ChatGPT, OpenAI’s AI-powered chatbot platform, can now straight edit code — in case you’re on macOS, that’s.
The most recent model of the ChatGPT app for macOS can take motion to edit code in supported developer instruments, together with Xcode, VS Code, and JetBrains. Customers can optionally activate an “auto-apply” mode so ChatGPT could make edits with out the necessity for extra clicks.
Subscribers to ChatGPT Plus, Professional, and Staff can use the code modifying function as of Thursday by updating their macOS app. OpenAI says that code modifying will roll out to Enterprise, Edu, and free customers subsequent week.
In a post on X, Alexander Embiricos, a member of OpenAI’s product workers engaged on desktop software program, added that the ChatGPT app for Windows will get direct code modifying “quickly.”
ChatGPT for macOS can now edit code straight in IDEs. Obtainable to Plus, Professional, and Staff customers. pic.twitter.com/WPB2RMP0tj
— OpenAI Builders (@OpenAIDevs) March 6, 2025
Direct code modifying builds on OpenAI’s “work with apps” ChatGPT capability, which the corporate launched in beta in November 2024. “Work with apps” permits the ChatGPT app for macOS to learn code in a handful of dev-focused coding environments, minimizing the necessity to copy and paste code into ChatGPT.
With the flexibility to straight edit code, ChatGPT now competes extra straight with in style AI coding instruments like Cursor and GitHub Copilot. OpenAI reportedly has ambitions to launch a dedicated product to help software program engineering within the months forward.
AI coding assistants have gotten wildly in style, with the vast majority of respondents in GitHub’s newest ballot saying that they’ve adopted AI instruments in some type. Y Combinator accomplice Jared Friedman recently claimed 1 / 4 of YC’s W25 startup batch have 95% of their codebases generated by AI.
However there are a selection of security, copyright, and reliability risks related to AI-powered assistive coding instruments. A survey from software vendor Harness discovered that almost all of builders spend extra time debugging AI-generated code and safety vulnerabilities in comparison with human-written contributions. A Google report, in the meantime, discovered that AI can quicken code critiques and profit documentation, however at the price of supply stability.
About The Author
