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.

Moonbase59

#!/bin/bash

# pl-copyfiles
#
# Copies media files from M3U playlists to a destination folder,
# keeping folder structure and file attributes.
#
# Can use .m3u, .m3u8 (or actually any text file containing a newline-
# separated list of files) with absolute or relative file paths,
# both simple (one line per file) and #EXTM3U formats.

mugi-uno

リモートワークスタイルチェック

昨今の社会情勢の影響もありリモートワークを導入する企業・チームが増えてきましたが、 一口に「リモートワーク」といってもさまざまなスタイルがあります。

企業側と働く側のミスマッチを防ぐため、リモートワークにおける観点を列挙してみました。

リモートワーク比重度

どの程度リモートワークに比重を置いて導入しているかのチェックリストです。

ClementNerma

ZSH CheatSheet

This is a cheat sheet for how to perform various actions to ZSH, which can be tricky to find on the web as the syntax is not intuitive and it is generally not very well-documented.

Strings

Description	Syntax
Get the length of a string	${#VARNAME}
Get a single character	${VARNAME[index]}

senderle

So you want to modify the text of a PDF by hand...

If you, like me, resent every dollar spent on commercial PDF tools, you might want to know how to change the text content of a PDF without having to pay for Adobe Acrobat or another PDF tool. I didn't see an obvious open-source tool that lets you dig into PDF internals, but I did discover a few useful facts about how PDFs are structured that I think may prove useful to others (or myself) in the future. They are recorded here. They are surely not universally applicable --
the PDF standard is truly Byzantine -- but they worked for my case.

paul-krohn

Preamble

There is a longstanding issue/missing feature/bug with sockets on Docker on macOS; it may never work; you'll need to use a network connection between Docker containers and X11 on macOS for the foreseeable future.

I started from this gist and made some adjustments:

• the volume mappings aren't relevant/used, due to the socket issue above.
• this method only allows X11 connections from your Mac, not the entire local network, which would include everyone on the café/airport WiFi.
• updated to include using the host.docker.internal name for the the container host, instead.
• you have to restart XQuartz after the config change.

OliverJAsh

import * as React from 'react';
import { Component, ComponentClass, createRef, forwardRef, Ref } from 'react';

const myHoc = <ComposedComponentProps extends {}>(
    ComposedComponent: ComponentClass<ComposedComponentProps>,
) => {
    type ComposedComponentInstance = InstanceType<typeof ComposedComponent>;

    type WrapperComponentProps = ComposedComponentProps & {
        wrapperComponentProp: number;

domenkozar

    services.xserver = {
      enable = true;
      monitorSection = ''
        Option   "NODPMS"
      '';
      serverLayoutSection = ''
        Option   "BlankTime" "0"
        Option   "DPMS" "false"
      '';
      displayManager.auto.user = "guest";

pvik

An animated cheatsheet for smartparens using the example configuration specified here by the smartparens author. Inspired by this tutorial for paredit.

Traversal

C-M-f	sp-forward-sexp
C-M-b	sp-backward-sexp

infinisil

#! /usr/bin/env nix-shell
#! nix-shell -i bash -p jq less

nix-instantiate --eval --strict -E 'map (x: x.name) (import <nixpkgs/nixos> {}).config.environment.systemPackages' --json | jq -r '.[]' | sort -u | less