First, how is this different from having your IDE fill in your loop templates?
I don’t do that actually, but I think there are some differences.
One is if there’s a loop template in your IDE, you know it’s going to work. With LLMs you have to double check stuff (or just have it be wrong some of the time).
You don’t have to type in a bunch of instructions to use a loop template. You also don’t really have to wait for the filled in template to get generated.
People don’t usually use that because they just don’t know how to write the loop themselves, it’s a convenience feature.
That said:
I’m usually doing this for a customer in a language I’ll never use again.
Maybe you’re the one in a million exception where this approach is a benefit. Most of the time when you talk to people on the internet, they’re going to assume you’re a reasonably typical case and not the extremely rare exception.
I don’t do that actually, but I think there are some differences.
That said:
Maybe you’re the one in a million exception where this approach is a benefit. Most of the time when you talk to people on the internet, they’re going to assume you’re a reasonably typical case and not the extremely rare exception.