[jltsiren]

I think this is an interface problem. Given a generic prompt, the AI draws a generic image, like a beginner would. Things you don't specify explicitly default to generic options.

A more sensible response would perhaps invent additional requirements to get more interesting and more varied outcomes. The right amount of variance depends on the context, but it's rarely as low as the current interfaces default to.

[TheOtherHobbes]

I've wrestled with StableDiffusion and it's very, very biased.

I wanted a photo of an average-looking older woman and it was unbelievably hard to get it to produce that. And even after some very detailed, emphatic prompts the results still weren't as good as generic stock photo - never mind someone you might see in the real world.

SD believes most women are in their 20s and have big boobs. It's comically obvious if you try to get any fantasy art out of it and you want something that isn't big-boobed porn.

It's a content problem, not a prompt problem. It's been modified since to make it less porn-y but it's still a very long way from supporting straightforward prompt access to the face and body space most humans live in.

So it's a fair criticism to say it's stereotyping. Most of what comes out of it is a white middle class male's idea of what [thing] looks like.

This is inevitable with small training sets. AI is basically data compression. But the lack of awareness that the output comes from a lumpy dumbed down version of the training space is worrying.

It's textbook worse-is-better - narrowing experience and possibility towards flawed mediocrity, with the firm implication no one should have higher expectations. Because that's as good as it gets, and it's fine.

[onos]

> Most of what comes out of it is a white middle class male's idea of what [thing] looks like.

ITT people complaining about stereotypes while stereotyping.

[rowanG077]

Why do you think it's reproducing what "white middle class male's idea of what [thing] looks like."? This seems an incredible leap. And incredibly racist and sexist.

[Kuinox]

> SD believes most women are in their 20s and have big boobs

You means the community-made checkpoint.

[KittenInABox]

I actually heavily disagree with this. Most AI has one specific depiction of a thing and really struggles to get away from that specificity, which honestly is something I consider to be a fundamental failing of ML modeling currently.

For example: trying to get chatgpt to write about psychotic post-partum symptoms, getting stable diffusion to produce a realistic looking woman above the age of 50, or writing an immigration narrative that isn't "home country bad, new country better".

[ben_w]

> "home country bad, new country better".

I think the deeper problem is that it only writes happy endings.

A while back someone pointed out that Dracula, Sherlock Holmes, and Winnie the Pooh had all become public domain characters on the same day, so I tried asking it for a story that combined them — it read like I expected it to (a terrible premise written with middling skill), but it also insisted on wrapping everything up with a twee "and then all three of them went on more jolly adventures" kind of ending.

Likewise the time I asked it for one about alien invaders, where it wrote them turning (without good reason) from villains into friends at the end.

[simonw]

I've found that problem is pretty easy to counter with a bit of extra prompting.

"Give it a surprising, dark ending" or "add a twist".

The majority of stories people tell have happy endings, so it's not surprising that it defaults to those twee resolutions.