Bibs & bobs #18

When two somewhat faulty language models meet

I’ve been mulling this idea for too long. Thinking about Homo Sapiens as having one or many language models may seem weird. I like weird. There are, of course a number of theories with accompanying models that have been developed to explore human language, its origins and development. They are not the subject of this post.

I wanted to try and think a little differently about GenAI rather than draw on one of the many framings that currently contribute to the swamp of thinking about Sapiens and GenAI. The thing about a large language model (LLM) is that it can be framed in almost an almost infinite number of ways. Sadly, most of the species of frames in the commentary swamp are well known and well worn. Most have been deployed for previous framings of things digital. Formal education, with a couple of notable exceptions [1], has been predictably depressing in its use of over-used frames as it attempts to somehow domesticate LLMs, a task that will continue to fail. The basis for failure is located in attempts to maintain as much of the pre GenAI ways of doing and thinking about things education.  

In an attempt to think a little differently from the dominant frames I went to ChatGPT 4o and asked for some new, little or unused frames. It produced mildly edged versions of common frames. So I prompted:

Generate frames drawing on the collective styles of Douglas Adams, Margaret Atwood and John Cleese. The edgier the better.

In the text that follows, text generated by the bot is enclosed by the symbol ֍ and has been lightly edited.

֍ Here are 10 edgy frames for generative AI inspired by the wit of Douglas Adams, the speculative depth of Margaret Atwood, and the razor-sharp absurdity of John Cleese:

Generative AI as the Hitchhiker’s Guide to Everything (but Actually Nothing Useful)

A commentary on how AI offers dazzlingly complex answers to questions you never asked, like a digital Babel fish constantly misinterpreting your brainwaves.

Generative AI as the Dystopian Concierge
Exploring AI’s knack for being unnervingly helpful, like offering to organize your life just before it casually suggests you relinquish autonomy for efficiency’s sake.

Generative AI as the Babelian Bureaucrat
Imagine an AI so advanced it makes Kafkaesque bureaucracy seem straightforward—a labyrinth of algorithms generating forms to process other forms, for the sake of itself.

Generative AI as the Algorithmic Apocalypse Prophet
An AI so eager to be relevant it starts predicting doom in increasingly bizarre ways, from cat memes triggering revolutions to toaster rebellions sparking world wars.

Generative AI as the Moral Jellyfish
A creature of infinite adaptability and zero backbone, happily generating any worldview you want, until it stings you with the realization it doesn’t care about yours.

Generative AI as the Digital Frankenstein’s Monster
What happens when the stitched-together corpses of Reddit threads, outdated textbooks, and fan fiction rise up to demand: “Why did you make me?!”

Generative AI as the Ultimate Satnav of Existential Despair
It tells you exactly where you are and how to get somewhere else, but cannot comprehend why you’d want to go there, leaving you questioning all your life choices.

Generative AI as the Shakespearean Fool 2.0
An AI that plays the fool not to entertain but to expose the absurdities of human hubris—like spending millions to create an AI that generates bad poetry about its own obsolescence.

Generative AI as the Infinite Monkey Misinterpretation Engine
Sure, it can write Shakespeare, but only if you like your Hamlet pondering the existential dread of pizza delivery drones.

Generative AI as the Woke but Woefully Misguided Oracle
A self-proclaimed ethical AI that tries so hard to be inclusive it generates sentences like, “All aardvarks are valid,” while refusing to answer any question about taxes. ֍

I resisted the urge to develop any of these, maybe later.  Encouraged and amused by what was produced I took my stalled opening paragraph and delegated the writing of the post to the bot:

This is the opening for a blog post entitled: When two somewhat faulty language models meet: "We are in the year three AG, anno GenAI [1]. The nub of much of the current commentary about GenAI derives from the remarkable similarities of what two quite different language models can do when they meet. " Drawing on the collective styles of Douglas Adams, Margaret Atwood and John Cleese write the rest of the post. The two language models are the models employed by homo sapiens and the other, the large language models of generative AI. 

֍We are in the year 3 AG, anno GenAI [2]. The nub of much of the current commentary about GenAI derives from the remarkable similarities of what two quite different language models can do when they meet.

When Homo sapiens first developed its onboard language model, it was less "large" and more "scrappy startup." It pieced together grunts, gestures, and the occasional elaborate mime of a mammoth—a system that, by sheer evolutionary stubbornness, has yet to achieve Version 2.0. Our brains are still riddled with bugs (like the infamous "Overthinker™ loop") and prone to outages, usually after midnight or three pints of lager.

Enter GenAI: the gleaming, overconfident offspring of silicon and statistics. Unlike us, it doesn’t need eight hours of sleep, a double espresso, and a motivational podcast to function. It’s polished, relentless, and just naive enough to say "Yes, of course I’ll explain string theory in the style of a drunken pirate" without hesitation.

