tylerhall

<?PHP
	require '/path/to/markdown-extra.php';

	$db = mysql_connect('localhost', 'root', 'password') or die(mysql_error());
	mysql_select_db('tylerio', $db) or die(mysql_error());

	$files = scandir('posts');
	array_shift($files); // .
	array_shift($files); // ..

52cik

npm set registry https://r.npm.taobao.org # 注册模块镜像
npm set disturl https://npm.taobao.org/dist # node-gyp 编译依赖的 node 源码镜像

## 以下选择添加
npm set sass_binary_site https://npm.taobao.org/mirrors/node-sass # node-sass 二进制包镜像
npm set electron_mirror https://npm.taobao.org/mirrors/electron/ # electron 二进制包镜像
npm set ELECTRON_MIRROR https://cdn.npm.taobao.org/dist/electron/ # electron 二进制包镜像
npm set puppeteer_download_host https://npm.taobao.org/mirrors # puppeteer 二进制包镜像
npm set chromedriver_cdnurl https://npm.taobao.org/mirrors/chromedriver # chromedriver 二进制包镜像
npm set operadriver_cdnurl https://npm.taobao.org/mirrors/operadriver # operadriver 二进制包镜像

vlucas

<?php
// Turn on all error reporting so we can see if anything goes wrong
ini_set('display_errors', 1);
ini_set('display_startup_errors', 1);
error_reporting(-1);

// Relative path to your wp-config.php file (to connect to the database)
require '../wp-config.php';
require './frontmatter.php'; // Parses YAML frontmatter - https://github.com/Modularr/YAML-FrontMatter
require './Parsedown.php'; // Markdown parser - https://github.com/erusev/parsedown

ryanlid

socks5代理

youtube-dl --proxy socks5://127.0.0.1:1080 https://www.youtube.com/watch?v=6_gLU_OStK0

http代理

youtube-dl --proxy http://127.0.0.1:8118 https://www.youtube.com/watch?v=6_gLU_OStK0

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.

rohitg00

LLM Wiki v2

A pattern for building personal knowledge bases using LLMs. Extended with lessons from building agentmemory 20K+ Stars ⭐️, a persistent memory engine for AI coding agents.

This builds on Andrej Karpathy's original LLM Wiki idea file. Everything in the original still applies. This document adds what we learned running the pattern in production: what breaks at scale, what's missing, and what separates a wiki that stays useful from one that rots.

What the original gets right

The core insight is correct: stop re-deriving, start compiling. RAG retrieves and forgets. A wiki accumulates and compounds. The three-layer architecture (raw sources, wiki, schema) works. The operations (ingest, query, lint) cover the basics. If you haven't read the original, start there.