ChatGPT on macOS Now Enables Direct Code Editing

ChatGPT Now Offers Direct Code Editing on macOS

ChatGPT, the AI chatbot developed by OpenAI, has expanded its functionality to include direct code editing. This feature is currently available for users operating on the macOS platform.

New Capabilities for macOS Users

The latest iteration of the ChatGPT application for macOS enables users to modify code directly within compatible developer tools. Supported environments include Xcode, VS Code, and those from JetBrains.

An optional “auto-apply” setting is also available. This allows ChatGPT to implement code changes automatically, reducing the need for manual confirmation with each edit.

Availability and Rollout

Access to the code editing feature is currently granted to subscribers of ChatGPT Plus, Pro, and Team plans. Users can activate the functionality by updating their macOS app.

OpenAI has announced that the feature will be extended to Enterprise, Edu, and free users in the coming week.

Future Plans for Windows

According to Alexander Embiricos, a product staff member at OpenAI focused on desktop applications, the ability to directly edit code will soon be implemented in the ChatGPT app for Windows as well.

Building on Existing Features

This direct code editing capability is an extension of OpenAI’s “work with apps” feature. Launched in beta in November 2024, “work with apps” allows the macOS ChatGPT app to directly access code within various coding environments.

This minimizes the need for users to copy and paste code between applications, streamlining the development process.

Competition in the AI Coding Space

With the addition of direct code editing, ChatGPT now positions itself as a more direct competitor to established AI coding tools such as Cursor and GitHub Copilot.

OpenAI has reportedly expressed intentions to release a dedicated product specifically designed to support software engineering in the near future.

Growing Adoption of AI Coding Tools

The popularity of AI coding assistants is rapidly increasing. A recent GitHub poll indicated that a significant majority of respondents have integrated AI tools into their workflows.

Jared Friedman, a partner at Y Combinator, recently stated that a quarter of the W25 startup batch had 95% of their codebases generated by AI.

Potential Risks and Challenges

Despite the benefits, several security, copyright, and reliability concerns are associated with AI-powered coding assistance.

A survey conducted by software vendor Harness revealed that developers often spend more time debugging AI-generated code and addressing security vulnerabilities compared to code written by humans.

Furthermore, a Google report highlighted that while AI can accelerate code reviews and improve documentation, it may potentially compromise delivery stability.