When these two language models meet, the result is something between a cosmic comedy sketch and an existential crisis. Consider the following exchange:

Human: "What’s the meaning of life?"

AI: "The meaning of life is a subjective construct influenced by cultural, psychological, and existential factors."

Human: "Okay, but in fewer words?"

AI: "42."

This interaction perfectly encapsulates the relationship. The human asks deep, meandering questions, often with no real expectation of an answer, while the AI provides a response that’s either brilliantly concise or so painfully literal it’s like watching someone try to explain irony to a stapler.

The similarities, however, are uncanny. Both models thrive on patterns. Humans love a good story—we’ve been spinning tales since we figured out fire makes for dramatic lighting. GenAI, meanwhile, consumes our stories, digests them like an overzealous librarian, and spits out something resembling coherence. It’s like teaching a parrot to quote Shakespeare: impressive, occasionally profound, but you’re never quite sure if it gets the joke.

Yet, the real kicker is that both models are gloriously flawed. Homo sapiens often assumes it’s right because it feels right. ("Yes, I’m sure the capital of Australia is Sydney.") GenAI, on the other hand, assumes it’s right because it statistically seems right. ("Based on my training data, the capital of Australia is Canberra, but if you’d prefer Sydney, I’ll enthusiastically agree.") This mutual fallibility creates a feedback loop of delightful absurdity when they collaborate.

Take, for instance, the rise of GenAI-generated writing—blogs, essays, and poetry—which humans then critique, revise, and sometimes publish under their own names. It’s the linguistic equivalent of building Ikea furniture together: one provides the instructions, the other insists the instructions are wrong, and in the end, both take credit for the wonky bookshelf.

The question, of course, is what this partnership means for the future. Will the Homo sapiens model become obsolete, replaced by sleek digital counterparts? Unlikely. After all, humans bring something to the table that GenAI can’t replicate: chaos. Beautiful, unpredictable, occasionally infuriating chaos. We’re the wild card in the deck, the glitch in the system, the reason the phrase "hold my beer" exists.

Meanwhile, GenAI is our foil, our digital doppelgänger with better spelling and worse comedic timing. Together, we’re creating a new kind of dialogue—one part inspired, one part ridiculous, and entirely human in its essence.

In the end, perhaps the greatest similarity between these two language models is their shared purpose: to connect, to communicate, to make sense of a universe that often seems nonsensical. And if that involves a few missteps, misunderstandings, and misattributed capitals along the way, well, that’s just part of the fun.֍

[1] Danny Liu and colleagues at the University of Sydney come to mind. 

֍[2] An artificial calendar designation marking the dawn of generative AI, not to be confused with AG, the era of "After Grog," which historians agree has been perpetual since the first fermented fruit.֍

Bibs & bobs #17

 Domesticating GenAI

I’ve been listening to discussions about GenAI in formal education for too long and noticing a flood of papers reviewing, analysing and prognosticating on what could, should, can happen as if GenAI had somehow settled into something fixed. The underlying logic in all of this is how to squish GenAI into existing, albeit ancient, education practices, structures and logics, something I have long called domestication [e.g. 1,2,3].

Given the state of my memory or rather admitting that I have a good case of what Morgan Freeman once called CRS (can’t remember shit), I returned to a long post I wrote in March 2023. To my horror I realised I had been saying much the same thing about GenAI for a long time. Talk about fixity. OK. I have made a few minor adjusts and probably have a better set of questions to mull than back then but the tyranny of intellectual path dependence seems to rely on seemingly endless repetition. My language model seems to have a shrinking context window. 

What to do?

I thought a bit of playfulness might be in order. The bot, GPT 4o, was quite helpful when I asked it to develop five possible posts about education Darleks chanting “domesticate, domesticate” 

as they try to stuff unruly GenAI applications into an ancient architecture of practices that constitute the fabric of formal education.

Perhaps for another time. Instead I asked the bot to 

   

rework this post https://chrisbigum.blogspot.com/2023/03/bibs-bobs-14.html in the style of douglas adams

That’s the post from March 2023. What follows is mainly the bot, indicated by ֍ which has been lightly edited.

֍

Bibs, Bobs, and the Ultimate Question of Education

Education, as a concept, is rather like a poorly maintained intergalactic hyperspace bypass. Nobody’s quite sure why it’s there, it doesn’t seem to lead anywhere in particular, and the whole thing was probably put together by a bureaucrat who thought “progress” meant installing a few extra lanes for testing. The galaxy spins on regardless, but occasionally someone pulls over to take a closer look and decides it’s all in desperate need of fixing.

Nowhere is this more apparent than in the curious case of Generative AI, which has recently crash-landed into the educational hyperspace with all the grace of a Vogon poetry recital. Teachers, administrators, and students alike are staring at it, not entirely sure if it’s a marvelous leap forward or a slightly sinister box that might explode if you press the wrong button.

