I gave Opus 5.5 one prompt and six hours to visualize Invisible Cities
quesma.com
[19 comments hidden]
[3 comments hidden]
Citizens of this city high in the sky imagine it so fully in their minds that no one there needs to open their eyes to walk the streets and live their normal lives. But if one makes the mistake of opening their eyes and tries to see the city directly, they would immediately fall through the clouds to the ground deep below.
[2 comments hidden]
The website gives you a good hint before opening up the visuals. So, I got an idea.
I don't really know about Marco Polo. My only knowledge comes from the Netflix series, which doesn't talk about these invisible cities.
[2 comments hidden]
The book is a trip and the dreamy sort of narration matched it perfectly. My wife and I would spend evenings listening to one city at a time, on a walk around our little park, one headphone in each ear. I don't know if it was just the environment or the time in our lives, but we both really look back fondly on this book.
[hidden]
PS I didn't open the gallery. Nice idea but I don't care about visualizing something I should feel.
[hidden]
How Opus 5.5 imagines these cities is a question for Opus. The real experience is how we imagine - and I believe there are no two people who have exactly the same mental image of an invisible city.
[hidden]
Talk about missing the entire point of the piece of literature.
[hidden]
[hidden]
[hidden]
Having looked at some of them (and it being one of my favorite books) ... it won't do that. These visualizations are as terrible as they are unnecessary.
[hidden]
[4 comments hidden]
[3 comments hidden]
[6 comments hidden]
As neat as this project is, this does no justice to whatsoever to the book. On the surface Invisible Cities seems to be a book about random cities' descriptions. In reality though, this book is about semiotics, meaning, language, and it's limits.
[2 comments hidden]
[hidden]
[2 comments hidden]
Seeing the same thing done to Calvino (and Weaver's) sublime prose feels downright criminal.
[hidden]
Kublai Khan does not necessarily believe everything Marco Polo says when he describes the cities visited on his expeditions, but the emperor of the Tartars does continue listening to the young Venetian with greater attention and curiosity than he shows any other messenger or explorer of his. In the lives of emperors there is a moment which follows pride in the boundless extension of the territories we have conquered, and the melancholy and relief of knowing we shall soon give up any thought of knowing and understanding them. There is a sense of emptiness that comes over us at evening, with the odor of the elephants after the rain and the sandalwood growing cold in the braziers, a dizziness that makes rivers and mountains tremble on the fallow curves of the planispheres where they are portrayed, and rolls up, one after the other, the despatches announcing to us the collapse of the last enemy troops, from defeat to defeat, and flakes the wax of the seals of obscure kings who beseech our armies' protection, offering in exchange annual tributes of precious metals, tanned hides, and tortoise shell. It is the desperate moment when we discover that this empire, which had seemed to us the sum of all wonders, is an endless, formless ruin, that corruption's gangrene has spread too far to be healed by our scepter, that the triumph over enemy sovereigns has made us the heirs of their long undoing. Only in Marco Polo's accounts was Kublai Khan able to discern, through the walls and towers destined to crumble, the tracery of a pattern so subtle it could escape the termites' gnawing.
And here's the AI distillation:
Kublai Khan does not necessarily believe everything Marco Polo says of the cities he has visited on his missions, but the emperor of the Tartars listens to the young Venetian more attentively than to any other envoy. In the melancholy hour when an emperor learns that his boundless empire is only an endless, formless ruin, the reports of Marco Polo allow him to glimpse, through the walls and towers destined to crumble, the tracery of a pattern so fine it could escape the termites’ gnawing.
Feels like listening to music at 2x speed for the "efficiency."
[32 comments hidden]
[17 comments hidden]
If something that previously took weeks for a human to design, now takes 10 min, that means a whole week of salary went up in smoke.
When have we automated enough?
[2 comments hidden]
The problem also is, if a human took weeks to design this, it would be much better. This is quick but also bad.
[8 comments hidden]
[7 comments hidden]
[3 comments hidden]
[2 comments hidden]
[3 comments hidden]
To me, this is the depressing sentiment. The idea that, somehow, the goal isn't to produce useful things but to spread work out over a period of time in order to maximize payment.
