Slate Star Scratchpad — slatestarscratchpad: The AI projects I’ve found...

slatestarscratchpad
slatestarscratchpad

The AI projects I’ve found most interesting are GPT-2 (generates text from a prompt) and StyleGAN (can redraw one picture in the style of another picture).

GPT-2’s medium is text, and its purpose is generation. StyleGAN’s medium is images, and its purpose is style change. Is there any necessary reason why each medium is matched to its respective purpose?

Could you have an image generator - a model trained on every image on the Internet - and if you give it most of an image with one part missing, it can fill in the missing part?  I mean, obviously you can, this is how your eye fills in the blind spot, but could AI scientists make it today? What about something where if you give it half an image, it can generate the rest of it? A body, given a head? A tree, given a trunk? If not, why not?

And could you have a text style changer? Something that can rewrite Harry Potter in the voice of Ernest Hemingway, or give you The Da Vinci Code in the heroic meter of the Iliad, or the Dao De Ching as writen by @nostalgebraist? If not, why not?

slatestarscratchpad

Thanks to everyone who wrote very thoughtful replies here, but the real answer to the first question turned out to be “wait two weeks and OpenAI will release exactly this”.