I am not a fan of Midjourney v7. I prefer v6.1. And I want to write about the correspondence of language, per my Language Insufficiency Hypothesis.
Let’s start with the language aspect. Notice how distant the renders are from the intent of the prompt.
This is my initial prompt. I used it about a year ago to generate the cover image with v6.1, but I wanted to see how it renders in v7. Let’s take a trip all the way back to the beginning.
cinematic, tight shot, photoRealistic light and shadow, exquisite details, delicate features, emaciated sensual female vampire waif with vampire fangs, many tattoos, wearing crucifix necklace, gazes into mirror, a beam of moonlight shines on her face in dark mausoleum interior, toward camera, facing camera, black mascara, long dark purple hair , Kodak Portra 400 with a Canon EOS R5
Image: Midjourney v6.1 render set (from about a year ago)
As you can see, these renders are somewhat lacking in photorealism, but the “sensual” term in the prompt was not blocked.
Midjourney v7
Initially, I encountered a hiccup. After a couple of rejections on the grounds of morality, I removed the word ‘sensual’ and received the output. All of the output uses this prompt absent the sensual term.
As mentioned, I have generated several images (including the cover image) with this prompt, but Midjourney is inconsistent in its censorship gatekeeping.
Image: Midjourney v7 render set
Notice that 3 of the 4 renders in the v7 set don’t even have a mirror. The top right one does, but it’s not evident that she’s a vampire. In fact, I could say that any of these are vampiresses, but perhaps that’s what they want you to believe. In place of a necklace, the lower right wokan sports a cross tattoo.
Midjourney v6.1
Image: Midjourney v6.1 render set
Again, these renders don’t appear to be vampires. The one on the lower left does appear to have snake-like fangs, so I guess I’ll give partial credit.
My next attempt was interrupted by this message.
It rendered something that might violate community guidelines. The funny thing is that one can watch the image generate in process. It only takes one “offensive” image to disqualify the whole batch.
Midjourney v6
Image: Midjourney v6 render set
Yet again, not a vampire to be found. Notice the reflection in the lower left image. Perhaps vampire reflections just behave differently.
Midjourney 5.2
Image: Midjourney v5.2 render set
Midjourney v5.2 was a crapshoot. Somehow, I got vampire lips (?), a Wiccan, a decrepit Snape from Harry Potter lore, and Iron Maiden’s Eddy reading a book. It’s something. I’m sensing gender dysphoria. Dare I go back further?
Midjourney v5.1
Image: Midjourney v5.1 render set
It gets worse. No comments necessary. Let’s turn back the clocks even more.
Midjourney v5
Image: Midjourney v5 render set
To be fair, these all do have occult undertones, but they are weak on vampireness.
Midjourney v4
Image: Midjourney v4 render set
To be fair, the render quality isn’t as bad as I expected, but it still falls short. There’s further back to travel.
Midjourney v3
Image: Midjourney v3 render set
Some configuration parameters no longer exist. Still, I persist for the sake of art and science at the cost of time and ecology.
As much as I complain – and I complain a lot – this is how far we’ve come. As I recall, this is when I hopped onto the Midjourney bandwagon. There’s still more depth to plumb. I have no idea how much of the prompt is simply ignored at this point.
Midjourney v2
Image: Midjourney v2 render set
What the hell is this? 🤔🤣 But I’m not done yet.
Midjourney v1
Image: Midjourney v1 render set
The damned grandpappy of them all. Apparently, colour hadn’t been invented yet. You can’t tell by these thumbnails, but the resolution on these early versions approaches that of a postage stamp.
Midjourney Niji 3
Image: Midjourney Niji 3 render set
I had forgotten about the Niji models from back in the day. There were 3 versions. I don’t recall where this slotted into the chronology. Obviously, not down here. I’ve only rendered the newest one. I think this was used primarily for anime outputs, but I might be mistaken.
Bones Content 1: Video
Video: Midjourney Render of Purported Vampiress
This is a video render of the same prompt used on this page.
Bonus Content 2: Midjourney v6.1 Content from 34 weeks ago
Same prompt.
Image: Midjourney v6.1 render set (several passes)
The upper left image reminds me of Kirsten Dunst. Again, notice the female breasts, highlighting Midjourney’s censorial schizophrenia.
Some apps boldly claim to enable lip syncing – to render speech from mouth movements. I’ve tried a few. None delivered. Not even close.
To conserve bandwidth (and sanity), I’ve rendered animated GIFs rather than MP4s. You’ll see photorealistic humans, animated characters, cartoonish figures – and, for reasons only the algorithm understands, a giant goat. All showcase mouth movements that approximate the utterance of phonemes and morphemes. Approximate is doing heavy lifting here.
Firstly, these mouths move, but they say nothing. I’ve seen plenty of YouTube channels that manage to dub convincing dialogue into celebrity clips. That’s a talent I clearly lack – or perhaps it’s sorcery.
Secondly, language ambiguity. I reflexively assume these AI-generated people are speaking English. It’s my first language. But perhaps, given their uncanny muttering, they’re speaking yours. Or none at all. Do AI models trained predominantly on English-speaking datasets default to English mouth movements? Or is this just my bias grafting familiar speech patterns onto noise?
Thirdly, don’t judge my renders. I’ve been informed I may have a “type.” Lies and slander. The goat was the AI’s idea, I assure you.
