Nothing to see here, just a rationalist reinventing a well known 2000yo memory technique from first principles.

His first image looks like cell from dragon ball z. The plagiarism machine at work.

People have been doing this 'this thing drawn as an anime (girl)' thing for ages now btw, but the bonus of doing it by hand is a unified style which is part of the appeal, a thing missing here.

Funny that this whole article is just another distraction of the hard work of actually learning the things he wants to learn.

And looking at the upvotes, nobody there wants to learn these things they just want to look at anime. Get a different hobby folks.

Horny slop text fed into a second machine to make horny slop pictures. Surely this will solve the problem of learning molecular biology.

What stuck with me was Anima. My goodness, how variable it is, and how much it changes the linework and composition just based on which artist names you add to the prompt. Beautiful. Does it generate an extra finger here and there? Perhaps. Does it mess up character color or prop shape? Yes, it happens. But it's a fair price for just how much effortless variability you get on a style level with a single pipeline. All of the gene images you see in this post were produced by a local anima-preview on my laptop without any style prompt changes except for the artist names.

The images: interchangeable, forgettable. All of them so crammed full of shit that every ostensibly noteworthy particular is drowned out.

someone hopped on the NFT train a few years too late