I was finishing Invisible Cities yesterday, because the book was due at my local library today. I was wondering whether the cities could be adapted into some visual art form. And obviously I thought about feeding it to Opus. 24 hours later, I see this post…
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.
$74 vs $ 10 vs $25 for the same prompt,
The interesting number is not actually quality, its what we can get per dollar like 6 subagents runs in parallel.
Six hours of continuous runtime is the underrated part here. Most one-shot demos fall apart well before that, so this doubles as an endurance benchmark.
Why, I once encountered a running session longer than a day!
The agent had spun up a backward shell script to watch for the shutdown of another process, but wrote a bug in the script that would have left it running indefinitely until I got home and noticed it.
This was with Fable, no less! And it happened a few more times, though I caught them sooner.
I’m not sure runtime is an important metric at all. Shouldn’t we aim for 0 runtime with maximal results?
The first city I clicked on at random had the opening phrase:
> 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.
If you haven’t read the book yet, I’m tempted to warn you against opening the visualization. Part of the joy of reading this book is letting your mind’s eye run wild, and I fear if I read it for the first time after toying with this site, I’d be remembering the cities rather than conjuring them.
That is the exact problem with the city of Dinipro.
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.
I heartily recommend the audiobook, narrated by John Lee.
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.
I read the book decades ago, then I lost it in one of the many relocations. I always thought I should buy it again but never acted on the idea... A few years ago, I was walking by an antiquarian, and noticed a thin unmarked gray spine. I entered, picked it up, paid, and walked away.
PS I didn't open the gallery. Nice idea but I don't care about visualizing something I should feel.
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.
It's a techie creating the torment nexus but the imagination version. No need to picture in your mind the invisible cities! Time to make them visible!!!
Talk about missing the entire point of the piece of literature.
Maybe the interactive link in the article for the optic focus can lead you on a fun journey instead. And the bottom-right of every visualization is a link to yet another fun diorama to explore.
> I’d be remembering the cities rather than conjuring them
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.
Aphantasia can be cured by deliberately engaging the imagination even when nothing is seen - you might not see anything at first but eventually you gain the ability through letting go of external awareness and developing the imagination pathways.
In fact, having a physicalized 3D representation of the cities is IMHO antithetical to the text. I don't think OP ever stopped to ask if there was more to Calvino's work than 'cool city descriptions'.
The uprose could be as little as trying something new. Some of you have seem to lack curiosity and you are jerks, too, shitting on somebody for trying something new.
A couple of years ago, after reading the book, I sketched some of them on Procreate with an isometric grid, but not all 55. I only arrived at number 4, since each took multiple hour...
Since this project (both yours and OP's) seem more for personal fulfillment and enjoyment, I wonder who got more enjoyment out of the process, and also who will remember the results better in ten years.
One is a toy. Created on a whim, it will end up in the bin with other toys. They might pick it up and paw at it later, stir up some memories, and then put it back.
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.
> 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.
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.
The amount of time and effort a human put into something very much does tend to determine its value, both to that human and others in their social circle.
> The amount of time or effort put into something does not determine its value.
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.
It’s interesting, with a human made piece of art, I’m always drawn to « zoom in », to see how you did little details, if you have hidden something here and there, how you connected different parts.
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.
I always consider AI-generated content to be a draft — or, in its parlance: something that takes the shape of the final product.
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.
Are they really? Nothing of value is produced unless the exact artifact is transmuted into a professional good? There’s nothing to be gained from sketching preliminary drafts or notes because they’re never polished for publication?
Not what I meant. The point was work under a certain grain size of effort has very little (or negative) value to others.
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.
Not much, because they are fundamentally different types of errors. A slightly off perspective doesn’t change what the artist was trying to convey.
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.
The only reason a human will not give you a nonsense bridge is that a human is running a 2.5kWh spacial physics calculation engine in his/her head.
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.
> Make a three.js (pnpm) visualization of all Invisible Cities by Italo Calvino. Don’t ask questions, it is a one-shot task. You have 6h of work, use it until it becomes a masterpiece.
> 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.
I'd much rather see yours than the slop version. One of the nice things about the book is that everybody sees the cities different in their minds eye, this link above came from no mind.
Invisible Cities is my favorite piece of literature hands down. The audiobook narrated by Richard Higgins is also done so beautifully and can't recommend it more.
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.
I recently saw a project that intended to turn House of Leaves into a game. The graphics were shoddy and the mechanics were dull, but by far the worst aspect was how it "paraphrased" passages from the book into Claudespeak (allegedly for copyright reasons).
Seeing the same thing done to Calvino (and Weaver's) sublime prose feels downright criminal.
Just as an example, here's the beautiful opening of the book:
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."
both the linked camera lens example as well as the last one the author linked runs at ~5fps on vivaldi and pegs CPU 100%. i have never seen any 3d visualization website have performance this bad, i assume they're not using webgl given my GPU is 0% utilization.
This is probably one amazing positive these models have brought forward - the ability to break out of a single modality, and utilise others to help us learn and visualise. While the visuals here are amazing, my son for example prefers to learn by listening and talking, so we convert lot of his study materials into audio and real-time voice roleplay.
I'm a little torn by this sort of demonstration, because while many of the scenes have obvious markers of slop (impossible intersecting geometry, bridges to nowhere, and so on), the scenes largely do work to convey the intended concept/emotion, and the low-poly aesthetic is executed decently well.
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.
What AI is doing is unbelievable. Each of these examples would have cost hundreds of thousands of dollars and months of dev time to achieve, and they still wouldn't have been as polished as these are.
Before AI, in order to build something like this you had to be both creative, and you had to know how to do it. The latter part takes years to accumulate the experience to even know where to begin. Now, you just have to be creative. The days of techies gatekeeping these experiences are over.
This is more comparable to a mass produced plastic replica than the handcrafted work of an artist. Experience and skill are not orthogonal to creativity or taste.
172 comments
[ 3.6 ms ] story [ 58.7 ms ] threadSource code: https://github.com/stared/invisible-cities-opus-5.5
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.
The agent had spun up a backward shell script to watch for the shutdown of another process, but wrote a bug in the script that would have left it running indefinitely until I got home and noticed it.
This was with Fable, no less! And it happened a few more times, though I caught them sooner.
I’m not sure runtime is an important metric at all. Shouldn’t we aim for 0 runtime with maximal results?
> 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.
Opus Eutropia has a few isekai circle cities with one of them... ON the river, giving no space for ship traffic.
Slop has never been this beautiful before!
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.
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.
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.
PS I didn't open the gallery. Nice idea but I don't care about visualizing something I should feel.
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.
Talk about missing the entire point of the piece of literature.
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.
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.
https://camillovisini.com/drawing/fc4jc6-le-citta-invisibili...
https://camillovisini.com/drawing/p2yrdj-le-citta-invisibili...
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.
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.
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.
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.
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.
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.
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.
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.
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.
> 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.
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.
Seeing the same thing done to Calvino (and Weaver's) sublime prose feels downright criminal.
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."
Vanadium (chrome)
https://imgur.com/a/nGLyJf6
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.
Before AI, in order to build something like this you had to be both creative, and you had to know how to do it. The latter part takes years to accumulate the experience to even know where to begin. Now, you just have to be creative. The days of techies gatekeeping these experiences are over.
I'm so glad I'm able to witness this Cambrian explosion of software :).