I am also surprised by this. Especially because we can just run Claude Code from anywhere. Cursor, VS Code, Zed, emacs, vim, JetBrains, etc.
Cursor CLI, Codex and Gemini work too, but lag slightly behind in a variety of different ways that matter.
And if you think you’re getting better visual feedback through Cursor it’s likely you’re just not using Claude with your IDE correctly.
I mean the problem with Claude Code is you have to use Claude
The model most people have been recommending you use in Cursor for the last year or so… Which model do you find significantly better?
I've been using GPT-5, and hoping to use gpt-5-codex soon