Assembly already exists.
Once upon a beginning I believe assbly actually had human authors and readers in mind.
LLVM IR is a better example.
https://en.wikipedia.org/wiki/Intermediate_representation#La...
Nerd: A language for LLMs, not humans
21–30 of 110 posts
Re: Nerd: A language for LLMs, not humans
#22I have the exact opposite prediction. LLMs may end up writing most code, but humans will still want to review what's being written. We should instead be making life easier for humans with more verbose syntax since it's all the same to an LLM. Information dense code is fun to write but not so much to read.
Re: Nerd: A language for LLMs, not humans
#23Earlier quoted context omitted.
> 40% of code is now machine-written How did you arrive at that number?
Ran a simple test with the examples you find in the project. Will publish those benchmarks.. actually that makes me think, I should probably do a public test suite showing the results. :)
Ok, now I'm even more confused. 40% of what code is machine written?
Re: Nerd: A language for LLMs, not humans
#24Would it make more sense to instead train a model and tokenise the syntax of languages differently so that white space isn’t counted, keywords are all a single token each and so on?
Re: Nerd: A language for LLMs, not humans
#25I was going to try and resist posting for as long as possible in 2026 (self dare) and here I am on day 1 -- this is a pretty bad idea. are you going to trust the llm to write software you depend on with your life? your money? your whatever? worst idea so far of 2026. wheres the accountability when things go wrong?
Re: Nerd: A language for LLMs, not humans
#26>NERD is what source code becomes when humans stop pretending they need to write it.
It is so annoying to realise mid read that a piece of text was written by an LLM.
It’s the same feeling as bothering to answer a call to hear a spam recording.
Re: Nerd: A language for LLMs, not humans
#27Creator 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…
> "Why is Claude writing TypeScript I'm supposed to read?" 40% of code is now machine-written. That number's only going up.
How much of the code is read by humans, though? I think using languages that LLMs work well with, like TS or Python, makes a lot of sense but the chosen language still needs to be readable by humans.
Re: Nerd: A language for LLMs, not humans
#28That's not true, the first not-for-humans language is Pel: https://arxiv.org/abs/2505.13453
Re: Nerd: A language for LLMs, not humans
#29> Do you debug JVM bytecode? V8's internals? No.
I can't speak for the author, but I do often do this. IMO it's a misleading comparison though, you don't have to debug those things because rarely does the compiler output incorrect code compared to the code you provided, it's not so simple for an LLM.
Re: Nerd: A language for LLMs, not humans
#30A curly brace is multiple tokens? Even in models trained to read and write code? Even if true, I’m not sure how much that matters, but if it does, it can be fixed.
Imagine saying existing human languages like English are “inefficient” for LLMs so we need to invent a new language. The whole thing LLMs are good at is producing output that resembles their training data, right?