What we have here is a 'KQRN vs kqrpp' mate in 3 chess problem generated autonomously by Chesthetica using the 'Digital Synaptic Neural Substrate' computational creativity approach which does not use any kind of deep learning. There is also no proven limit to the quantity or type of legal compositions that can be automatically generated. Noteworthy here is that a chess position with over 7 pieces could not have been derived or taken from an endgame tablebase because 7 pieces is the present limit.
White to Play and Mate in 3
Chesthetica v11.62 (Selangor, Malaysia)
Generated on 29 Feb 2020 at 6:06:20 AM
Chesthetica, especially if running on multiple computers or operating system user accounts, is capable of generating far too many compositions than can be published in a timely fashion here. The newer ones will therefore only be published some time later. This is why the composition date above does not match today's date. White has a slight material advantage over Black. Try to solve this as quickly as you can. If you like it, please share with your friends. Over time, the tactics you see in these puzzles will help you improve your game.