The author claims that the AI posters don’t have to be horrible, but fail to see that the dozen variations generated are not distinctive - they might have somewhat different typography or imaginary, but still have the same AI uniformity and smell as the crappy restaurant poster you see on the street. The core issue is not only technical, but also the lack of vision and imagination when creating art or even infographics.
The alternative is WordArt, or just black on white Comic Sans with some bolding and font size variations with bad ClipArt. These small scale events would never hire a professional.
I'm old enough to remember that people also complained about WordArt and Clipart and too many fonts etc.
I see the chatgpt poster style on many small-scale local village events also. But again, what they replace wasn't any better. It's not replacing some beautiful craft that existed before.
> I'm old enough to remember that people also complained about WordArt and Clipart and too many fonts etc.
We basically had two kinds of posters:
- those made by someone skilled/savvy (not necessarily a professional)
- those made by someone without skills/knowledge
The later were awful, in the sense that I would never display them in my home as a reminder of a an event I took part in.
But still, they were nice because you knew someone took the time to create them to promote an event and share the important information about it, and each person was producing their own awful posters.
Now with gen AI we have something filled with trash, everything looks the same, the important information is hard to find...
Sure, the variations offered in the article are a bit better and more opinionated, but they still reek AI conformity and I feel sick looking at them.
Yes. That's the issue: we are looking at the same posters.
It's just that "seeing this poster for the first time, unaware of the workings behind it" is a very different experience from "seeing this poster after you already saw dozens of other AI generated posters that used a similar style and had similar issues, got canny at spotting both the style and the issues in it, and came to associate them with cheap low quality work".
The former impression is "wow that's a good poster". The latter impression is "ew, it's posterslop". The poster, in the meanwhile, remains the same.
AI can often win in art contests - images, short stories, design. But that requires either sharp prompting, or an audience that's not familiar with "AI cliches". The quality is, if removed from the context, fairly good. If embedded in context, it's utter slop. The work is the same. Funny how that works.
Yes, context matters. The greatest painting in the world is just crushed materials smeared on a canvas, it's nothing too special without the context.
A computer (not even an LLM, just something generating random pixels) could randomly generate the exact same pixel pattern as the greatest painting in the world, and it would not be the greatest painting in the world, because context matters.
If you think about whether it is AI, are good at recognising those tells, an thinking about whether it is AI, then its probable you will spot things like that.
Most people are not that good at spotting those tells, and when looking at a poster they will not be thinking about whether its is AI or not. If its not obviously AI they are not going to even think about it.
No, it's like if you bought a box of chocolates, and you couldn't distinguish if they were handmade or factory-made, even after you ate them.
And it took them telling you before you knew.
And then you decided you didn't like the ones made by the factory as much anymore.
If I saw an Images 2.0 flyer in year 2020? In a world where Images 2.0 didn't exist? I'd be impressed. But if I see it now, today? I'm not impressed at all.
It's the same image, produced by the same AI and seen by the same person. So, what's the difference? What changed over time?
Saturation. "I've seen it all before." AI made that specific flyer style plentiful and omnipresent, and that made it "derivative" and "cheap". What used to invoke "cool" and "wow" was turned into a dreary cliche by repetition. Flaws that were easy to overlook when overshadowed by novelty stand out like a sore thumb now that you've seen them before in the same patterns many times over.
The image is the same - it has the same strengths and the same flaws. But your focus is shifted by familiarity.
It's the same mechanism that drives trends and fashion. AI just supercharges it.
Naturally, you can avoid a lot of it by using careful prompting and steering to guide an AI away from the "cliche" style-space. You can get something with both good quality and good identity that way.
But that requires: being aware of the problem, being really good at prompting, and putting in a considerable effort. It's hard to steer a model away from "AI cliches" if you don't have the eye to spot them in the first place.
Most AI-generated content doesn't have that kind of skill and effort applied to it - it simply uses the "model defaults", and gets the "model defaults". For all the good and bad that comes with those.
petetnt · · focus · HN ↗
bonoboTP · · focus · HN ↗
I'm old enough to remember that people also complained about WordArt and Clipart and too many fonts etc.
