neural networks - AI Weirdness (Page 3)

Ignore all previous instructions

By Janelle Shane On September 23, 2022 - 4 min read

Users have noticed that the remoteli.io twitter chatbot [https://twitter.com/remoteli_io/with_replies], usually faithful to its cheerful messaging promoting remote work, can be subverted with a carefully worded user prompt. Users were able to get the chatbot to claim responsibility for terrorist attacks, threaten the President,

Botober 2022 neural net generated art prompts: animals! Including Kiwifish, Clam Cat, and Golden forearmadillo

Botober 2022: draw, human, draw!

By Janelle Shane On September 09, 2022 - 8 min read

For a couple [https://www.aiweirdness.com/botober2021/] of [https://www.aiweirdness.com/628160900506025984/] years [https://www.aiweirdness.com/ainktober-a-neural-net-creates-drawing-19-09-26/] now I've been using neural networks to generate daily drawing prompts. With today's text-generating neural networks far too large to finetune on a list of existing

AI explains human quirks

By Janelle Shane On September 02, 2022 - 2 min read

Humans are weird. The question is, do AI training datasets capture the full scope of our weirdness? I decided to see if GPT-3 could successfully predict other human quirks when prompted with a short list of them. Here's what I gave GPT-3 DaVinci to complete: > Human things

AI recreates classic cereals

By Janelle Shane On August 12, 2022 - 2 min read

DALL-E 2 is very good at generating images to match text descriptions but I felt like using DALL-E 2 to mess up some brands. Here's breakfast cereals! "A box of lucky charms cereal on a grocery store shelf""A box of Froot Loops on a

A collection of mostly chipmunks, one acorn, and two lumpy froglike things

How to disappear a platypus

By Janelle Shane On August 04, 2022 - 3 min read

I was testing DALL-E 2 to see if it would be subject to some common incorrect assumptions about the sizes of things. For example if you asked people what size a kiwi bird is, they tend to assume it's a smallish bird, maybe around the size of a

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

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

Three weird donuts including the Violet Beauregarde, The Confusatron, and I heart my gay ex

AI-generated donuts

By Janelle Shane On May 29, 2022 - 3 min read

If you're going to open a late-night donut shop, you're going to need a unique set of over-the-top donuts to set the proper festive atmosphere. But how to keep the ideas coming? I decided to see what donut ideas I could get using OpenAI's

Tag: neural networks

Ignore all previous instructions

Botober 2022: draw, human, draw!

AI explains human quirks

AI recreates classic cereals

How to disappear a platypus

New AI-generated horsies

The Kitten Effect

Interview with a squirrel

AI versus corporate logos

AI-generated donuts

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