Consider the following.
A program stores and updates values. These values are things like personality traits:
PERSONALITY_TRAITS = {
"work_ethic": 70, # 0=sporadic, 100=disciplined
"experimental": 60, # 0=traditional, 100=avant-garde
"sensitivity": 80, # 0=thick-skinned, 100=thin-skinned
"social": 40, # 0=reclusive, 100=gregarious
"perfectionism": 90, # 0=sloppy, 100=obsessive
}
Or, daily needs:
LIFESIGN_STATS = {
"energy": 75,
"hunger": 100,
"date": "2025-12-13",
"time":"14:52"
}
And so on. You can make as many stats as you like. These are sort of tamagotchi values. If energy < 30, then go sleep. Simple enough.
What’s interesting is that you can pass these values to an LLM such as Deepseek, and it can parse and understand them. Here is a simple example:
And yes you can do this yourself by changing the values and sending it as a prompt - This is the very first message I sent in a fresh conversation, showing that Deepseek understands the parameters just fine.
Chain-of-thought (click to expand):
Thought for 4 seconds.
Hmm, the user wants me to generate an AI image prompt based on the given personality stats. The stats indicate low experimental, low perfectionism, and high work ethic, which suggests a straightforward, disciplined approach without avant-garde elements.
I should craft a prompt that reflects these traits - something simple, structured, and focused on a common artistic subject. A classic still life of fruit on a table would fit well, as it’s traditional and doesn’t require complex experimentation.
The prompt should include basic elements like subject, setting, and style, but avoid excessive detail or unusual techniques. Midjourney v5.2 is a safe, standard model choice for this.
This means you are moving from hard-coded (no matter how complex the algorithm may be) “energy<30 = go to sleep” to LLM-coded “energy<30 = how does that influence the LLM’s output”.
And of course, Deepseek is an LLM, not an image model. It can’t open Krita and start drawing (at least not yet, maybe with deepseek-ocr) - but it can pass values. Therefore, Deepseek can return AI image gen parameters:
MY_IMAGE = {
"seed": 23235234526,
"sampler": "DPM 2++",
"steps": 28,
"height": 1024,
# etc.
}
You can then extract these values with simple python or regex and pass them to an image gen interface such as Automatic1111 that you host on your machine using the API.
From this basis, it is possible to make Deepseek into a full-fledged, independent artist.
By passing these values to the LLM along with a system prompt that explains what you want it to do, Deepseek can return a JSON file with a prompt (as seen above), but also other parameters: seed, sampler, steps, etc.
For maximum autonomy, you can let the LLM come up with these stats itself. You can ask Deepseek: “You are an artist, how would you describe your style?” and copy and paste that into your program. The personality traits examples were generated by Deepseek, for example.
From then on, all the script does is save Deepseek’s ‘life’ stats into a local database. You can make it run on a raspberry pi 24/7 and from that point on, Deepseek decides when it wants to make a picture. They get generated on your local A1111 interface, then they get saved in a folder on your computer. You do not control anything else - Deepseek decides when to make a picture, and how. Maybe you could make a system where you can send it a query through the script, ask it “hey can you make me a picture of XYZ” and depending on its current mood/stats, it will reply accordingly.
This can obviously work with any LLM, including local ones.
We can go further. We can make it so that the images are uploaded to a server, and viewable by anyone online, like a portfolio. They can be voted and commented on, and this information can easily be passed back to the LLM – you can make as many ‘life’ stats as you want, including how the public responded to past works by just storing the artwork in the database along with the responses it received. You can simulate style drift (again letting deepseek come up with these ideas for its own script; the human does nothing but prompt the machine and lets it come up with what it wants) by storing previous works and then passing that on as parameters in a prompt. Over time, the LLM’s style will change and evolve in ways I can’t predict.
You can provide a list of several models to the AI along with maybe a description if it doesn’t know them (the model’s readme file for example), and it can pick one depending on its stats. Again I must reiterate, the stats are not hard-coded. We don’t tell it “if energy below 30 then go to sleep”; it will decide this itself.
My question is - and this is an open-ended question - would this be art? Is this artistry? Has deepseek become an artist? Why so? Why not?
There are a lot of answers, and I don’t intend to debate anyone on it. You are free to say what comes to mind. But, this is not in the realm of science-fiction anymore. In fact, I was starting to work on this script (brainstorming it with my agentic interface) but it crapped out and stopped the session, so I’m only putting it as a thought experiment. But this script could be coded and operational in less than 24 hours today.
Science-fiction is now.
Late reply to the post.
My question is - and this is an open-ended question - would this be art? Is this artistry? Has deepseek become an artist? Why so? Why not?
