Getting AI tools to produce better code is not that hard; if you know how to do things right yourself. Basically, all you need to do is ask it to. Ask it to follow SOLID principles. Ask it to stick to guard rails. Ask it to eliminate code duplication, write tests, harden code bases, etc. It will do it. Most people just don't know what to ask for. Or even that they should be asking for it. Or how to ask for it. A lot of people getting messy results need to look in the mirror.

I'm using AI for coding just like everybody else. More or less exclusively since a few months. It's sometimes frustrating to get things done the right way but mostly I get the job done. I've been coding since the nineties. So, I know how to do things right and what doing it wrong looks like. If I catch my AI coding tools doing it wrong, I tell it to fix it and then adjust skills and guard rails to prevent it going off the rails.

AI tools actually seem to self correct when used in a nice code base. If there are tests, they'll just write more tests without needing to be prompted. If there is documentation, that gets updated along with the code. When you start with a vibe coded mess it can escalate quickly unless you make it clean up the mess. Sometimes the tests it adds are a bit meh and you have to tell it off by "add some tests for the non happy path cases, make sure to cover all possible exceptions, etc.". You can actually ask for a critical code review and then tell it "fix all of that". Sometimes it's as simple as that.