I disagree with the author when they say something along the lines of “why don’t we use buttons instead of using these new assistive technology? Buttons are much faster, and I proved humans like fast.”
I think that’s false. Why after 10 years of software development I haven’t learned EMACS? Because I’m lazy, because I don’t think it’s the bottleneck of my work. My bottleneck might be creativity or knowledge and conversational interfaces might be the best thing there are for these (in the lack of a knowledgeable and kind human, which the author also seems to agree with).
Anyway, I don’t know, I found the title a bit disconnected from the content and the conclusions a bit overlappingly confusing but this is a complicated question. In the end I agree that we want a mix of things, we want a couple of keyboard strokes and we want chats. But most of all we probably want direct brain interface! ;)