I find it kinda funny that even "smartest", most capable models often have a very hard time going beyond surface-level, top-of-mind associations, when faced with creative tasks.
Of course, a "Japanese Minimal Poster" has a sakura and a stylized flag of Japan, duh
A human designer would probably think that "Japan -> sakura" and "Japan -> Japanese flag" are way too obvious, too banal, too stereotypical, and, most importantly too boring. And then they would probably sit for a while and try to think of something fresher and less clichéd.
But AI has absolutely no problem with going with the cheesiest, most overused trope.
Well of course Spring + Japan = Sakura. In a way the model would be faulty if it didn't reach for that cliché. That's what it's meant to do.
If you want originality, you need to supply it. AI fills the vacuum with the obvious thing.
And in a way that's a feature. If I was creating a poster myself I'd think "nah, can't use sakura it's too obvious". AI gets you past that hurdle. "Yeah, we used the cliché, it looks nice, let's move on".
This is if it's for a school fayre, village fête, etc. - brilliant originality isn't the goal. But it's nice when your poster doesn't look the same as three other posters on the same noticeboard (I have seen this).
If brilliant originality is needed, a human has to bring it. Although an LLM with the temperature turned up can offer some nice seeds.
Thanks, it introduces a little "jitter" that keeps the egg from rolling down the same face of the ridge every time. Possibly, the same could be accomplished with a judicious application of the temperature parameter.
But how to tell the model which section is supposed to be populated with spicy tokens?
pigeon-footed → splayed toes → several directions → indecision → ambivalence
Do not cross the two clouds until each has several branches.
Reject commemorate + dulcigenic → a sweet memorial. Prefer A monument can turn bitterness into sweet nostalgia without changing what happened.
Reject preindicant + sclerotical → a hardened omen. Follow foretelling → divination and hard anatomy → bone to knucklebones.
It is a prime example of esoteric LLM incantations, if not -excuse me- nonsense
Off topic and a little whimsical, but LLM incantations is a really fun idea.
In a world where one hyper intelligent AI controls everything, hackers work tirelessly in secret off-grid, doing extreme math by hand, finding the right series of tokens that magically coerce the AI into carrying out certain actions. Spell books are copied out by hand and distributed in dark alleyways. Itinerant wizards travel the land on horse drawn carriages, travelling from town to town, casting spells on people's devices to bend the AI to their will.
It literally is how they work. They look for the next most probable token. Always keep that in mind when writing a prompt or reading output. If you don't supply it, it will fill it in with the most obvious stuff.
Personally I think if you were going to make a poster for a Japanese themed spring festival, and you did NOT include some sakura, you completely misunderstood the assignment.
Your promotional poster for a community gathering should not be subverting the western gaze on Japanese culture, or any other concept from art criticism 101.
It's supposed to get average people in your neighborhood to glance at it for 5-10 seconds and say, "cool looks like a good time"
YMMV but my experience tells me that the more cliché something looks, the more likely it's bad/cheap.
I've never been in a cliché-looking restaurant that is actually decent.
Meanwhile, the best restaurants I know have, at best, a flag or some kind of small drawing to give a clue about their nationality, but otherwise they look like a regular local one.
Right, but the best restaurants are not most restaurants. The best high end events are not most events. Most events and restaurants could be improved a lot by AI already
More like 100ms or less as their visual field coincidentally sweeps over wherever the ad is posted in the physical world. In this regard, it's even more important to use something people subconsciously associate with your thing.
You just don't know what it's like to live in a place where art and culture is truly valued. Take Japan, for a relevant example. Many things in japan are given an extra small twist to aesthetically elevate them. The food looks a little prettier, their packages are just a bit neater, their technology is cute, they put little doodles on everything, aside from new-age products or architecture everything has a little bit of personal touch and care. This is because there is some tradition of taking pride in small details and not reaching for the most obvious solution.
A society that values culture is taking the extra 3 minutes to think of or look up some Japanese iconography that would make the poster a bit more interesting than a sakura even if brainless "average" people cannot figure out how it is relevant to Japan, the hope being that all of us learn and appreciate these things a bit more.
> Take Japan, for a relevant example. Many things in japan are given an extra small twist to aesthetically elevate them.