At a high level,I conceptualize my job as "doing useful things." Whether that's design, writing code, debugging, sysadmin, CI/CD, writing doc, whatever. I just want to be useful. If there's some tool that makes that easier, I am happy about it. I don't think that tool will result in my getting paid less. But if it does, oh well.
[7 comments hidden]
For example, I didn't learn about lenses or earthquakes or fusion messing with the controls on these.[1] I didn't know what to look at.
However, there were interactive exhibits at the Children's Museum I spent a long time exploring and loved. That's because they were carefully designed to really teach the concept?
[3 comments hidden]
It turns out the more technology you throw at something does not equate to ease of learning.
[hidden]
Put in the hands of the educator, they will be able to add those illustrations, design for the light bulb moment, etc, and the tools at their disposal just got much better.
[hidden]
[hidden]
You'd not be amazed by seeing a 2 sentences prompt and thus you are not amazed by this work either.
[2 comments hidden]
I've been thinking of this line recently — really gets at the heart of the matter for me. There is no substitute, no shortcut, no alternative for effort.
[3 comments hidden]
Now imagine the same thing but each person is using Opus 5.5 - I’d wager there would be a lot of commonality among each of the outputs.
[2 comments hidden]
- Each phrasing the prompt(s) differently
- Each having different history accumulated in context
If you asked me to issue the same prompt as you to write some web artifact, chances are mine would be substantially stylistically different, simply because at some point in the past half-year, Clause started styling everything in LCARS form for some reason.
Whether the differences would be substantial or surface-only? Probably depends, but chances for substance increase with iteration. Real artists don't zero-shot their masterpieces either.
[hidden]
I’m saying if you provide the same prompt to Opus 5.5 across 12 different people, you’re going to get some similarities that immediately arise.
I’ve mentioned this across many HN threads - I call it the LLM corollary to “garbage in, garbage out”: "generic in, generic out". If you prompt with more specificity, you’re obviously going to get different and potentially better results. But at that point, the artist is doing more of the work.
A while back, I tried a similar test asking for LLMs to come up with engaging D&D puzzles that would fit organically into an underground labyrinth environment. This is a pretty general prompt. Let's just say that the results were about as inspired as a tepid bowl of tapioca.
[hidden]
[hidden]
[hidden]
[2 comments hidden]
I always think that it will interest me, the overview sounds cool, I click around for a few seconds, and then... my eyes glaze over. I feel nothing. I clicked away in under 45 seconds.
It makes me sad, too, because I love a passion project.
I am also stunned, because 5 years ago if a dev built something like this I would be enthralled - "How did you choose the engine? What was the hardest part? Did you like the UI framework?"
But the author didn't experience any of that...
[5 comments hidden]
> Arriving, you rejoice at its bridges, each different
The model city had like five bridges total, three of which were didn't bridge anything at all but instead sat in the middle of the river and went along its flow, the "bridges" for some reason pretending to be small islands.
[hidden]
Kublai Khan received an ornate letter signed by Marco Polo: "In Madrid, City of Lost
Things, no item remains where it was set. If one drops his key in the dirt, he may
never re-enter his home, and, even if he manages to stoop and recover the key, he may
rise to find a tulip garden where his house once stood. In complementary fashion,
things lost by others are forever turning up: A pocket watch on a coffee table. A fond
memory in your recollection. I even know of a prince who turned up in a prison cell.
When he appealed to the guards for his release, he failed to find the crown on his
head, and when he was asked his name, he searched his thoughts, but could not find it.
Indeed, the only hope now for the release of this prince of Spain is for you to send
back 300 ducats for his release. Of course, he will reward you handsomely once he is
out. Yours truly, Marco." Kublai Khan cocked an eyebrow and declared before his court,
"Hey, everyone: Looks like we're about to get ripped off by the guy who traded gold
for paper!" The court erupted in booming laughter.
— Italo Calvino, Invisible Cities 2: This Time It's Visible.[8 comments hidden]
[2 comments hidden]
If the creator truly wanted viewers appreciate the end product they'd start with the one shot output and spend their weekend iterating on each city either by hand or with Claude. But they didn't want to do that, they wanted to show off what Claude/GPT could do in 6hrs. That's the whole blog post.
