IMO no one knows what LLMs are capable of yet and the goal post keeping moving every few months that building any specific UIs right now risks rendering them obsolete or too slow.

e.g. We went from somewhat smarter code autocomplete, to asking chatgpt copy paste, to cli agent running inside your project, managing session, to GUI to manage that, to projects where you talk to a "Chief of Staff" agent that manages other sessions, to who knows what's next.

I think the right interfaces for LLMs right now need to be very simple and easy to change/evolve. And chat still seems to be the best default solution.

We have all that? I'm still copying and pasting off the WebUI of ChatGPT.

Traditional and boring works for me.