I started with Claude for a basic JS project. It failed over and over. Gemini sorted out the same problems faster. Claude was always wanting to rip out huge blocks of code and replace them. Did it fix the problem? Almost never. It was a small JS code base Claude made itself.

Claude was my first coding AI, I liked it, I wanted to use it. But when I ran out of tokens I went to Gemini and got way better results.

And now every day I see Claude spam like it's the best thing that ever happened. Real world use tells a different story. I didnt just "one off" try it and have a problem. This is week and weeks of issues.

Claude fails basic questions when given very clear prompts - ON VANILLA JAVASCRIPT.