Published online for the first time, consider this KRBBNP vs kqbnn chess problem generated 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. You can learn more about the DSNS here. Any chess position with this many pieces could not possibly have been obtained from known endgame databases. Chesthetica is therefore the real McCoy. 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.
4n3/8/5qBP/3k4/8/B1b3Rn/5N2/2K5 w – – 0 1
White to Play and Draw
Chesthetica v10.86 : Selangor, Malaysia
Generated on 2 Jan 2019 at 9:49:09 PM
A seemingly earlier version of Chesthetica on a problem composed later (based on the date and time stamp) simply means that version may have been running on a different computer or operating system user account. Get a glimpse into the ‘mind’ of a computer composer. Try to solve this as quickly as you can. If you like it, please share with others. 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)