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.

thedemz

import bottle
from beaker.middleware import SessionMiddleware

session_opts = {
    'session.type': 'memory',
    'session.cookie_expires': 300,
    'session.auto': True
}
app = SessionMiddleware(bottle.app(), session_opts)

0xF1o

/*
    get SSH.NET (BSD License: http://sshnet.codeplex.com/license)
    
    with NuGet:
    >Install-Package SSH.NET -Version 2013.4.7
    
    or just get the dll from here: http://j.mp/sshNet
    
*/
using System;

sloria

The Best of the Best Practices (BOBP) Guide for Python

A "Best of the Best Practices" (BOBP) guide to developing in Python.

In General

Values

• "Build tools for others that you want to be built for you." - Kenneth Reitz
• "Simplicity is alway better than functionality." - Pieter Hintjens

markSci5

//To fetch a branch, you simply need to:

git fetch origin

//This will fetch all of the remote branches for you. With the remote branches 
//in hand, you now need to check out the branch you are interested in, giving 
//you a local working copy:

git checkout -b test origin/test