Still use last.fm. Most "You might like this" algorithms go straight for the low-hanging fruit, and often fail to take any kind of nuance into account. I can't tell you how many of the streaming services will see my Black Sabbath play history and immediately recommend, "If you like Black Sabbath, you should love...Slipknot!" But I've never had a real person make that mistake, because a real person who looks at my las…
"You like X" "Person Y also likes X" "Person Y also likes Z" "I should recommended Z to you" (proportional to the number of people there are who liked X and Z, compared to other options)
If this is the case (and perhaps I'm wrong), it's nothing to do with the algorithm not understanding the subtleties of the genre, but it's actually just that on average those subtleties disappear because they are unique to you. (Forgive me, I don't know your genres at all, but), I would guess that on average people who like Black Sabbath really do typically like Slipknot as well, and that is why the algorithm recommends them to you.
It's not that the algo is any worse than human recommendations, it's just that it's an average of all humans likes, which will never fit your exact personal unique preferences because they aren't you.