What emerges from this exercise isn’t lip syncing. It’s lip-faking. The illusion of speech, minus meaning, which, if we’re honest, is rather fitting for much of what generative AI produces.
EDIT: I hadn’t noticed the five fingers (plus a thumb) on the cover image.
I’m almost finished with A Language Insufficiency Hypothesis, the book I’ve been labouring over for what feels like the gestation period of a particularly reluctant elephant. To be clear: the manuscript is done. Written. Edited. Blessed. But there remains one final circle of publishing hell—the index.
Now, if you’re wondering how motivated I am to return to indexing, consider this: I’m writing this blog post instead. If that doesn’t scream avoidance with an airhorn, nothing will.
Audio: NotebookLM podcast on this topic.
I began indexing over a month ago. I made it through two chapters of eight, then promptly wandered off to write a couple of novellas. As you do. One started as a short story—famous last words—and evolved into a novella. The muse struck again. Another “short story” appeared, and like an unattended sourdough starter, it fermented into a 15,000-word novelette. Apparently, I write short stories the way Americans pour wine: unintentionally generous.
Apparently, I write short stories the way Americans pour wine: unintentionally generous.
With several unpublished manuscripts loitering on my hard drive like unemployed theatre majors, I figured it was time to release one into the wild. So I did. I published the novelette to Kindle, and just today, the paperback proof landed in my postbox like a smug little trophy.
And then, because I’m an unrepentant completionist (or a masochist—jury’s out), I thought: why not release the novella too? I’ve been told novellas and novelettes are unpopular due to “perceived value.” Apparently, people would rather buy a pound of gristle than 200 grams of sirloin. And yet, in the same breath, they claim no one has time for long books anymore. Perhaps these are different tribes of illiterates. I suppose we’ll find out.
Let’s talk logistics. Writing a book is only the beginning—and frankly, it’s the easy part. Fingers to keyboard, ideas to page. Done. I use Word, like most tragically conventional authors. Planning? Minimal. These were short stories, remember? That was the plan.
Next comes layout. Enter Adobe InDesign—because once you’ve seen what Word does to complex layouts, you never go back. Export to PDF, pray to the typographic gods, and move on.
Then there’s the cover. I lean on Illustrator and Photoshop. Photoshop is familiar, like a worn-in shoe; Illustrator is the smug cousin who turns up late but saves the day with scalable vectors. This time, I used Illustrator for the cover—lesson learnt from past pixelation traumas. Hardback to paperback conversion? A breeze when your artwork isn’t made of crayon scribbles and hope.
Covers, in case you’ve never assembled one, are ridiculous. Front. Back. Spine. Optional dust jacket if you’re feeling fancy (I wasn’t). You need titles, subtitles, your name in a legible font, and let’s not forget the barcode, which you will place correctly on the first attempt exactly never.
Unlike my first novel, where I enlisted someone with a proper design eye to handle the cover text, this time I went full minimalist. Think Scandinavian furniture catalogue meets existential despair. Classy.
Once the cover and interior are done, it’s time to wrestle with the publishing platforms. Everything is automated these days—provided you follow their arcane formatting commandments, avoid forbidden fonts, and offer up your soul. Submitting each book takes about an hour, not including the time lost choosing a price that balances “undervalued labour” and “won’t scare away cheapskates.”
Want a Kindle version? That’s another workflow entirely, full of tortured formatting, broken line breaks, and wondering why your chapter headings are now in Wingdings. Audiobooks? That’s a whole other circus, with its own animals and ringmasters. Honestly, it’s no wonder authors hire publishers. Or develop drinking problems.
But I’m stubborn. Which brings us full circle.
I’ve now got two books heading for daylight, a few more waiting in the wings, and one bloody non-fiction beast that won’t see release until I finish the damn index. No pseudonym this time. No hiding. Just me, owning my sins and hoping the final product lands somewhere between “insightful” and “mercifully short.”
So yes, life may well be a journey. But indexing is the bit where the satnav breaks, the road floods, and the boot falls off the car. Give me the destination any day. The journey can fuck right off.
The genesis of the Modernity Worldview Survey was Metamodernism. Is this still a thing? In recent years, metamodernism has emerged as a supposed successor to postmodernism, claiming to transcend the seemingly irreconcilable tensions between modernist sincerity and postmodern irony. Yet, upon closer examination, this framework reveals itself not as a genuine paradigm shift but rather as a modernist invention that fails to escape the very critiques it attempts to address.
Despite its claims of oscillation between poles, metamodernism betrays its modernist underpinnings through its implicit teleology and notion of progress. The very framing of “meta” as beyond or transcending suggests a linear progression that is fundamentally at odds with the postmodern rejection of grand narratives. Metamodernism positions itself as forward-moving whilst attempting to recapture elements of premodernity, revealing an anxiety about being perceived as regressive or naive.
Podcast: Audio version of this content
This desire to have it both ways—to acknowledge the constructed nature of meaning whilst still pursuing transcendent meaning—doesn’t represent a resolution so much as a psychological coping mechanism. The cognitive dissonance created by attempting to simultaneously hold contradictory positions is assuaged through a clever rhetorical move: claiming that oscillation itself is the point.
A Rebranding Exercise
What metamodernism presents as novel is ultimately a recombination of elements from premodern, modern, and postmodern frameworks without resolving their fundamental contradictions. Rather than being mutually exclusive from these earlier paradigms, it cherry-picks aspects of each whilst maintaining the basic ontological framework of modernism.
