Category: Memes

  • “Beautiful Cabin Crew”: What Would Jean Baudrillard Say?

    “Beautiful Cabin Crew”: What Would Jean Baudrillard Say?

    Let’s look at the several months old phenomenon of the “Beautiful Cabin Crew”, and then write an essay about it, from the perspective of Jean Baudrillard.

    An example of the FB AI Slop on the theme of “beautiful cabin crew” / Jean Baudrillard (portrait generated by Leonardo)

    Before we start with this essay, here is some background. In case you don’t know what all this is about, let me explain:

    Beautiful Cabin Crew / Scarlett Johansson / Boom Challenge

    The “beautiful cabin crew” phenomenon on Facebook is part of a broader trend known as the “Facebook AI Slop” epidemic. Sometimes it’s also referred to as “AI Boomer trap”.

    Basically it’s a large number of AI-generated images being spammed across Facebook, often accompanied by bizarre or nonsensical captions.

    Examples of “beautiful cabin crew” posts

    The phrase “beautiful cabin crew” specifically originated from AI-generated images of flight attendants holding pictures of religious figures like Jesus Christ, which began circulating in late 2023.

    These posts often use engagement baiting tactics, with phrases designed to attract likes, shares, and comments.

    Other common phrases include:

    • “You will never regret liking this photo,”
    • “Why don’t pictures like this ever trend”,
    • “#BOOMchallenge,” and
    • references to celebrities like Scarlett Johansson and Jennifer Lopez.

    The trend has been heavily criticized and parodied, particularly because the content is low-quality and appears to target users who might not realize it’s AI-generated.

    And of course I just had to create an AI rendition of this. Here’s the first video I made:

    My first video on the Beautiful Cabin Crew

    A few weeks later I felt compelled to make one more. Let’s see if this will become a series, because I’m seriously addicted to this aesthetic.

    Now, before we get to this (ChatGPT-generated) essay by Jean Baudrillard about the beautiful cabin crew, here’s a brief info about who Baudrillard is.

    Jean Baudrillard (1929–2007)

    Baudrillard was a French sociologist and philosopher. Baudrillard’s theories on hyperreality and simulacra have been influential in media studies, particularly in understanding how media creates realities that can be more influential than the actual events they depict.

    His concept of hyperreality explores how media, through constant reproduction and simulation of images, blurs the line between the real and the simulated, leading to a state where the distinction between reality and its representation becomes indiscernible.

    In this state of hyperreality, the simulation of events often holds more power and significance than the events themselves. This is evident in contemporary media, where news cycles, advertisements, and social media platforms create a world that is experienced through a lens of curated and manipulated images.

    Baudrillard’s work has profound implications for understanding the power of media in shaping public perception and the nature of reality in the digital age.

    His analysis extends to the ways in which reality TV, social media, and digital culture have created a new form of reality—one that is manufactured, controlled, and consumed as a commodity.

    Baudrillard’s ideas challenge us to question the authenticity of our experiences and the extent to which our lives are mediated by images that no longer reflect an objective reality, but instead, construct a new, simulated world.


    The Beautiful Cabin Crew: A Simulation of Hyperreal Beauty

    By Jean Baudrillard (as imagined)

    In the labyrinth of modern digital culture, the “beautiful cabin crew” phenomenon on Facebook emerges not as a mere trend but as a profound symbol of the hyperreality that now governs our collective consciousness.

    Here, the image supplants the reality, creating a simulacrum—a world where the representation of beauty overtakes and obliterates any genuine experience of it.

    The Simulacrum of Beauty

    The “beautiful cabin crew” does not exist as a simple admiration of attractive individuals in a service role. Rather, it is a simulation, a copy without an original. In our hyperreal society, the image of the beautiful cabin crew becomes detached from the reality of the individuals it portrays.

    What is circulated, liked, and shared on Facebook is not the person, nor the role of the cabin crew, but an image of idealized beauty—a beauty that has been constructed, mediated, and amplified through layers of digital manipulation and societal expectation.

    In my terms, this phenomenon is a perfect example of the third order of simulacra: the hyperreal.

    Here, the image of the cabin crew is no longer a representation of real people working in aviation but a simulacrum—a self-referential image that exists only to perpetuate its own existence. This is the phase where the image bears no relation to any reality whatsoever; it is its own pure simulacrum.

