@php_martin: After 88 seconds, it started working on its own｜1/5
Summary
The author tested the Codex AI Agent, which went from installation to automatically executing tasks in just 88 seconds, including file organization, web scraping, writing code, and running scripts, all locally. This marks the entry of AI Agent into ordinary users' computers.
View Cached Full Text
Cached at: 06/15/26, 09:09 PM
🎬 88 seconds later, it started working on its own | 1/5
Originally, I just wanted to test Codex.
As a result, from installation complete to the first Agent starting work, it only took 88 seconds.
Organizing files, scraping web pages, writing code, running scripts—all running locally.
🚀 For the first time, I felt that AI Agents have started entering ordinary people’s computers. https://t.co/BPuTMtJ4o0
From completion of installing Codex + the local model to the first Agent starting to work (organizing files, scraping web pages, writing code, running scripts), the entire process took only 88 seconds, and it ran completely offline locally. Key takeaway: AI Agents are truly starting to enter ordinary people’s computers.
Similar Articles
@Saccc_c: https://x.com/Saccc_c/status/2058057029810594206
The article provides a detailed introduction to OpenAI's AI Agent desktop application, Codex App, covering its core features (local file read/write, web search, software control, automation, etc.), installation steps, usage tips, and differences from ChatGPT, helping users get started quickly.
@QingQ77: Describe requirements in natural language, and the AI Agent automatically breaks down steps, calls tools to complete development, file operations, browser control, and other tasks, while also providing a full-fledged editor and terminal. https://github.com/Liuchun-oss/codelf-agent… Codelf is…
Codelf is an open-source desktop AI assistant that lets you describe requirements in natural language. It automatically breaks down steps and calls tools to handle development, file operations, browser control, and more, all while providing a complete editor and terminal. It supports models like DeepSeek, Claude, and ChatGPT, works well on domestic networks, and includes local RAG knowledge base capabilities.
@php_martin: Codex Deep Dive 1/5 – You spend $20/month on ChatGPT Plus, install Codex, have it build a webpage, and think that's it? You're using less than 20% of its capability. I've broken this 58-minute video into 5 hot takes. Here's the opener: Fork / AGEN…
This article points out that many ChatGPT Plus users have only leveraged less than 20% of Codex's capability, and introduces advanced features such as Fork, AGENTS.md, Plan Mode, Plugin, scheduled tasks, and mobile remote control, which can boost work efficiency by 10 times.
@php_martin: OpenAI Codex is now free. But what really shocked me isn't the free part — it's that local open-source models can deliver AI Agent performance close to the cloud experience. The video demonstrates 4 real-world scenarios: fixing a crashed space game, building a Whac-A-Mole web game in minutes, generating an Apple-style product homepage, and even launching a browser to search, download, and save files on its own.
OpenAI Codex is now free, but even more surprising is that local open-source models can achieve AI Agent performance close to the cloud, demonstrating scenarios like fixing games and developing web games without requiring API keys or internet.
@php_martin: https://x.com/php_martin/status/2064975977860440439
This article provides a comprehensive introduction to the features and usage of the OpenAI Codex desktop application, including project management, skill/plugin system, automation, and multi-task parallel development strategies. It also offers practical cases and risk warnings, aiming to help users efficiently utilize AI agents for parallel development.