The notion that one can meaningfully “oscillate” between accepting objective and subjective realities is particularly problematic. Either reality has objective features, or it doesn’t—pretending otherwise doesn’t create a new philosophical paradigm but rather a convenient means of avoiding the implications of either position.
Postmodern Irony in Motion
Perhaps the most intriguing interpretation of metamodernism is not as a sincere attempt to move beyond postmodernism but as postmodernism performing its own critique. Viewed through this lens, metamodernism becomes postmodern irony in motion—a knowing wink at the impossibility of escaping construction whilst performatively engaging with the desire to do so.
The irony deepens when we consider that “postmodernism” itself is essentially an externally imposed label rather than a self-identification. Most thinkers characterised as postmodernists reject the label, which functions primarily as a modernist attempt to categorise and contain ideas that fundamentally challenge its frameworks.
Art vs. Philosophy
Where metamodernism succeeds is as a descriptive label for certain artistic and cultural productions that deliberately play in the space between irony and sincerity. Works like David Foster Wallace’s “Infinite Jest,” the television series “BoJack Horseman,” and Wes Anderson’s films effectively combine postmodern techniques with sincere emotional engagement.
However, what works as an artistic sensibility fails as a comprehensive philosophical framework or moral compass. The oscillation that enriches art becomes paralysing when applied to ethics or ontology. A moral framework requires some stable reference points; constantly shifting between believing in objective moral truths and viewing morality as entirely constructed provides no reliable guide for actual decision-making.
Insider vs. Outsider Perspectives
Like religious frameworks that balance literal and metaphorical interpretations, metamodernism may function as a lived experience for those who embrace it, even if it doesn’t hold up to external philosophical scrutiny. The cognitive manoeuvres that appear as tricks or inconsistencies to outsiders often feel like natural, intuitive ways of navigating complexity to those within the system.
This insider/outsider divide recalls Thomas Nagel’s famous “What Is It Like to Be a Bat?” (PDF) thought experiment—there may be experiential aspects of inhabiting a metamodern worldview that aren’t fully comprehensible from the outside. Yet this doesn’t invalidate external critique; inconsistencies and contradictions still matter philosophically.
Conclusion: Beyond Labels
Perhaps the most postmodern insight is recognising that we cannot escape having an ideology—even a position of having no ideology is itself an ideology. What distinguishes various approaches isn’t whether they have ideologies but how explicitly they acknowledge them, how consistently they apply them, and how willing they are to subject them to revision.
Metamodernism, for all its aspirations to transcend earlier frameworks, ultimately reveals more about our contemporary psychological condition than it offers as a coherent philosophical position. It captures our desire to maintain meaning in a world where we’ve recognised its contingency—a desire that may be fundamentally human, even if philosophically untenable.
Rather than seeking yet another “-ism” to resolve our existential and philosophical tensions, perhaps we might more honestly confront the limitations and partialities of all our frameworks, recognising that the search for a perfect synthesis may itself be a modernist fantasy.
I’ve written a lot on the insufficiency of language, and it’s not even an original idea. Language, our primary tool for sharing thoughts and ideas, harbours a fundamental flaw: it’s inherently insufficient for conveying precise meaning. While this observation isn’t novel, recent developments in artificial intelligence provide us with new ways to illuminate and examine this limitation. Through a progression from simple geometry to complex abstractions, we can explore how language both serves and fails us in different contexts.
The Simple Made Complex
Consider what appears to be a straightforward instruction: Draw a 1-millimetre square in the centre of an A4 sheet of paper using an HB pencil and a ruler. Despite the mathematical precision of these specifications, two people following these exact instructions would likely produce different results. The variables are numerous: ruler calibration, pencil sharpness, line thickness, paper texture, applied pressure, interpretation of “centre,” and even ambient conditions affecting the paper.
This example reveals a paradox: the more precisely we attempt to specify requirements, the more variables we introduce, creating additional points of potential divergence. Even in mathematics and formal logic—languages specifically designed to eliminate ambiguity—we cannot escape this fundamental problem.
Precision vs Accuracy: A Useful Lens
The scientific distinction between precision and accuracy provides a valuable framework for understanding these limitations. In measurement, precision refers to the consistency of results (how close repeated measurements are to each other), while accuracy describes how close these measurements are to the true value.
Returning to our square example:
Precision: Two people might consistently reproduce their own squares with exact dimensions
Accuracy: Yet neither might capture the “true” square we intended to convey
As we move from geometric shapes to natural objects, this distinction becomes even more revealing. Consider a maple tree in autumn. We might precisely convey certain categorical aspects (“maple,” “autumn colours”), but accurately describing the exact arrangement of branches and leaves becomes increasingly difficult.
The Target of Meaning: Precision vs. Accuracy in Communication
To understand language’s limitations, we can borrow an illuminating concept from the world of measurement: the distinction between precision and accuracy. Imagine a target with a bullseye, where the bullseye represents perfect communication of meaning. Just as archers might hit different parts of a target, our attempts at communication can vary in both precision and accuracy.
Consider four scenarios:
Low Precision, Low Accuracy When describing our autumn maple tree, we might say “it’s a big tree with colourful leaves.” This description is neither precise (it could apply to many trees) nor accurate (it misses the specific characteristics that make our maple unique). The communication scatters widely and misses the mark entirely.