    Hyperreality in the Digital Age

    Social media, particularly platforms like Facebook, functions as the epicenter of hyperreality, where the boundary between the real and the imagined has long since dissolved. The images of the cabin crew members are not reflections of their true selves but are instead meticulously curated representations designed to fulfill and perpetuate a collective fantasy.

    These images are imbued with a kind of seductive power, not because of their connection to any real-world individual or situation, but precisely because they exist within a digital realm where appearance and image are everything.

    The “beautiful cabin crew” becomes a spectacle, a “perfect crime,” in my sense, where the reality of the individuals—complete with their flaws, their struggles, their humanity—is murdered by the seduction of the image.

    The Obscene and the Fascination

    In “The Evil Demon of Images,” I argue that in a world where images no longer refer to any reality, the obscene becomes the only means of existence.

    The “beautiful cabin crew” phenomenon represents this obscenity. It is not pornographic in the traditional sense, but it is obscene in its pure visibility, its excess, and its relentless self-reference.

    The very idea of beauty is stripped of its traditional connotations of depth and significance, leaving only a hollow shell—a façade that is consumed, reproduced, and circulated endlessly without any reference to the real.

    The obsession with such images is not born out of a desire to engage with the real world but from a fascination with the hyperreal. We are drawn to these images because they offer a version of reality that is more desirable, more seductive, and more complete than reality itself.

    The “beautiful cabin crew” is not celebrated for their service, their skill, or their individuality, but for their ability to perfectly embody the hyperreal image of beauty that our society worships.

    The Death of the Real

    In the end, the “beautiful cabin crew” is a testament to the death of the real in the digital age. In a world dominated by simulacra, where images no longer correspond to any reality, the real has been replaced by the hyperreal.

    The cabin crew member as a real person ceases to exist in the public consciousness, replaced entirely by the simulacrum of their image.

    This is the ultimate consequence of the “beautiful cabin crew” phenomenon: a world where the image not only represents but replaces reality, where the hyperreal is not merely an illusion but a more desirable, more powerful version of existence. It is a world where we have lost touch with the real, seduced entirely by the simulation.

    In this hyperreal world, the “beautiful cabin crew” phenomenon is not just a trend but a manifestation of our collective loss—a loss of the real, a loss of depth, and ultimately, a loss of meaning in the digital age.


    PS. Here is my second video on the topic of “Beautiful Cabin Crew”:

    Enjoy, Gobless, and Amen.

  • AI Interprets a Drake Meme

    AI Interprets a Drake Meme

    I’ve been seeing this new genre of memes on Instagram recently. They go like “X: Died 1992 / Y: Born 1992 / Welcome back, X”. Since ChatGPT can make educated guesses about images, I’ve let it write an interpretation of such a meme. Results below.

    An example of the kind of meme I’m talking about (source: knowyourmeme)

    My prompt wasn’t really that much sophisticated, but sufficient, as I’m happy with the result.

    Here’s the prompt:

    Write a professional review of this meme.

    Here’s the meme:

    Source: @trashcanpaul

    Below is ChatGPT’s reply. I’m (somewhat) impressed by the fact that it has recognized that the humorous part of the meme revolves around the concept of reincarnation.


    ChatGPT:

    The meme juxtaposes two seemingly unrelated events: the Chernobyl disaster of 1986 and the birth of a popular figure in the same year, creating a humorous connection through the concept of reincarnation.

    The left side shows a historical photo of the Chernobyl nuclear disaster site with the text “Died 1986,” while the right side shows a contemporary portrait of the individual with the text “Born 1986,” with a caption that humorously welcomes back the Chernobyl Reactor 4, personifying it.

    The meme’s humor derives from the absurd idea of a nuclear reactor being reincarnated as a person. The use of a well-known individual intensifies the effect as it plays on their public image and the fame they have achieved. It’s a simple but effective piece of internet humor that relies on the viewer’s knowledge of both the historical event and the person’s identity to land the joke.


    For my next trick, I’ll pick a more advanced meme to be interpreted. Stay tuned.

    In other news: I’m working towards becoming a verified builder on OpenAI! So hopefully soon I’ll be able to publish FreudGPT (and my other GPTs).

