OpenAI has launched a new “canvas” interface for ChatGPT. This allows users to adjust sections of text or code generated by a chatbot in parallel collaboration. Canvas opens a separate editing window next to the existing ChatGPT chat box. You can use this window to manually change text or code, or highlight specific sections to better target editing suggestions and feedback from ChatGPT.
“Canvas allows ChatGPT to better understand the context of what you are trying to accomplish,” OpenAI said in the announcement. “To make AI more useful and accessible, we need to rethink how we interact with it. Canvas is a new approach and the first major update to ChatGPT’s visual interface since its launch two years ago. .”
ChatGPT Canvas provides users with inline editing suggestions, quick grammar and clarity checks, and a menu of shortcuts to adjust text length and reading level. Some coding-specific shortcuts can also be used for debugging, adding logs and comments, and translating your code to other languages. It’s a similar concept to the “Artifacts” feature that rival AI developer Anthropic rolled out for Claude in August.
Prior to this, ChatGPT users typically had to repeatedly enter new prompts to adjust what the chatbot spits out. Canvas is less cumbersome and provides additional control to the user. There’s a “back” button that lets you restore previous versions of your work, and OpenAI says it’s optimized when the canvas is automatically activated to avoid confusing power users. . For example, reducing the chance that a coding task will trigger a canvas.
The canvas interface is currently in beta and can be accessed by selecting (GPT-4o with Canvas) in ChatGPT’s model picker drop-down menu. It’s rolling out globally to ChatGPT Plus and Teams users, with access expanding to Enterprise and Edu users next week. Once the beta version ends, Canvas will be available to ChatGPT’s free users and will be opened automatically “when ChatGPT detects a potentially useful scenario,” according to OpenAI.