Hacker News new | ask | show | jobs
by ModernMech 101 days ago
The reason it works so well is that everyone’s “personal unique language” really isn’t all that different from what’s been proposed before, and any semantic differences are probably not novel. If you make your language C + transactional memory, the LLM probably has enough information about both to reason about your code without having to be trained on a billion lines.

Probably if you’re trying to be esoteric and arcane then yeah, you might have trouble, but that’s not normally how languages evolve.
1 comments
dmd 101 days ago
No, mine's a esoteric declarative data description/transform language. It's pretty damn weird.
link
wizzwizz4 101 days ago
You may underestimate the weirdness of existing declarative data transformation languages. On a scale of 1 to 10, XSLT is about a 2 or 3.
link
dmd 101 days ago
Mine's a weird, bad copy of Ab Initio's DML. https://www.google.com/search?q=ab+initio+dml+language
link
ModernMech 101 days ago
When you say "weird" you mean "different from mainstream languages", but the exact way in which your language is weird (declarative data description/transformation) is probably exactly where languages will be going in the future because of how well-suited they are for LLM reading and writing. Those languages expose the structure of the computation directly such as data shapes and the relationships that transform them, rather than burying intent inside control flow.

With more explicit types and dataflow information, the model doesn't need to simulate execution (something LLMs are particularly bad at) as much as recognize and extend a transformation graph (something LLMs are particularly good at). So it's probably just that your particularly weird language is particularly well-adapted to LLM technology.

link