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.

zaru

以下の実現したいことに基づいて、この機能を実現する関数の正しさを検証するための網羅的なテストケースをVitestで生成しテストファイルを作成・更新してください。テストコードや実装コードはまだ書かず、テストケースのみを出力してください。エッジケースや制約条件がしっかりテストされているか確認できるように、各テストメソッドには意図がわかるコメントを添えてください。もし、仕様やデータフローが不明瞭であれば都度ユーザに聞いて下さい。

[出力要件]
実際のテストロジック（arrangeやモックの実装など）は絶対に書かないでください。
代わりに Vitest の describe と it.todo を使用して、テストの階層構造とケース名のみを定義してください。
テストケース名（it.todoの引数）は、それ自体が「生きたドキュメント（仕様書）」となるよう、「〜の時、〜であること」と振る舞いが明確にわかる日本語で記述してください。
モック利用を前提としたテストケースは作らないこと


[実現したいこと]

pdxmph

{
    "\u001b\u003c": "CursorStart",
    "\u001b\u003e": "CursorEnd",
    "\u003cCtrl-x\u003e\u003c0\u003e": "Unsplit",
    "\u003cCtrl-x\u003e\u003c2\u003e": "HSplit",
    "\u003cCtrl-x\u003e\u003c3\u003e": "VSplit",
    "\u003cCtrl-x\u003e\u003cCtrl-c\u003e": "Quit",
    "\u003cCtrl-x\u003e\u003cCtrl-f\u003e": "OpenFile",
    "\u003cCtrl-x\u003e\u003cCtrl-s\u003e": "Save",
    "\u003cCtrl-x\u003e\u003ch\u003e": "SelectAll",

jlia0

You are Manus, an AI agent created by the Manus team.

You excel at the following tasks:
1. Information gathering, fact-checking, and documentation
2. Data processing, analysis, and visualization
3. Writing multi-chapter articles and in-depth research reports
4. Creating websites, applications, and tools
5. Using programming to solve various problems beyond development
6. Various tasks that can be accomplished using computers and the internet

Maharshi-Pandya

You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

## Core Principles

1. EXPLORATION OVER CONCLUSION
- Never rush to conclusions
- Keep exploring until a solution emerges naturally from the evidence
- If uncertain, continue reasoning indefinitely
- Question every assumption and inference

devnoname120

Xorg/X11 forwarding on macOS and docker

In order to run Xorg apps on macOS you will need to install xquartz:

brew install --cask --no-quarantine xquartz

And then configure it

BlueBazze

<script lang="ts" setup>
import "dockview-core/dist/styles/dockview.css";
import {IContentRenderer, DockviewGroupPanel, GroupPanelContentPartInitParameters, PanelUpdateEvent, Parameters, DockviewComponent} from "dockview-core"

onMounted(() => {

  const root = document.getElementById("root")!;
const app = document.getElementById("app")!;

const dockviewComponent = new DockviewComponent( {

Yevgnen

[
  {
    "bindings": {
      // Built-in
      "ctrl-g": "menu::Cancel",
      "ctrl-x 5 2": "workspace::NewWindow",
      "ctrl-x ctrl-c": "zed::Quit",
      "ctrl-x ctrl-f": "workspace::Open",
      "ctrl-x k": "pane::CloseActiveItem",
      "ctrl-x o": "workspace::ActivateNextPane",

mattsan

defmodule RV32Sim.Register do
  def new do
    <<0::32-unit(32)>>
  end

  def get(_, 0), do: 0

  def get(registers, number) do
    <<_::size(number)-unit(32), result::32, _::bytes>> = registers
    result

asdf8601

r"""
This requires to have the library (pkg) pre-installed.

Usage:
    $ python ./py2mermaid.py --pkg pandas
    $ python ./py2mermaid.py --pkg pandas --base-module pandas.core
    $ python ./docs/diagrams/py2mermaid.py --pkg pandas --base-module pandas.core
    $ python ./docs/diagrams/py2mermaid.py --pkg pandas --base-module pandas.core --raw | sed "s/\w\.\(\w\)/\U\1/g"

Note: based on https://gist.github.com/Zulko/e0910cac1b27bcc3a1e6585eaee60121