  • The Adventures of Pope Francis (AI-Generated Video)

    The Adventures of Pope Francis (AI-Generated Video)

    Am I obsessed with Pope Francis? Probably. This time I made a video collection of my newest AI animations, only the ones with the Pope. And since I also have a Youtube channel for this, I’ve uploaded the fresh content straightaway.

    I have this little YT channel for AI stuff. Anyways, here is the video:

    The video is made with Pika Labs via their Discord.

    Why Pope Francis?

    There’s a nice NY Times article from April 2023 about why people choose the Pope for their AI experiments. Here’s a quote from there:

    Global religious figures like the pope are natural subjects of political satire and artistic expression, said Jennifer Herdt, a professor of Christian ethics at Yale Divinity School. Francis is ideal, she added, because he “is known for his simplicity, his solidarity with the poorest of the poor,” so when he is the subject of far-out scenarios such as flying a fighter jet, “it’s definitely the height of incongruity, of defying expectations.”

    Here’s a summary of the article:

    Depicting Pope Francis in unlikely scenarios has been gaining significant popularity online. Pope Francis is shown in these images in various informal or adventurous situations, like wearing a puffer jacket or riding a motorcycle, which contrasts with his usual formal appearances.

    This phenomenon has made him a favorite subject over other public figures in A.I. imagery, with these creations gaining more attention and sparking a trend of placing him in increasingly odd situations. The images, while fake, tap into Francis’s image as a relatable and approachable leader, which resonates with the public.

    Despite the potential for misuse in spreading misinformation, most of these playful depictions are received with amusement. The Vatican has not commented on this A.I.-generated fame. The trend reflects both the capabilities and the potential cultural impact of new A.I. image-generating tools.

  • My New Insta Account / Cultural Implications of AI Memes

    My New Insta Account / Cultural Implications of AI Memes

    Since AI can now make memes, I decided to create an Instagram account purely for AI-generated memes. It’s probably safe to assume that such accounts will start popping up on larger scale in the future, since DALLE-3, which has become so much better at generating text. In this article I also briefly address what the emergence of AI-generated memes means for us culturally.

    Sunsets and stuff

    As you can see the topics of my memes are pretty random, so far I’m just experimenting. I might continue keeping it general and not “niched down” on any subject, because this is not about the subject, but more about the creation process (and its creator – ChatGPT 4/DALLE-3).

    I will keep you updated on this development. In the meantime, I again joined Twitter/X, as Swetlana AI. Let’s see how long I’ll last there.

    What would Deleuze say?

    So AI is making memes now. What does all this mean culturally? Let’s ask BenjaminGPT. But before we do that, why don’t we ask all the other philosophers.

    Here’s how other philosophers would see this. I asked ChatGPT, below is a short summary of several approaches.

    The replies are fairly vague, but they could be expanded. Each of the following ideas could potentially become a book, and I could make a big fuzz about it. Soo many rabbit holes. Especially given the fact that these philosophers weren’t around when memes themselves became a thing.

    Foucault thinking about AI

    Jean Baudrillard:
    Simulation and Hyperreality: Baudrillard’s work on simulation and hyperreality explores how the distinction between reality and its representation becomes blurred. AI-generated art and memes would be a fascinating case study for his theories, as they represent a new level of simulation, where the artwork is not just a representation but a creation of an algorithm.


    Arthur Danto:
    The End of Art: Danto argued that art reached its “end” in the sense that anything could now be considered art. AI-generated art could be a perfect example of this, challenging traditional notions of creativity and authorship.


    Martin Heidegger:
    Technology and Being: Heidegger explored the relationship between humans and technology, arguing that technology shapes our understanding of the world and ourselves. He might be interested in how AI as a technology influences our conception of art and creativity.


    John Dewey:
    Art as Experience: Dewey saw art as a participatory and experiential process. He might be interested in exploring how AI-generated art fits into this framework and what it means for the experience of both the creator and the viewer.


    Gilles Deleuze and Félix Guattari:
    Rhizomes and Deterritorialization: Their work on rhizomes and deterritorialization could provide a lens through which to understand the decentralized, non-hierarchical nature of AI-generated content, and its potential to challenge traditional artistic and cultural structures.


