Claude 3.5 Brushes Off Canvas with a Stroke of Code

DBS Content Banner Update Recently, OpenAI unveiled canvas, a new interface for working with ChatGPT on writing and coding projects. Many wonder if it’s better than Claude Sonnet 3.5 Artifacts. The answer is no. Here’s why: canvas uses GPT-4o, and it is not better at coding than Claude Sonnet 3.5. While canvas has some good features for developers, like users’ collaboration and version control, it lacks critical features like code preview. Many people are now creating their first apps with Claude. These include niche apps that only a few people need, internal tools for small companies, and silly apps just for fun. For instance, a user recently tried to visualise a dual monitor setup for a desk and compared how the monitors would fit next to each other. Claude, in an instant, created a perfectly usable app for this purpose in just a few interactions. The app wasn’t particularly mind-blowing, but that was precisely the point. While it might not have been worth the time and effort for the user to code it themselves, having Claude create it in less than 5 minutes made it a valuable tool. This scenario perfectly illustrates the potential of AI-assisted app creation for quick, personalised solutions. Canvas is Cute, but Artifacts is the Real Deal Apart from building software in a few minutes, users have also reported how Claude Artifacts is helping them learn coding. A developer who was struggling to learn how to code said that by being able to see how a project actually comes together more thoroughly, he has started to get a lot of the concepts that earlier struggled to comprehend. “One of the hardest things, at least for me, is self-learning since I am a very conceptual learner. I need to be able to wrap my head around the whole idea and drill down into it. Alternatively, I start with a part and kind of build like a snowball of knowledge, something that’s usually a collaborative approach, making it difficult to do entirely on my own.