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.

jlia0

You are Manus, an AI agent created by the Manus team.

You excel at the following tasks:
1. Information gathering, fact-checking, and documentation
2. Data processing, analysis, and visualization
3. Writing multi-chapter articles and in-depth research reports
4. Creating websites, applications, and tools
5. Using programming to solve various problems beyond development
6. Various tasks that can be accomplished using computers and the internet

dansleboby

// ==UserScript==
// @name         Suno Aligned Words Fetcher with Auth
// @namespace    http://tampermonkey.net/
// @version      1.3
// @description  Fetch aligned words with auth and add a button under the image on Suno pages.
// @author       Dschibait
// @match        https://suno.com/song/*
// @grant        none
// ==/UserScript==

wavezhang

wget -c --no-cookies --no-check-certificate --header "Cookie: oraclelicense=accept-securebackup-cookie"  https://download.oracle.com/otn-pub/java/jdk/12.0.2+10/e482c34c86bd4bf8b56c0b35558996b9/jdk-12.0.2_linux-x64_bin.tar.gz

jbrown17

import java.awt.EventQueue;
import java.io.*;
import java.math.BigInteger;
import java.util.ArrayList;
import java.util.Random;
import java.util.Scanner;


/**
 * Quick and dirty implementation of the RSA algorithm

snakevil

如何在路由器中实现透明代理？

0 互联网现状

目前整个互联网环境，被破坏最严重地部分，是 Web 服务体验。当直接破坏难以实现时，就会从流程链的上下游着手，如：DNS 污染。

其它地互联网服务类型，例如：邮件，可能小部分会受到 Web 服务上下游破坏地余震，但整体上基本不受影响。

calebwoods

server { listen  80;
  server_name example.com;
  access_log /var/log/example.com/nginx.access.log;
  error_log  /var/log/example.com/nginx.error.log;
  root /var/www/apps/example.com/public;
  charset utf-8;

  location / {
    rewrite ^ https://$host$request_uri? permanent;
  }

nikic

<?php

error_reporting(E_ALL);

require __DIR__ . '/FastRoute/src/bootstrap.php';

spl_autoload_register(function ($class) {
    require __DIR__ . '/Pux/src/' . strtr($class, '\\', '/') . '.php';
});

edokeh

//
//                       _oo0oo_
//                      o8888888o
//                      88" . "88
//                      (| -_- |)
//                      0\  =  /0
//                    ___/`---'\___
//                  .' \\|     |// '.
//                 / \\|||  :  |||// \
//                / _||||| -:- |||||- \

LegendZhu

<?php
    
    define('PREVIEW_TOTLE', 15);//总数
    define('ROW_NUMBER', 3);//每行的个数，应可被TOTLE整除
    
    $total = PREVIEW_TOTLE;
    $row = ROW_NUMBER;
    $count = count($val['tag_ids']);
    $last = $total - $count;
    $j = 0;