zlacker

[return to "Nerd: A language for LLMs, not humans"]
1. gnanag+d[view] [source] 2026-01-01 01:15:17
>>gnanag+(OP)
Creator here. This started as a dumb question while using Claude Code: "Why is Claude writing TypeScript I'm supposed to read?"

40% of code is now machine-written. That number's only going up. So I spent some weekends asking: what would an intermediate language look like if we stopped pretending humans are the authors?

NERD is the experiment.

Bootstrap compiler works, compiles to native via LLVM. It's rough, probably wrong in interesting ways, but it runs. Could be a terrible idea. Could be onto something. Either way, it was a fun rabbit hole.

Contributors welcome if this seems interesting to you - early stage, lots to figure out: https://github.com/Nerd-Lang/nerd-lang-core

Happy to chat about design decisions or argue about whether this makes any sense at all.

◧◩
2. wrs+Bf[view] [source] 2026-01-01 04:02:27
>>gnanag+d
Now that we know code is a killer app for LLMs, why would we keep tokenizing code as if it were human language? I would expect someone's fixing their tokenizer to densify existing code patterns for upcoming training runs (and make them more semantically aligned).
[go to top]