The ai does what you ask it to do. One thing you can ask is for it to refactor the code base to achieve some goal, for example to make new features easier to add , or to just make it more readable (though that’s a bad goal, no one agrees what is readable, and what AI finds readable may be different from what you think).

I am saying this because I haven’t seen latest gen AI unable to implement something no matter how convoluted the code base. On the other hand, people easily get overwhelmed. These days I have more faith in Claude implementing something for me than for a person, including me , doing it thoroughly enough on unfamiliar code bases (and for any big enough code base, large swathes of it will be unfamiliar to any individual developer).

In order for you to properly guide it through a refactor, you have to understand the code, which becomes less possible as it grows into a mess of spaghetti. I think that's just setting yourself up for a massive amount of frustration. When there are multiple systems that need a refactor, each individual refactor becomes that much more complicated. And trusting the tool that created the mess to sort it out seems a tad delusional.

It's true that AI has an incredible ability to take in a massive amount of information and do useful work with it. But it has no direct ability to exercise judgment, and with each iteration of reasoning and applied changes, its ability to hold the original intent degrades very differently from a human intelligence.