Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Imagen, a text-to-image diffusion model

gweb-research-imagen.appspot.com

Post reply on HN
Print view View original

281–290 of 661 posts

Re: Imagen, a text-to-image diffusion model

#281

Post by paisawalla »

colinmhayes wrote: post #140
curiousgal wrote: post #64

Earlier quoted context omitted.

> it will be used in ways we haven’t anticipated Oh yeah, as a woman who grew up in a Third World country, how an AI model generates images would have deeply affected my daily struggles! /s It's kinda insulting that they think that this would be insulting. Like "Oh no I asked the model to draw a doctor and it drew a male doctor, I guess there's no point in me pursuing medical studies" ...

Yes actually, subconscious bias due to historical prejudice does have a large effect on society. Obviously there are things with much larger effects, that doesn't mean that this doesn't exist. > Oh no I asked the model to draw a doctor and it drew a male doctor, I guess there's no point in me pursuing medical studies If you don't think this is a real thing that happens to children you're not thinking especially hard.…

> subconscious bias due to historical prejudice does have a large effect on society.

The quality of the evidence for this, as with almost all social science and much of psychology, is extremely low bordering on just certified opinions. I would love to understand why you think otherwise.

> Obviously there are things with much larger effects, that doesn't mean that this doesn't exist.

What a hedge. How should we estimate the size of this effect, so that we can accurately measure whether/when the self-appointed hall monitors are doing more harm than good?

Re: Imagen, a text-to-image diffusion model

#282

Post by layer8 »

mdp2021 wrote: post #242
layer8 wrote: post #237

Earlier quoted context omitted.

Humans overwhelmingly learn meaning by use, not by definition.

> Humans overwhelmingly learn meaning by use, not by definition Preliminarily and provisionally. Then, they start discussing their concepts - it is the very definition of Intelligence.

Most humans don’t do that for most things they have a notion of in their head. It would be much too time consuming to start discussing the meaning of even just a significant fraction of them. For a rough reference point, the English language has over 150.000 words that you could each discuss the meaning of and try to come up with a definition. Not to speak of the difficulties to make that set of definitions noncircular.

Re: Imagen, a text-to-image diffusion model

#283

Post by dougmwne »

sydthrowaway wrote: post #9
james-redwood wrote: post #6

Metacalculus, a mass forecasting site, has steadily brought forward the prediction date for a weakly general AI. Jaw-dropping advances like this, only increase my confidence in this prediction. "The future is now, old man." https://www.metaculus.com/questions/3479/date-weakly-general...

How can we prepare for this? This will result in mass social unrest.

I think the serious answer is that it is yet another labor multiplier like electricity and software. Our tech since the industrial revolution has allowed us to elevate ourselves from a largely agrarian society to space and cyberspace. AI, by all appearances, continues to be a tool, just the latest in a long line of better tools. It still requires a human to provide intent and direction. Right now in my job, I command the collect output of a million medieval scribes. In the future I will command a million Michelangelos.

Should ML/AI deliver on the wildest promises, it will be like a SpaceX Starship for the mind.

Re: Imagen, a text-to-image diffusion model

#284

Post by ALittleLight »

Interesting to me that this one can draw legible text. DALLE models seem to generate weird glyphs that only look like text. The examples they show here have perfectly legible characters and correct spelling. The difference between this and DALLE makes me suspicious / curious. I wish I could play with this model.

Re: Imagen, a text-to-image diffusion model

#285

Post by magicalist »

tines wrote: post #231
slg wrote: post #193

Earlier quoted context omitted.

This type of bias sounds a lot easier to explain away as a non-issue when we are using "nurse" as the hypothetical prompt. What if the prompt is "criminal", "rapist", or some other negative? Would that change your thought process or would you be okay with the system always returning a person of the same race and gender that statistics indicate is the most likely? Do you see how that could be a problem?

Not the person you responded to, but I do see how someone could be hurt by that, and I want to avoid hurting people. But is this the level at which we should do it? Could skewing search results, i.e. hiding the bias of the real world, give us the impression that everything is fine and we don't need to do anything to actually help people? I have a feeling that we need to be real with ourselves and solve problems and n…

> Could skewing search results, i.e. hiding the bias of the real world

Which real world? The population you sample from is going to make a big difference. Do you expect it to reflect your day to day life in your own city? Own country? The entire world? Results will vary significantly.

