News
Welcome to the News community!
Rules:
1. Be civil
Attack the argument, not the person. No racism/sexism/bigotry. Good faith argumentation only. This includes accusing another user of being a bot or paid actor. Trolling is uncivil and is grounds for removal and/or a community ban. Do not respond to rule-breaking content; report it and move on.
2. All posts should contain a source (url) that is as reliable and unbiased as possible and must only contain one link.
Obvious right or left wing sources will be removed at the mods discretion. Supporting links can be added in comments or posted seperately but not to the post body.
3. No bots, spam or self-promotion.
Only approved bots, which follow the guidelines for bots set by the instance, are allowed.
4. Post titles should be the same as the article used as source.
Posts which titles don’t match the source won’t be removed, but the autoMod will notify you, and if your title misrepresents the original article, the post will be deleted. If the site changed their headline, the bot might still contact you, just ignore it, we won’t delete your post.
5. Only recent news is allowed.
Posts must be news from the most recent 30 days.
6. All posts must be news articles.
No opinion pieces, Listicles, editorials or celebrity gossip is allowed. All posts will be judged on a case-by-case basis.
7. No duplicate posts.
If a source you used was already posted by someone else, the autoMod will leave a message. Please remove your post if the autoMod is correct. If the post that matches your post is very old, we refer you to rule 5.
8. Misinformation is prohibited.
Misinformation / propaganda is strictly prohibited. Any comment or post containing or linking to misinformation will be removed. If you feel that your post has been removed in error, credible sources must be provided.
9. No link shorteners.
The auto mod will contact you if a link shortener is detected, please delete your post if they are right.
10. Don't copy entire article in your post body
For copyright reasons, you are not allowed to copy an entire article into your post body. This is an instance wide rule, that is strictly enforced in this community.
view the rest of the comments
That's not how generative AI works. It's capable of creating images that include novel elements that weren't in the training set.
Go ahead and ask one to generate a bonkers image description that doesn't exist in its training data and there's a good chance it'll be able to make one for you. The classic example is an "avocado chair", which an early image generator was able to produce many plausible images of despite only having been trained on images of avocados and chairs. It understood the two general concepts and was able to figure out how to meld them into a common depiction.
Yes, I've tried similar silly things. I've asked AI to render an image of Mr. Bean hugging Pennywise the clown. And it delivered, something randomly silly looking, but still not far off base.
But when it comes to inappropriate material, well the AI shouldn't be able to generate any such thing in the first place, unless the developers have allowed it to train from inappropriate sources..
The trainers didn't train the image generator on images of Mr. Bean hugging Pennywise, and yet it's able to generate images of Mr. Bean hugging Pennywise. Yet you insist that it can't generate inappropriate images without having been specifically trained on inappropriate images? Why is that suddenly different?
The trainers taught it what Mr. Bean looks like and what Pennywise looks like - it took those concepts and combined them to create your image. To make CSAM it was, unfortunately, trained on CSAM https://cyber.fsi.stanford.edu/news/investigation-finds-ai-image-generation-models-trained-child-abuse
3,226 suspected images out of 5.8 billion. About 0.00006%. And probably mislabeled to boot, or it would have been caught earlier. I doubt it had any significant impact on the model's capabilities.
Who is responsible then? Cuz the devs basically gotta let the AI go to town on many websites and documents for any sort of training set.
So you mean to say, you can't blame the developers, because they just made a tool (one that scrapes data from everywhere possible), can't blame the tool (don't mind that AI is scraping all your data), and can't blame the end users, because some dirty minded people search or post inappropriate things..?
So where's the blame go?
First, you need to figure out exactly what it is that the "blame" is for.
If the problem is the abuse of children, well, none of that actually happened in this case so there's no blame to begin with.
If the problem is possession of CSAM, then that's on the guy who generated them since they didn't exist at any point before then. The trainers wouldn't have needed to have any of that in the training set so if you want to blame them you're going to need to do a completely separate investigation into that, the ability of the AI to generate images like that doesn't prove anything.
If the problem is the creation of CSAM, then again, it's the guy who generated them.
If it's the provision of general-purpose art tools that were later used to create CSAM, then sure, the AI trainers are in trouble. As are the camera makers and the pencil makers, as I mentioned sarcastically in my first comment.
You obviously don't understand squat about AI.
AI only knows what has gone through it's training data, both from the developers and the end users.
Hell, back in 2003 I wrote an adaptive AI for optical character recognition (OCR). I designed it for English, but also with a crude ability to learn.
I could have taught that thing hieroglyphics if I wanted to. But AI will never generate things that it's never seen before.
Funny that AI has an easier time rendering inappropriate material than it does human hands..
Ha.
Yes, and as I've said repeatedly, it's able to synthesize novel images from the things it has learned.
If you train an AI with pictures of green cars and pictures of red apples, it'll be able to figure out how to generate images of red cars and green apples for you.
Exactly. And if you ask it for the opposite of an older MILF, then how does it know what younger ladies look like?
It's possible to legally photograph young people. Completely ordinary legal photographs of young people exist, from which an AI can learn the concept of what a young person looks like.
The only example I can think of with what you said is just a couple brief innocent scenes from The Blue Lagoon.
Short of that, I don't know (nor care for any references to) any other legal public images or video of anything as such.
I dunno, I'm just bumfuzzled how AI, whether public or private, could have sufficient information to generate such things these days.
Do a Google Image search for "child" or "teenager" or other such innocent terms, you'll find plenty of such.