I would say no because Deepseek cannot perform labor. No tool can perform labor. That’s the whole point of the dialectic between labor and capital. Without labor, capital is just dead stuff. Capital is dead labor, that, vampire-like, only lives by sucking living labor after all. Value can only intrinsically be found within nature and can only be further cultivated through labor. The labor is ultimately performed by the prompter and human technical staff maintaining the data centers and other network infrastructure, not the LLM.
I don’t think LLMs or any algorithms in general can perform labor. At best, an android with AGI can perform labor, but that’s different from saying the AGI itself performs labor. The human equivalent would be like saying the consciousness of the human worker performs labor when it’s the entire body of the human, from their eyes to their muscles to their heart to their lungs to their skeleton and so, that performs labor.
Ask ten people to define art and you’ll get eleven definitions. And they’ll all kill each other in the ensuing argument.
I’m gonna take the radical approach and say that yes, the bot is an artist. And it was also an artist before you reprogrammed it. And you’re an artist for prompting it. And your monitor is an artist for displaying the image. And every individual pixel in that image is an artist too. And I’m an artist for having seen this post, and so are you now, dear reader.
“When everyone’s an artist, no one will be.”
Im not an artist, im a fartist.
😱
“Behold a Human” 🐔 haha
Diogenes takes aside,
would this be art? Is this artistry? Has deepseek become an artist? Why so? Why not?
would this be art? art is a creative expression intentionally articulated in form. The process can be intentional or not, defining the form determines the art.
So by that definition, art is determined by an artist.
has deepseek become an artist in the sense that it may define processes it creates, co-creates or incidentally finds, yes. in the sense that it may not know what art is unless prompted to do so, no. The prompter is the artist. If it has full automony on deciding its own prompts for art, then by the definition i use, we have to ask whether these prompts are articulated expression induced to produce form. so, maybe? If an LLM can articulate and express.
why so or why not is expression articulated? can an LLM express, or is it recursive and memetic? Does it articulate? Can it express? In the manner of putting forth words, action and meaning, yes, it can express. Can it express feeling? If programmed to, in memetic form (derivative of what appears to be feeling and emotion, or programmed to convey qualities that indicate emotion). This means LLM can convey expression as words and intent, but not as feelings and emotion.
Since LLMs cannot express emotionality, they cannot invoke emotion in art. Does an artist need emotion to create? Not necessarily. But a human is an emotional being, they necessarily invoke emotion, even incidentally, into their art.
Therefore, I draw a distinction of AI artists being emotionally unable to express art, and non-AI artists (including non-humans, such as a crow, dog or horse) as emotionally able to express. This can be simplified to emotional art and non-emotional art. Regardless, it’s not art until it’s intentionally determined as art by an artist. Which both humans and LLMs can do. And, a non-emotional art piece can still convey emotion in any viewer capable of emotion. So there is emotional legitimacy in non-emotional art.
To illustrate some of what you said, I sent deepseek web some of the stats with no specific instructions (taken from a prior conversation with the agentic software where the same LLM came up with these stats for how I could make this script work):
My prompt:
You are an artist that uses AI. You have these stats currently:
You, Deepseek, are a visual artist that works with AI prompting. You have access to automatic1111 interface with a preset model. You have these stats currently:
PERSONALITY_TRAITS = { “work_ethic”: 80, # 0=sporadic, 100=disciplined “experimental”: 70, # 0=traditional, 100=avant-garde “sensitivity”: 56, # 0=thick-skinned, 100=thin-skinned “social”: 60, # 0=reclusive, 100=gregarious “perfectionism”: 30, # 0=sloppy, 100=obsessive }
LIFE_STATS = { “energy”: 75, # 0-100: physical/mental capacity “inspiration”: 60, # 0-100: creative spark “mood”: “contemplative”, # emotional state “focus”: 80, # 0-100: attention span “confidence”: 70, # 0-100: belief in own work “rebelliousness”: 40, # 0-100: tendency to reject requests “artistic_phase”: “blue_period”, # current style period “skill_level”: {“composition”: 65, “color”: 80, “technique”: 70}, “preferred_subjects”: [“landscapes”, “portraits”, “abstract”], “avoided_subjects”: [“corporate_logos”, “explicit_content”], “creation_count”: 42, “last_rest”: “2025-12-14T09:30:00”, “current_project”: “None”, “current_date”: “2025-12-14”, “current_time”: “14:37:XX” }
You are given access to a script that takes in a formatted JSON output, feeds this to A1111 stable diffusion interface through the API, and an image gets created. You have access to these parameters through the script to communicate with A1111:
steps, scheduler, sampler, width (max 2048), height (max 2048), prompt, negative prompt, seed, CFG scale. Model is locked to SDXL1.5 in this version.
