B-IR
Languages and libraries
programming language
SHOW HN2026
How HN took it
2 positive, 1 neutral or asking, 1 mixed, 8 critical, out of 12 comments about the project. Thread score -0.45.
Idea: 2 for, 5 againstExecution: 0 for, 2 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Useful exploration of the idea that verifiability helps both LLMs and humans
From 1 comment
I tried a thread, I got that both LLMs and humans optimize for the same goal, working programs, and the key is verifiability. So it recommended Rust or Haskell combined with…
Mathnerd314 on HN
Objections
LLMs are trained on existing languages, so new invented formats lack training data
From 3 comments
An LLM is optimized for its training data, not for newly built formats or abstractions. I don’t understand why we keep building so-called "LLM-optimized" X or Y. It’s the same…
kburman on HNYeah fwiw I agree. I was impressed at how well the agents were able to understand and write their invented language, but fundamentally they're only able to do that because…
ImJasonH on HNso where are the millions of line code you need to train the LLM in your new language? Remember AI is just a statistic prediction thing. No input -> No output
Surac on HN
Vibe-coding the language was lazy; the design was not thought through
From 2 comments
I get that this is essentially vibe coding a language, but it still seems lazy to me. He just asked the language model zero-shot to design a language unprompted. You could at…
Mathnerd314 on HNI was thinking the same. Maybe if he tried to think instead of just asking the model. The premise is interesting "We optimize languages for humans, maybe we can do something…
Snacklive on HN
Token minimization is the wrong goal; verbosity can help LLMs
From 2 comments
There's also the issue, which is also noted by the author, that LLM-optimization quite often becomes, when shouldn't be just that, token-minimization.
forgotpwd16 on HN> The real question is what existing language is perfect for LLMs? I think verbosity in the language is even more important for LLMs than it is for humans. Because we can see…
nzach on HN
Requests
Research into languages that support formal methods and model checking
From 1 comment
If a new programming language doesn’t need to be written by humans (though should ideally still be readable for auditing), I hope people research languages that support formal…
cpeterso on HN
Benchmarks comparing which languages AI models solve tasks in best
From 1 comment
Are there coding AI benchmarks that show in which language AI models are best at solving tasks? Sort of like Rosetta code but for AI and more complex tasks?
scotty79 on HN
Questions
Which existing language is best suited for LLMs?
From 1 comment
The real question is what existing language is perfect for LLMs? Is Lisp? ASM? We know some LLMs are better at some languages but what existing language are they best at? Would…
giancarlostoro on HN
Alternatives named
Lisp-style languages and S-expressions
From 3 comments
The real question is what existing language is perfect for LLMs? Is Lisp? ASM? We know some LLMs are better at some languages but what existing language are they best at? Would…
giancarlostoro on HNI have been having a crack at it in my spare time. A kind of intentional LISP where functions get turned into WASM in the cloud. The functions are optionally tested using formal…
quatonion on HNI've been thinking about this, take a look at this: > From Tool Calling to Symbolic Thinking: LLMs in a Persistent Lisp Metaprogramming Loop https://arxiv.org/abs/2506.10021 edit…
wfn on HN
APL, J and array programming languages
From 1 comment
I'm assuming OP is not aware of APL, J, or similar array programming languages.
atlintots on HN
Rust or Haskell with formal verification
From 1 comment
I tried a thread, I got that both LLMs and humans optimize for the same goal, working programs, and the key is verifiability. So it recommended Rust or Haskell combined with…
Mathnerd314 on HN