Why the Latest Codex Update Is a Game‑Changer for Windows Users
OpenAI's recent Codex update adds true Computer Use support on Windows, letting the model see the screen, click buttons, type, and control desktop applications, with a simple @Paint or @computer prompt, though it runs in the foreground and requires ChatGPT Plus or higher.
OpenAI has refreshed Codex with a major feature: Computer Use now works on Windows. Unlike the previous Mac‑only capability, the model can actually see the screen, click UI elements, type text, and drive desktop applications, enabling automation of software that lacks an API.
To trigger this behavior, users add the special token @Paint or @computer in their prompt, and Codex understands which application to operate without further clarification.
On Windows the Computer Use agent runs in the foreground, so it takes exclusive control of mouse and keyboard; users cannot interact with the PC simultaneously. This differs from the Mac implementation, which can operate silently in the background.
OpenAI mitigates the foreground limitation by recommending the ChatGPT mobile app (iOS or Android) to monitor and issue commands remotely while the Windows agent performs long‑running tasks.
Enabling the feature is straightforward: open Codex settings, locate the Computer Use tab, click install, and grant the requested permissions. The capability is available to ChatGPT Plus, Pro, or Enterprise users who have updated to the latest version from the Microsoft Store.
The author notes that this UI‑level control expands AI automation beyond pure code generation, allowing AI to handle many applications that previously required manual interaction, opening up many future use cases.
Signed-in readers can open the original source through BestHub's protected redirect.
This article has been distilled and summarized from source material, then republished for learning and reference. If you believe it infringes your rights, please contactand we will review it promptly.
Architect's Tech Stack
Java backend, microservices, distributed systems, containerized programming, and more.
How this landed with the community
Was this worth your time?
0 Comments
Thoughtful readers leave field notes, pushback, and hard-won operational detail here.