Well "most" devs is doing a lot of work here.

I'm not sure about other devs, or even their number, but AI can most definitely NOT produce better code than I can.

I use it after I have done the hard architectural work: defining complex types and interfaces, figuring out code organization, solving thorny issues. When these are done, it's now time to hand over to the agent to apply stuff everywhere following my patterns. And even there SOTA model like Opus make silly mistakes, you need to watch them carefully. Sometimes it loses track of the big picture.

I also use them to check my code and to write bash scripts. They are useful for all these.

You’re equating two things that aren’t the same. I’m not still manually writing code, but it’s not at all because Claude can produce better code than me. It’s worse at CRUD apps and a lot worse at domain specific bits. But it’s more parallelizable, so if I drive it well I can focus my skill on the small subset of problems that actually require it and achieve increased throughput.

It can produce better code than most devs in the hands of a good dev. The bullshit code I see coming from juniors using AI..

[dead]