OpenAI unveiled Canvas, the company’s ” new interface for working with ChatGPT on writing and coding projects that go beyond simple chat.”

OpenAI has been released a slew of ChatGPT products and improved models, but its latest release is aimed specifically at writers and coders. Although writers and coders are already using ChatGPT, Canvas improves on the experience in important ways.

Catch our chat on OpenAI’s game-changing new coding tool, Canvas!

People use ChatGPT every day for help with writing and code. Although the chat interface is easy to use and works well for many tasks, it’s limited when you want to work on projects that require editing and revisions. Canvas offers a new interface for this kind of work.

With canvas, ChatGPT can better understand the context of what you’re trying to accomplish. You can highlight specific sections to indicate exactly what you want ChatGPT to focus on. Like a copy editor or code reviewer, it can give inline feedback and suggestions with the entire project in mind.

You control the project in canvas. You can directly edit text or code. There’s a menu of shortcuts for you to ask ChatGPT to adjust writing length, debug your code, and quickly perform other useful actions. You can also restore previous versions of your work by using the back button in canvas.

Interestingly, Canvas is designed to open automatically when writing or coding is detected.

Canvas opens automatically when ChatGPT detects a scenario in which it could be helpful. You can also include “use canvas” in your prompt to open canvas and use it to work on an existing project.

OpenAI says Canvas shows significant improvement over baseline GPT-4o in applicable tasks.

We measured progress with over 20 automated internal evaluations. We used novel synthetic data generation techniques, such as distilling outputs from OpenAI o1-preview, to post-train the model for its core behaviors. This approach allowed us to rapidly address writing quality and new user interactions, all without relying on human-generated data.

A key challenge was defining when to trigger a canvas. We taught the model to open a canvas for prompts like “Write a blog post about the history of coffee beans” while avoiding over-triggering for general Q&A tasks like “Help me cook a new recipe for dinner.” For writing tasks, we prioritized improving “correct triggers” (at the expense of “correct non-triggers”), reaching 83% compared to a baseline zero-shot GPT-4o with prompted instructions.

For writing and coding tasks, we improved correctly triggering the canvas decision boundary, reaching 83% and 94% respectively compared to a baseline zero-shot GPT-4o with prompted instructions.

Open AI has been transforming itself into a for-profit company, instead of a nonprofit organization. A large part of that is demonstrating use cases for which users are willing to pay for its AI products. Canvas is a big step in that direction.