Janelle Shane @JanelleCShane Research Scientist in optics. Plays with neural networks. Avid reader, writer, and player of Irish flute. she/her. wandering.shop/@janellecshane Jul. 13, 2019 1 min read

Fascinated by the way this crochet-trained neural net deals with non-crochet prompts.

Since HAT3000 started out as vanilla GPT-2 345M trained on huge sections on the internet, it still remembers how to generate stories and fan fiction. But now it tries its hardest to gradually turn them into crochet hat patterns.

This one I find particularly interesting - HAT3000’s story isn’t about hats at first, but is weirdly conceptually similar.

HAT3000's stories often end up with intricately choreographed fight scenes. The resemblance to crochet pattern directions is striking (even before the AI introduces a flying ball of yarn).

You can follow @JanelleCShane.


Tip: mention @threader_app on a Twitter thread with the keyword “compile” to get a link to it.

Enjoy Threader? Sign up.

Threader is an independent project created by only two developers. The site gets 500,000+ visits a month and our iOS Twitter client was featured as an App of the Day by Apple. Running this space is expensive and time consuming. If you find Threader useful, please consider supporting us to make it a sustainable project.