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.

igorbabko

🎨 Beautiful Minimal Zed Setup

🍿 Watch on YouTube

• English
• Russian

jake-stewart

Terminals should generate the 256-color palette from the user's base16 theme.

If you've spent much time in the terminal, you've probably set a custom base16 theme. They work well. You define a handful of colors in one place and all your programs use them.

The drawback is that 16 colors is limiting. Complex and color-heavy programs struggle with such a small palette.

emschwartz

This is an OPML version of the HN Popularity Contest results for 2025, for importing into RSS feed readers.

Plug: if you want to find content related to your interests from thousands of obscure blogs and noisy sources like HN Newest, check out Scour. It's a free, personalized content feed I work on where you define your interests in your own words and it ranks content based on how closely related it is to those topics.

hoangtrung99

import axios, { type AxiosError, type InternalAxiosRequestConfig, type AxiosResponse } from 'axios'

/**
 * Create axios instance with default configuration
 */
const request = axios.create({
  baseURL: import.meta.env.VITE_API_URL,
  timeout: 5000
})

nafiesl

How to get Telegram Bot Chat ID

Content :

1. Create a Telegram Bot and get a Bot Token
2. Get Chat ID for a Private Chat
3. Get Chat ID for a Channel
4. Get Chat ID for a Group Chat
5. Get Chat ID for a Topic in a Group Chat

Create a Telegram Bot and get a Bot Token

gaearon

Next.js client-only SPA example

Made this example to show how to use Next.js router for a 100% SPA (no JS server) app.

You use Next.js router like normally, but don't define getStaticProps and such. Instead you do client-only fetching with swr, react-query, or similar methods.

You can generate HTML fallback for the page if there's something meaningful to show before you "know" the params. (Remember, HTML is static, so it can't respond to dynamic query. But it can be different per route.)

Don't like Next? Here's how to do the same in Gatsby.

erdomke

declare namespace Backbone {
  class Model<T> {
    constructor(attr?:T, opt?:any)
    attributes : T
    collection: Collection<this>
    cid: string
    get<K extends keyof T>(prop:K) : T[K]
    set<K extends keyof T>(prop:K , val:T[K]) : void
    defaults() : T
    on(eventName: string, callback: (...args: any[]) => void)

tieppt

// path: qmk_firmware/keyboards/gmmk/pro/ansi/keymaps/viapro/config.h
#pragma once

#ifdef RGB_MATRIX_ENABLE
    #define RGB_DISABLE_WHEN_USB_SUSPENDED true
#endif // RGB_MATRIX_ENABLE

mmansoor

Export CloudWatch Metrics

This document outlines how to export CloudWatch Metrics to CSV.

Pre Reqs

1. AWS CLI (Command Line Interface) from here
2. jq is a lightweight and flexible command-line JSON processor from here

How to export