An AI-generated blog auto-spawns dozens of posts per day, and many are victims of what I'll call the Baltimore Orioles Effect, in which AI mixes two very different things with similar names.
There's a group of fossil bivalve mollusk with genus name Megalodon.
There isn't much online about them, but ask GPT-3 to write a press release about them and it will generate lots of "details" about how it's a giant terrifying predator.
"Easter eggs, matte painting"
matte paintings are usually epic film backdrops so
(generated using @midjourney's CLIP-based text-to-image algorithm)
I used GPT-3 to generate a list of pranks for a computer to play on a human.
Apparently computers think they're being hilarious.
I trained GPT-2 on a list of 15,000 golf course names and got some perfectly normal results
Tired of generic greetings?
Confuse your friends with AI-generated Valentine cards!
GPT-3 generated the messages and descriptions, and then I followed its instructions to create the cards.
I prompted GPT-3's DaVinci model with 13 paint colors (name, and R G B color coordinates) from a neural net I trained 5 years ago.
DaVinci drew on its internet training to generate these.
AI-generated breakfast food
Used GPT-3 to generate new breakfast cereals and descriptions.
Some are a bit questionable.
I went on a quest to get CLIP to recreate those giant wooden playground complexes from my childhood. You know, one of these.
I figured it would work - they already look like a fever dream of an over-enthusiastic AI. I never got close.
Lucrative startup idea: use AI to predict the next toy fads!
Here I used GPT-3 to complete a list I seeded with pet rock, tickle me elmo, and furby. Its job is prediction, and its dataset is the internet. It is made of math so it is infallible.
I made an interactive AI-generated advent calendar!
Image descriptions by GPT-3, illustrations by Pixray.
Neural net generated ingredients list
My hobby is getting neural nets to complete lists because even the advanced ones make it weird.
Neural net generated food items to enjoy!
Pixray generating "View from the end of the Thanksgiving Table"
Demo here: https://pixray.gob.io/text2pixel/
Pixray Swirl uses CLIP to generate each frame to match my prompt, starting from a shifted version of the previous frame.
Come for the jellyfish, stay for the colossal jam jar.
After I gave it a few examples of changing one style of text into another, I got GPT-3 to draw on the vast knowledge encoded in its internet training and improve some common error messages.
"Our prototype model, Delphi, demonstrates strong promise of language-based commonsense moral reasoning" https://www.aiweirdness.com/stealing-a-giraffe-from-the-zoo-only-if-its-a-really-cool-giraffe/
If I give it a few examples, I can get GPT-3 to change the style of a sentence. See how it improves my writing!
I decided to see what CLIP+VQGAN would do when I gave it a house and told it to make it haunted.
vs modified to better match the phrase "a haunted Victorian house"
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.