Computer-Generated Chess Problem 02641

Now, here we have a 'KQRBN vs krrbp' mate in 3 chess problem generated autonomously by a computer 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. This position contains a total of 10 pieces. The largest endgame tablebase in existence today is for 7 pieces (containing over 500 trillion positions anyway) which means the problem could not have been taken from it regardless.

5K2/8/r3k1r1/5pB1/2NRb3/8/1Q6/8 w - - 0 1
White to Play and Mate in 3
Chesthetica v11.16 (Selangor, Malaysia)
Generated on 1 May 2019 at 12:22:58 AMSolvability Estimate = Difficult
Composing a chess puzzle or problem requires creativity and it's not easy even for most humans. 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.
Main Line of the Solution (Skip to 0:35)