← Back to context

Comment by sanderjd

4 days ago

Yeah but this is exactly why using LLMs doesn't actually preclude problem solving. You still have to do all these things. You just don't have to physically type out as much code.

To make a limping analogy, writing a novel actually requires the writing process. You can instruct an LLM to write prose, but the result won't be the same. I do a lot of thinking by coding, by looking up existing parts of the code base, library documentation and such, to decide how to best combine things, to determine what edge cases have to be solved and implementation decisions to be made. Once I know how things fit, I'm already halfway done. And it's usually more fun to do the rest myself than to instruct the LLM about all the details of the solution I have in mind. There are cases where using the LLM makes sense for truly tedious parts, of course, but it's not the majority of the work.

  • Yeah I would agree with "it's not the majority of the work".

    This is what's making these discussions feel so contentious I think. People say "these are very useful tools!" and people push back on that. But then a lot of times it turns out that people pushing back just mean "they can't do the majority of my work!". Well yeah, but that wasn't the claim being made!

    But then I'm also sympathetic, because there is a huge amount of hype, there are lots of people claiming the these things can do everything.

    So it's just a jumble where the claims being made in either direction just aren't super clear.