Take a look at this KQNNPPP vs krppp chess problem generated autonomously by the 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.
White has a decisive material advantage in this position but the winning sequence may not be immediately clear. The default solving time of 30 seconds may be too short for you if the problem is difficult so feel free to hit the pause button and solve at your own pace. Do share and try out some of the others too. As a whole, these problems are intended to cater to players of all skill levels.
Facebook | Twitter | Kindle E-book | Website