alt Hacker NewsAnd before long you have a solution that is made up of a thousand pieces of spaghetti that neither you nor anyone else understands. And when your solution becomes too brittle to use, cannot be maintained, or fails catastrophically, then what? Just hope that's someone else's problem?
Replies
That's the point. Your prototype doesn't need to be pretty. It just needs to prove that the value is there for it to be made pretty.
You actually get what you ask for. And you can ask for anything, vaguely or not.
You'll end with spaghetti if you'll play a bad manager and only ever allocate time for new features and never for cleanups.
You can go through code, add REFACTOR comments based on your tastes and thoughts, and get your result and iterate to your heart's wishes. You just don't need to do the direct code typing.
Refactoring is cheap too, but you have to read your code and know when to stop and ask the agent to refactor, rewrite, adopt or change libs, fix issues presented by linters and code quality scanners, change abstractions and rethink the architecture.
It's never been easier to replace chunks of code with sane software patterns, but you have to have a feel for those patterns. And also understand what's under the hood.
You folks speak like the only function of the agent is to spit code and features. Get a grip and treat your deliverables with care, otherwise you only have yourself to blame, not the AI.