It’s true. StackOverflow is basically obsolete. My coding workflow has changed completely. ChatGPT even implemented several novel body parts to improve the functionality of the Baby class (!!!)
Learning a lot about the long, untold history of the “no-no button” - even Darwin was fascinated by it.
I've tried to simplify this in interviews (& I suck at math): The deep learning process organizes all faces along a main face-axis in multidimensional space. If you follow this vector to its end you find Loab: the last face; an eigenface that one type of face-ness extends toward.
Probably, all the different face-nesses are represented on different axes and the Loab axis is just one of many. All faces are found in relationship to these axes. Collapse the idea to an x,y plane: imagine a simple system of 2 face-ness axes, where one is a Loabness axis.
The map of possible faces is finite though, so it has a geometry with edges and vertices and outward protrusions. A negative weighted prompt makes you likely to get caught inside one of these extremities with the spooky eigenfaces and the very few non-face things that are nearby.
A brief typology of AI feet.
These are created with the simple prompt "feet" in Midjourney.
Foot type 1: Non-terminal toes. Toes extend from the foot and fuse to each other, or loop back into the foot. A foot is a bundle of toes fused together into a thick main trunk.
Foot type 2: Prehensile heels. Heels are elongated, similar to high-heeled shoes or lotus foot binding. They act as the "thumb" of the foot. They grow vestigial toes of their own.
Foot type 3: The Foot-in-itself. These represent the transcendental ideal of a foot, liberated from its real-world context as a human appendage. They are generally oriented towards the heavens, like monumental pillars of glory.
🧵: I discovered this woman, who I call Loab, in April. The AI reproduced her more easily than most celebrities. Her presence is persistent, and she haunts every image she touches. CW: Take a seat. This is a true horror story, and veers sharply macabre.
I'll explain negative prompt weights, in case you don't know. With these, instead of creating an image of the text prompt, the AI tries to make the image look as different from the prompt as possible. This logo was the result of the negatively weighted prompt "Brando::-1".
I wondered: is the opposite of that logo, in turn, going to be a picture of Marlon Brando? I typed "DIGITA PNTICS skyline logo::-1" as a prompt. I received these off-putting images, all of the same devastated-looking older woman with defined triangles of rosacea(?) on her cheeks.