Computer-Generated Chess Problem 03086

A 'KQRNP vs knp' mate in 3 chess problem generated by a computer program, Chesthetica, using the Digital Synaptic Neural Substrate (DSNS) computational creativity approach. It doesn't use endgame tablebases, deep learning or any kind of traditional AI. You can learn more about the DSNS here. The largest endgame tablebase in existence today is for 7 pieces (Lomonosov) which contains over 500 trillion positions, most of which have not been seen by human eyes. This problem with 8 pieces goes even beyond that and was therefore composed without any such help.

8/1K6/8/2N5/1n6/k1P5/1p3Q2/2R5 w - - 0 1
White to Play and Mate in 3
Chesthetica v11.98 (Selangor, Malaysia)
Generated on 16 Oct 2020 at 6:05:01 AMSolvability Estimate = Difficult
Most changes to Chesthetica that result in a slightly higher 'version number' are simply to improve the interface, by the way. What was the machine 'thinking' when it came up with this? Leave a comment below, if you like. Solving chess puzzles like this can be good for your health as it keeps your brain active. It may even delay or prevent dementia.
A Similar Chess Problem by Chesthetica: 00410
Solution