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.

tanbro

单机多用户 JupyterLab 环境搭建

概述

在这篇短文中，我们记录了如何在使用 [Ubuntu][] 1804 LTS 操作系统的单台服务器上，建立用户隔离的 [JupyterLab][] Web 环境。

目标是：

• 操作系统的用户可以各自不受干扰的使用独立的 [JupyterLab][]
• 各个用户的 [Conda][] 环境可以自动的出现在 [JupyterLab][] 的 Kernel 列表中

thrawn01

package main

import (
	"context"
	"fmt"
	"os"
	"os/signal"
	"syscall"
	"time"

apalala

from __future__ import print_function
from math import sin, cos, radians
import timeit

'''
A simple Python benchmark.

Results on an overclocked AMD FX-8150 Eight-Core CPU @ 3.0 GHz, and
an Intel Core i5-2410M CPU @ 2.30GHz.

mjackson

/**
 * Converts an RGB color value to HSL. Conversion formula
 * adapted from http://en.wikipedia.org/wiki/HSL_color_space.
 * Assumes r, g, and b are contained in the set [0, 255] and
 * returns h, s, and l in the set [0, 1].
 *
 * @param   Number  r       The red color value
 * @param   Number  g       The green color value
 * @param   Number  b       The blue color value
 * @return  Array           The HSL representation