Algebraic effects are the way forward, but that's a long way off.

Programming languages, in contrast, are constructed and vary much more in their designs. They are formal languages, making them closer to math than spoken language. LLMs being able to describe concepts more thoroughly and precisely through more expressive semantics obviously makes some languages more suitable than others.

The type system of a language is just one aspect of it that allows the language to provide guarantees to the LLM (and the user) about correctness of the code it's writing.

I am not speaking about specific types in specific programs. I am talking about the ability to describe complex constraints that LLMs (and humans) end up using to make writing correct code easier and more productive. Some programming languages absolutely are more effective at this than others, and that's always been true even before LLMs.

Until you need a library that was written with the assumption of using a garbage collector.

Users should be able to have full control over their experience interacting with third parties if they want it. This isn't unique to post-LLM stacks like this, but it seems like this shifts the balance of power.

The next step after injecting custom UI controls is to build completely alternative frontends. The next step after that should be to build generic local frontends that abstract over multiple comparable thirdparty providers.