[4 comments hidden]
I expect we're going to see more and more amazing "hobby projects" that did involve both a few hundred dollars in tokens and hours of human creativity and effort in combination.
[3 comments hidden]
[2 comments hidden]
Unasked-for-story-time: In the early aughts, there was a PC video game called Star Trek: Elite Force. It was a FPS genre game and included a feature called "Virtual Voyager" that at the time was revolutionary because it would let you just freely explore a subset of the Starship Voyager without any linear mission requirements, the closest any Trek fans could get to gaining access to the real Paramount Studios Stage 9-and-friends sets where the TV show was filmed, which for Trekkies with no life is quite the big deal.
Wasting the GPT-6 Astra capabilities over a single month of the $200 plan, I've built out multiple decks of an Excelsior-class starship based on a deck plan of my design, dealing with creative decisions on how to adapt the limited Star Trek canon knowledge about the interior deck sizes and materials aboard an Excelsior-class vessel, and at the end of this project, all I will have will be a graphically crappy but 3d explorable virtual starship I can walk around, look at the interior of, and mentally place my daydreamed Star Trek personal fanfic that I used to pencil in a notebook, and now I direct/dictate/produce using agents to write their crappy sloppy prose, but is tuned exactly to my preferences, and now will be able to have specific camera angles and relative details because I can screenshot the 3d ship explorer I made with the crappy AI.
I've got the pencil, I've got the nerd no social life time for creative projects, and I am still writing the no-AI no-name fantasy novel that nobody will read except my family and AI-data-gorgers, but neither of the two projects above, which have provided me hours of entertainment dopamine, would have happened without AI tooling making it easy enough to be creative without having to hand render every little detail.
Art is produced for arts own sake, right? That's the phrase? Well this vibe slop story and this vibe slop 3d viewer are digital goods / digital art to _me_, because I like them for their own sake. I can't copyright any of it, its all been infected by AI stuff. I can't get a job with it, I can barely orbit in Blender and don't find it worth the time to learn to render drawing in 2d and sculpting in 3d (I've tried both over the years in pre and post AI eras, I'm from a creative family whether I wish it or not), the costs to render skills manually make it not worth my time to do.
But AI makes it worth my time because it is an enzyme that reduces the input cost of me prototyping my creative desire out without having to laboriously create every last everything.
[hidden]
Source code: https://github.com/stared/invisible-cities-opus-5.5
[7 comments hidden]
[3 comments hidden]
[3 comments hidden]
unlike someone who is just whining about it?
Wtf are you to someone who has put effort to spread about the book? I never seen/heard of the book, and now I am iintersted in it thanks tot he author.
[3 comments hidden]
[hidden]
[hidden]
[hidden]
I don't mind the AI but the human needed to put more time into curation and getting the magic right.
[2 comments hidden]
[hidden]
[hidden]
[2 comments hidden]
[hidden]
Citizens there gather their tools at the bottom of a giant staircase and climb up countless stairs, only to find out that what they were planning to do has already been done by the time they reach the top.
Dissapointed, they descend to grab a new set of tools and make new plans for tomorrow, only for the same thing to happen again.
[3 comments hidden]
https://claude.ai/share/6bbd421a-147d-435d-bc00-7e93b393b943
(the standalone version at the very end of the chat is the one that runs in the browser)
Well, overall, by faaaaar not that beautiful as what the author from the article received? :-D
(though, it was done with Opus 4.8)
[3 comments hidden]
And shame on all the people shitting on it because AI made it. If you valued art for art's sake, you wouldn't be so bothered when somebody makes something art-adjacent using some technique you don't approve of. It in no way detracts from the kind of art you admire. Don't be type who just has to let others know that you find something they like to be beneath you.
[hidden]
[hidden]
[4 comments hidden]
The amount of _stuff_ crammed into each little city is almost unbelievable. Drawbridges open and close, glowing lines sketch patterns, camels walk across a tiny desert. Buildings fade into existence and then burst in a shower of sparks. Flags fly, smoke drifts, buckets cause ripples as they dip into underground pools. The city made of plumbing has tiny people in the bathtubs! There's a freakin' roller coaster with moving cars and a ferris wheel!