    Theodor Adorno:
    Culture Industry: Adorno critiqued the commodification of culture and the arts. AI-generated memes and art, often created for quick consumption and viral potential, could be seen as an extension of the culture industry, raising questions about originality, authenticity, and the commodification of creativity.


    Marshall McLuhan:
    The Medium is the Message: McLuhan’s famous phrase could be applied to AI-generated art and memes, exploring how the medium of AI shapes the content, meaning, and impact of these artworks.


    Ludwig Wittgenstein:
    Language and Meaning: Wittgenstein’s later work explored how language games shape our understanding of the world. AI-generated memes, which often play with language, imagery, and cultural references, could be an interesting area of exploration in this context.

    Philosophers in a room

    … and Walter Benjamin

    Walter Benjamin, who has been my subject of admiration multiple times, has been dealing with the aura/authenticity of images a lot. Again, I asked ChatGPT (damn, am I lazy?), here’s the reply:


    Walter Benjamin, a German Jewish philosopher and cultural critic, was deeply interested in the role of art, media, and technology in society. He is most famous for his work “The Work of Art in the Age of Mechanical Reproduction,” in which he explores how the reproduction of art changes its perception, value, and role in society.

    If Walter Benjamin were alive to witness the advent of AI-generated memes and art, he would likely have much to say on the subject. Here are a few themes he might explore:

    1. Authenticity and Aura: Benjamin argued that mechanical reproduction (like printing or photography) strips an artwork of its “aura”—the unique presence and authenticity it has when encountered directly. He might see AI-generated art as a further extension of this trend, as these works are generated algorithmically and can be easily replicated.
    2. The Democratization of Art: On the other hand, Benjamin also saw potential in mechanical reproduction to democratize art, making it more accessible to the masses. He might see AI-generated memes and art as a continuation of this trend, as they allow for the rapid creation and dissemination of visual content.
    3. The Role of the Artist: Benjamin believed that mechanical reproduction had the potential to change the role of the artist in society. With AI-generated art, this change is even more pronounced, as the “artist” becomes a programmer or data scientist, and the creative process is mediated by algorithms.
    4. The Impact on Perception: Benjamin was interested in how changes in art and media influence perception and consciousness. He might explore how the prevalence of AI-generated content changes the way we see and understand the world, as well as how it shapes our tastes, values, and expectations.
    5. Political Implications: Benjamin was deeply concerned with the political implications of art and media. He might investigate how AI-generated memes and art are used for political purposes, exploring how they can both challenge and reinforce power structures.

    Overall, Walter Benjamin would likely approach the phenomenon of AI-generated memes and art with a critical eye, seeking to understand its implications for art, society, and politics. His work provides a valuable framework for thinking about these issues, highlighting the complexities and contradictions inherent in the intersection of art, technology, and society.

  • ChatGPT x DALL-E 3: Creating Memes and Artwork

    ChatGPT x DALL-E 3: Creating Memes and Artwork

    ChatGPT can now produce images! 🤯 And they are shockingly accurate. Today I’m trying out the new image generation feature (DALL-E 3!), and I’m definitely thrilled by the possibilities. This is way more exciting than Midjourney or standalone Stable Diffusion. And yet again I feel distracted from my recent project (on which I will update you in time). Yay!

    I asked DALL-E 3 to create a meme illustration about gentrification

    Ok, so this development is already a month (or so) old, so I’m a bit late to the party. But hey, better late than never.

    In this article I’m including some memes and illustrations (particularly interesting for POD designers, and, well, illustrators).

    How To Use DALL-E 3

    First things first — here is how you can access DALL-E 3. It’s fairly simple.

    1. Go on ChatGPT. You need to have the subscription in order to use DALL-E 3, at least at the time of writing this.
    2. Make sure to select ChatGPT 4 as a model in the upper left corner.
    3. Write a prompt! It’s perfectly fine to keep it simple, you will achieve interesting results anyway, as ChatGPT will do the thinking for you

    Example Prompts for DALL-E 3

    A simple short prompt will go a long way. Try things like:

    • Create an image of a hedgehog in the rain
    • Make a meme about a messy kitchen
    • Create a logo for my bakery
    • Create a meme about my friend Janet who is always late

    Especially the latter point is proving to be very interesting for me, as I love surprising my friends with some crazy imagery. Best thing you can do is experiment a bit, and see what comes out. Oftentimes the results are entertaining.

