I’ve trained this open-source neural network framework on a variety of datasets, including recipes, Pokemon, knock-knock jokes, and pick up lines.

Here’s the latest: a list of 365 different spells you can cast in Dungeons and Dragons.

It’s a really small dataset, actually - so small that in almost no time at all, it learned to reproduce the original input data verbatim, in order. But by setting the “temperature” flag to a really high value (i.e. it has a higher chance of NOT going with its best guess for the next character in the phrase), I can at least induce spelling mistakes. Then the neural network has to try to recover from these, with often entertaining results.

I give you: D&D magic spells, designed by neural network

Moss Healing Word
Hold Mouse
Barking Sphere
Heat on Farm
True Steake
Finger of Enftebtemang
Fomend’s Beating Sphere
Purping Lightsin
Farming
Wrathful Hound
Q’s Invisibility
Cow of Auraly
Mind Blark
Stone Share
Puijune Magic Furs
Grove of Plants
Conjure Velemert
Vicious Markers
End Wall
Mous of Farts
Cursing
Gland Growth

Part 2: http://lewisandquark.tumblr.com/post/165373096197/a-neural-network-learns-to-create-better-dd

I’m collecting D&D character names for a future project. If you go to this form (no email required), you can enter your character’s name, race, and class. Once I have enough of these, I’ll give them to the neural network and see what happens. Edit: wow, over 3500 responses so far! (Check them out at this link) Keep them coming!

NEW POLL! Neural networks want to hear your character’s backstory! Submit as many as you like. https://goo.gl/forms/ReInNw0Tz0mwzTLO2

Subscribe now