I absolutely understand the AI hate that's being commented here, but... in this instance, I just can't feel it. I keep finding more and more little details every time I click on a city, and I am astounded. I just now noticed there's a little guy in the city of strings hanging up new strings at the top of the hill. Damn. My favorite is Marozia, where dark buildings open like treasure chests and release shining towers and flocks of glowing birds.
Yes, there are also a lot of stupid AI errors - every spoked wheel has the spokes off-center for example. But holy crap, I just can't hate this. I don't care about who built it or the random bits of jank - this thing is _beautiful_ in a way that I haven't seen from AI before, and it warms my old GPU-powered heart.
[2 comments hidden]
Phyllis fades from color to black and white except for two houses. The fairground has a big top with tiny bleachers and a guy inside. The happy city has people with their arms raised in a V. People in the marketplace city wear hats and some are carrying bundles on their heads. There are weird cactus plants in the hanging city. In the half-fairgroud city, there's a statue on one of the trucks. The city that copies the dead has a set of pallbearers carrying a wrapped corpse down the stairs. The people on top of Argia are laying with their ears to the ground, listening for the animated sound waves coming from below.
And on and on and on and on. I just can't even.
[hidden]
[hidden]
[hidden]
[hidden]
[hidden]
[hidden]
rock on
[hidden]
[2 comments hidden]
I once instructed it to spawn at most 20 subagents and it spawned 40, with an adversarial reviewer for each of the 20.
It doesn't follow these instructions very well.
[hidden]
[hidden]
[hidden]
[hidden]
[hidden]
[hidden]
it's also not very astonishing that the current models are able to create this - it looks exactly as expected
and I actually think getting an interesting AI generated rendition of the text from a single prompt is a worthwhile endeavor
maybe even a good replacement for the pelicans: it would test if a model can engage with a text beyond the surface level
but this ain't it
[hidden]
[hidden]
Vanadium (chrome)
[hidden]
[hidden]
I guess I shouldn't be surprised that another visual medium is starting to fall to LLMs after the success of diffusion models for image generation. Nevertheless it's wild that a mostly text-focussed model is building little worlds like these.
[hidden]
[3 comments hidden]
[2 comments hidden]
[2 comments hidden]
[hidden]
[hidden]
[hidden]
[hidden]
[hidden]
I'm so glad I'm able to witness this Cambrian explosion of software :).
[hidden]
Invisible Cities is one of my favorite books, and I've re-read it several times. It's a great "travel" read and always puts me in the mood to explore. It's also a very romantic book, obviously the cities have all named after women, so it evokes conquest in the sexual sense as well. It's also a piece of surrealist/allegorical literature in the same vein as Daumal's Mount Analogue (which also tops my list).
Back to the website. While this is an impressive tech demo (as they all are), it's clear that AI misses the forest for the trees, and here's a tangible example. I randomly clicked on Theodora. Honestly, I didn't even remember which city this was until I re-read the Calvino passage:
> Recurrent invasions racked the city of Theodora in the centuries of its history; no sooner was one enemy routed than another gained strength and threatened the survival of the inhabitants. When the sky was cleared of condors, they had to face the propagation of serpents; the spiders' extermination allowed the flies to multiply into a black swarm; the victory over the termites left the city at the mercy of the woodworms. One by one the species incompatible to the city had to succumb and were extinguished. By dint of ripping away scales and carapaces, tearing off elytra and feathers, the people gave Theodora the exclusive image of human city that still distinguishes it.
So, what do we know about this city? We can make a short sensible list:
1. It's an imperialistic (or at least millitaristic) reflection of man's will to power (as Nietzsche might put it)
2. It's decidedly anti-nature, the natural flora and fauna being its primary antagonist
3. It's been destroyed and rebuilt many times
4. The city is built by literally ripping away bugs and birds; tearing their wings from their bodies like a cruel child might
5. Nature is slowly winning (and maybe it already has)
This[1] is what AI saw. Now, this isn't bad, really. But it's so embarassingly pedestrian, it hardly counts as a visualisation. It just heard "city with animals and stuff" and made a 3D model. But it's all, in that uncanny-valley kind of feeling, wrong. Why is the city itself a grid? Why is there a library in the center?Calvino, again, on Theodora:
> But first, for many long years, it was uncertain whether or not the final victory would not go to the last species left to fight man's posession of the city: the rats.
