Earlier quoted context omitted.
> Eventual shortcomings will be fixed not by looking into the code, but by typing in another prompt, asking another agent. So, you'll rely on the tech that created buggy code to somehow suddenly create bug-free code?
Isn’t it the same as relying on human developers? Gotchas aside: I’m not saying the end of programming is a good thing. I’m just saying: it’s happening. Unless the LLM tech will suddenly hit any sort of ceiling.
Re: It's not the end of programming
#91Different. You have a wide choice of good human developers.