I don't think any new languages will easily beat the existing ones, simply because of the mass of training data that is available. An LLM will have a much easier time one-shotting Java than even Rust today because it doesn't have to look up much and the ecosystem was stable for many years, so the internet is filled with content that is still up2date. Building a new language (or even altering existing ones) will take much longer to get into the models.
LLMs that have to constantly fix their code and look up libraries or features are much slower, more expensive and more prone to create inefficient and slightly wrong code. Sure, an LLM can just create a new web framework from scratch, but you usually don't want to spend your tokens on that.
I also think that with LLMs, new languages will have more trouble building an ecosystem, because until now, the popular libraries had a "proof of work" that kinda also made sure that they were well-trodden and maintained. Now, anyone can just push their new generated library and we have no clue on how to compare (and tbh reading LLM-generated READMEs is also not pleasant).
Tremendous amounts of the Java out there in the training corpus would be based on outdated patterns, especially anything pre-Java 8 or pre-Java 21 (Pattern Matching, Project Loom). I don’t think this negatively impacts the quality of LLM Java code but it sort of calls into question whether this is simply a case of more is better.
My personal experience is that LLMs are quite good at one-shotting complex solutions in both Rust and Go, and tend to be idiomatic.
mqus · · focus · HN ↗
LLMs that have to constantly fix their code and look up libraries or features are much slower, more expensive and more prone to create inefficient and slightly wrong code. Sure, an LLM can just create a new web framework from scratch, but you usually don't want to spend your tokens on that.
I also think that with LLMs, new languages will have more trouble building an ecosystem, because until now, the popular libraries had a "proof of work" that kinda also made sure that they were well-trodden and maintained. Now, anyone can just push their new generated library and we have no clue on how to compare (and tbh reading LLM-generated READMEs is also not pleasant).
fcarraldo · · focus · HN ↗
My personal experience is that LLMs are quite good at one-shotting complex solutions in both Rust and Go, and tend to be idiomatic.