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.

donaldguy

#!/bin/zsh --norcs

set -o NO_UNSET -o ERREXIT

if (! sudo -nv) {
  echo "re-run after caching sudo in parent shell, by e.g. running:\n\t sudo -v" >&2
  exit 1
}

autoload -Uz colors && colors

rafa-thayto

// Place your key bindings in this file to override the defaults
[
  {
    "key": "cmd+i",
    "command": "composerMode.agent"
  },
  {
    "key": "y",
    "command": "filesExplorer.copy",
    "when": "explorerViewletFocus && !inputFocus"

clouedoc

A guide to leaving Arc for Zen Browser

The problem with Arc is that it doesn't allow exporting data (history, bookmarks) to a file natively.

One way to do this is to use a script but that only exports Bookmarks and not the history.

I don't really use the bookmarks feature that much; what I really liked about Arc was that it was really easy to navigate to somewhere I already visited.

So, if you're like me, follow this guide and you'll be able to import your browsing history into Zen browser!

adtac

#!/usr/bin/env -S bash -c "docker run -p 8080:8080 -it --rm \$(docker build --progress plain -f \$0 . 2>&1 | tee /dev/stderr | grep -oP 'sha256:[0-9a-f]*')"

# syntax = docker/dockerfile:1.4.0

FROM node:20

WORKDIR /root

RUN npm install sqlite3

b0gdanw

#!/bin/zsh
# WARNING! The script is meant to show how and what can be disabled. Don’t use it as it is, adapt it to your needs.
# Credit: Original idea and script disable.sh by pwnsdx https://gist.github.com/pwnsdx/d87b034c4c0210b988040ad2f85a68d3
# Disabling unwanted services on macOS Big Sur (11), macOS Monterey (12), macOS Ventura (13) and macOS Sonoma (14)
# Disabling SIP is required  ("csrutil disable" from Terminal in Recovery)
# Modifications are written in /private/var/db/com.apple.xpc.launchd/ disabled.plist, disabled.501.plist
# To revert, delete /private/var/db/com.apple.xpc.launchd/ disabled.plist and disabled.501.plist and reboot; sudo rm -r /private/var/db/com.apple.xpc.launchd/*


# user

swarn

Semantic Highlighting in Neovim

• What is Semantic Highlighting?
• Default Highlighting
  • Tokens to Highlights
  • Changing Highlights
  • Disable Semantic Highlighting
• Using LspTokenUpdate for Complex Highlighting
  • Highlighting Based on More Than One Modifier
• Dealing with Ambiguity

Blackshome

blueprint:
  name: Sensor Light
  description: >
    # 💡 Sensor Light

    **Version: 8.5**


    Your lighting experience, your way - take control and customize it to perfection! 💡✨

aidenlx

#!/bin/bash
 
# Script for installing Fish Shell on systems without root access.
# Fish Shell will be installed in $HOME/.local
# It's assumed that wget and following packages is installed (https://github.com/fish-shell/fish-shell#dependencies-1)
# 1. a C++11 compiler (g++ 4.8 or later, or clang 3.3 or later)
# 2. CMake (version 3.5 or later)
 
# exit on error
set -e

EldonMcGuinness

0.0.0.0 activate.adobe.com
0.0.0.0 practivate.adobe.com
0.0.0.0 ereg.adobe.com
0.0.0.0 wip3.adobe.com
0.0.0.0 activate.wip3.adobe.com
0.0.0.0 3dns-3.adobe.com
0.0.0.0 3dns-2.adobe.com
0.0.0.0 adobe-dns.adobe.com
0.0.0.0 adobe-dns-2.adobe.com
0.0.0.0 adobe-dns-3.adobe.com