It's the opposite: the average person likes the AI look of images (the more "aesthetic" look) and RLHF keep converging toward that.

It is entirely possible to prompt engineer away from that style, but that requires effort and knowledge that said average person does not have, so it's stuck in a feedback loop.

I still can’t believe the amount of deepfakes and slop I see just everywhere including food menus and people don’t even seem to notice.

This kind of content is here to stay and we’re going to see more and more of it. Unfortunately…

> people don’t even seem to notice.

I've been seeing "AI slop" stickers posted on things

> I see just everywhere including food menus

The places I have seen it in use, are the places that would have a handwritten scribble that was misspelt and would be something mocked by people because it was written by ESOL (or vice versa, English speakers trying, but failing, to write in a different language)

Honestly, I think the AI slop is a step up - I can read the signs clearly, and they are only mildly offensive

People definitely seem to notice.

I see restaurants post AI flyers and ads to random local Facebook groups and most of the replies are about them being AI slop. I think it’s an uncanny valley problem: People don’t mind if you post a real photo of your food or a cartoon drawing of a pizza or a pig on a spit, but when it’s a weird fake photo with texture issues, it looks gross, especially when it’s food.

I think a lot of people who open restaurants probably aren’t extremely online, partly because it would be physically impossible with the amount of work they have to do, but they definitely pay attention -sometimes too much attention — to public online feedback.

I get why restaurants use the cartoon-looking slop. If you don't particularly care that it signals that you put no effort into your menu or ad or that your restaurant's menu has the same shitty aesthetic as all other slop, fine. It's a cartoon and I could understand someone thinking it looks ok.

I absolutely do not get the uncanny-valley images. Those all look gross. Besides not actually being representative of the dish, the images have all sorts of weird texture issues, look too glossy, and are just unappetizing. I cannot why a restaurant owner would want to put up an ad that has food that looks straight up gross.

Professional food photography is expensive. This is a case of the free mediocre offer crowding out the much better but expensive option. Same way that free mail with ads crowded out email without ads.

The thing with those "AI Slop" comments are generally from people whom are opinionated about the image. However it's abundantly clear that the target demographic which is the customers generally don't mind. If you think about it, We have been conditioned by the "for illustrative purposes only" label on most food images that at this point most people just want a reference so they can decide what to eat. I'd take an AI image over just words any day.

The saddest words of tongue or pen: “you’re not the target demographic”

Isn't this the sum of dating apps?

No, you are confusing a model with reality.

This is not true. Think of the problems AI has with creating appetizing food imagery, for example. Images that every human annotator marks as unappealing with a high degree of consensus.

The problem is in the rewards, but it's more how they average across domains and contexts, so AI misapplies them. Actually, in human preference evaluations, most of Gen Z in particular extremely adverse to the common look of AI images.

So it's not the annotators involved in RLHF, it's the models failing to map to human preferences at the task level. The failure rate is also uneven across domains.

Where there are challenges with human annotation, it's not the ability to gauge what's good but rather how to correct what's wrong. Most people can tell when something is off but struggle to articulate why. That's where more domain expertise is required.

> Think of the problems AI has with creating appetizing food imagery, for example.

The memetic ugly food can be controlled and mostly filtered out with prompt engineering. Here's a quick ad hoc test example which (hopefully) uses the new model: https://chatgpt.com/share/6aebf030-9d38-83e8-a103-3509883905...

First image is fine, but attempts to make it more wacky turn it to the AI food slop. So then followup prompts deslopify it, mostly successfully.

tbh it got worse every time, the first one is the best lol

Eh, looks like slop still in my opinion. The evenness and density of the teeth especially stands out to me as uncanny.

>This is not true. Think of the problems AI has with creating appetizing food imagery, for example. Images that every human annotator marks as unappealing with a high degree of consensus.

I think the way they'll solve it in the end is to create an ultra-high-fidelity simulation of the world including modelling taste and other senses on the level of physics, and then incorporate all of this into the training rewards.

I think this is how the machines know what tasty wheat tasted like.

I think this is fundamental. People will probably dislike whatever it is that AI images look like, because whatever they look like is going to be associated with cheap. They could have a totally different aesthetic and I think most people's conception of cheap would adapt to whatever that is.

Very true. My theory is that if AI was able to produce a diverse enough range of styles (not artistic style, more like "artist's touch/bias"), then it would be much better. Exactly like Claude, talking to it wouldn't be so grating if it had, say, a 1000 different "writing styles" instead of the single one we have to engage with.

The current models have a fundamental architectural flaw: Every pixel they output costs the model as much effort as every other one. When you see detail in a work a human produced, the fact that there is detail communicates something about what the artist was focussing on. It shows you what they cared about, and by extension what you, the viewer, should care about to understand the piece. The AI, as currently designed, can’t do that, because it’s outputting entire raster images at once (and multi-pass generations tend to degrade into melty nonsense), it emphasises everything, and so emphasises nothing.

The “AI look” is a manifestation of the architecture itself, and that’s why you can really train or prompt around it. At best, bigger models have been able to partially suppress the worst aspects of it by throwing more parameters at the problem, but put the models under even a tiny bit of stress and the same flaws reemerge.

for the same reason they can't train llmisms out of text.

Some of it has to do with Classifier Free Guidance (CFG), a math thing that makes it more likely for a diffusion model to follow what you ask for in the prompt. However, turning up CFG inevitably causes high contrast and certain other artifacts.

With that being said, my understanding of that issue is a few years old, people have always said CFG is a havk until models get better at following prompts on their own. So thee “look” that tools like Nano Banana ends up with could be something else. It may or may not be a necessary artifact of some part of the process.

The problem isn't the classifier free guidance itself, but the choice of parameters. When a parameter above 1 is chosen you get images which very stronger conform to theme, but which there's not a good mathematical justification for.

Yeah, it must be some algorithmic thing like CFG, or some other technique, that causes the unrealistic AI look. Because Dall-E 2 didn't have it, but Dall-E 3 did to an extreme degree. Google's Imagen <= 3 also didn't have it, but Imagen 4 (and Nano Banana, which seems to use Imagen 4 in the background) suddenly had significant AI look, apart from much better prompt following and fewer visual mistakes (like too many fingers).

Yeah. I just read a bit about it and looked at some examples, and it seems CFG>1 is a hack to get sharper images from a given model, at the cost of giving them the "AI look". As models get better, we'll be able to use CFG=1 and much of the problem will go away.

You are actually a very skilled pattern recognizing machine. There's likely always going to be some bias and purple are going to be able to detect it and the human style will move away from it.