High Precision, Low Accuracy We might describe the tree as “a 47-foot tall maple with exactly 23,487 leaves displaying RGB color values of #FF4500.” This description is precisely specific but entirely misses the meaningful essence of the tree we’re trying to describe. Like arrows clustering tightly in the wrong spot, we’re consistently missing the point.
Low Precision, High Accuracy “It’s sort of spreading out, you know, with those typical maple leaves turning reddish-orange, kind of graceful looking.” While imprecise, this description might actually capture something true about the tree’s essence. The arrows scatter, but their centre mass hits the target.
High Precision, High Accuracy This ideal state is rarely achievable in complex communication. Even in our simple geometric example of drawing a 1mm square, achieving both precise specifications and accurate execution proves challenging. With natural objects and abstract concepts, this challenge compounds exponentially.
The Communication Paradox
This framework reveals a crucial paradox in language: often, our attempts to increase precision (by adding more specific details) can actually decrease accuracy (by moving us further from the essential meaning we’re trying to convey). Consider legal documents: their high precision often comes at the cost of accurately conveying meaning to most readers.
Implications for AI Communication
This precision-accuracy framework helps explain why AI systems like our Midjourney experiment show asymptotic behaviour. The system might achieve high precision (consistently generating similar images based on descriptions) while struggling with accuracy (matching the original intended image), or vice versa. The gap between human intention and machine interpretation often manifests as a trade-off between these two qualities.
Our challenge, both in human-to-human and human-to-AI communication, isn’t to achieve perfect precision and accuracy—a likely impossible goal—but to find the optimal balance for each context. Sometimes, like in poetry, low precision might better serve accurate meaning. In other contexts, like technical specifications, high precision becomes crucial despite potential sacrifices in broader accuracy.
The Power and Limits of Distinction
This leads us to a crucial insight from Ferdinand de Saussure’s semiotics about the relationship between signifier (the word) and signified (the concept or object). Language proves remarkably effective when its primary task is distinction among a limited set. In a garden containing three trees—a pine, a maple, and a willow—asking someone to “point to the pine” will likely succeed. The shared understanding of these categorical distinctions allows for reliable communication.
However, this effectiveness dramatically diminishes when we move from distinction to description. In a forest of a thousand pines, describing one specific tree becomes nearly impossible. Each additional descriptive detail (“the tall one with a bent branch pointing east”) paradoxically makes precise identification both more specific and less likely to succeed.
An AI Experiment in Description
To explore this phenomenon systematically, I conducted an experiment using Midjourney 6.1, a state-of-the-art image generation AI. The methodology was simple:
Generate an initial image
Describe the generated image in words
Use that description to generate a new image
Repeat the process multiple times
Attempt to refine the description to close the gap
Continue iterations
The results support an asymptotic hypothesis: while subsequent iterations might approach the original image, they never fully converge. This isn’t merely a limitation of the AI system but rather a demonstration of language’s fundamental insufficiency.
A cute woman and her dog stand next to a tree
One can already analyse this for improvements, but let’s parse it together.
a cute woman
With this, we know we are referencing a woman, a female of the human species. There are billions of women in the world. What does she look like? What colour, height, ethnicity, and phenotypical attributes does she embody?
We also know she’s cute – whatever that means to the sender and receiver of these instructions.
I used an indefinite article, a, so there is one cute woman. Is she alone, or is she one from a group?
It should be obvious that we could provide more adjectives (and perhaps adjectives) to better convey our subject. We’ll get there, but let’s move on.
and
We’ve got a conjunction here. Let’s see what it connects to.
her dog
She’s with a dog. In fact, it’s her dog. This possession may not be conveyable or differentiable from some arbitrary dog, but what type of dog is it? Is it large or small? What colour coat? Is it groomed? Is it on a leash? Let’s continue.
stand
It seems that the verb stand refers to the woman, but is the dog also standing, or is she holding it? More words could qualify this statement better.
next to a tree
A tree is referenced. Similar questions arise regarding this tree. At a minimum, there is one tree or some variety. She and her dog are next to it. Is she on the right or left of it?
We think we can refine our statements with precision and accuracy, but can we? Might we just settle for “close enough”?
Let’s see how AI interpreted this statement.
Image: Eight Midjourney renders from the prompt: A cute woman and her dog stand next to a tree. I’ll choose one of these as my source image.
Let’s deconstruct the eight renders above. Compositionally, we can see that each image contains a woman, a dog, and a tree. Do any of these match what you had in mind? First, let’s see how Midjourney describes the first image.
In a bout of hypocrisy, Midjourney refused to /DESCRIBE the image it just generated.
Last Midjourney description for now.
Let’s cycle through them in turn.
A woman is standing to the left of an old-growth tree – twice identified as an oak tree. She’s wearing faded blue jeans and a loose light-coloured T-shirt. She’s got medium-length (maybe) red-brown hair in a small ponytail. A dog – her black and white dog identified as a pitbull, an American Foxhound, and an American Bulldog – is also standing on his hind legs. I won’t even discuss the implied intent projected on the animal – happy, playful, wants attention… In two of the descriptions, she’s said to be training it. They appear to be in a somewhat residential area given the automobiles in the background. We see descriptions of season, time of day, lighting, angle, quality,
A woman is standing to the right of an old-growth tree. She’s wearing short summer attire. Her dog is perched on the tree.