    Memes

    So the first thing I’ve tried was to generate memes, as I keep seeing AI-generated memes all over my social media. 

    As you can see there are barely any typos, which is pretty impressive

    And the beautiful thing here is that ChatGPT comes up with its own prompt, adding new thoughts to your idea. At this point, it basically does all the (conceptual) thinking. 

    You might be wondering: how is DALL-E handling text / alphabet characters displayed in images? Well, it got waay better, although of course there are occasional glitches. Compared to earlier versions of DALL-E though this is a significant improvement. I also like the font used here.

    As you can probably guess, the sky is the limit here. Generating this type of content like this could be a game-changer for anyone who wants to run, say, a meme Instagram account.

    Illustrations and Shirt Designs

    But wait, there’s more. Memes obviously weren’t enough, so I went straight ahead to shirt design illustrations. And as a “seasoned artist”, I have to say I’m impressed. To check for possible copyright breaches, I performed a Google image search for several of these designs, and found nothing similar enough.

    For this one, I told ChatGPT to create a meme about gentrification:

    ChatGPT came up with the slogan “When the block gets a little too hip”, pretty funky idea

    And here is an illustration about marketing, or made FOR the marketer. This one is a bit more glitchy, maybe because of the amount of words involved:

    And while it has errors and glitches, it’s conceptually still a great idea that could work well on a shirt. Personally for me I have decided that I definitely will use this as an inspiration for my actual designs.

    Of course I made more than these images, so if you’re curious, you might as well ask me. You can get in contact via my contact form

    or Instagram, for example: https://www.instagram.com/swetlana_ai/

    Here’s one more about boomers and millennials:

    ChatGPT and DALL-E 3

    Here’s what all the fuzz is about: ChatGPT now offers a unique image creation feature for Plus and Enterprise users. Simply describe your vision, and ChatGPT will provide visuals for you to refine and request revisions in the chat.

    DALL·E 3 is a highly advanced image model resulting from extensive research, offering visually stunning and detailed images. It excels in handling detailed prompts, supports various aspect ratios, and focuses more on user-supplied captions

    With DALL·E 3, you can unleash your creativity like never before. The only BUT: it doesn’t replicate the style of living artists. Additionally, you have the option to exclude your images from future model training. Learn more in their research paper here.

    Here’s the summary of the research paper: 

    Recent advancements in generative modeling have significantly improved text-to-image generative models. These improvements stem from two main approaches: using sampling-based methods like autoregressive generative modeling or diffusion processes, which break down image generation into manageable steps for neural networks. Additionally, researchers have developed image generators based on self-attention layers, separating image generation from convolutional spatial biases and leveraging transformer scaling properties.

    When coupled with large datasets, these approaches enable the training of text-to-image models that can produce imagery approaching human-quality photos and artwork. However, a key challenge in this field is “prompt following,” where models often struggle to capture word meanings, order, or context in given captions.

    Several works have highlighted this challenge, proposing various solutions. This paper introduces a novel approach to address prompt following: caption improvement. The authors believe that the poor quality of text-image pairings in training datasets is a fundamental issue. To tackle this, they develop a robust image captioning system to generate detailed, accurate descriptions for images, enhancing the dataset’s captions. Subsequently, they train text-to-image models on this improved dataset.

    While training on synthetic data is not new, this work focuses on the development of a descriptive image captioning system and assesses the impact of using synthetic captions in training generative models. The paper primarily evaluates the enhanced prompt following capabilities of DALL-E 3, achieved through training on highly descriptive generated captions. It does not delve into the technical details of the DALL-E 3 model but provides an overview of the training strategy, evaluations, and discussions of limitations and risks.

  • Pope Francis Spotted on the Sidewalk at Night

    Pope Francis Spotted on the Sidewalk at Night

    Was he buying cigarettes, or coming back from a club? A photo has surfaced on social media showing Pope Francis walking alone on a city street at night. The photo, which appears to have been taken with a smartphone, has sparked controversy and raised questions about the safety and security of the pontiff.

