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.

plumhead

extension String {
    func size(withAttributes attrs: [String:AnyObject], constrainedTo box: NSSize) -> NSRect {
        let storage = NSTextStorage(string: self)
        let container = NSTextContainer(containerSize: NSSize(width: box.width, height: box.height))
        let layout = NSLayoutManager()
        layout.addTextContainer(container)
        storage.addLayoutManager(layout)
        storage.addAttributes(attrs, range: NSMakeRange(0, storage.length))
        container.lineFragmentPadding = 0.0
        let _ = layout.glyphRangeForTextContainer(container)

ihoneymon

[공통] 마크다운 markdown 작성법

영어지만, 조금 더 상세하게 마크다운 사용법을 안내하고 있는
"Markdown Guide (https://www.markdownguide.org/)" 를 보시는 것을 추천합니다. ^^

아, 그리고 마크다운만으로 표현이 부족하다고 느끼신다면, HTML 태그를 활용하시는 것도 좋습니다.

1. 마크다운에 관하여

neojou

import Foundation


func input() -> String {
    var keyboard = NSFileHandle.fileHandleWithStandardInput()
    var inputData = keyboard.availableData
    return NSString(data: inputData, encoding:NSUTF8StringEncoding)
}

mohayonao

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import re
import sys
import math
import array
import random
import itertools
import collections