OpenAI has just introduced Canvas, a new tool designed to take ChatGPT beyond simple chat interactions and turn it into a more collaborative workspace for writing and coding.
Unlike the traditional chat window, Canvas opens a separate work area with a chat window on the right side. This allows users to work hand-in-hand with ChatGPT, refining and editing ideas directly within their documents or code.
With this addition, OpenAI is clearly responding to the main problem of its previous interface: the exchange of messages in the chat, the repetition of results and its limitation of response with characters are not good for working on more complex multi-step projects. over time.
While I haven’t been able to test it live yet (the company said it’s started rolling it out to Plus subscribers, but I haven’t gotten it to me), the demos clearly show both its cool powers and its limitations. The new user experience is a reaction to what others have already done in the AI-enhanced productivity space. Both Google and Microsoft have been working on their own AI integrations (Gemini in Google Docs and CoPilot in Microsoft Word) long before Canvas came out. In fact, both Gemini and CoPilot have essentially taken the same human-AI collaboration approach to document editing.
[Imagen: OpenAI]
What is OpenAI Canvas exactly?
Canvas brings a new user experience and workflow to ChatGPT, especially in its ability to understand and adapt to the context of what users are trying to achieve. It is intended to function as a collaborative editor, offering comments directly on the text or code. For writers, says the companyyou can suggest edits, adjust the length of the document, and even modify the reading level to adjust the tone.
For coders, the tool reviews code, adds debug logs and comments, translating code between programming languages when necessary. OpenAI claims that “Canvas can provide online feedback and suggestions taking the entire project into account,” improving the interaction between the user and the AI in a way that was not possible with just the chat interface.
We’re rolling out an early version of canvas—a new way to work with ChatGPT on writing & coding projects that go beyond simple chat.
Starting today, Plus & Team users can try it by selecting “GPT-4o with canvas” in the model picker. https://t.co/GoGZiRzCsB
— OpenAI (@OpenAI) October 3, 2024
Instead of repeatedly iterating over ChatGPT’s output to get what you want, or asking it to rewrite a specific section in a message, Canvas allows people to select text from a live document and then ask AI to help refine the selected part. Just like Docs and Word do.
According to OpenAI, Canvas is available to ChatGPT Plus and Team users starting today, with Enterprise and Educational users getting access next week. The broader release for all ChatGPT Free users is planned after the beta phase. For now, the tool is an exclusive feature for GPT-4 users, launching automatically when ChatGPT detects writing or coding scenarios it could help with. Users can also activate it manually by typing “use canvas” in a message.
Following the trail of Google and Microsoft
From the demos, it’s clear that Canvas will be much more useful than the current mode if your goal is to write longer documents or code. But its simplicity and elegance, again from what I’ve seen, make it much more limited than Google Gemini on Google Docs when it comes to writing and word processing. The side icon bar in Docs is similar to the one in Canvas, but it gives you more options, including the ability to adjust tone, summarize, bullet points, elaborate, shorten, rephrase, and an open prompt that can do anything you ask it to do. , how to rewrite your prose to turn it into a poem.
Docs may be more powerful today, but its interface is also more complex and cluttered than Canvas. For example, pop-ups take control of the part of the text you want to edit to display the results of your commands before sending them to the page. This modal window adds the option to further refine the result before replacing the selected text or inserting it as new paragraphs. ChatGPT’s Canvas, on the other hand, has the quality of being quite simple, writing directly on the text as if an invisible collaborative editor were taking over the writing task. The result feels sharper and more attractive.
Maybe I’m speaking from a writer’s perspective; However, this simplicity and cleanliness of the interface helps you focus, without being distracted by the unnecessary user interface elements of a classic word processor. I’m a fan of iA Writer, an extremely clean word processor designed for writers that’s the closest thing to typing on a typewriter with some added benefits of being digital. Canvas feels a bit like that, except it has artificial intelligence to benefit from.
Canvas can switch to its “coding personality” when it detects coding tasks. It can help users review, debug, and transfer code between languages. OpenAI’s blog post seems to indicate that the feature will adopt this changing personality, adapting to what it thinks users may want. Maybe in the future you can automatically switch from “novel writer personality” to “college essay personality,” by adapting the tools available in your sidebar. That seems like a nice and distinctive UX path to follow.
For now, Canvas appears to be a response to the limitations of its current UX. It offers a more focused and cleaner workspace, but its underlying approach reflects much of what Google and Microsoft have already implemented, rather than introducing a truly innovative UX to address the same problem. It’s a great thing to have, and will be very useful for pure ChatGPT fans, but will it be enough to replace a dated word processor or programming environment with an AI assistant on the side?
