I agree with your last point to an extent. There's something about "inexpressiveness" that can actually be good, in that it requires you to simplify your data model. However, I imagine as it gets more complex, SQL becomes completely unwieldable. You basically have to use a NoSQL db as the author points out.
Ideally a RDBMS can also be a NoSQL DB. There is no reason it can't/shouldn't, if you have JSON-formatted columns.
Mostly the noSQL pattern is a mistake because you almost certainly have columns that recur reasonably frequently, but if you do have high-dimensional data or want to store processed documents/etc, you can represent them as a JSON/JSONB in postgres/etc, and even run indexes or queries on them.
