[smolder]

> There is absolutely no reason why software today has to be written like software of yesterday.

I get what you're saying, but the irony is that AI tools have sort of frozen the state of the art of software development in time. There is now less incentive to innovate on language design, code style, patterns, etc., when it goes outside the range of what an LLM has been trained on and will produce.

[ctoth]

> frozen the state of the art

Personally I am experimenting with a lot more data-driven, declarative, correct-by-construction work by default now.

AI handles the polyglot grunt work, which frees you to experiment above the language layer.

I have a dimensional analysis typing metacompiler that enforces physical unit coherence (length + time = compile error) across 25 languages. 23,000 lines of declarative test specs compile down to language-specific validation suites. The LLM shits out templates; it never touches the architecture.

We are still at very very early days.

Specs for my hobby physical types metacompiler tests:

https://gist.github.com/ctoth/c082981b2766e40ad7c8ad68261957...

[williamcotton]

I have been writing my own DSL (and LSP) for making web apps and LLMs can do a pretty decent job of writing this new language.

https://github.com/williamcotton/webpipe/tree/webpipe-2.0

https://github.com/williamcotton/webpipe-lsp/tree/webpipe-2....

[noman-land]

Citation needed. I see no reason at all why that's true any more than the screwdriver freezing the state of home design in time.

[smolder]

LLMs aren't like a screwdriver at all, the analogy doesn't work. I think I was clear. LLMs aren't useful outside the domain of what they were trained on. They are copycats. To really innovate on software design means going outside what has been done before, which an LLM won't help you do.