What we have here is a 'KQBBNP vs kqbpp' three-move chess problem generated autonomously by the prototype computer 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. 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.
If you notice an earlier version of Chesthetica listed with a newer problem, that simply means an earlier version may have been running on a different computer or OS user account. White is significantly ahead in material. Do share and try out some of the others too. Feel free to copy the position into a chess engine and discover even more variations of the solution. If you're bored of standard chess, though, why not try this?
