Citation very much needed. Otherwise you're basically arguing that the problems associated with people writing bad code somehow go away when they're suddenly in a position to direct the quality of code generated for them.
For "terrible programmers" (I use this loosely, sometimes thats me! - not a value judgement of the person. Might be inexperience, working outside usual area, bad week etc) code shifts from being "fractally wrong how do I even explain to you why it's wrong, you clearly have zero mental model of whats going on here", to "actually ok code but wrong approach and you didn't need to add a 200 line Python script for this". The rework process is explaining the right approach which gets meat proxied to Claude who DOES get it.
I get that a lot of people feel mugged giving feedback and having it proxied, without a _relationship_ where you can see a person is growing and mistakes won't recur. It's like the "author" is just using a robot to steal your time. Sometimes I personally feel relief at work though, because it would steal WAY MORE time to explain detailed and intricate stuff across a really large knowledge gap... in which case I am actually grateful that they have Claude as a cognitive prosthesis. At times I am the one who needs the prosthesis.
Even in the absence of good feedback I frequently see stuff go from "not even wrong" to "thats kinda messed up but it'll get the job done".
Other places, the "good (but not highly conscientious) dev -> slop cannon" effect might be dominating. I feel like AI is raising the floor and ceiling of what people can do (a strong senior / expert can whip the AI until the output is actually good) but having particularly weird effects in the middle. Its enabling people to attempt things outside their usual area (devs doing infra, sres doing more dev, backends & frontends doing each other's jobs) and IMHO that's where good feedback really helps.