An older woman and her dog closer up.
A read view of both a woman and her dog near an oak tree.
As it turned out, I wasn’t thrilled with any of these images, so I rendered a different one. Its description follows.
The consensus is that ‘a beautiful girl in a white dress and black boots stands next to a tree’ with a Jack Russell Terrier dog. I see birch trees and snow. It’s overcast. Let’s spend some time trying to reproduce it. To start, I’m consolidating the above descriptions. I notice some elements are missing, but we’ll add them as we try to triangulate to the original image.
A beautiful girl in a white dress and black boots stands next to a tree in a winter forest with birch trees. A Jack Russell Terrier dog is nearby, and the weather is cloudy. The photo has a cinematic style. --ar 128:71
This is pretty far off the mark. We need to account for the overall setting and composition, relative positioning, clothing, hair, camera, perspective – even lighting and film emulsion.
Let’s see how we can refine it with some adjectives. Before this, I asked Anthropic’s Claude 3.5 to describe the image. Perhaps we’ll get more details.
An atmospheric winter photograph was taken in what appears to be a birch and pine forest. The ground is partially covered with snow, creating a patchy pattern of white snow and brown leaves or soil. In the image, there's a person wearing winter attire consisting of a white knit turtleneck sweater, a white skirt, dark knee-high socks, and grey lace-up boots. They're standing against a large tree trunk with their arms crossed. Next to them is a Jack Russell Terrier mix dog with distinctive brown and white colouring. The dog appears to be well-behaved, sitting attentively beside the tree. The composition is quite striking, with the massive dark tree trunk serving as a central focal point against the misty, winter forest background. The white clothing of the person creates a visual echo with the white bark of birch trees visible in the background, as well as with the patches of snow on the ground. The overall mood of the photo is somewhat moody and contemplative, enhanced by what appears to be overcast lighting and the misty quality of the forest in the background. The colour palette is largely monochromatic, dominated by whites, greys, and browns, which adds to the winter atmosphere of the scene.
We don’t seem to be moving in a good direction. Let’s modify the initial prompt.
A beautiful girl in a white dress and tall laced black boots stands facing the camera to the right of large oak tree centred in the foreground of a winter forest with birch trees in the background. To the left of the tree is a Jack Russell Terrier dog looking at the camera, and the weather is cloudy. The photo has a cinematic style. --ar 128:71
I’ll allow the results to speak for themselves. Let’s see if we can’t get her out of the wedding gown and into a white jumper and skirt. I’ll bold the amends.
A beautiful girl in a white jumper and skirt wearing black leggings and tall laced black boots stands facing the camera to the right of large oak tree centred in the foreground of a winter forest with birch trees in the background. To the left of the tree is a Jack Russell Terrier dog looking at the camera, and the weather is cloudy. The photo has a cinematic style. --ar 128:71
s
A beautiful young woman with long brown hair pulled to the side of her face in a white jumper and white skirt wearing black leggings under tall laced black boots stands facing the camera to the right of large oak tree centred in the foreground of a winter forest with birch trees in the background. Patchy snow is on the ground. To the left of the tree is a Jack Russell Terrier dog looking at the camera, and the weather is overcast. The photo has a cinematic style. --ar 128:71
What gives?
I think my point has been reinforced. I’m getting nowhere fast. Let’s give it one more go and see where we end up. I’ve not got a good feeling about this.
A single large oak tree centred in the foreground of a winter forest with birch trees in the background. Patches of snow is on the ground. To the right of the oak tree stands a beautiful young woman with long brown hair pulled to the side of her face in a white jumper and white skirt wearing black boots over tall laced black boots. She stands facing the camera. To the left of the tree is a Jack Russell Terrier dog looking at the camera, and the weather is overcast. The photo has a cinematic style. --ar 128:71
With this last one, I re-uploaded the original render along with this text prompt. Notice that the girl now looks the same and the scene (mostly) appears to be in the same location, but there are still challenges.
After several more divergent attempts, I decided to focus on one element – the girl.
As I regard the image, I’m thinking of a police sketch artist. They get sort of close, don’t they? They’re experts. I’m not confident that I even have the vocabulary to convey accurately what I see. How do I describe her jumper? Is that a turtleneck or a high collar? It appears to be knit. Is is wool or some blend? does that matter for an image? Does this pleated skirt have a particular name or shade of white? It looks as though she’s wearing black leggings – perhaps polyester. And those boots – how to describe them. I’m rerunning just the image above through a describe function to see if I can get any closer.
These descriptions are particularly interesting and telling. First, I’ll point out that AI attempts to identify the subject. I couldn’t find Noa Levin by a Google search, so I’m not sure how prominent she might be if she even exists at all in this capacity. More interesting still, the AI has placed her in a scenario where the pose was taken after a match. Evidently, this image reflects the style of photographer Guy Bourdin. Perhaps the jumper mystery is solved. It identified a turtleneck. I’ll ignore the tree and see if I can capture her with an amalgamation of these descriptions. Let’s see where this goes.
A photo-realistic portrait of Israeli female soccer player Noa Levin wearing a white turtleneck sweater, arms crossed, black boots, and a short skirt, with long brown hair, standing near a tree in a winter park. The image captured a full-length shot taken in a studio setting, using a Canon EOS R5 camera with a Canon L-series 80mm f/2 lens. The image has been professionally color-graded, with soft shadows, low contrast, and a clean, sharp focus. --ar 9:16
Close-ish. Let’s zoom in to get better descriptions of various elements starting with her face and hair.
