[heytakeiteasy]

> The more specialized or obscure of things you have to do, the less LLMs help you.

I've been impressed by how this isn't quite true. A lot of my coding life is spent in the popular languages, which the LLMs obviously excel at.

But a random dates-to-the-80s robotics language (Karel)? I unfortunately have to use it sometimes, and Claude ingested a 100s of pages long PDF manual for the language and now it's better at it than I am. It doesn't even have a compiler to test against, and still it rarely makes mistakes.

I think the trick with a lot of these LLMs is just figuring out the best techniques for using them. Fortunately a lot of people are working all the time to figure this out.

[jatora]

Agreed. This sentiment you are replying to is a common one and is just people self-aggrandizing. No, almost nobody is working on code novel enough to be difficult for an LLM. All code projects build on things LLM's understand very well.

Even if your architectural idea is completely unique... a never before seen magnum opus, the building blocks are still legos.

[tsukurimashou]

the building blocks never were the hard part tho

[xondono]

> I've been impressed by how this isn't quite true.

I’d say it’s true, but the LLMs and humans don’t have the exact same definition of what “obscure” is.

Karel is almost a subset of Pascal with some keyword swaps. And there’s a LOT of Pascal (and similar languages) around.

From the PoV of a statistical based tool like an LLM, Karel is just another flavor of a very popular structure.