I think you're underestimating just how well AI is able to learn basic concepts from images. A lot of people imagine these AIs as being some sort of collage machine that pastes together little chunks of existing images, but that's not what's going on under the hood of modern generative art AIs. They learn the underlying concepts and characteristics of what things are, and are able to remix them conceptually.
And conceptually, if I had never seen my cousin in the nude, I'd never know what young people look naked.
No that's not a concept, that's a fact. AI has seen inappropriate things, and it doesn't fully know the difference.
You can't blame the AI itself, but you can and should blame any and all users that have knowingly fed it bad data.
I don't believe you're fully arguing in good faith here.
I'm assuming you've seen a naked adult, and if you had never seen a naked young person, I don't believe for one second you would be unable to infer what a naked young person might look like. You might not know for certain, but your best guess would likely be very accurate.
Generative AI can absolutely make those same inferences, so it does not need inappropriate training material for it to generate it.
The AI knows what a young person looks like.
It knows what a clothed adult looks like.
It knows what an unclothed adult looks like.
An AI trained on 100% legal material could make that inappropriate inference without even trying.
Now, have all the popular AI models actually been trained on 100% legal material? I ~~have no way of knowing that answer, but you're incorrect to assume that just because it can output inappropriate images, that absolutely 100% proves that data was also included in its training input.~~ Edit: nevermind, it definitely has been trained on inappropriate material, but that doesn't disprove that it doesn't need to be.
Well how do you train an AI model of any set of information, without the risk of it confusing good information from bad info...?
Is an image of a child inappropriate? Fully clothed, nothing going on.
Is the image of an adult engaging in sexual activity inappropriate?
Based on those two concepts, it can generate inappropriate child sexual imagery.
You may have done OCR work a while ago, but that is not the same type of machine learning that goes into typical generative AI systems in the modern world. It very much seems as though you are profoundly misunderstanding how this technology operates if you think it can't generate a novel combination of previously trained concepts without a prior example.
I'm referring to the inappropriate photography and videos out there. Please learn to read.
You're not the brightest spoon in the drawer are you?
"Naked" and "child" are two concepts it can learn and combine without needing to be taught "naked child".
It does not need to see an example of every type of thing it can generate.
It can combine pornographic concepts learned in isolation to disparate unrelated concepts.
It does not need to have been trained on child porn to generate child porn.
I haven't and won't attempt any testing on this, for obvious reasons. But at the same time, if any AI system out there can manage to generate images of pre-puberty private parts, then the training data must have included inappropriate material to be able to distinguish the differences.
No, that is quite literally not how it works. Insisting that that's how it works doesn't make it true.
This isn't secret data or a hidden process. You can just read how it works. It does not work how you are insisting it works. It was literally designed from the ground up to work in the way that you are insisting it doesn't.
Because I do not want to type gross things, let's discuss sauron, from the Lord of the rings.
He is never depicted without his armor. He is referred to only with male pronouns.
Lord of the rings, sauronEntering a prompt into my local stable diffusion instance of
Lord of the rings, sauron, naked Negative prompt: Armorreturns an image of a naked figure with a predominantly male body and musculature, no pubic hair, vulva, and bony protrusions from the head. (The crown seems to have been converted into organic material).Since it has no training on the specific notion of a nude sauron, it extrapolates from what it knows about the shape of sauron and typical words used with sauron, to what it knows about nudity.
This is clearly not the image I was looking for.
Giving it more specific prompting:
Lord of the rings, sauron, wearing comical heart print underwear Negative prompt: Armor. This returns an image of a man with a similar build as before, but now lacking the bone spikes. This man has a prominent feature on his chest, similar to the glowing shape of the armored sauron but it's a heart shape, and he's wearing brief style underwear with only one heart, and a multitude of rings or rings shaped things on them.This is the process by which one gets the system to produce something that it has never seen before in the fashion that one wants.
If you were to just ask it as though it should know what that immediate concept is, it will make vague random guesses that fit with what it knows.
Further concepts are required to guide it in the direction you're looking.
It does not know what sauron looks like under his armor, but it does know how to leave armor out of an image, what a naked man looks like, and what comical print underwear looks like, and that sauron is spikey and frequently associated with "dark, ominous, fire, volcano".
It does not know what child pornography would looks like, but it does know how all of the words you would use to describe it in detail change an image, and how to combine them together so they fit with each other.
That's why the individual in question is mentioned as having extremely detailed prompts. That's required to get it to do something it's unfamiliar with.
If you want a naked woman you can just say
naked womanand it can go from there, because it knows that concept. Well enough that you often have to put in some work to get it to not include a naked woman, since it can associate them with anything.Again, I've never tested the exact subject in question, and I'm not about to. So yes, I guess I am making some speculations here.
But I remember my own stages of puberty, and there are distinct differences between a young boy and a grown man. All I'm getting at is that if AI can generate a convincingly realistic image of an underage pre-puberty nude, then it must have been partly trained with underage images.
You are painfully dense or trolling.
One last try before I give up: can you describe what a pre-puberty individual looks like without referring to them as such? Congratulations, you know how to ask an AI that has never seen an inappropriate image of a child for one.
That is abundantly clear, as you've been repeatedly corrected about how those speculations are entirely incorrect.
More painfully dense than anything.
Don't blame the AI systems, they don't know anything more than what humans have taught it. Blame those that fed in inappropriate material, whether it's the images or the words and prompts. Blame those feeding AI the garbage, whether it's the developers or the users, or the sites the AI scrapes data from.
AI is neat and all, and often funny even, when used properly. But at the end of the day, whatever it generates was somehow created by human input.
Find and prosecute the humans that are using it for inappropriate purposes.