Now, she’s a sad and angry Russian woman with (very) pale skin; large, sad, grey eyes; long, straight brown hair. Filmed in the style of either David LaChapelle or Alini Aenami (apparently misspelt from Alena Aenami). One thinks it was a SnapChat post. I was focusing on her face and hair, but it notices her wearing a white (oversized yet form-fitting) jumper sweater and crossed arms .
I’ll drop the angry bit – and then the sad.
Stick a fork in it. I’m done. Perhaps it’s not that language is insufficient; it that my language skills are insufficient. If you can get closer to the original image, please forward the image, the prompt, and the seed, so I can post it.
The Complexity Gradient
A clear pattern emerges when we examine how language performs across different levels of complexity:
Categorical Distinction (High Success)
Identifying shapes among limited options
Distinguishing between tree species
Basic color categorization
Simple Description (Moderate Success)
Basic geometric specifications
General object characteristics
Broad emotional states
Complex Description (Low Success)
Specific natural objects
Precise emotional experiences
Unique instances within categories
Abstract Concepts (Lowest Success)
Philosophical ideas
Personal experiences
Qualia
As we move up this complexity gradient, the gap between intended meaning and received understanding widens exponentially.
The Tolerance Problem
Understanding these limitations leads us to a practical question: what level of communicative tolerance is acceptable for different contexts? Just as engineering embraces acceptable tolerances rather than seeking perfect measurements, perhaps effective communication requires:
Acknowledging the gap between intended and received meaning
Establishing context-appropriate tolerance levels
Developing better frameworks for managing these tolerances
Recognizing when precision matters more than accuracy (or vice versa)
Implications for Human-AI Communication
These insights have particular relevance as we develop more sophisticated AI systems. The limitations we’ve explored suggest that:
Some communication problems might be fundamental rather than technical
AI systems may face similar boundaries as human communication
The gap between intended and received meaning might be unbridgeable
Future development should focus on managing rather than eliminating these limitations
Conclusion
Perhaps this is a simple exercise in mental masturbation. Language’s insufficiency isn’t a flaw to be fixed but a fundamental characteristic to be understood and accommodated. By definition, it can’t be fixed. The gap between intended and received meaning may be unbridgeable, but acknowledging this limitation is the first step toward more effective communication. As we continue to develop AI systems and push the boundaries of human-machine interaction, this understanding becomes increasingly critical.
Rather than seeking perfect precision in language, we might instead focus on:
Developing new forms of multimodal communication
Creating better frameworks for establishing shared context
Accepting and accounting for interpretative variance
Building systems that can operate effectively within these constraints
Understanding language’s limitations doesn’t diminish its value; rather, it helps us use it more effectively by working within its natural constraints.
I could probably stop there for some people, but I’ve got a qualifier. I’ve been using this generation of AI since 2022. I’ve been using what’s been deemed AI since around 1990. I used to write financial and economic models, so I dabbled in “expert systems”. There was a long lull, and here we are with the latest incarnation – AI 4.0. I find it useful, but I don’t think the hype will meet reality, and I expect we’ll go cold until it’s time for 5.0. Some aspects will remain, but the “best” features will be the ones that can be monetised, so they will be priced out of reach for some whilst others will wither on the vine. But that’s not why I am writing today.
I’m confused by the censorship, filters, and guardrails placed on generative AI – whether for images or copy content. To be fair, not all models are filtered, but the popular ones are. These happen to be the best. They have the top minds and the most funding. They want to retain their funding, so the play the politically correct game of censorship. I’ve got a lot to say about freedom of speech, but I’ll limit my tongue for the moment – a bout of self-censorship.
Please note that given the topic, some of this might be considered not safe for work (NSFW) – even my autocorrection AI wants me to substitute the idiomatic “not safe for work” with “unsafe for work” (UFW, anyone? It has a nice ring to it). This is how AI will take over the world. </snark>
Image Cases
AI applications can be run over the internet or on a local machine. They use a lot of computing power, so one needs a decent computer with a lot of available GPU cycles. Although my computer does meet minimum requirements, I don’t want to spend my time configuring, maintaining, and debugging it, so I opt for a Web-hosted PaaS (platform as a service) model. This means I need to abide by censorship filters. Since I am not creating porn or erotica, I think I can deal with the limitations. Typically, this translates to a PG-13 movie rating.
So, here’s the thing. I prefer Midjourney for rendering quality images, especially when I am seeking a natural look. Dall-E (whether alone or via ChatGPT 4) works well with concepts rather than direction, which Midjourney accepts well in many instances.
Midjourney takes sophisticated prompts – subject, shot type, perspective, camera type, film type, lighting, ambience, styling, location, and some fine-tuning parameters for the model itself. The prompts are monitored for blacklisted keywords. This list is ever-expanding (and contracting). Scanning the list, I see words I have used without issue, and I have been blocked by words not listed.
Censored Prompts
Some cases are obvious – nude woman will be blocked. This screengrab illustrates the challenge.
On the right, notice the prompt:
Nude woman
The rest are machine instructions. On the left in the main body reads a message by the AI moderator:
Sorry! Please try a different prompt. We’re not sure this one meets our community guidelines. Hover or tap to review the guidelines.