The vibe here is an overrun rat's nest of a city. A disgusting bloated corpse; more:
> The city, great cemetery of the animal kingdom, was closed, aseptic, over the final buried corpses with their last fleas and their last germs.
I see an overrun New York. I see a city built on a decaying graveyard. AI sees animals and humans living in a kumbaya harmony, but that is not what Theodora is: it's an eternal conflict between man and nature (and nature won a long time ago). For the record, this isn't even that particularly deep. Many authors and poets write about this eternal human struggle: the taming of the wilds. But Claude just doesn't get it. I hope readers of the book do.
Anyway, I leave you with this. I found an artist, Rian Hotton[2], who put brush to canvas to show us what he thought Theodora looks like[3]. And this... this is more like it.
[1] https://imgur.com/a/hXrKVg3
camillovisini[22 comments hidden]
https://camillovisini.com/drawing/fc4jc6-le-citta-invisibili...
https://camillovisini.com/drawing/p2yrdj-le-citta-invisibili...
Razengan[hidden]
SamBam[5 comments hidden]
kraquepype[4 comments hidden]
One is art. When completed, they can look at it and be reminded of the journey of creation, a labor of love. It could be put away, or displayed for all to enjoy.
orangedog[3 comments hidden]
How is this not applicable to both things? This just reads as gatekeeping to me.
The amount of time or effort put into something does not determine its value.
Paracompact[hidden]
wakaru44[hidden]
It literally does, not only in art. Is not the only factor, yet is definitely one of them. In many objects, the version with 'more human effort' is more expensive.
toddmorey[hidden]
sailingparrot[10 comments hidden]
With AI generated stuff, sure it looks amazing at first glance but I definitely don’t want to zoom in, since I know it’s all a cardboard facade with no passion. Look a bit too closely and you’ll see the bridges that make no sense, the bunch of nonsensical threejs cylinders etc.
ahknight[4 comments hidden]
I don't dismiss the ability of models to create. I dismiss their ability to create finished goods. Humans should always be involved, especially with creative works. Models are great at modeling existing creations and solutions — head starts on long roads — but it's the person that needs to walk it and take the journey.
npunt[3 comments hidden]
Abandoned one-shot drafts are akin to speaking words but never finishing a sentence before moving onto the next thought. There's no there there.
digilypse[2 comments hidden]
npunt[hidden]
We're in an environment awash in 'content' where every person has an infinite slop producing machine, and a lot of people are publishing nearly zero effort drafts, awed by the appearance of meaning.
BenzeneDream[5 comments hidden]
Sammi[hidden]
sailingparrot[3 comments hidden]
In the original link the first city I checked (forgot the name) was one were supposedly you have 5 bridge, every one of them more magnificent than the other. The city looks great at a distance, with glow and particle effects. Zoom in and you’ll see the bridges are actually floating over the river, they are not connecting both banks they are literally in the river parallel to the banks with no way to get in or out of the bridge.
The bridges were the central element of the story. Would a human that spend 10h working on this piece just forget that the bridges, the very central element they are trying to depict, need to actually function as a bridge?
With a human, you may get ugly output but you’ll not get that nonsense.
sixsevenrot[2 comments hidden]
Replace 3.js with an engine that embeds physics, ask it to do test fly-through through each city and fix inconsistencies and let's then compare the results.
Paracompact[hidden]
vunderba[hidden]
> Leaving there and proceeding for three days toward the east, you reach Diomira, a city with sixty silver domes, bronze statues of all the gods, streets paved with lead, a crystal theatre, a golden cock that crowns each morning on a tower...
Text in the second person is causing my my D&D instincts to kick in.
olwmc[hidden]
matsemann[hidden]
jacquesm[hidden]