> AIs like to write a lot of code

I vibe coded a greenfield side project last weekend for the first time and I was not prepared for this. It wrote probably 5x more functions than it needed or used, and it absolutely did not trust the type definitions. It added runtime guards for so many random property accesses.

I enjoyed watching it go from taking credit for writing new files and changes, and then slowly forgetting after a few hours that it was the one that wrote it ... repeatedly calling calling it "legacy" code and assuming the intents of the original author.

But yeah, it, Claude (no idea which one), likes to be verbose!

I especially find it funny when it would load the web app in the built-in browser to check its work, and then claiming it found the problem before the page even finishes opening.

I noticed it's really obsessed with using Python tooling... in a typescript/node/npm project.

Overall it was fun and useful, but we've got a long way to go before PMs and non-engineers can write production-quality software from scratch via prompts.

In my experience Claude Sonnet is much more verbose than Claude Opus, and writes worse code as a result. The difference is pretty striking once you try using them both for the same task.

It generally feels like Opus gives you the 5th or 10th iteration, but Sonnet gives you the first possible solution.