oozoofrog

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.

oozoofrog

import sys
import requests
import yt_dlp
import openai

def get_best_format(m3u8_url):
    ydl_opts = {
        'listformats': True,
    }
    

oozoofrog

try:
    import lldb
except:
    pass
import textwrap
import hashlib

from collections import namedtuple

object_register = ""

oozoofrog

extension Notification.Name {
    static let testNotification: Notification.Name = .init("TestNotification")
}

final class NotificationConcurrencyTests: XCTestCase {

    func testWaitNotification() async throws {
        let expect = XCTestExpectation(description: "DisposableNotification")
        let queue = DispatchQueue(label: "test", attributes: .concurrent)
        for _ in 0...10 {

oozoofrog

public extension NotificationCenter {
    private class FirstReceiver: NSObject {

        let notificationName: Notification.Name

        init(_ name: Notification.Name) {
            notificationName = name
            super.init()
        }

oozoofrog

final class PreviewView: UIView, LayoutBuilding {
    
    var capTop = true {
        didSet {
            UIView.animate(withDuration: 1.0) {
                self.updateLayout()
            }
        }
    }
    

oozoofrog

Debugging the Swift Toolchain

Use these steps to debug components of the Swift toolchain. This allows you to see Swift's source code from the debugger – instead of disassembly. The debugger can also provide some variable names and values. This has been initially tested with libswiftCore.dylib.

These instructions were updated as of Swift 5.2.1.

Prerequisites

oozoofrog

import Cocoa

var str = "궉토abcd스234꾹타ㅎ하후훼의"
extension Collection {
    var toArray: [Element] {
        return Array(self)
    }
}

protocol UnicodeScalarCreatable {

oozoofrog

Keybase proof

I hereby claim:

• I am rollmind on github.
• I am rollmind (https://keybase.io/rollmind) on keybase.
• I have a public key ASDHVKuqfnxsGNBCmHuUiLoLqU4GdFa6tJUiK3tKYF95vgo

To claim this, I am signing this object:

oozoofrog

struct Be<Value> {
	let value: Value
}

protocol BeAddible {
	var be: Be<Self> { get }
}

extension Be where Value: Comparable {