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.

pythonbuddha

What are the consequences for a person driving a motor vehicle under the influence of drugs (e.g. hashish, heroin, cocaine)?

[x] Confiscation of driving licence or driving ban
[x] Compulsory medical/psychological examination
[x] Fine and/or imprisonment

In which instances do you have to approach a pedestrian crossing with particular care?

[x] If pedestrians want to cross the road

[x] If the view of the pedestrian crossing is restricted

Mahedi-61

#!/bin/bash

### steps ####
# Verify the system has a cuda-capable gpu
# Download and install the nvidia cuda toolkit and cudnn
# Setup environmental variables
# Verify the installation
###

### to verify your gpu is cuda enable check

bzerangue

Verify and Repair Disk Permissions via Terminal (Mac OS X)

Verify Permissions

diskutil verifyPermissions /

Repair Permissions

diskutil repairPermissions /