Comment by grishka
6 days ago
But when I'm doing my job as a software developer, I don't want to be fuzzy. I want to be exact at telling the computer what to do, and for that, the most efficient way is still a programming language, not English. The only place where LLMs are an improvement is voice assistants. But voice assistants themselves are rather niche.
I want to be fuzzy and I want the LLM to generate something exact.
Is this sarcasm? I can’t tell anymore. Unless your ideas aren’t new, this is just impossible.
Why? I want the LLM to understand my intent and build something exact. That already happens many times.
It can get you 80% of the way there, you can still be exacting in telling it where it went wrong or fine tuning the result by hand.