Computer-Generated Chess Problem 02113
Now, this is a 'KQBNN vs kqpp' mate in 5 chess construct composed autonomously by the program, Chesthetica, using the 'Digital Synaptic Neural Substrate' computational creativity method. It does not use endgame tablebases, artificial neural networks, machine learning or any kind of typical AI. There is also no proven limit to the quantity or type of legal compositions that can be automatically generated. This position contains a total of 9 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.
White to Play and Mate in 5
Chesthetica v10.67 : Selangor, Malaysia
2018.5.27 8:38:16 PM
Composing a chess puzzle or problem requires creativity and it's not easy even for most humans. White is over a rook's worth in material but the precise win in this position still needs to be found. Do share and try out some of the others too. Take some time to study the analysis and you might appreciate the puzzle a little more.
Solution (Skip to 0:35)