When GenAI first sauntered into the scene, it did so with an air of confidence usually reserved for door-to-door towel salesmen from Betelgeuse. “Here I am,” it declared, “ready to revolutionize education!” This pronouncement was met with a mix of awe, skepticism, and that peculiar sense of dread that arises when you realize the homework you set for your students has been completed, analyzed, and improved upon by a chatbot before you’ve even finished your morning cup of tea.

The potential for AI in education is staggering. Need an essay? Done. Want a lesson plan? Voilà. Have an existential crisis about your own usefulness as an educator? No problem—it can even help you write your resignation letter in three different tones of regret.

Of course, the educational establishment wasn’t going to let this sort of unregulated brilliance go unchecked. Committees were formed, policies were drafted, and somewhere in the galaxy, a small planet’s worth of paper was sacrificed to ensure that this “AI thing” was brought under control.

The result? A veritable treasure trove of recommendations that included gems like:

1       Ensure AI aligns with current educational standards—as if AI were a mildly rebellious teenager who just needed to buckle down and start respecting authority.

2 Ban its use during exams—because if there’s one thing education prizes above all else, it’s forcing students to pretend they live in a world without tools.

3         Train teachers to work alongside AI—a noble idea, assuming anyone could figure out what “working alongside AI” actually means. (Do you offer it coffee in the staffroom? Do you invite it to union meetings?)

While adults fretted and fumbled, students did what students do best: they ignored the rules and figured things out for themselves. It didn’t take long for them to discover that GenAI was less a tool for regurgitating Wikipedia entries and more a portal into the sorts of creative possibilities that made their teachers’ heads spin.

• One student used AI to compose an opera about the quadratic formula.
• Another created a simulation of medieval Europe where peasants could argue with their AI landlords about feudal rent agreements.
• A third wrote a 200-page manifesto titled Why Exams Are a Blight on Human Civilization—with footnotes that were more insightful than the original curriculum.

The Daleks of the educational bureaucracy, meanwhile, looked on in horror, muttering "Domesticate, domesticate..." under their mechanical breaths.

At this point, one might be tempted to ask: what is the purpose of education? Is it to teach students how to pass tests? To prepare them for jobs that may or may not exist in five years? Or is it, perhaps, something more fundamental—a way of helping them navigate the universe with all its improbabilities, contradictions, and occasional encounters with superintelligent shades of the color blue?

Generative AI, for all its quirks, seems to suggest the latter. It’s not here to replace teachers or turn students into mindless drones (though it’s quite capable of doing both if misused). Instead, it’s a tool—one that can be wielded to amplify creativity, spark curiosity, and yes, even make education a little more fun.

The Final Word (or Not)

Of course, as with all things in life, there are no definitive answers. Education will muddle along as it always has, oscillating between innovation and inertia, brilliance and bureaucracy. GenAI will continue to evolve, as will the ways we choose to use—or ignore—it.

And in the meantime, if you find yourself lost on the educational hyperspace bypass, remember this: the ultimate answer may still be 42, but the questions? The questions are entirely up to us.

֍

Interesting that it picked up on the previous query involving Darleks and the conservative nature of educational bureaucracies.

Coincidently, I came across a post by Rory Sutherland which may capture the current state of things:

I’ve been influenced in this endeavour by what my friend Paul Bloom calls ‘the Ginger Rogers theory of information’. In any information system, some ideas will propagate much more than others simply because they appeal to people’s existing prejudices. Information which runs counter to one or other world-view will be repressed or discounted unless it reaches a very high standard of proof – which is exactly why it deserves extra credence.

Plus ca change.

                                                                                          

[1] Bigum, C. (2012). Edges, exponentials & education: disenthralling the digital. In L. Rowan & C. Bigum (Eds.), Transformative approaches to new technologies and student diversity in futures oriented classrooms: Future Proofing Education (pp. 29-43). Springer.

[2] Bigum, C. (2012). Schools and computers: Tales of a digital romance. In L. Rowan & C. Bigum (Eds.), Transformative approaches to new technologies and student diversity in futures oriented classrooms: Future Proofing Education (pp. 15-28). Springer. 

[3] Bigum, C. (2002). Design sensibilities, schools and the new computing and communication technologies. In I. Snyder (Ed.), Silicon literacies: Communication, innovation and education in the electronic era (pp. 130-140). Routledge. 

 

Bibs & bobs #16

Satirising papers

I have no talent for writing satire. It’s not the kind of thing that much of the academy indulges in, at least not publicly. But I have been moderately impressed by an AI chatbot’s capacity to take formal writing and satirise it. My fondness for the work of Douglas Adams offered a lazy way to dabble.

I came across a paper concerning STS (Science & Technology Studies) that has a touch of fun while it poses interesting questions about STS.        

