I wanted to integrate a WYSIWYG Markdown editor into my ReactJS application. I carefully explained what I was trying to achieve—but notably did not specify which library I wanted to use. This was intentional. I was curious to see how the agent would choose a library on its own, and whether it could reliably search for and identify a good tool for the job. I was using Opus with Cursor. After executing my request, I opened the page and immediately noticed something peculiar: although I could “edit” the content, the editing experience was limited to raw Markdown. The nicely formatted text—the whole point of WYSIWYG—was available only in preview mode. Naturally, I asked the agent to modify the application so users could edit the formatted text directly, like civilized people. The agent began to think. And think. I’m confident these were deep thoughts, because the pause was longer than usual. After a few seconds of coding, it triumphantly declared, “There you go—sorry, I didn’t understand...
I was excited to finally have a new side project to work on, and naturally, I wanted to vibe code. So I fired up Cursor. For the rest of this post, I’m going to refer to Cursor as “him”, because it genuinely felt like I was pair-programming with a very confident senior software engineer — the kind who types extremely fast and never doubts his decisions. The Design I asked ChatGPT to create designs for: The home page User dashboard Login page Forgot password page Sign-up page I provided the theme colors and a one-line idea for the project. ChatGPT’s first response was… an HTML file with all the styles embedded inside it. Not exactly what I had in mind. Since I didn’t want just code, I politely asked it to generate actual design images instead. After a few iterations, I was able to finalize the UI and download both the HTML and styles. This was a surprisingly interesting experience for me. In the past, when I had an idea for ...