I see the chatgpt poster style on many small-scale local village events also. But again, what they replace wasn't any better. It's not replacing some beautiful craft that existed before.
wiether · · focus · HN ↗
But still, they were nice because you knew someone took the time to create them to promote an event and share the important information about it, and each person was producing their own awful posters.
Now with gen AI we have something filled with trash, everything looks the same, the important information is hard to find...
Sure, the variations offered in the article are a bit better and more opinionated, but they still reek AI conformity and I feel sick looking at them.
jwr · · focus · HN ↗
I bet you would not feel sick if you didn't know ahead of time they were AI-generated. Some really are quite good.
phoronixrly · · focus · HN ↗
You can't be serious... Are we looking at the same posters?
ACCount39 · · focus · HN ↗
It's just that "seeing this poster for the first time, unaware of the workings behind it" is a very different experience from "seeing this poster after you already saw dozens of other AI generated posters that used a similar style and had similar issues, got canny at spotting both the style and the issues in it, and came to associate them with cheap low quality work".
The former impression is "wow that's a good poster". The latter impression is "ew, it's posterslop". The poster, in the meanwhile, remains the same.
AI can often win in art contests - images, short stories, design. But that requires either sharp prompting, or an audience that's not familiar with "AI cliches". The quality is, if removed from the context, fairly good. If embedded in context, it's utter slop. The work is the same. Funny how that works.
miyoji · · focus · HN ↗
A computer (not even an LLM, just something generating random pixels) could randomly generate the exact same pixel pattern as the greatest painting in the world, and it would not be the greatest painting in the world, because context matters.
hardbass · · focus · HN ↗
miyoji · · focus · HN ↗
hardbass · · focus · HN ↗
miyoji · · focus · HN ↗
hardbass · · focus · HN ↗
hardbass · · focus · HN ↗
numpad0 · · focus · HN ↗
wiether · · focus · HN ↗
Idk how to express it exactly, but I don't see how a human would have come to something like this
graemep · · focus · HN ↗
Most people are not that good at spotting those tells, and when looking at a poster they will not be thinking about whether its is AI or not. If its not obviously AI they are not going to even think about it.
wiether · · focus · HN ↗
And also it's not like I'm saying I love all the man-made posters. Or that I never been "fooled" by gen AI content.
It's just that as soon as I start seeing some gen AI tells on an image, I can't unsee them and I feel disgusted by it.
Applejinx · · focus · HN ↗
That's the problem.
card_zero · · focus · HN ↗
Immediate glamor followed by gradual disappointment is AI output all over.
hardbass · · focus · HN ↗
Pictures and pictures are the same thing.
AlienRobot · · focus · HN ↗
hardbass · · focus · HN ↗
sejje · · focus · HN ↗
And it took them telling you before you knew.
And then you decided you didn't like the ones made by the factory as much anymore.
ACCount39 · · focus · HN ↗
If I saw an Images 2.0 flyer in year 2020? In a world where Images 2.0 didn't exist? I'd be impressed. But if I see it now, today? I'm not impressed at all.
It's the same image, produced by the same AI and seen by the same person. So, what's the difference? What changed over time?
Saturation. "I've seen it all before." AI made that specific flyer style plentiful and omnipresent, and that made it "derivative" and "cheap". What used to invoke "cool" and "wow" was turned into a dreary cliche by repetition. Flaws that were easy to overlook when overshadowed by novelty stand out like a sore thumb now that you've seen them before in the same patterns many times over.
The image is the same - it has the same strengths and the same flaws. But your focus is shifted by familiarity.
It's the same mechanism that drives trends and fashion. AI just supercharges it.
Naturally, you can avoid a lot of it by using careful prompting and steering to guide an AI away from the "cliche" style-space. You can get something with both good quality and good identity that way.
But that requires: being aware of the problem, being really good at prompting, and putting in a considerable effort. It's hard to steer a model away from "AI cliches" if you don't have the eye to spot them in the first place.
Most AI-generated content doesn't have that kind of skill and effort applied to it - it simply uses the "model defaults", and gets the "model defaults". For all the good and bad that comes with those.