need to upload to a server while your app is backgrounded.
// Solve by using URLSession background functionality. I will here use Alamofire to enable multipart upload.

class Networking {
  static let sharedInstance = Networking()
  public var sessionManager: Alamofire.SessionManager // most of your web service clients will call through sessionManager
  public var backgroundSessionManager: Alamofire.SessionManager // your web services you intend to keep running when the system backgrounds your app will use this
  private init() {
    self.sessionManager = Alamofire.SessionManager(configuration: URLSessionConfiguration.default)
    self.backgroundSessionManager = Alamofire.SessionManager(configuration: URLSessionConfiguration.background(withIdentifier: "com.lava.app.backgroundtransfer"))

kevin-smets

Default

Powerlevel10k