AI Weirdness (Page 10)

Three guinea pig horse toys, stocky with guinea pig faces and guinea pig markings.

New AI-generated horsies

By Janelle Shane On July 22, 2022 - 2 min read

Recently I've been experimenting with DALL-E 2, one of the models that uses CLIP to generate images from my text descriptions. It was trained on internet text and images, so there's a lot it can do, and a lot of ways it can remix the stuff

The Kitten Effect

By Janelle Shane On July 15, 2022 - 3 min read

One thing I've noticed with image-generating algorithms is that the more of something they have to put in an image, the worse it is. I first noticed this with the kitten-generating variant of StyleGAN, which often does okay on one cat: alternative for shocked_pikachu.pngbut is terrible

Teacups with mostly nonsensical messages written in, or sometimes on, the leaves.

Reading tea leaves

By Janelle Shane On July 01, 2022 - 5 min read

DALL-E (and other text-to-image generators) will often add text to their images even when you don't ask for any. Ask for a picture of a Halifax Pier [https://www.aiweirdness.com/the-terror-of-the-sea/] and it could end up covered in messy writing, variously legible versions of "Halifax"

This is the transcript of an interview with an advanced AI named GPT-3, who is secretly a squirrel.

Interview with a squirrel

By Janelle Shane On June 16, 2022 - 5 min read

Google's large language model, LaMDA, has recently been making headlines after a Google engineer (now on administrative leave), claimed to be swayed by an interview in which GPT-3 described the experience of being conscious. Almost everyone else who has used these large text-generating AIs, myself included, is entirely

AI versus corporate logos

By Janelle Shane On June 03, 2022 - 3 min read

I recently started playing with DALL-E 2, which will attempt to generate an image to go with whatever text prompt you give it. Like its predecessor DALL-E, it uses CLIP, which OpenAI trained on a huge collection of internet images and nearby text. I've experimented with a few

New AI-generated horsies

The Kitten Effect

Reading tea leaves

Interview with a squirrel

AI versus corporate logos

Writing

Subscribe

Recent Posts

ChatGPT will apologize for anything

Revised instructions for troubleshooting the warp confabulator

Minecraft with object impermanence

Bonus: In Which The Adventurer Attempts to Build a Website

Botober 2024

Bonus: "Ignore all previous instructions" gets weirder

Follow

ChatGPT will apologize for anything

Revised instructions for troubleshooting the warp confabulator

Minecraft with object impermanence