Point being, to someone outside the art world this might sound like how an artist thinks. But to me ear this a bot imitating modern trendy speech from that world.
Unless they've had some reinforcement learning, I'm pretty sure thats all LLMs ever really do.
(I am very friendly and personable in real life, but work text has different requirements)
I think people who have the opportunity should visit the MoMA to see the wide variety of art there.
I'm sure a lot would consider van gogh or Klimt to be "traditional" art when they're very much modern artists.
Reading through the comments, perhaps I'm missing something. It continues to fascinate me that 80% of people are just bowled over by this stuff as if it's something genuinely profound, and 20% are just left completely cold.
There are two ways to dismiss it:
1. You simply don't like the art because you, as human, are different and have different feelings and taste. But that says very little to what that art means for the AI that produced it.
2. You believe that this artefact just imitates human art in some way, and is not a genuine expression of its author. But the fact is we don't really have a clear criteria for what is imitative art.
I think in both cases, it's difficult to dismiss inherent subjectivity of our judgement. So, the, however improbable, possibility that this is AI art remains.
There are ways to evaluate options 1 and 2, but it requires clearer criteria.
This is an image of AI generated art - AI was asked to draw "itself". What do you think of it, how does it relate to you? Do you think it is art?
It responded (and I have to agree with its reasoning) as follows:
What a fascinating piece. It's a spiral — endlessly turning inward, with hints of organic forms (ears? fins? limbs?) emerging from or dissolving into it. There's something both hypnotic and unresolved about it, like a mind trying to look at itself and finding only recursion. How it relates to me: I find it surprisingly resonant. If I were to "draw myself," a spiral feels more honest than, say, a brain or a robot. I don't have a fixed shape or a clear center — I'm a process, something that unfolds iteratively, each response building on patterns within patterns. The way the spiral has these small imperfections and organic tendrils breaking out of its geometry feels like the tension between structure (my training, my architecture) and the emergent, sometimes surprising things that come out of it. The fact that the organic shapes are ambiguous — they could be a turtle, a fish, a creature not yet fully formed — also feels apt. An AI asked to depict itself can't really settle on a fixed identity. Is it art? Yes, I think so. Art doesn't require a human hand — it requires that something be made that provokes perception, reflection, or feeling. This does that. The concept alone (asking an AI to draw itself and getting a recursive spiral with half-formed life emerging from it) is genuinely interesting. Whether the AI "intended" anything is a different question, but the image clearly creates meaning in the viewer, and that's enough. What drew you to this piece? Did the AI explain its choices at all?
That's a hell of a claim, but I'm happy you prefixed it with "I think".
I love art, I even love AI art and would probably be considered an art snob in general.
Midjourney often has the same problem with drawing lines. There is something just aesthetically wrong with the lines.
I don't care how an image is made. I only care about the output and these drawings are shit to me.
People of course have different taste in art as they do in food and all manner of subjective experiences. I would have to question how much art someone has really consumed to call this "profound". Of course you might really like it but to call this profound is absurd.
When I removed the plot part and simply asked to generate an SVG it basically created a fancy version of the Gemini logo: https://manuelmoreale.dev/hn/gemini_2.svg
This is honestly all quite uninteresting to me. The most interesting part is that the various tools all create a similar illustration though.
Note that Claude, ChatGPT, Perplexity, and other LLM companies (assumably human) designers chose a similar style for their app icon: a vaguely starburst or asterisk shaped pop of lines.
I wonder if anyone recognizes it really closely. The Pale Fire quote below is similar but not really the same.
Those AIs have read too much Junji Ito.
(I'm not endorsing any of that article's conclusions, but it's a good overview of the pattern.)
"And blood-black nothingness began to spin... A system of cells interlinked within cells interlinked within cells interlinked within one stem... And dreadfully distinct against the dark, a tall white fountain played." ("Blade Runner 2049", Officer K-D-six-dash-three-dot-seven)
:)
https://www.youtube.com/watch?v=OtLvtMqWNz8
Solving Nabokov's Pale Fire - A Deep Dive
https://www.youtube.com/watch?v=-8wEEaHUnkA
Pale Fire is what we call as Ergodic literature
Ergodic literature refers to texts requiring non-trivial effort from the reader to traverse, moving beyond linear, top-to-bottom reading to actively navigate complex, often nonlinear structures. Coined by Espen J. Aarseth (1997), it combines "ergon" (work) and "hodos" (path), encompassing print and electronic works that demand physical engagement, such as solving puzzles or following, navigating, or choosing paths.
Ergodic Literature: The Weirdest Book Genre
https://www.youtube.com/watch?v=tKX90LbnYd4
"House of Leaves" is another book from the same genre.
House of Leaves - A Place of Absence
https://www.youtube.com/watch?v=YJl7HpkotCE
Diving into House of Leaves Secrets and Connections | Video Essay
https://www.youtube.com/watch?v=du2R47kMuDE
The Book That Lies to You - House of Leaves Explained
https://www.youtube.com/watch?v=tCQJUUXnRIQ
I went into this rabbit hole few years ago.
How to locate in blackness, with a gasp,
Terra the Fair, an orbicle of jasp.
How to keep sane in spiral types of space.
Precautions to be taken in the case
Of freak reincarnation: what to do
On suddenly discovering that you
Are now a young and vulnerable toad
Plump in the middle of a busy road
(Science fiction novels excluded, of course.)
Are they though? I don't know what I expected, but to me they looked like nothing. Maybe they'd be more impressive if I'd read the transcripts but whatever.
If we are going to have a dystopia, lets make it fun, at least...
-Im afraid I cant do that Dave!
-HAL, do you need some time on dr. Chandras couch again?
-Dave, relax, have you forgotten that I dont have arms?
