> Because LLMs make it that much faster to develop software

I feel as though "facts" such as this are presented to me all the time on HN, but in my every day job I encounter devs creating piles of slop that even the most die-hard AI enthusiasts in my office can't stand and have started to push against.

I know, I know "they just don't know how to use LLMs the right way!!!", but all of the better engineers I know, the ones capable of quickly assessing the output of an LLM, tend to use LLMs much more sparingly in their code. Meanwhile the ones that never really understood software that well in the first place are the ones building agent-based Rube Goldberg machines that ultimately slow everyone down

If we can continue living in the this AI hallucination for 5 more years, I think the only people capable of producing anything of use or value will be devs that continued to devote some of their free time to coding in languages like Gleam, and continued to maintain and sharpen their ability to understand and reason about code.

I don't think this is actually true. LLMs have an impressive amount of ability to do knowledge-transfer between domains, it only makes sense that that would also apply to programming languages, since the basic underlying concepts (functions, data structures, etc.) exist nearly everywhere.

If this does appear to become a problem, is it not hard to apply the same RLHF infrastructure that's used to get LLMs effective at writing syntactically-correct code that accomplishes sets of goals in existing programming languages to new ones.

I bet LLMs create their version of Jevons paradox.

More trial and error because trial is cheap, in the end less typing but hardly faster end results

I would argue it's more important than ever to make new languages with new ideas as we move towards new programming paradigms. I think the existence of modern LLMs encourages designing a language with all of the following attributes:

- Simple semantics (e.g. easy to understand for developers + LLMs, code is "obviously" correct)

- Very strongly typed, so you can model even very complex domains in a way the compiler can verify

- Really good error messages, to make agent loops more productive

- [Maybe] Easily integrates with existing languages, or at least makes it easy to port from existing languages

We may get to a point where humans don't need to look at the code at all, but we aren't there yet, so making the code easy to vet is important. Plus, there's also a few bajillion lines of legacy code that we need to deal with, wouldn't it be cool if you could port (or at least extend it) it into some standardized, performant, LLM-friendly language for future development?

> It’d be like inventing a new assembly language when everyone is writing code in higher level languages that compile to assembly.

Isn't that what WASM is? Or more or less what is going on when people devise a new intermediate representation for a new virtual machine? Creating new assembly languages is a useful thing that people continue to do!

I believe prompting an AI is more like delegation than abstraction especially considering the non-deterministic nature of the results.

We may end up using AI to create simplified bespoke subset languages that fit our preferences. Like a DSL of sorts but with better performance characteristics than a traditional DSL and a small enough surface area.