Halloween costumes by tiny neural net

I've recently been experimenting with one of my favorite old-school neural networks, a tiny program that runs on my laptop and knows only about the data I give it. Without internet training, char-rnn doesn't have outside references to draw on (for better or for worse) but

Oct 17, 2025 - 15:00
 1
Halloween costumes by tiny neural net
Halloween costumes by tiny neural net

I've recently been experimenting with one of my favorite old-school neural networks, a tiny program that runs on my laptop and knows only about the data I give it. Without internet training, char-rnn doesn't have outside references to draw on (for better or for worse) but it still manages to remix the data into interesting new things.

In 2017 I asked AI Weirdness readers to help me crowdsource a list of Halloween costumes and then trained char-rnn on the nearly 4,500 submissions I got. Today I'm returning both to the dataset and to char-rnn (here's a version that runs on modern Python), mainly because they still entertain me. My laptop is more powerful now than the 2010 Macbook I was using back then, so I'm able to run a bigger version of char-rnn. I actually can't tell whether it helps. But I do know I'm entertained:

The Skypug
Hungry Boats
Mid wonka
Burderous bread cat
Holy Cheesarenda
Moth fairy
A magicial slice
Fall wearing monster
The Godfish

I checked, and nobody in the training data from 2017 was using "mid" as an adjective, so "Mid wonka" is a happy coincidence. The larger version of char-rnn was better than I expected at remixing costumes, producing interesting new characters.

science horse
Lady Doo
Captain Gay
Silence Minister
Cheetos Captain
A scorph Doo
Undead Mario
Sailor Who

There were a couple of Scooby Doo costumes in the original training data, which is probably why the neural net is putting doo in its costumes.

Know what was not in its 2017 era training data? Kpop Demon Hunters, which I have it on good authority will not be an unknown costume in 2025. For fun I asked the neural net to complete the phrases "Kpop " and "Kpop D" and "Kpop De":

Kpop Punk
Kpop and the man and a bus
Kpop Bader Ginsburg
Kpop Dog
Kpop Donald science
Kpop Devil Monster
Kpop Dead Death
Kpop Demetic
Kpop Dead of Turtles

This holds for larger language models like ChatGPT as well, of course. If a current event or a perspective is missing from the training data, it's missing from the result.

The submission form for crowdsourced Halloween costumes is still open, so if you have a few costumes you've seen or dreamed of recently, you can help bring the training data up to date! If I get enough new submissions maybe I'll train the neural network again. (The dataset as of Oct 4 2018 is available on my github).

Bonus content for AI Weirdness supporters: a few more of my favorite costumes trained from the 2018 dataset!