It should be better for the reasons explained in the article. Pure functions require no context to understand. If they are typed, it's even simpler. LLMs perform badly on code that has lots of state and complex semantics. Those are hard to track.

In fact, synthesis of pure Haskell powered by SAT/SMT (e.g. Hoogle, Djinn, and MagicHaskeller) was already of some utility prior to the advent of LLMs. Furthermore, pure functions are also easy to test given that type signatures can be used for property-based test generation.

I think once all these components (LLMs, SAT/SMT, and lightweight formal methods) get combined, some interesting ways to build new software with a human-in-the-loop might emerge, yielding higher quality artifacts and/or enhancing productivity.

▲

td2 2 days ago | parent [-]

Wouldnt a fair counter argument be, that llms have been trained on way less fu ctional code though?

Like they are trained on a LOT of js code -> good at js Way less functional code -> worse performance?

▲

mvellandi 2 days ago | parent | next [-]

You can write functional-style code in many languages, as I have in JS and occasionally Python to great benefit.

	▲	DeathArrow a day ago \| parent [-]
		For sure. I write functional style code in C# but it is not the same thing as writing OCaml or F#.

▲

nextos 2 days ago | parent | prev [-]

That's a very fair point. There are some publications showing lower performance for languages with less training data. I imagine it also applies to different paradigms. Most training code will be imperative and of lower quality.