Those things are LLMs, with text and language at the core of their capabilities. UIs are, notably, not text.

An LLM being able to build up interfaces that look recognizably like an UI from a real OS? That sure suggests a degree of multimodal understanding.

UIs made in the HyperText Markup Language are, in fact, text.

While it is obviously much easier than creating a real OS, some people have created desktop managers web apps, with resizeable and movable windows, apps such as terminals, nodepads, file explorer etc.

This is still a challenging task and requires lots of work to get this far.