[pornel]

The author is using special prompts exploiting flaws of the old models, and doesn't like that new models interpret the hacks literally instead.

The new models have prompt adherence precise enough to distinguish what "British Museum" or "auction at Christie's" is from the art itself, instead of blending a bag of words together into a single vector and implicitly copying all of the features of all works containing "museum" or "ArtStation" in their description.

[RHSeeger]

The prompts bothered me a lot, too. I don't do a lot of work with AI, but

> A painting sold at Sotheby's

and

> A painting in the style of something that would be sold at Sotheby's

convey very different meaning (to me).