If you need to jump into large, unknown, codebases LLMs are pretty damn good at explaining how they work and where you can find stuff.
A lot faster than clicking through functions in an IDE or doing a desperate "find in project" for something.
And just sticking a stack trace in an LLM assistant, in my opinion, in about 90% of the cases I've encountered will either give you the correct fix immediately or at the very least point you to the correct place to fix things.
I'll accept there may be cases where you can take the LLM output and use it as a suggestion, or something to be carefully checked, and perhaps save some time. So there may be uses for them even if they sometimes generate complete garbage.
Perhaps, but I thought the original poster was talking about replacing the "output" from arbitrary professionals, like doctors, lawyers or architects. I'm a bit wary of what may go wrong.
If you need to jump into large, unknown, codebases LLMs are pretty damn good at explaining how they work and where you can find stuff.
A lot faster than clicking through functions in an IDE or doing a desperate "find in project" for something.
And just sticking a stack trace in an LLM assistant, in my opinion, in about 90% of the cases I've encountered will either give you the correct fix immediately or at the very least point you to the correct place to fix things.