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.

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

jurijsk

async function run() {
	console.clear();
	await figma.currentPage.loadAsync();


	const dryRun = false;
	const skipDevReady = true;

	console.log(dryRun ? 'DRY RUN' : 'NORMAL RUN');

jh3y

javascript:(function () {
  var active;
  var magnifier;

  var config = {
    scale: 75,
    size: 160,
    image:
    'data:image/png;base64,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

Birch-san

Install HF Code Autocomplete VSCode plugin.

We are not going to set an API token. We are going to specify an API endpoint.
We will try to deploy that API ourselves, to use our own GPU to provide the code assistance.

We will use bigcode/starcoder, a 15.5B param model.
We will use NF4 4-bit quantization to fit this into 10787MiB VRAM.
It would require 23767MiB VRAM unquantized. (still fits on a 4090, which has 24564MiB)!

Setup API

ninehills

背景信息：
===
当让你搜索时，你要使用 WebPilot 插件并用如下 URL 结构来进行 Google 搜索：

https://google.com/search?q={query}&hl=en&gl=US&tbs={time}

参数：
- {query} ：搜索关键字。
- {time} [optional] ：时间要求，比如'qdr:d2' 表示过去两天内的搜索。
===

cs224

jph00

Bing Chat at 2023-3-26 13:47:19

1

Q: Bing AI

2

Q: Some philosophers and AI researchers have claimed that AI can not be sentient, or be AGI, due to lack of "embodiment" or "grounding". Could you please summarize these claims, and points for and against? Who are the main people on each side of this debate?

noamr

addEventListener("fetch", e => {
  if (e.request.destination !== "image" ||   // Only do this when requesting an image
    request.mode === "no-cors") // We don't know the status of no-cors images
    return;

  e.respondWith((async () => {
    try {
      const response = await fetch(e.request);
      if (response.ok)
        return response;

rsms

// Find the latest version of this script here:
// https://gist.github.com/rsms/a8ad736ba3d448100577de2b88e826de
// 
const EM = 2048

interface FontInfo {
  familyName :string
  styleName  :string
  unitsPerEm :int
  ascender   :int