    The Vatican has not yet commented on the photo, but many are speculating that the Pope may have been attempting to escape the confines of the Vatican and experience life outside the walls of the holy city. Others are concerned that the Pope may have been putting himself in danger by wandering alone through a city at night.

    In case you hadn’t already noticed: The above text is fake, and so is the image. It sounds like a win for BuzzFeed and the likes, for its entertaining value, but it can will also lead to deteriorating trust towards the media. Towards ANY media! Because I’m feeling like having silly fun today, I’m going to add some fuel to the dumpster fire.

    Some of you might have heard of the famous “Pope Drip” meme, depicting the current Pope wearing a Balenciaga puff jacket. This image has obviously been generated by Midjourney, but perhaps we all wish it would be real.

    And here is a prompt that can be used to create it:

    AI is cool, but it can also deceive, and so far I can’t even imagine the consequences of the mass freakshow that’s about to hit us. Below are my own little Pope Francis deepfakes (sorry, world) aka contribution to the chaos. The Age of Disinformation is in its infancy, and how are we going to verify anything in the future?

    But anyways, let’s continue where we left off. Here are some more images of the Pope that I made:

    Pope Francis and Kanye West in a taxi

    Here once again Pope and Ye, but this time drunk:

    Drunk Pope and Kanye

    Pope Francis with face tattoos:

    Pope at a burger eating contest:

    Pope at a Burger contest - Swetlana AI x Midjourney
    Yummy

    Here’s one more because why not:

    Aand here he is at a fashion show wearing sunglasses:

    And why stop at Pope Francis? Here’s a photo of Barack Obama and Angela Merkel getting married:

  • AI Is Terrible At Memes

    AI Is Terrible At Memes

    Imgflip has an AI meme generator. I’ve tested it several times, and so far it has failed to impress me. Its extreme randomness, however, is sometimes entertaining. Let’s look at some memes I have generated.

    Memes have become a cultural phenomenon, a form of digital communication that spreads virally and permeates social media. From Grumpy Cat to the Success Kid, memes have become a ubiquitous part of our online experience. With the rise of artificial intelligence (AI), it was only a matter of time before AI-generated memes entered the scene. However, while these memes may seem like a fun novelty at first glance, they lack the humor and originality of their human-generated counterparts.

    One of the key appeals of memes is their relatability. They often draw on shared cultural references or experiences, and their humor often stems from a clever twist or subversion of expectations. While AI-generated memes may be able to mimic the structure and style of a traditional meme, they often lack the cultural awareness and contextual understanding needed to create truly relatable or humorous content.

    Additionally, AI-generated memes often rely on the same set of pre-existing templates or templates generated from a specific dataset, leading to a lack of originality. This can make them feel repetitive or unoriginal, ultimately diminishing their impact and entertainment value.

    Moreover, AI-generated memes can also perpetuate harmful stereotypes or offensive content, particularly when the algorithms are trained on biased or problematic data. Without the critical eye and moral judgment of a human creator, these memes can spread harmful or insensitive content that may be damaging to certain communities.

    Of course, this is not to say that AI-generated memes can never be funny or entertaining. There have been some instances where AI-generated memes have garnered attention and humor, such as the popular “This Person Does Not Exist” meme. However, it is important to recognize the limitations and potential drawbacks of relying solely on AI to create memes.

    In conclusion, while AI-generated memes may seem like a fun and novel way to explore the capabilities of artificial intelligence, they often lack the cultural awareness, originality, and humor of their human-generated counterparts. As we continue to integrate AI into our daily lives, it is important to remain critical of its limitations and potential biases, and to recognize the value of human creativity and humor in the digital landscape.

    Here’s what imgflip says about their image generator:

    Find a good one? Save it and submit it to the AI Memes stream!


    These captions are generated by a deep artificial neural network. Nothing about the text generation is hardcoded, except that the maximum text length is limited for sanity. The model uses character-level prediction, so you can specify prefix text of one or more characters to influence the text generated. Using someone’s name or other short text as a prefix works best.

    The network was trained using public images generated by users of the Imgflip Meme Generator for the top 48 most popular Meme Templates. Beware, no profanity filtering was done on the training data so you may encounter vulgarity.

    Curious about the technical details of building the network? Check out the accompanying article Meme Text Generation with a Convolutional Network in Keras & Tensorflow.

    Imgflip