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.

manti-by

#!/bin/bash
echo "Add user and disable password prompt"
adduser manti
usermod -aG sudo manti
echo "manti   ALL=(ALL) NOPASSWD:ALL" >> /etc/sudoers

echo "Remove unnecessary packages"
apt remove -y needrestart

echo "Install base system packages"

manti-by

Setup Traktor Audio 6 on Ubuntu

Update pulsaduio config

When plugged-in, the soundcard was given a different idProduct than expected (1011 instead of 1010).

1. Open file /lib/udev/rules.d/90-pulseaudio.rules
2. Find line with text usb 1-2: New USB device found, idVendor=17cc, idProduct=1011

checco

--
-- Read only 
--

-- Create a group
CREATE ROLE postgres_ro_group;

-- Grant access to existing tables
GRANT USAGE ON SCHEMA public TO postgres_ro_group;
GRANT SELECT ON ALL TABLES IN SCHEMA public TO postgres_ro_group;

ketanbhatt

from django.contrib.admin import ModelAdmin

class MyTableAdmin(ModelAdmin):
    ...
    paginator = LargeTablePaginator
    ...
    

bastman

Docker - How to cleanup (unused) resources

Once in a while, you may need to cleanup resources (containers, volumes, images, networks) ...

delete volumes

// see: https://github.com/chadoe/docker-cleanup-volumes

$ docker volume rm $(docker volume ls -qf dangling=true)

$ docker volume ls -qf dangling=true | xargs -r docker volume rm

chadrien

Debug your PHP in Docker with Intellij/PHPStorm and Xdebug

1. For your local dev, create a Dockerfile that is based on your production image and simply install xdebug into it. Exemple:

FROM php:5

RUN yes | pecl install xdebug \
&& echo "zend_extension=$(find /usr/local/lib/php/extensions/ -name xdebug.so)" > /usr/local/etc/php/conf.d/xdebug.ini \

glen-cheney

Encoding Video

Installing

Install FFmpeg with homebrew. You'll need to install it with a couple flags for webm and the AAC audio codec.

brew install ffmpeg --with-libvpx --with-libvorbis --with-fdk-aac --with-opus

mandiwise

// Reference: http://www.blackdogfoundry.com/blog/moving-repository-from-bitbucket-to-github/
// See also: http://www.paulund.co.uk/change-url-of-git-repository

$ cd $HOME/Code/repo-directory
$ git remote rename origin bitbucket
$ git remote add origin https://github.com/mandiwise/awesome-new-repo.git
$ git push origin master

$ git remote rm bitbucket