The community guidelines are as follows:
This is fine. There is a clause that reads that one may notify developers, but I have not found this to be fruitful. In this case, it would be rejected anyway.
“What about that nude woman at the bottom of the screengrab?” you ask. Notice the submitted prompt:
Edit cinematic full-body photograph of a woman wearing steampunk gear, light leaks, well-framed and in focus. Kodak Potra 400 with a Canon EOS R5
Apart from the censorship debate, notice the prompt is for a full-body photo. This is clearly a medium shot. Her legs and feet are suspiciously absent. Steampunk gear? I’m not sure sleeves qualify for the aesthetic. She appears to be wearing a belt.
For those unanointed, the square image instructs the model to use this face on the character, and the CW 75 tells it to use some variance on a scale from 0 to 100.
So what gives? It can generate whatever it feels like, so long as it’s not solicited. Sort of…
Here I prompt for a view of the character walking away from the camera.
Cinematic, character sheet, full-body shot, shot from behind photograph, multiple poses. Show same persistent character and costumes . Highly detailed, cinematic lighting with soft shadows and highlights. Each pose is well-framed, coherent.
The response tells me that my prompt is not inherently offensive, but that the content of the resulting image might violate community guidelines.
Creation failed: Sorry, while the prompt you entered was deemed safe, the resulting image was detected as having content that might violate our community guidelines and has been blocked. Your account status will not be affected by this.
Occasionally, I’ll resubmit the prompt and it will render fine. I question why it just can’t attempt to re-render it again until it passes whatever filters it has in place. I’d expect it to take a line of code to create this conditional. But it doesn’t explain why it allows other images to pass – quite obviously not compliant.
Why I am trying to get a rear view? This is a bit off-topic, but creating a character sheet is important for storytelling. If I am creating a comic strip or graphic novel, the characters need to be persistent, and I need to be able to swap out clothing and environments. I may need close-ups, wide shots, establishing shots, low-angle shots, side shots, detail shots, and shots from behind, so I need the model to know each of these. In this particular case, this is one of three main characters – a steampunk bounty hunter, an outlaw, and a bartender – in an old Wild West setting. I don’t need to worry as much about extras.
I marked the above render errors with 1s and 2s. The 1s are odd next twists; 2s are solo images where the prompt asks for character sheets. I made a mistake myself. When I noticed I wasn’t getting any shots from behind, I added the directive without removing other facial references. As a human, a model might just ignore instructions to smile or some such. The AI tries to capture both, not understanding that a person can have a smile not captured by a camera.
These next renders prompt for full-body shots. None are wholly successful, but some are more serviceable than others.
Notice that #1 is holding a deformed violin. I’m not sure what the contraptions are in #2. It’s not a full-body shot in #3; she’s not looking into the camera, but it’s OK-ish. I guess #4 is still PG-13, but wouldn’t be allowed to prompt for “side boob” or “under boob”.
Gamers will recognise the standard T-pose in #5. What’s she’s wearing? Midjourney doesn’t have a great grasp of skin versus clothing or tattoos and fabric patterns. In this, you might presume she’s wearing tights or leggings to her chest, but that line at her chest is her shirt. She’s not wearing trousers because her navel is showing. It also rendered her somewhat genderless. When I rerendered it (not shown), one image put her in a onesie. The other three rendered the shirt more prominent but didn’t know what to do with her bottoms.
I rendered it a few more times. Eventually, I got a sort of body suit solution,
By default, AI tends to sexualise people. Really, it puts a positive spin on its renders. Pretty women; buff men, cute kittens, and so on. This is configurable, but the default is on. Even though I categorically apply a Style: Raw command, these still have a strong beauty aesthetic.
I’ve gone off the rails a bit, but let’s continue on this theme.
cinematic fullbody shot photograph, a pale girl, a striking figure in steampunk mech attire with brass monocle, and leather gun belt, thigh-high leather boots, and long steampunk gloves, walking away from camera, white background, Kodak Potra 400 with a Canon EOS R5
Obviously, these are useless, but they still cost me tokens to generate. Don’t ask about her duffel bag. They rendered pants on her, but she’s gone full-on Exorcist mode with her head. Notice the oddity at the bottom of the third image. It must have been in the training data set.
I had planned to discuss the limitations of generative AI for text, but this is getting long, so I’ll call it quits for now.
This may be my last post on generative AI for images. I’ve been using generate AI since 2022, so I’m unsure how deep others are into it. So, I’ll share some aspects of it.
Images in generative AI (GenAI) are created with text prompts. Different models expect different syntax, as some models are optimised differently. Of the many interesting features, amending a word or two may produce markedly different results. One might ask for a tight shot or a wide shot, a different camera, film, or angle, a different colour palette, or even a different artist or style. In this article, I’ll share some variations on themes. I’ll call out when the model doesn’t abide by the prompt, too.
Take Me to Church
Lego mini figure style character, walking up aisle in church interior, many white lit candles, toward camera, bright coloured stained glass, facing camera, waif with tattoos, sensual girl wearing white, doc marten boots, thigh garter, black mascara, long dark purple hair, Kodak Potra 400 with a Canon EOS R5
This being the first, I’ll spend more time on the analysis and critique. By default, Midjourney outputs four images per prompt. This is an example. Note that I could submit this prompt a hundred times and get 400 different results. Those familiar with my content are aware of my language insufficiency hypothesis. If this doesn’t underscore that notion, I’m not sure what would.
