Siri wasn’t great but it was way, way more usable before the “machine learning” update whenever that was. Before it was a verbal command line, but at least you could learn some commands.
I think the problem is adding on to a clunky paradigm.
It wasn't a good verbal command line. It was usable because even an imperfect command line UI is inherently usable if use cases are limited. Building on to that though... you always overreach.
Personally, I always thought voice+screen interface was an under-explored. That (for example) would let you go from command line to command line navigator... a natural progression.
Voice UI kind of needs to be "one shot" to be pleasant: Play "Fortunate Son." Once you have to go back and forth, listen to list of options... it's no fun anymore. The Windows/Mac/Xerox GUI paradigm required a mouse, keyboard & screen. Voice only is limiting... perhaps.
Now it’s a crapshoot.