harry potter - AI Weirdness

AI + Vintage American cooking: a combination that cannot be unseen

By Janelle Shane On February 08, 2020 - 4 min read

A week ago, in a sudden fit of terrible judgement [https://tmblr.co/ZP7VLs2nUqA3O], I decided to find out what would happen if I: 1. Asked people to help me collect examples of the worst, the weirdest, the most gelatinous recipes that vintage American cooking has to offer, then 2.

Dungeon crawling or lucid dreaming?

By Janelle Shane On September 11, 2019 - 7 min read

I’ve done several experiments with a text-generating neural network called GPT-2. Trained at great expense by OpenAI (to the tune of tens of thousands of dollars worth of computing power), GPT-2 learned to imitate all kinds of text from the internet. I’ve interacted with the basic model, discovering

First there was SkyKnit. Now there's HAT3000

By Janelle Shane On September 04, 2019 - 6 min read

[Chunky Hat”, crocheted by Joannastar] A while ago, I tried to train a neural network to generate knitting patterns by showing it a few thousand existing patterns so it could use trial and error to generate new patterns. I called the project SkyKnit [https://aiweirdness.com/post/173096796277/skyknit-when-knitters-teamed-up-with-a-neural] , and

Bigger than before! A larger neural net tries to write fanfiction

By Janelle Shane On August 30, 2019 - 5 min read

I’ve done several experiments with GPT-2, a neural net that OpenAI trained on millions of pages from the internet. OpenAI has been releasing the neural net in stages, with the second-biggest model, 774M, just recently released. I decided to put it through its paces. Last week’s experiment, where

It takes a bot to know one?

By Janelle Shane On March 08, 2019 - 4 min read

A couple of weeks ago, I wrote about GPT-2 [http://aiweirdness.com/post/182824715257/gpt-2-it-learned-on-the-internet], a text-generating algorithm whose huge size and long-term analysis abilities mean that it can generate text with an impressive degree of coherence. So impressive, in fact, that its programmers at OpenAI have only released a

Harry Potter spells, generated by neural network

By Janelle Shane On September 21, 2017 - 3 min read

Last week [http://lewisandquark.tumblr.com/post/165373096197/a-neural-network-learns-to-create-better-dd] , I trained a neural network [https://github.com/karpathy/char-rnn] to generate the names of magic spells from the game Dungeons and Dragons, by giving it a list of existing spells and asking it to generate more like them. It obliged,

Harry Potter and the word-level recurrent neural network

By Janelle Shane On August 17, 2017 - 6 min read

> Welcome Home by Alisanne | Severus will quite continue in a muggle book. In a previous experiment [http://lewisandquark.tumblr.com/post/162668008357/harry-potter-and-the-neural-network-fan-fiction] , I trained a character-level recurrent neural network (char-rnn [https://github.com/crazydonkey200/tensorflow-char-rnn]) to generate titles and summaries of Harry Potter fan fiction, based on over

Harry Potter and the Neural Network fan fiction

By Janelle Shane On July 06, 2017 - 5 min read

Or, what happens if you train a neural network on the titles and plot summaries of over 100,000 works of Harry Potter fan fiction. In the decades since the Harry Potter books were published, fans have written literally hundreds of thousands of Harry Potter stories of their own, and

Tag: harry potter

AI + Vintage American cooking: a combination that cannot be unseen

Dungeon crawling or lucid dreaming?

First there was SkyKnit. Now there's HAT3000

Bigger than before! A larger neural net tries to write fanfiction

It takes a bot to know one?

Harry Potter spells, generated by neural network

Harry Potter and the word-level recurrent neural network

Harry Potter and the Neural Network fan fiction

Writing

Subscribe

Recent Posts

Botober 2024

Bonus: "Ignore all previous instructions" gets weirder

An exercise in frustration

Bonus: A unicorn goes downhill

Hidden 3D Pictures

Hidden sheep

Follow

Botober 2024

Bonus: "Ignore all previous instructions" gets weirder

An exercise in frustration