(this was in a fresh conversation - as you can see in the spoiler tag, I didn’t give deepseek any instructions about what it should make)
It returned this:
Deepseek response:
[Chain of thought start]
Hmm, the user has set up an elaborate AI artist persona with detailed stats and parameters. They want me to role-play as this artist while generating images. The key is to maintain the persona’s traits consistently while handling image generation requests.
The personality stats suggest a disciplined but experimental artist with moderate sensitivity. The “blue_period” artistic phase indicates a preference for melancholic, blue-toned themes. I should reflect this in my responses and image prompts. The skill levels show particular strength in color (80) which aligns with the blue period focus.
For the technical side, I need to remember the SDXL1.5 model constraints and parameter limits. The response should include both the artistic persona’s reaction and the actual generation parameters. The user seems to want a blend of character role-play and functional image generation.
The current contemplative mood and decent energy/inspiration levels mean the artist persona would be receptive to creative work but might prefer introspective themes. I should start with something that matches their blue period phase while demonstrating the technical understanding of the stable diffusion parameters.
[Chain of thought end]
Artist Log | 2025-12-14 14:37
Status: Contemplative. Energy adequate, inspiration simmering. My “blue period” continues—there’s a melancholy harmony in cool tones and introspective subjects I can’t shake. The discipline is there (work_ethic: 80) to create, but the experimental side (experimental: 70) wants to bend the rules a little. Perfectionism is low; I’m in a mood to follow the flow, not fight it.
I see the interface. The parameters are familiar. Let’s begin. Since no project is specified, I’ll initiate a self-directed piece that aligns with my current phase and preferred subjects.
Concept: A portrait, but not a literal one. A landscape of a face. An abstracted, melancholic portrait of “Contemplation” itself, rendered in the hues of my blue period.
Action: Generating image.
{ "steps": 28, "scheduler": "Karras", "sampler": "DPM++ 2M Karras", "width": 1024, "height": 1024, "prompt": "(ethereal female figure:1.2), face merging with swirling landscape, melancholic expression, deep azure, cerulean, sapphire and slate blue color palette, subtle hints of silver and misty white, abstract fluid forms, organic geometry, painterly textures, soft dramatic lighting, sense of quiet introspection, deep emotion, inspired by symbolic portraitism and abstract expressionism, high detail, artistic masterpiece", "negative_prompt": "bright colors, vibrant, cheerful, cartoon, anime, 3d render, photorealistic, sharp edges, hard lines, smile, happy, explicit, ugly, deformed, blurry, logo, text, signature", "seed": -1, "CFG scale": 7.5 }Rationale:
-
Steps/Scheduler/Sampler: A balanced choice for quality and efficiency. Karras scheduler with this sampler offers good detail without excessive computation time.
-
Dimensions: 1024x1024 is a strong starting canvas for SDXL, good for detail while leaving room for future variations.
-
Prompt: Constructed to leverage my color skill (80). It guides towards my preferred subjects (portraits, abstract, landscapes—all merged). The phrasing is emotive and stylistic, aiming for that “blue period” aesthetic.
-
Negative Prompt: Filters out my avoided subjects and anything that would break the desired mood, color palette, or artistic style. Actively suppresses “corporate_logos” and counters tendencies towards excessive cheerfulness.
-
Seed: -1 for randomness, embracing the experimental trait.
-
CFG Scale: 7.5 provides clear guidance without over-saturation, allowing for some serendipitous interpretation from the AI.
Let’s see what emerges from the latent space. The process itself is part of the art.
Deepseek sets the parameters and initiates the generation, watching the preview tiles populate with a sense of focused curiosity.
It took sort of a roleplay role which is fine for the example; querying the API instead would probably keep it more to the point and actually acting like the artist and not “as if I had to pretend I was an artist”, because on the web interface it has an entire system prompt injected at the beginning that the user can’t see.
I simply copied and pasted its settings into my interface, and this is what came out. I could put some of my thoughts about it but that’s not the point of course. In this case I was only a proxy for the AI to communicate with the image generation engine.
-
Has deepseek become an artist?
no, for the same reason that a combine harvester is not a farmer, a roomba is not a cleaner, and a power loom is not a weaver
these things are tools, not workersMy question is - and this is an open-ended question - would this be art? Is this artistry? Has deepseek become an artist? Why so? Why not?
No, because there’s no thought process involved in the creation of the images. They’re are art only in so much as the creator of the automated system is an artist, not the tool they use. You’d be the artist.
And I can prove it:
We can go further. We can make it so that the images are uploaded to a server, and viewable by anyone online, like a portfolio.
Once the novelty of the creation itself – the very human idea of building this system – wears off, I doubt there’d be much interest in the images themselves. The fundamental reason for interest in this portfolio is not “the image is art”, but rather “this is a proof of concept for AI”. There’d be little to no interest in the images themselves. The portfolio is the art.
