News for hackers. Stuff that matters.
Re:Imagen, a text-to-image diffusion model by Imnimo on Monday May 23, 2022 @06:15PM (#31485503)
>If some particular demographic shows up in 51% of the data but 100% of the model's output shows that one demographic, that does seem like a statistics problem that the model could correct by just picking less likely "next token" predictions.

Yeah, but you get that same effect on every axis, not just the one you're trying to correct. You might get male nurses, but they have green hair and six fingers, because you're sampling from the tail on all axes.

Re:Imagen, a text-to-image diffusion model by tines on Monday May 23, 2022 @06:19PM (#31485548)
Yeah, good point, it's not as simple as I thought.