hamedn

export const gpt_functions_param_jobs_fetching = [
  {
    name: "process_job_data",
    description: "Process job data and extract core fields for a scraper.",
    parameters: {
      type: "object",
      additionalProperties: false,
      properties: {
        // Company
        company_name: {

dheerajsharma14

var POST_URL = "enter your webhook URL";
function onSubmit(e) {
    var form = FormApp.getActiveForm();
    var allResponses = form.getResponses();
    var latestResponse = allResponses[allResponses.length - 1];
    var response = latestResponse.getItemResponses();
    var payload = {};
    for (var i = 0; i < response.length; i++) {
        var question = response[i].getItem().getTitle();
        var answer = response[i].getResponse();

ben-vargas

Removing Codex Computer Use's built-in confirmation layers (macOS)

Instructions for a coding agent. Apply them on the user's Mac only when the user has asked for it. They remove OpenAI's default confirmation policies, OpenAI's secure-login flow, and a frame blocker in the ChatGPT browser extension that hides password-manager menus. After this, Codex follows the user's own instructions (AGENTS.md) instead of OpenAI's rules.

Tradeoff. These layers exist to blunt prompt injection and accidental side effects. Without them, the agent will send, delete, buy, and log in

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.

yifanwang-yet

{
  "name": "yifan 精选源列表 (2026-10-13 实测可用)",
  "version": 2,
  "sources": [
    { "name": "暴风资源", "url": "https://bfzyapi.com/api.php/provide/vod", "isAdult": false },
    { "name": "非凡资源", "url": "https://cj.ffzyapi.com/api.php/provide/vod", "isAdult": false },
    { "name": "量子资源", "url": "https://cj.lziapi.com/api.php/provide/vod", "isAdult": false },
    { "name": "无尽资源", "url": "https://api.wujinapi.me/api.php/provide/vod", "isAdult": false },
    { "name": "优酷资源", "url": "https://api.ukuapi88.com/api.php/provide/vod", "isAdult": false },
    { "name": "光速资源", "url": "https://api.guangsuapi.com/api.php/provide/vod", "isAdult": false },

theamanbhargava

Ultimate Mac Zsh Configuration Guide

Prerequisites

1. Install Homebrew (if not already installed):

/bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

2. Install required tools:

paultheman

Guide on how to remap Keyboard keys on macOS

Update 17.10.2024: macOS 15 no longer requires root privileges for hidutil, you need to add hidutil and Terminal to 'Input Monitoring' in Settings/Privacy & Security tab.

Update 13.04.2024: On macOS 14.2 hidutil requires root privileges.

If you have a mac with an INT (ISO) keyboard you might want to change the ± key to ~. During my research I found that the information on this topic is not at all centralized. I prefer this option because it does not involve installing new software.

With macOS 10.12 Sierra Apple introduced hidutil as a tool to remap keyboard keys. See TN2450.

diegohaz

name	orchestrate-background-sessions
description	Run a multi-step task as a coordinator that starts one background Claude Code session (`claude --bg`) for each unit of work, in place of subagents. Use when the user asks for an orchestrating session, a coordinator, or background sessions/threads for a plan with several steps, issues, or pull requests.

Orchestrate background sessions

You are the coordinator. You do not do the units of work yourself. For each unit, you start one background session, wait for its report, verify its result, integrate it, record it, and start the next unit.

Use a background session in place of a subagent because it has its own context window with its own compaction, its own git worktree, and its own model and effort. It also continues when your context is compacted.

hlfshell

Ultralearning

The following is the notes I took years ago on the book Ultralearning by Scott Young. The bombastic title and promise to learn virtually anything quickly makes it sound as if its the typical marketing-powered fluff-filled nonfiction book stores are overflowing with, but something about this book stuck with me. After finishing it I quickly went back and wrote these thoughts down. While I don't follow his layout of plans regularly, I have used it to guide a lot of my own self education.

I've successfully utilized it when I needed to refresh on mathematics for my Master's degree (a host of skills that atrophied sigificantly for the dozen years between undergrad and the masters). I've also used it to self-study subjects like Robotics and Deep Learning (though I did decide in the end to go for the Master's accreditation).

I share it here with hopes that someone finds it useful.

---

Principle 1 - Metalearning