Take a look at this 'KQRBNN vs krr' four-move chess problem generated autonomously by a computer program, Chesthetica, using the Digital Synaptic Neural Substrate (DSNS) computational creativity approach. The DSNS does not use endgame tablebases, neural networks or any kind of machine learning found in traditional artificial intelligence (AI). It also has nothing to do with deep learning. The position below contains 9 pieces which means it simply could not have been derived even from an existing endgame tablebase which is presently limited to 7 pieces.
White to Play and Mate in 4
Chesthetica v11.32 (Selangor, Malaysia)
Generated on 31 Jul 2019 at 6:03:40 PM
Some of the earliest chess problems by humans are over 10 centuries old but original ones by computer are very recent. White has a decisive material advantage in this position but the winning sequence may not be immediately clear. Try to solve this as quickly as you can. If you like it, please share with others. Solving chess puzzles like this can be good for your health as it keeps your brain active. It may even delay or prevent dementia.
Main Line of the Solution
<| Books | DTube | Facebook | Instagram | Twitter | Website |>