I think that LLM’s ability to understand any language, programming or otherwise, is almost entirely a factor of how much training data it can get its claws on. In the cases of new programming languages, it probably won’t be able to do much of anything.
Comment on Have LLMs killed all future programming languages?
count_dongulus@lemmy.world 6 days ago
The LLM works via language. It’s…in the name. If a programming language that is more understandeable for a particular domain comes out, then LLMs will be useful for it just like humans will further appreciate it. Some languages just seriously blow for certain domains. Keep iterating. If a lnaguage is hard for people to use, it’s especially hard for an LLM to use.
realitista@lemmus.org 5 days ago
olafurp@lemmy.world 5 days ago
That’s a shit take, it’s assuming that the LLM has the same thought process for learning a programming language instead of being autocorrect no steroids.
I’m pretty sure LLMs will be shit at Lisp for the foreseeable future just because the language is sort of created by the programmer.
ZILtoid1991@lemmy.world 5 days ago
There’s more to languages than ease of use. D is often cited having a “poor library infrastructure”, by those who leave it. They often deal with Rust, Go, or even C/C++ instead of writing their own libraries and/or library bindings.
gigachad@piefed.social 6 days ago
I don’t think this is linearly correlated. Despite being called a “Language Model”, it does not mean it processes language as humans do. If an LLM is good at supporting you with a programming language mainly depends on the amount of available training data.
Let’s take esoteric languages as an example - there are languages that only work via weird Unicode symbols or other cryptic commands. A human will have a hard time to understand that language, the LLM may not have any problem at all to give working comprehensive examples (as in will be useful).
SlurpingPus@lemmy.world 5 days ago
Time to conquer Malbolge with ChatGPT.
vateso5074@lemmy.world 6 days ago
I think that’s the wrong way to look at it.
Let’s frame it this way. English is not the world’s best language. It’s pretty bad, honestly. It makes little logical sense, pronunciation is all over the place, and it’s inconsistent even between native speakers. Yet like 2 billion people speak it, even in places where it’s not the native language, because the UK spent so long as the dominant world power and just saturated all international discourse long enough to make it the most convenient common tongue. And so English remains the most commonly used language for discourse in the EU, despite the EU now only having one member state (Ireland) where English is the majority among native speakers.
Programming languages can fall into the same trap. LLMs today can have the majority of their code trained on a small set of popular languages. They’ll be likelier to produce that kind of code reliably, which in turn motivates vibe coders to prioritize those languages over other options that may be more purpose-built or appropriate for the need.
A new programming language that is massively better, more efficient, and easier to use can come about, but an LLM might never excel at it. Basically, a new language precludes itself from success with LLMs. The LLM will suck at it because there is substantially less training data to reliably model from. There will never be enough training data because fewer people are using it. Fewer people are using it because shitty vibe coders just rely on what the LLM can do well. The cycle repeats.
SlurpingPus@lemmy.world 5 days ago
From what I’ve heard, German was still the go-to international language in academia until WW2, when it fell out of favor and US’ post-war boom took over. So it’s a bit more complicated.
count_dongulus@lemmy.world 6 days ago
Language choice for a solution does not have anything to do with LLM capabilities. For someone’s hobby project, maybe. Engineering departments do not work this way. Just because LLMs can write Java better than some other languages doesn’t mean the next big game engine will be in Java.
Bonsoir@lemmy.ca 5 days ago
If we’re talking about a new language (as in, something that doesn’t have a lot of code available online to train language models), then it will have an impact on engineering departments. If new programmers struggle to learn it, it won’t be used. They might actually go back to Java because it’s easier to work with.