It sounds like one of those recursive ANN things. On the scale of seconds, it's quite good. But there's no higher-level structure. For "folk", this is obvious; for ambient, you'd probably never notice.

The goal for this technology is to beat the two guys who write most popular music.[1] Another few years.

[1] http://nypost.com/2015/10/04/your-favorite-song-on-the-radio...