Now, this is a ‘KRNPPPP vs krbbppp’ study construct 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. Depending on the type and complexity of the problem desired, a single instance of Chesthetica running on a desktop computer can probably generate anywhere between one and ten problems per hour. 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 14 pieces goes even beyond that and was therefore composed without any such help. The solution shown for this study may not be the best line possible because it depends on the engine that was used and how much time it had to analyze. Regardless, the first move and overall evaluation (e.g. win, draw) should be right.
3k4/2b5/4P1p1/2R1N1K1/4rpp1/7P/b2PP3/8 w – – 0 1
Chesthetica v10.69 : Selangor, Malaysia
White to Play and Draw : 2018.8.6 7:31:35 PM
White actually has less material than Black yet manages to play for a draw. The white army is down by about 2 (Shannon) pawn units in value. Why not time yourself how long it took you to solve this? Note that not all the chess problems are like this. They cover quite the spectrum of solving ability and there are thousands published already.
Main Line of the Solution (Skip to 0:35)