Comment by egorfine
2 days ago
So I decided to try the revered hands-off approach and have Claude Code create me a small tool in JS for *.dylib bundle consolidation on macOS.
I have used AskUserQuestionTool to complete my initial spec. And then Opus 4.5 created the tool according to that extensive and detailed spec.
It appeared to work out of the box.
Boy how horrific was the code. Unnecessary recursions, unused variables, data structures being built with no usage, deep branch nesting and weird code that is hard to understand because of how illogical it is.
And yes, it was broken on many levels and did not and could not do the job properly.
I then had to rewrite the tool from scratch and overall I have definitely spent more time spec'ing and understanding Claude code than if I have just written this tool from scratch initially.
Then I tried again for a small tool I needed to run codesign in parallel: https://github.com/egorFiNE/codesign-parallel
Same thing. Same outcome, had to rewrite.
That’s the opposite of my experience. Weird. But I’m also not the kind of person who gets hung up on whether someone used a loop or recursion or if their methods are five times as long as what I would’ve done myself unless there is a performance impact that matters to me as a user. But I’m also the kind of person who doesn’t get paid by the hour to write programs. I use programs in the service of other paid work.
Yes, this experience is unlike most people. Perhaps the problem is that most people are satisfied by the appearance of a working app despite it not working at all. Say, the first tool I was doing, did actually not recurse into subdirs with dylibs which made it useless.
So, AI slop, yes.