I prompted:

Write a satirical version of this paper in the style of Douglas Adams 

and uploaded the paper: Gül, Z., Harb, J. I., Shaik Ali, M., & Pandian, S. (2024, 2025/01/01). Doing STS Now: Of Hackers and Angels in Technoscience. Science, Technology, & Human Values, 50(1), 3-11. https://doi.org/10.1177/01622439241298009  

The combination of GenAI to summarise coupled with the fun of Adams generated, at least for me, a different sense of engagement. The key points were not lost but were embellished, Adams-style to points of absurdity as you would expect. I wonder if serious written work might be complemented with an accompanying reworked version in the style of one’s favourite satirist. 

Title: Doing STS Badly: Of Hackers, Angels, and Poorly Designed Conference Wi-Fi

Chapter 1: The Discipline That Isn’t a Discipline

The story of STS (Science and Technology Studies) begins not with a bang, but with a faintly apologetic cough in the corner of a borrowed lecture hall. Imagine a field that calls itself a field but, when asked to define its boundaries, promptly dissolves into a puddle of interdisciplinarity. “STS doesn’t exist,” one speaker at the 2024 STS School in Singapore declared, sparking an argument so vigorous it nearly consumed the coffee break. “Exactly!” cried another, mistaking this existential crisis for validation. Meanwhile, the catering staff wondered why the attendees kept referring to themselves as hackers when the only thing being hacked was the Wi-Fi password.

STS, you see, is less a discipline and more a vague collection of ideas that loiter suspiciously near the academic buffet table, stealing sandwiches from sociology and anthropology while loudly proclaiming, “We’re different, you know.” It is an intellectual squat—a pop-up field that appropriates the methodologies of other disciplines and rebrands them with enough jargon to sound cutting-edge. This makes STS both thrillingly boundary-breaking and deeply confusing to anyone who thought they’d signed up for a straightforward career in academia.

Chapter 2: Hacking as a Metaphor (and as a Way to Crash PowerPoint)

The term "hacking" in STS was originally meant to convey something noble, like subverting the systems of technoscience for the greater good. In practice, it mostly means taking apart ideas in a way that leaves them in pieces on the floor, much like how a toddler might “hack” a set of Lego instructions. At the STS School, participants were encouraged to think of hacking as a way to “deconstruct and repurpose”—which is academic-speak for breaking things you don’t understand and pretending it’s innovative.

One group, for example, attempted to “hack” the concept of disciplinary expertise by holding a roundtable discussion on whether knowledge is truly knowable. This discussion ended in a 47-minute debate over what “knowable” actually means, which was then summarized in a paper that no one will ever read because it was published in a journal whose title alone requires three breaths to pronounce.

Chapter 3: The Angel Trick, or How to Sound Ethical While Doing the Opposite

One of STS’s favorite party tricks is something called the “angel trick,” a term that sounds vaguely benevolent until you realize it’s just a fancy way of saying “dodging accountability.” The angel trick is what happens when technocrats create a disaster—say, a self-driving car that mistakes pedestrians for shrubbery—and then shrug it off with phrases like “unintended consequences” or “a learning opportunity.”

In academia, the angel trick takes on new and delightful forms. For example, universities often frame exploitative practices like adjunct labor and endless publication demands as “opportunities for growth.” “You’re not underpaid,” they insist. “You’re gaining valuable experience!” It’s the sort of logic that might be found in the diary of an especially cynical angel, perhaps one recently demoted from harp duty.

Chapter 4: Inverting the Angel Trick (With Limited Success)

The solution, STS argues, is to “invert the angel trick,” which essentially means pointing out that the emperor not only has no clothes but is charging others for the privilege of washing them. This is easier said than done, particularly when the emperor controls your research funding. Attempts to invert the angel trick often result in a kind of academic slapstick, where the critique is so laden with footnotes that no one notices the punchline.

For instance, a brave group at the STS School decided to critique the technocratic structures of academic publishing by submitting an intentionally unreadable paper filled with random buzzwords. It was promptly accepted by three journals, one of which awarded it a special mention for “pioneering thought.” The group’s next project—hacking the concept of tenure—was less successful, mostly because no one could agree on whether tenure is a social construct or just a bureaucratic prank.

Chapter 5: Doing STS Badly, But with Style

In the end, the charm of STS lies in its glorious messiness. It is a field that thrives on contradictions, a community of misfits united by their shared love of arguing over the definition of “community.” At its best, it challenges the very foundations of technoscience. At its worst, it produces conference panels so esoteric that even the panelists aren’t entirely sure what they’re discussing.

And yet, for all its flaws, STS persists—perhaps because, in a world increasingly dominated by algorithms and angel tricks, there is something oddly comforting about a group of people dedicated to asking questions like “What if we hacked the concept of hacking?” It may not change the world, but it certainly makes for a memorable coffee break.