Take a look at this 'KPP vs k' chess problem generated autonomously by a computer program, Chesthetica, using the Digital Synaptic Neural Substrate (DSNS) computational creativity approach. It doesn't use endgame tablebases, neural networks or any kind of machine learning found in 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.
Chesthetica v10.56 : Selangor, Malaysia
White to Play and Mate in 3 : 2017.10.17 6:27:33 AM
White has a slight material advantage over Black. See if you can solve this puzzle within 30 seconds or hit pause and take your time. The solution is provided after that followed by some analysis. If this one is too easy or too difficult for you, try out some of the others. Over time, the tactics you see in these puzzles will help you improve your game.
Facebook | Twitter | Get the Book | Website