OpenAI’s ChatGPT, the AI-driven chatbot platform, has introduced the ability to edit code directly, but currently only for macOS users.
The latest iteration of the ChatGPT app for macOS allows users to modify code within compatible developer environments such as Xcode, VS Code, and JetBrains. An optional “auto-apply” feature enables ChatGPT to execute edits automatically, eliminating the need for any further clicks.
As of Thursday, ChatGPT Plus, Pro, and Team subscribers can access the code editing functionality by updating their macOS application. OpenAI has announced that this feature will also be available for Enterprise, Edu, and free accounts next week.
In a post on X, Alexander Embiricos, who works on OpenAI’s desktop software, mentioned that a direct code editing feature for the Windows version of ChatGPT will be arriving “soon.”
ChatGPT for macOS can now edit code directly in IDEs. Available to Plus, Pro, and Team users. pic.twitter.com/WPB2RMP0tj
— OpenAI Developers (@OpenAIDevs) March 6, 2025
This direct code editing capability extends OpenAI’s earlier beta feature, “work with apps,” which was introduced last November. The work with apps functionality enables the ChatGPT app for macOS to read code within select development-focused coding settings, thus reducing the need for users to copy and paste code into ChatGPT.
With the addition of direct code editing, ChatGPT positions itself more competitively against established AI coding solutions like Cursor and GitHub Copilot. Reports indicate that OpenAI plans to release a specialized product aimed at enhancing software engineering in the near future.
The popularity of AI coding assistants is surging, as evidenced by a survey indicating that a substantial majority of participants have integrated AI tools into their workflow. Y Combinator partner Jared Friedman noted that approximately 25% of the companies from YC’s W25 startup cohort have 95% of their codebases generated by AI.
However, there are several security, copyright, and reliability concerns linked to these AI-driven coding assistants. A report from software provider Harness revealed that most developers find themselves spending more time addressing bugs and security issues in AI-generated code than they do with code authored by humans. Furthermore, a Google study highlighted that while AI can accelerate code reviews and enhance documentation, it may compromise the stability of deliveries.
Compiled by Techarena.au.
Fanpage: TechArena.au
Watch more about AI – Artificial Intelligence
