Earlier this year, researchers tried teaching an AI to play the original Sonic the Hedgehog as part of the The OpenAI Retro Contest. The AI was told to prioritise increasing its score, which in Sonic means doing stuff like defeating enemies and collecting rings while also trying to beat a level as fast as possible.

This dogged pursuit of one particular definition of success led to strange results: In one case, the AI began glitching through walls in the game’s water zones in order to finish more quickly.

Once upon a time I painted a lot. I won some minor awards in high school, and I almost studied art in college. But the closest I ever got was watching Terry Zwigoff’s 2006 satire Art School Confidential.

It’s a about a wide-eyed college freshman whose idealism is beaten out of him by the pettiness, cynicism, and insecurity of the institution and its people. I decided to try to become an engineer instead.

From recipes to paint colour names to Hearthstone cards, everything is better when you make a bot do it. Check out how this machine-learning algorithm named locations on the Fortnite map.

Dungeons & Dragons is full of mixed up creatures like owlbears, which are half bear and half owl, and perytons, the deer-headed eagles of your dreams and nightmares. D&D creatures generated by a neural network are even weirder.

A lot of the time, video game names sound like they were generated by a machine. So, I decided to see if I could teach a neural network to name a game.