OpenAI has launched a fresh “Canvas interface for ChatGPT, which allows users to customize sections of text or code generated by the chatbot in a side-by-side collaboration. Canvas opens a separate editing window next to the existing ChatGPT chat window, which you can use to manually change text or code, or highlight specific sections to better target editing suggestions and feedback from ChatGPT.
“With canvas, ChatGPT can better understand the context of what you are trying to achieve,” OpenAI said in its announcement. “Making AI more useful and accessible requires rethinking the way we interact with it. Canvas is a new approach and the first major update to the ChatGPT visual interface since its launch two years ago.”
ChatGPT Canvas provides users with shortcut menus to suggest inline changes, quickly check grammar and clarity, and adjust text length and readability level. Some coding-specific shortcuts are also available for debugging, adding logs and comments, and translating code to other languages. It’s a similar concept to the “Artifacts” feature that rival AI developer Anthropic rolled out for Claude in August.
Previously, ChatGPT users typically had to repeatedly enter new suggestions to refine what the chatbot spit out. Canvas sounds much less boring and gives users additional control. It provides a back button that can restore previous versions of your work, and OpenAI says it optimizes when Canvas automatically activates – for example, it reduces the likelihood of coding tasks starting to avoid being cumbersome for power users.
The Canvas interface is currently in beta and can be accessed by selecting “GPT-4o with Canvas” from the ChatGPT model selection drop-down menu. The service will be rolled out globally to ChatGPT Plus and Teams users, with access expanding to Enterprise and Edu users next week. According to OpenAI, once the beta ends, Canvas will be available to free ChatGPT users and will open automatically “when ChatGPT detects a scenario where it can be helpful.”