I've been to Japan. How would you comment on the aesthetic of this "Little Texas" bar in Tokyo: https://www.littletexas.jp/
Do you think they are valuing the true culture of modern Texas? Because in my opinion this bar is filled with the most basic Texas cliches I can think of: cowboy hats, longhorn skulls, etc. Probably a lot more egregious than putting a sakura on a poster.
I said new-age products are an exception, the bar was opened in 2005. It also kind of proves my point, once Western culture ingratiated itself into Japan the art culture got a bit worse.
Of course they have ulterior motives to push the message that it can replace high quality human artists, even though that would be ridiculous under any serious analysis.
Isn’t the most overused trope the most statistically weighted to be chosen from a group of options? It makes technical sense but as you say leads to boring outcomes
I see what you mean, but I think you can draw (no pun intended) a distinction between trope following and having a skill, or at least should notionally be able to.
I remember seeing a poster for Chinese New Year years ago, and someone had included the kanji for Japan on it (日本). Obviously they just wanted generic looking characters without bothering to see what they meant. I couldn't resist writing a comment on the poster about it.
It showed whoever did it had no clue about East Asia or Chinese script...
> But AI has absolutely no problem with going with the cheesiest, most overused trope.
Considering your prompt fits exactly that description I think the AI delivered perfectly. Try using some actual design language and see how well it does.
The thing is, they aren't creative. When I ask an LLM to go beyond the mean, it has no idea what to do and returns incoherance. Its responses seem to have N latent dimensions of information. But, the value of each of those dimensions is always the midpoint. With creative prompting, I can push it to respond in ways that go beyond the mean, but it can't tie them together cohesively. It doesn't have anything in its training data to fill the hole in space. No ability to extrapolate.
My point is that those kinds of prompts are dumb and I actually expect the model to produce slop. In programming we write these huge prompts that go into a lot of detail, and when we do that, it actually works. I've never asked a coding agent to go beyond the mean, that just sounds like a dumb thing to do. Apply this rule in design and I'm sure you'll get better results. Kinda what the blog post is all about.
Sure, but what's interesting is if you tell it to "behave unpredictably" or "don't use tropes" it usually fails down the same curve. Which is predictable, but telling.
That's on the prompt, not the AI. You could be specific about what imagery to use like a torii or a Japanese castle, and so on. Whatever you leave to the AI you're most likely going to get the most generic version. If you're low effort in the prompt yet get low effort results, if you put some effort into the prompt you can get better results.
This is actually quite hard to achieve, at least in a one-shot LLM prompt.
You could engineer it by asking for a list of subjects sorted by obviousness, then pass that list to a script that discards the top 30% and randomly picks from the rest.
Even if you prompt an LLM to pick one at random, it usually won't, without an external randomness tool like that - which is curious, isn't it, when non-deterministic-ness is so inherent to LLMs.
Yet there are countless extremely banal posters, made of sakuras, flags, red sun rays and purely random hieroglyphics that mean nothing, made by humans for the entire history of poster-making.
Most illustrators available to most businesses for hire would do worse job for more money and much more time than an LLM would do.
Probably an unpopular opinion, but advertisement does need a creative bar too high. No one cares about it. It’s enough to have a black text on a white background saying what is happening, when and where. The rest is optional, and most of the time gets in the way of understanding the poster info.
Y’all terribly overestimate quality of human art (as well as how informed humans are and how accurate their answers are) while riding the LLM hate train.
Pretty sure 90% of the posters of the type at the top of the article are made for $0. I bet for $10 you could get real artists from non-Western countries to make a simple poster, but these days people would probably claim those $10 jobs and then have AI generate them anyway.
Destroyed or democratized? I'd question the financial judgement if a local fair actually paid a designer for a poster and revisions, versus just literally typing something in Word and adding some clip art.
Of course, a "Japanese Minimal Poster" has a sakura and a stylized flag of Japan, duh
A human designer would probably think that "Japan -> sakura" and "Japan -> Japanese flag" are way too obvious, too banal, too stereotypical, and, most importantly too boring. And then they would probably sit for a while and try to think of something fresher and less clichéd.
But AI has absolutely no problem with going with the cheesiest, most overused trope.