Published online for the first time, consider this KQBNPP vs krrbbppp study construct generated by Chesthetica using the computational creativity approach which doesn't use any kind of traditional AI or even deep learning. Chesthetica is able to generate three-movers, four-moves, five-movers and study-like constructs and also compose problems using specific pieces types fed into it (e.g. instructing it to compose something using a queen, rook and bishop vs. queen and two knights). Read more about it on ChessBase. The largest endgame tablebase in existence today is for 7 pieces (Lomonosov) which contains over 500 trillion positions, most of which have not and never will be seen by human eyes. This problem with 14 pieces goes even beyond that and was therefore composed without any such help whatsoever. The analysis presented for this study may not be perfect as it depends on the engine used and time allocated to it. However, the key move should be right.