Re: Imagen, a text-to-image diffusion model

#286

Post by rvnx »

daenz wrote: post #213
nomel wrote: post #157

Earlier quoted context omitted.

How do you pick what should and shouldn't be restricted? Is there some "offense threshold"? I suspect all queries relating to religion, ethnicity, sexuality, and gender will need to be restricted, which almost certainly means you probably can't include humans at all, other than ones artificially inserted with mathematically proven random attributes. Maybe that's why none are in this demo.

"Is Taiwan a country" also comes to mind.

What would a human who can freely speak without morale or being judged say on average after having ingested all the information on the internet ?

Re: Imagen, a text-to-image diffusion model

#287

Post by astrange »

codethief wrote: post #197
tines wrote: post #150

Earlier quoted context omitted.

Not really; the gender of a nurse is accidental, other properties are essential.

While not essential, I wouldn't exactly call the gender "accidental": > We investigated sex differences in 473,260 adolescents’ aspirations to work in things-oriented (e.g., mechanic), people-oriented (e.g., nurse), and STEM (e.g., mathematician) careers across 80 countries and economic regions using the 2018 Programme for International Student Assessment (PISA). We analyzed student career aspirations in combination…

If you ask it to generate “nurse” surely the problem isn’t that it’s going to just generate women, it’s that it’s going to give you women in those Halloween sexy nurse costumes.

If it did, would you believe that’s a real representative nurse because an image model gave it to you?

Re: Imagen, a text-to-image diffusion model

#288

Post by sangnoir »

bufbupa wrote: post #158
karpierz wrote: post #61

Earlier quoted context omitted.

It depends on whether you'd like the model to learn casual or correlative relationships. If you want the model to understand what a "nurse" actually is, then it shouldn't be associated with female. If you want the model to understand how the word "nurse" is usually used, without regard for what a "nurse" actually is, then associating it with female is fine. The issue with a correlative model is that it can easily be…

At the end of a day, if you ask for a nurse, should the model output a male or female by default? If the input text lacks context/nuance, then the model must have some bias to infer the user's intent. This holds true for any image it generates; not just the politically sensitive ones. For example, if I ask for a picture of a person, and don't get one with pink hair, is that a shortcoming of the model? I'd say that bi…

> At the end of a day, if you ask for a nurse, should the model output a male or female by default?

This depends on the application. As an example, it would be a problem if it's used as a CV-screening app that's implicitly down-ranking male-applicants to nurse positions, resulting in fewer interviews for them.

Re: Imagen, a text-to-image diffusion model

#289

Post by Shaanie »

joshcryer wrote: post #165
young_unixer wrote: post #124

Earlier quoted context omitted.

The very act of mentioning "western gender stereotypes" starts from a biased position. Why couldn't they be "northern gender stereotypes"? Is the world best explained as a division of west/east instead of north/south? The northern hemisphere has much more population than the south, and almost all rich countries are in the northern hemisphere. And precisely it's these rich countries pushing the concept of gender stere…

The bulk of the trained data is from western technology, images, books, television, movies, photography, media. That's where the very real and recognized biases come from. They're the result of a gap in data nothing more. Look at how DALL-E 2 produces little bears rather than bear sized bears. Because its data doesn't have a lot of context for how large bears are. So you wind up having to say "very large bear" to DAL…

That's true for some things, but the "gender bias for some professions" is likely to just be reflecting reality.

Re: Imagen, a text-to-image diffusion model

#290

Post by sangnoir »

magicalist wrote: post #285
tines wrote: post #231

Earlier quoted context omitted.

Not the person you responded to, but I do see how someone could be hurt by that, and I want to avoid hurting people. But is this the level at which we should do it? Could skewing search results, i.e. hiding the bias of the real world, give us the impression that everything is fine and we don't need to do anything to actually help people? I have a feeling that we need to be real with ourselves and solve problems and n…

> Could skewing search results, i.e. hiding the bias of the real world Which real world? The population you sample from is going to make a big difference. Do you expect it to reflect your day to day life in your own city? Own country? The entire world? Results will vary significantly.

For AI, "real world" is likely "the world, as seen by Silicon Valley."
Post reply on HN