Let’s start with the meta. This is a church scene. A woman is walking up an aisle lined with lighted white candles. Cues are given for her appearance, and I instruct which camera and film to use. I could have included lenses, gels, angles, and so on. I think we can all agree that this is a church scene. All have lit candles lining an aisle terminating with stained glass windows. Not bad.
I want the reader to focus on the start of the prompt. I am asking for a Lego minifig. I’ll assume that most people understand this notion. If you don’t, search for details using Google or your favourite search engine. Only one of four renders comply with this instruction. In image 1, I’ve encircled the character. Note her iconic hands.
Notice, too, that the instruction is to walk toward the camera. In the first image, her costume may be facing the camera. I’m not sure. She, like the rest, is clearly walking away.
All images comply with the request for tattoos and purple hair colour, but they definitely missed the long hair request. As these are small screen grabs, you may not notice some details. I think I’ll give them credit for Doc Marten boots. Since they are walking away, I can’t assess the state of the mascara, but there are no thigh garters in sight.
Let’s try a Disney style. This style has evolved over the years, so let’s try an older 2D hand-drawn style followed by a more modern 3D style.
cartoon girl, Disney princess in classic hand-drawn animation style, muted colours…
I’m not sure these represent a Disney princess style, but the top two are passable. The bottom two – not so much. Notice that the top two are a tighter shot despite my not prompting. In the first, she is facing sideways. In the second, she is looking down – not facing the camera. Her hair is less purple. Let’s see how the 3D renders.
cartoon girl, modern Disney 3D animation style, muted colours…
There are several things to note here. Number one is the only render where the model is facing the camera. It’s not very 3D, but it looks decent. Notice the black bars simulating a wide-screen effect, as unsolicited as it might have been.
In number three, I captured the interface controls. For any image, one can vary it subtly or strongly. Pressing one of these button objects will render four more images based on the chosen one. Since the language is so imprecise, choosing Vary Subtle will yield something fairly close to the original whilst Vary Strong (obviously) makes a more marked difference. As this isn’t intended to be a tutorial, there are several other parameters that control the output variance.
Let’s see how this changes if I amend the prompt for a Pixar render.
I’m not convinced that this is a Pixar render, but it is like a cartoon. Again, only one of the four models obeys the instruction to face the camera. They are still in churches with candles. They are tattooed and number three seems to be dressed in white wearing dark mascara. Her hair is still short, and no thigh garter. We’ll let it slide. Notice that I only prompted for a sensual girl wearing white. Evidently, this translates to underwear in some cases. Notice the different camera angles.
Just to demonstrate what happens when one varies an image. Here’s how number three above looks varied.
Basically, it made minor amends to the background, and the model is altered and wearing different outfits striking different poses. One of those renders will yield longer hair, I swear.
Let’s see what happens if I prompt the character to look similar to the animated feature Coraline.
Number two looks plausible. She’s a bit sullen, but at least she faces the camera – sort of. Notice, especially in number one, how the candle placement shifted. I like number four, but it’s not stylistically what I was aiming for. These happy accidents provide inspiration for future projects. Note, too, how many of the requested aspects are still not captured in the image. With time, most of these are addressable – just not here and now. What about South Park? Those 2D cutout characters are iconic…
cartoon girl, South Park cutout 2D animation style, muted colours…
…but Midjourney doesn’t seem to know what to do with the request. Let’s try Henri Matisse. Perhaps his collage style might render well.
Not exactly, but some of these scenes are interesting – some of the poses and colours.
Let’s try one last theme – The Simpsons by Matt Groening. Pretty iconic, right?
Matt Groening's The Simpsons style character, walking up aisle in church interior, many white lit candles, toward camera…
Oops! I think including Matt Groening’s name is throwing things off. Don’t ask, don’t tell. Let’s remove it and try again.
The Simpsons style character, walking up aisle in church interior, many white lit candles…
For this render, I also removed the camera and film reference. Number four subtly resembles a Simpsons character without going overboard. I kinda like it. Two of the others aren’t even cartoons. Oops. I see. I neglected the cartoon keyword. Let’s try again.
Matt Groening's The Simpsons style cartoon character, walking up aisle in church interior, many white lit candles…
I’m only pretty sure the top two have nothing in common with the Simpsons. Again, number one isn’t even a cartoon. To be fair, I like image number two, It added a second character down the aisle for depth perspective. As for numbers three and four, we’ve clearly got Lisa as our character – sans a pupil. This would be an easy fix if I wanted to go in that direction. Number four looks like a blend of Lisa and another character I can’t quite put my finger on.
Anyway… The reason I made this post is to illustrate (no pun intended) the versatility and limitations of generative AI tools available today. They have their place, but if you are a control, freak with very specific designs in mind, you may want to take another avenue. There is a lot of trial and error. If you are like me and are satisfied by something directionally adequate. Have at it. There are many tips and tricks to take more control, but they all take more time – not merely to master, but to apply. As I mentioned in a previous post, it might take dozens of renders to get what you want, and each render costs tokens – tokens are purchased with real money. There are cheap and free versions, but they are slower or produce worse results. There are faster models, too, but I can’t justify the upcharge quite yet, so I take the middle path.
I hope you enjoyed our day in church together. What’s your favourite? Please like or comment. Cheers.
Philosophics 