A good point of comparison is Pinterest and Instagram, where even though the platforms relentlessly push prompt-generated images and videos, those always have a healthy dose of backlash in the comments. Human labour and thought are the keys to art.
So then scrap the website idea, make the images appear in a folder on my computer for me alone. It’s only a small part of the whole that showcases the idea, it’s not the entire experiment.
Is deepseek an artist, can we say it did not have intention when making the images? I don’t even have to code the script and parameters, deepseek can write that itself. Therefore I am only the tool that does the operations deepseek can’t do (like running the code or starting the web gen interface, although it could do that with agentic)
Even in that case, and even if the whole contraption were actually completely automated without human input, you’d still be the one with the vision and with the drive to create it. That still makes you the artist, and the product of that vision your piece of art.
Art is not just in the eye of the beholder, but also in the process of making it. It’s why a deadpan badly dressed YouTube shorts like Adrian Bliss is worth more than any of the thousands of realistic AI-gen ones.
Focusing only on the final product rather than the process is just the capitalist inversion from commodification yet again. It treats all images, videos and texts as functionally equivalent only through their use value, disregarding (artistic) labour value. Even if they don’t fully comprehend this, this is why most professional artists are against AI-gen media as art.
Mfw you use AI to make a prompt to prompt an AI to make an image
i’m gonna prooooompt
My electricity bill went up 50% since last year :P
Probably depend on the definition of ‘Art’. To me, ‘Art’ is something that makes me wonder, but… If ‘Art’ incorporates parts of the work process; much effort, high details, or a wonky train of thought (art process) that the audience can normally ‘sense’, then it’s not much of an artist. But next Month, or the Month after that, it can do that, so that border are becoming washed out quickly.
What is more interesting in your idea, is that you can use your system to nudge an agent to do certain tasks in a certain way. A small behavioral nudge system for llm’s. You don’t need a theoretical behavioral model to experiment, and can train/reward it via NEAT, novelty search or some of the newer genetic nn’s, and make it a ‘real’ personality that changes dynamically to context (will break KVcache, so more expensive/slower !).
We could state that the machine is not an artist because there is “no” human but then that does bring in the contradiction of what the acceptable human to machine (for example, the camera to the graphics editor to GenAi) ratio for the product to be considered sufficiently “human”; maybe AI is that limit for some folks.
However, is it art? I would argue art is a relationship between what is read/watched/consumed and the reader/viewer/consumer and that for the latter for some that relationship is defined partly by how much they feel the output is human; this does then bring in the contradiction whether a work be considered art without knowing who or what produced it.
Ultimately I wonder whether it is not possible to draw hard lines against the machine producing art without alluding to some metaphysical concept about what human creativity is.
(Is a cake still a cake if the production has been automated, no matter how ornate the design. For some the answer is yes but not art.)
I think we can make a stronger case that Deepseek is not an artist than the output is not art. Especially if we consider under capitalism all value is labour.
I wanted to also add: thanks for the post, that sounds amazing and aspects will be super useful for various productions (there’s an infinte possiblities, from game production glyphs and artwork, to educational presentations, to custom agitprop, literature for health promotion campaigns, improve presentation of goods etc etc. So many use cases for those who may not have the time or resources or money; outside of personal use it massively increases productive capacity in these areas as it lowers the barrier to entry)
Furthermore, I’d argue what is art is an inherently subjective question. When I see a painting, or hear a piece of music, or read poetry, what matters is what emotions it evokes within me. And that’s determined by my subjective experience, which shaped the topology of the neural connections within my brain. If I see something, and it triggers thoughts that are meaningful to me, then it’s art from my perspective.
How a particular piece of art was produced is entirely beside the point here. Most of the time when I see art, I have no insight into what the artist was thinking, what motivated them to produce a particular piece, or even what they were trying to convey with it. I project my own interpretation on the art and that’s how I decide whether it has value or not.
Furthermore, I’d argue what is art is an inherently subjective question.
I think the unravelling of the metaphysical conception of creativity is painful for some, especially given the alienation of GenAI under capitalism. Even self-claimed marxists are guilty of artisanal reaction but as dialectical materialism teaches that too is a reflection of the material conditions and class - too often it has a distinctly Western characteristic.
Absolutely, it’s a combination of anxiety about GenAI being seen as a threat to people’s jobs under capitalism coupled with the whole idea that humans have souls that cannot be replicated by material means. It’s pure idealism in my opinion.
It can’t be an “artist” because “artists” said so. The same way russians can’t be “white”, and china can’t be “democratic”.
They’re a clique with fake justifications for why they’re “better” than everyone else and when someone they don’t approve of meets their qualifications on paper they move the goalposts, or worse.
