News for hackers. Stuff that matters.
Re:Nanolang: A tiny experimental language designed to be tar... by nl on Monday January 19, 2026 @11:26PM (#46687906)
> My understanding/experience is that LLM performance in a language scales with how well the language is represented in the training data.

This isn't really true. LLMs understand grammars really really well. If you have a grammar for your language the LLM can one-shot perfect code.

What they don't know is the tooling around the language. But again, this is pretty easily fixed - they are good at exploring cli tools.

There are no comments on this comment yet.