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.

NigelEarle

Migrations & Seeding

What are migrations??

Migrations are a way to make database changes or updates, like creating or dropping tables, as well as updating a table with new columns with constraints via generated scripts. We can build these scripts via the command line using knex command line tool.

To learn more about migrations, check out this article on the different types of database migrations!

Creating/Dropping Tables

jayphelps

let buffer = getWebSocket()
  .bufferTime(1000);

let gate = new BehaviorSubject(true);
let batchSize = 50;
let batchSizeCounter = 0;

let results = gate
  .switchMap(enabled => enabled ? buffer : Observable.never())
  .do(buffer => {

huesitos

Git Cheat Sheet

Add & Commit

git init
Inicializa un repositorio.

git status
Muestra cuál es el estado actual del proyecto (qué archivos han sido modificados, cuáles están en el directorio de trabajo y cuáles en el stage area).

git add [file] ó git add --all
Agrega archivos al stage area.

jacobian

from django.db import models

class Person(models.Model):
    name = models.CharField(max_length=200)
    groups = models.ManyToManyField('Group', through='GroupMember', related_name='people')
    
    class Meta:
        ordering = ['name']
    
    def __unicode__(self):