Which is it is clear - the enthusiast have spent countless hours learning/configuring/adjusting, figuring out limitations, guarding against issue etc etc etc and now do 50 to 100 PRs per week like Boris
Others … need to roll up the sleeves and catch up
Merely counting PRs is not very impressive to me. My pre LLM average is around 50/week anyway. But I’m not going to claim that somehow makes me the best programmer ever. I’m sure someone with 1 super valuable PR can easily create more value than I do.
Or the tool makers could just make better tools. I'm in that camp, I say make the tool adapt to me. Computers are here to help humans, not the reverse.
There isn't anything clear until someone manages to publish measurable and reproducible results for these tools while working on real world use cases.
Until then it's just people pulling the lever on a black box.