This is not necessarily true. Many models have been trained on assembly code, and you can ask them to produce it. Some mad lad created some scripts a while ago to let AI “compile” to assembly and create an executable. It sometimes worked for simple “Hello, world” type stuff, which is hilarious.
But I guess it is easier for a large language model to produce working code for a higher level programming language, where concepts and functions are more defined in the body that it used to get trained.
uranibaba@lemmy.world 1 day ago
The compiler is likely better at producing machine code as well, if LLMs could produce it.
riskable@programming.dev 1 day ago
To add to this: It’s much more likely that AI will be used to improve compilers—not replace them.
Aside: AI is so damned slow already. Imagine AI compiler times… Yeesh!
naught101@lemmy.world 1 day ago
Strong doubt that AI would be useful for producing improved compilers. That’s a task that would require extremely detailed understanding of logical edge cases of a given language to machine code translation. By definition, no content exists that can be useful for training in that context. AIs will certainly try to help, because they are people pleasing machines. But I can’t see them being actually useful.
riskable@programming.dev 16 hours ago
Umm… AI has been used to improve compilers dating all the way back to 2004:
github.com/…/Artificial-Intelligence-in-Compiler-…
Sorry that I had to prove you wrong so overwhelmingly, so quickly 🤷
JustJack23@slrpnk.net 21 hours ago
I agree but I would clarify that this is true for the current gen of LLMs. AI is much broader subject.