Being vaccinated does NOT mean it's okay to ask neural nets to participate in meme formats about pandemics that didn't exist when their training data cut off in Oct 2019. You will get memes that make no sense. Be smart.
I used a few GPT-3 variants to generate April Fools pranks suitable for playing on oneself at home.
For the format they had to rely on pranks they'd seen during their internet training. Curie, the 2nd largest variant, sounded the most pranklike.
I assumed that if GPT-3 generated pickup lines, they would be terrible because they would be something like human pickup lines. Instead, they are terrible for more delightful reasons.
Gave the lyrics of this sea shanty to CLIP+FFT and had the AI generate illustrations.
It's a brand new kind of horrifying.
Obsessed with CLIP+FFT, which uses CLIP, an internet-trained image-judging AI, to steer a deep dream-like image generator.
It'll do what you ask, but it will do it excessively.
"Frodo Baggins delivering pizza through the mines of Moria"
Gave a neural net some examples from @mondomascots and it responded with some deeply weird mascots.
The Brando, a guesthouse in Tokyo, is represented by Garapon-kun, a shy yet terrifying Jack-in-the-box that likes to play with balloons.
Makuo, a sea anemone from Kagoshima, can see the future. His antennae are mittens, but he has eight toes on each hand.
I tried to generate images of candy hearts using Ryan Murdock's CLIP+BigGAN method.
The results were less sweet than I had hoped.
Decided to try GPT-3 at the task of generating candy hearts. They are not candy hearts you'll see in the store. https://janellecshane.substack.com/p/okay-gpt-3-candy-hearts?r=1lic4&utm_campaign=post&utm_medium=web&utm_source=twitter
"Leaning Tower of Pizza"
I used @advadnoun's Big Sleep program to steer BigGAN into generating weird images for me, using CLIP for feedback. Sometimes it worked. Sometimes it failed hilariously.
In which I revisit some AI Weirdness posts from 2020 that inspired humans to do delightfully weird stuff
Not only can DALL-E generate some pretty amazing pictures, but someone at @OpenAI put some very ai weirdness-worthy prompts in the demo. These are so much fun.
“That Time It Rained for Two Million Years”
“When Giant Scorpions Swarmed the Seas”
A lot of stuff has happened in 4.5 billion years.
I prompted GPT-3 with epic @EonsShow episode titles to see what the next billion years might hold.
Got GPT-3 to generate new Christmas carols.
Here is "Mild is Rudolph". Are you not cheered and comforted?
I gave a set of 2020 headlines to the neural net GPT-3, whose training data cut off in October 2019.
Having never seen 2020, it tried to predict what headlines are next on the list.
GPT-3 generates reviews for the tiny neural net char-rnn's chaotic recipes.
GPT-3 is apparently trying to produce reviews that could plausibly be written by whatever weird humans are visiting this mangled recipe website.
So I managed to get GPT-3 to generate new Victorian handkerchief flirting codes.
I hope you find them useful for adding subtext to your next zoom call
Since we all aren't busy enough, I used GPT-3 to generate new to-do items from DaVinci's notebooks.
This AI has never heard of #Blaseball but when I gave it the list of existing teams, GPT-3 predicted that these teams will come next.
The neural net GPT-3 has seen enough Halloween costumes in its general internet training that to get something unusual, you have to ask it for a twist.
I asked for high-visibility costumes for viewing in the age of covid, and was not disappointed.
Made a neural net version of one of those color memes.
I train neural networks to write humor at aiweirdness.com | Also a research scientist in optics. She/her
The Wandering Shop is a Mastodon instance initially geared for the science fiction and fantasy community but open to anyone. We want our 'local' timeline to have the feel of a coffee shop at a good convention: tables full of friendly conversation on a wide variety of topics. We welcome everyone who wants to participate, so long as you're willing to abide by our code of conduct.