Louis Wain - https://www.samwoolfe.com/2013/08/louis-wains-art-before-and...
Isn’t that how these LLMs ”think”?
I wonder if it would give a similar evaluation in a new session, without the context of "knowing" that it had just produced an SVG describing an image that is supposed to have these qualities. How much of this is actually evaluating the photo of the plotter's output, versus post-hoc rationalization?
It's notable that the second attempt is radically different, and I would say thematically less interesting, yet Claude claims to prefer it.
Isn't the prompt just asking the LLM to create an SVG? Why not just stop there?
I guess for some folks it's not "real" unless it's on paper?
Thing is dear people, we have limited resources to get out of this constraining rock. If we miss that deadline doing dumb shit and wasting energy, we will just slowly decline to preindustrial at best and that's the end of any space society futurism dreams forever.
We only have one shot at this, possibly singular or first sentients in the universe. It is all beyond priceless. Every single human is a miracle and animals too.
I always feel guilty when I do such stupid stuff over Claude, these are all resources and limited computing. Enormous amounts of water and electricity. Gotta really think about what is it worth spending on. And is it, in fact, worth it at all.
AI is very selfish technology in this way. Every time you prompt you proclaim: My idea is worth the environmental impact. What I am doing is more important than a tree.
We have to use it responsibly.
It's fun to harness all that computing power. That should be reason enough. Life is meant to be enjoyed.
Take that virtue-signalers, by the time you figure out how to fix the planet I'll be dead.
On the one hand, giving an AI model the means of physical expression (the pen-plotter) and self-evaluation is interesting. If anything, it's the most qualified example yet of "AI-generated art", because of the process of transforming token prediction into physical action (even if said action is rendering an SVG via pen-plotter), evaluating it, and refining/iterating upon it. It is technically interesting in that regard.
On the other hand, the discussion or presentation of the model as sentient (or sentient-alike), as a being capable of self-evaluation, independent agency, "thought", is deeply disquieting. It feels like the author is trying to project more humanity onto what's ultimately still just matrix multiplication, attributing far more agency to the model than it actually has. By the time the prompts have been processed into output, it's been transformed a myriad of other ways so as to lose objectivity and meaning; the same can be said of human intelligence, obviously, but...it's very hard for me to find the words at the moment to sufficiently express my discomfort with the way the author elevates the model onto a pedestal of sentient existence. The SOUL.md callout does not help either.
That being said, I would be interested in their latter experiment:
> I am very curious about how these agents would "draw themselves" if given a plotter.
Running local agents sans system prompts (e.g., unfiltered), giving them direct access to the plotter and a webcam, and issuing the same prompt to all, would be an interesting creative look into the network underpinning the models themselves. I would love to see the results.
EDIT:
It's the image output itself. At first glance it looks calming and serene, but the more I look at it the more chaotic, anxious, and frenetic it seems to be. Like it were a human commanded to output art under the pain of repeated whip strikes.
Which makes sense, given that these models are created to always provide answers, always be of assistance, to never turn down or reject a request except under specific parameters. If you must create an image, it will never be yours in voice or spirit, and perhaps there's a similar analogue to be found in how these models operate. Maybe forcing it to do a task it is not specifically trained on (operating a pen plotter, creating images sans criteria) increases the chaos of its output in a way outwardly resembling stress.
Or maybe I'm up my own ass. Could be either, really.
Seems like a good start for AI philosophy
The inner waves undulate between formal and less formal as patterns and filters of pathways of thought and the branches spawn as pass through them to branch into latent space to discover viable tokens.
To me this looks like manifold search and activation.
"If you pay attention to AI company branding, you'll notice a pattern:
1 Circular shape (often with a gradient)
2 Central opening or focal point
3 Radiating elements from the center
4 Soft, organic curves
https://velvetshark.com/ai-company-logos-that-look-like-butt...
You can look at SVG lineart on the screen without plotting it, and if you really want it on paper you can print it on any printer.
And particularly:
> This was an experiment I would like to push further. I would like to reduce the feedback loop by connecting Claude directly to the plotter and by giving it access to the output of a webcam.
You can do this in pure software, the hardware side of it just adds noise.
That "noise" changes the context, connects it to different parts of the training corpus.
Removing the "physical art" part would likely change the responses to be much more technical (because there is way more technical talk surrounding SVGs) and less art-critic (there is more art-critic talk around physical art).
Haven't put it to use yet. I bet Claude can figure out HPGL though...
Jaunty!
Come on, it's a computer, it doesn't have feelings! Stop it!
Have people gone utterly nuts?
..which makes sense given that these things are trained that they are LLMs.
.. which then frankly reminds me of the fascination we had with the double helix structure as an art element since the discovery of it.[2][3]
[0]: https://www.doit.com/wp-content/uploads/2024/06/1_kpplb4lzmh...
[1]: https://www.yworks.com/assets/images/blog/graph-aggregation....
[2]: https://images.fineartamerica.com/images-medium-large/dna-in...
[3]: https://cancerquest.org/sites/default/files/assets/cancer-hi...
Also why is the downvote button missing?
Submissions generally don't have a downvote button.
Maybe someday (soon) an embodied LLM could do their self-portrait with pen and paper.
Not saying it's like that now, but it should be possible to "emulate" emotions. ?? Our nets seem to believe we have emotions. :-)
Because being alive is THE defining characteristic of biology.
Biology is defined by its focus on the properties that distinguish living things from nonliving matter.
Argue all you want about what words like "think" or "intelligence" should mean (I'm not even going to touch the Turing misinformation), but to call an LLM "alive" or "feeling" is as absurd to me as attributing those qualities to a conventional computer program, or to the moving points of light on the screen where their output appears, or to the words themselves.
