causal

GANs Hide Hands Due To Adversarial Loss

GAN and diffusion models think differently because of their loss functions: GANs face an adversarial loss giving them an incentive to hide difficult things, so they are 'scared' and put hands off-screen and can't think about them, whereas diffusion models have no such incentive and do attempt hands, producing monstrous Cthulhu-esque distortions instead.

causalpending

Speaker

Gwern

Evidence Quote

“GAN models have incentives to hide things because it's an adversarial loss”

Source

Gwern — Anonymous writer who predicted AI trajectory on $12K/year salary— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:28:51 AM

Your notes

Loading notes...