Can you offer any specifics? The ToC looks quite extensive, which to me indicates a lot of design decisions needed to be made (probably involving many people) and unclear how that process might be accelerated by AI.
Unless you're suggesting the language design should also be vibed together?
> Unless you're suggesting the language design should also be vibed together?
Sounds like a fun little project, have a bunch of AI pushers fork Zig and see if they can do a better job. I want to see results, not snarky HN comments. After all this progress, ChatGPT should be able to one-shot a better language since AI is so good now... right?
One-shot, no, but there are a bunch of people pretty much solo-building their personal ideal language with AI and it's going quite well. You need to know just enough about language design to be dangerous, but you don't need to be a seasoned pro.
I'm doing it myself: <a href="https://zena-lang.dev/" rel="nofollow">https://zena-lang.dev/
It seems like such a strange thing to do, building a language that you aren't going to write by hand. It's guaranteed to perform worse at higher cost, fill up a lot more of the context window, and burn a ton more reasoning tokens.
If you're using AI, a language with a large training set is going to win.
I don't think those assertions about AI development necessarily hold. And I think it'd be a depressing future if we can't ever have anything new or better that wasn't popular in the training set as of November 2025.
I wrote about some of my thoughts with Zena and AI here: <a href="https://zena-lang.dev/blog/2026/09/languages-for-the-ai-era/" rel="nofollow">https://zena-lang.dev/blog/2026/09/languages-for-the-ai-era/
But you’re very clearly wrong. Just go ahead and try it: write your own language or just a DSL, write a brief description of how it works , let a LLM use it. Many of us have done this and everyone knows that it works extremely well, to most people’s surprise.
I'd suggest benchmarking the outcomes. It's going to "work", but at a higher cost with worse ontcomes compared to an existing language with a large training set.
I compare one algorithm across several programming languages and backends. There is no training data for Mech in the LLM yet it beats most other implementations in perf, which were optimized by LLM.
Maybe human performance engineers trained in these languages could write better implementations. But to answer the question of whether the LLM could write more performant code in languages it’s trained in versus languages it’s not, this comparison is at least illustartive.
jabedude · · focus · HN ↗
abc42 · · focus · HN ↗
greggoB · · focus · HN ↗
Unless you're suggesting the language design should also be vibed together?
nvme0n1p1 · · focus · HN ↗
Sounds like a fun little project, have a bunch of AI pushers fork Zig and see if they can do a better job. I want to see results, not snarky HN comments. After all this progress, ChatGPT should be able to one-shot a better language since AI is so good now... right?
spankalee · · focus · HN ↗
I'm doing it myself: <a href="https://zena-lang.dev/" rel="nofollow">https://zena-lang.dev/
0c3ca83 · · focus · HN ↗
If you're using AI, a language with a large training set is going to win.
spankalee · · focus · HN ↗
I wrote about some of my thoughts with Zena and AI here: <a href="https://zena-lang.dev/blog/2026/09/languages-for-the-ai-era/" rel="nofollow">https://zena-lang.dev/blog/2026/09/languages-for-the-ai-era/
0c3ca83 · · focus · HN ↗
brabel · · focus · HN ↗
0c3ca83 · · focus · HN ↗
cmontella · · focus · HN ↗
<a href="https://mech-lang.org/iros-r4r-2026/index.html#58054068114627774" rel="nofollow">https://mech-lang.org/iros-r4r-2026/index.html#5805406811462...
I compare one algorithm across several programming languages and backends. There is no training data for Mech in the LLM yet it beats most other implementations in perf, which were optimized by LLM.
Maybe human performance engineers trained in these languages could write better implementations. But to answer the question of whether the LLM could write more performant code in languages it’s trained in versus languages it’s not, this comparison is at least illustartive.