[zaptheimpaler]

At first I thought this is a real problem, but the more I think about it, the more it's one of those "I asked an AI how to be evil and it told me!!!!" situations.

The AI has to return something when given a vague prompt like that, and it is also specifically tuned to try to return similar things for the same prompt. It would be much less useful if it wasn't consistent because you wouldn't be able to gradually tune a prompt to get the image you want.

So then their ask reduces to make the AI return a specifically not-stereotypical image of the race even though all that's specified in the prompt is the race. That could be done but doesn't seem much better.

Maybe we should just expose the temperature control on these models and rename it to "diversity"..

[hn_acker]

> So then their ask reduces to make the AI return a specifically not-stereotypical image of the race even though all that's specified in the prompt is the race. That could be done but doesn't seem much better.

I'm guessing that what the researchers were hoping to see was less "a specifically not-stereotypical image of the race" and more like "across many generated images, some people showing stereotypes, some people showing other stereotypes, some people showing none of those stereotypes (but possibly though not necessarily yet other stereotypes)". Diversity isn't in "one image of one person" but can be in "multiple images of one person each", and I think that the researchers are aware of that.

[zaptheimpaler]

I addressed that in my comment. Having a relatively stable output for the same input is a core requirement of the models atleast with the default settings.