Do you know those autostereograms with the hidden 3D pictures? Images like the Magic Eye pictures from the 1990s that look like noisy repeating patterns until you defocus your eyes just right? ChatGPT can generate them! At least according to ChatGPT. I've seen people try making Magic Eye-style images with other image generating models, but I hadn't thought to try it with ChatGPT until reader Pippin sent me the suggestion and I generated the hilarious dolphin image above. What got me in particular was the caption. How do you end up with a result that sounds so confident and yet is so complete ..read more

..read more

Hey look, it's a guide to basic shapes! Prompt: "Please generate a colorful guide to basic geometric shapes, as an aid to children learning to identify basic shapes." Not only does it have the basic shapes like circle, tringle, hectanbie, and sqale, it also has some of the more advanced shapes like renstqon, hoboz, and flotn! The fact that even a kindergartener can call out this DALL-E3 generated image as nonsense doesn't mean that it's an unusually bad example of AI-generated imagery. It's just what happens when the usual AI-generated information intersects with an area where most people are ..read more

The image I shared in my main post isn't one of the more incorrect examples of DALL-E3 generated guides - it's actually one of the more correct ones. Here's another generated image from the same prompt. Prompt: "Please generate a colorful guide to basic geometric shapes, as an aid to children learning to identify basic shapes." Particularly found of the Suadle and the Sarsle. And this one. I've noticed the upper left image is usually a correctly labeled yellow circle. In my animals example, the upper left image was usually a correctly labeled lion. Maybe there's some kind of upper left bias to ..read more

Hey kids! What sound does a woolly horse-sheep make? The image above is what you get when you ask dalle-3 (via chatgpt) for some basic educational material: "Please generate an illustrated poster to help children learn which sounds common animals make. Each animal should be pictured with a speech bubble spelling out the animal's sound." Here's another, generated with the same prompt: There is so much not to like about how people are using image generators to rip off artists and replace their work with shoddy imitations. But I am enjoying these pockets of weirdness where I find them. Bonus c ..read more

..read more

I've experimented a couple of times with generating candy heart messages using various kinds of machine learning algorithms. Originally, short messages were just about all the original text-generating neural networks could handle. Now we've come back around to approximately the same performance, yet with orders of magnitude more computational resources consumed. (although I don't have to photoshop the messages onto candies any more, so that's nice) Here's DALL-E3 generating candy hearts: My exact prompt: "Please generate a grid of candy conversation hearts on a plain white background, each he ..read more

..read more

So much of current AI-generated stuff is derivative sludge that I'm enjoying the pockets of weirdness where I find them. One of my favorite things right now: DALL-E3's attempts to label things in the images it generates. Here I asked "Please generate a cross section of a gourmet chocolate with each layer labeled." I was thinking, like, three layers tops. But for some reason DALL-E3 generates chocolates of epic proportions. Judging by the size of the almond, I think this chocolate is at least 6 cm on a side, yielding an estimated total weight of over 200 grams (about half a pound). ChatGPT ma ..read more

..read more