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.

lncitador

This abstract Mapper class provides a flexible and type-safe way to serialize, transform, and label AdonisJS Lucid models and their paginated results. It is designed to help you build clean API responses and DTOs in AdonisJS projects.

Features

• Supports serialization of single models, arrays, and paginated results.
• Custom serialization logic via subclassing.
• Utility for picking specific fields and relations from models.
• Label mapping mechanism for enums or field names.

Use this utility to keep your API layer clean, consistent, and maintainable when working with AdonisJS and Lucid ORM.

DavidWells

/* Ultra lightweight Github REST Client */
// original inspiration via https://gist.github.com/v1vendi/75d5e5dad7a2d1ef3fcb48234e4528cb
const token = 'github-token-here'
const githubClient = generateAPI('https://api.github.com', {
  headers: {
    'User-Agent': 'xyz',
    'Authorization': `bearer ${token}`
  }
})

andrelandgraf

import childProcess from 'child_process';
import fs from 'fs';
import dotenv from 'dotenv';
import prettier from 'prettier';

const rootDir = process.cwd();

dotenv.config({
  path: `${rootDir}/.env.production`,
});

donn

iPhone Country Codes

Why I made this

The model regions on Apple wikis are missing some entries- and the entries are lacking some information that I would be critical for international buyers: there are some extreme differences between features in some regions: FaceTime support, Dual SIM support, etc.

What's worse is some regions have multiple codes, and sometimes even imported devices from other regions.

Unfortunately, Apple does not seem to acknowledge these region numbers exist at all and resort to nebulous claims about the feature differences, and it doesn't help that there are some conflicting reports on the internet.

So I'm going to try my best to maintain an up-to-date list. Any and all confirmations, additions and denials here would be extremely helpful. Please just leave a comment.

v1vendi

const fetch = (...args) => console.log(...args) // mock
function httpRequest(url, method, data) {
    const init = { method }
    switch (method) {
        case 'GET':
            if (data) url = `${url}?${new URLSearchParams(data)}`
            break
        case 'POST':
        case 'PUT':
        case 'PATCH':