Coding shortcuts in canvas include reviewing code, adding logs for debugging, inserting comments, fixing bugs, and porting code to different programming languages. For instance, in case your code is JavaScript, with just a few clicks it could actually grow to be PHP, TypeScript, Python, C++, or Java. As with GPT-4o by itself, you’ll likely still have to envision it for mistakes.
A screenshot of coding using ChatGPT with Canvas captured on October 4, 2024.
Credit:
Benj Edwards
Also, users can highlight specific sections to direct ChatGPT’s focus, and the AI model can provide inline feedback and suggestions while considering all the project, very similar to a replica editor or code reviewer. And the interface makes it easy to revive previous versions of a working document using a back button within the Canvas interface.
A brand new AI model
OpenAI says its research team developed recent core behaviors for GPT-4o to support Canvas, including triggering the canvas for appropriate tasks, generating certain content types, making targeted edits, rewriting documents, and providing inline critique.
One key challenge in development, based on OpenAI, was defining when to trigger a canvas. In an example on the Canvas blog post, the team says it taught the model to open a canvas for prompts like “Write a blog post in regards to the history of coffee beans” while avoiding triggering Canvas for general Q&A tasks like “Help me cook a brand new recipe for dinner.”
One other challenge involved tuning the model’s editing behavior once canvas was triggered, specifically deciding between targeted edits and full rewrites. The team trained the model to perform targeted edits when users specifically select text through the interface, otherwise favoring rewrites.
The corporate noted that canvas represents the primary major update to ChatGPT’s visual interface since its launch two years ago. While canvas continues to be in early beta, OpenAI plans to enhance its capabilities based on user feedback over time.
