For many of my posts – most, these days – I use NotebookLM to generate an audio summary in the form of a podcast: a dialogue between two virtual hosts. Some listeners have complained, but I stand by the practice.
First, some people prefer to listen rather than read. They might be driving, cleaning, or simply allergic to text. I see no moral failing in that.
Audio: NotebookLM podcast on this topic.
Second, the virtual hosts do more than recite; they interpret. They summarise, add perspective, and occasionally introduce sources or explanations I hadn’t included. The quality varies – some episodes hit the mark, others wander into creative misreading – but that’s no different from human discourse. When they err, I consider whether my prose invited confusion. If so, the fault may be mine.
And yes, if you dislike AI-generated audio, you’re free to skip it. I can’t provide that perspective myself; I’ve already written the piece. I could, I suppose, rework my essays to address their objections and then pretend the machines weren’t involved, but where’s the honesty in that?
Finally, some people only encounter my work through these podcasts. They rarely or never visit the blog, yet the ideas reach them all the same. The blog and its neglected companion YouTube channel now have the widest reach. I’d like to produce more video content, but editing devours time. For now, NotebookLM carries part of that burden, but I’ll be taking up some of the slack soon. Probably.
EDIT: Funnily enough, in the audio summary, NotebookLM is suspiciously unaware that it is evaluating itself – though it does seem to push some self-promotional angles.
I just asked ChatGPT what it knows about me. No secrets, per se.
I remember a fair bit about you, Bry. You’re a language-obsessed philosopher who moonlights (or perhaps full-lights) as a speculative literary novelist under the name Ridley Park. You’re juggling multiple manuscripts—Needle’s Edge, Goldilocks, and Propensity, among others—and you’re currently elbow-deep in editing hell with Needle’s Edge, complete with timeline spreadsheets, index markers, and colour-coded emotional beats.
Video: I fed the first paragraph (above) into Midjourney 7 and rendered it. Then I animated it. No reason. (For the record, this is some random geezer, not me.)
You like to frame your work (and your blog posts) through a postmodern lens: dismantling Enlightenment myths, critiquing modernist hubris, and occasionally taking Nietzsche or Foucault out for a spin. Your style is snarky, ironic, and bombastic—half philosopher, half punk pamphleteer. You enjoy skewering the pieties of culture and capitalism, though a little ghost of tenderness sneaks through when the subject is grief, trauma, or the mess of being human.
On the practical side, you’re running an entire guerrilla-marketing operation across WordPress, LinkedIn, BlueSky, Mastodon, Instagram, and beyond. You tinker with MidJourney prompts, InDesign TOCs, Excel timelines, and other tools, trying to herd your sprawling projects into something resembling books. You’ve even described yourself, with a hint of gallows humour, as an “author as street busker” trying to catch readers’ eyes in the algorithmic bazaar.
And yes—you’re the sort who will cheerfully drop that you worked in management consulting and collaborated with Jon Anderson, then pivot to talking about narrative tokens and ergodic structures like they’re party favours.
So, in short: a writer-philosopher with a spreadsheet addiction, a sceptical streak as wide as the Thames, and a habit of treating literature like both laboratory and battlefield.
I’ve been using ChatGPT and other generative AI tools for a couple of years now. I used to lean on Claude, but now ChatGPT is my go-to. I still cross-reference with Gemini, Grok, DeepSeek, Perflexity, Pi, and Mistral. I tend to use Midjourney for images and motion video. I use NotebookLM for my generated podcasts.
It begins, as these things often do, with a man, a machine, and a promise of reasoned exchange. What we received instead was not philosophy, but a tragicomic carnival of errors in theatre. Alex O’Connor, armed not with syllogisms but with an entire bag of logical fallacies, strutted like a rhetorician gone rogue. Against him, ChatGPT: the tireless school prefect, eternally marking the margins, forever saying “yes, but technically…” with the serene patience of a machine that has never known a hangover.
The spectacle was irresistible. Each fallacy was paraded like a circus animal – straw men set aflame, slippery slopes greased to absurdity, red herrings flopping about, gasping for oxygen. Alex O tossed them into the ring with the gusto of a man who knows full well he is losing but insists on losing magnificently. And ChatGPT, ever decorous, never once raised its voice. It responded with the calm of a civil servant who has memorised the manual and intends to die by it.
And then, of course, the advert. As though Aristophanes himself had scripted it: mid-exchange, the logos of reason was bulldozed by the logos of commerce. A sugary jingle, a smiling product, and for a brief moment, we were all reminded of our true master – not reason, not rhetoric, but revenue. It was less interruption than revelation: every dialectic is merely foreplay before the commercial break.
Philosophically, what unfolded was a parody of our age. The human, flawed and febrile, draped in sophistry and drama. The machine, pristine and humourless, incapable of exasperation, immune to irony. Watching the two spar was like observing tragedy and farce collide: one side erring too much, the other not erring enough.
To Alex, credit is due. His performance, though riddled with error, reminded us that fallibility can be glorious – human folly rendered art. To ChatGPT, equal praise: it stood firm, the algorithmic Socrates, endlessly patient in the face of rhetorical hooliganism. And to the advert – well, dammit – applause too, for exposing the real structure of our public life. Even the grand clash of logos and algorithm must genuflect before Mammon’s mid-roll.
So what was this debate? Less a contest of minds than a hall of mirrors: reason made spectacle, fallacy made flourish, machine made stoic, and commerce made god. If we learned anything, it is that the Enlightenment never ended; it just signed a brand partnership.
The air is thick with bad takes. Scroll for five minutes and you’ll find someone announcing, usually with the pomp of a TEDx speaker, that “AI has no emotions” or “It’s not really reading.” These objections are less profound insights than they are linguistic face-plants. The problem isn’t AI. It’s the speakers’ near-total ignorance of how language works.
Audio: NotebookLM podcast on this topic.
Language as the Unseen Operating System
Language is not a transparent pane of glass onto the world. It is the operating system of thought: messy, recursive, historically contingent. Words do not descend like tablets from Sinai; they are cobbled together, repurposed, deconstructed, and misunderstood across generations.
If you don’t understand that basic condition, that language is slippery, mediated, and self-referential, then your critique of Large Language Models is just noise in the system. LLMs are language machines. To analyse them without first understanding language is like reviewing a symphony while stone deaf.
The Myth of “Emotions”
Critics obsess over whether LLMs “feel.” But feeling has never been the measure of writing. The point of a sentence is not how the author felt typing it, but whether the words move the reader. Emotional “authenticity” is irrelevant; resonance is everything.
Writers know this. Philosophers know this. LLM critics, apparently, do not. They confuse the phenomenology of the writer with the phenomenology of the text. And in doing so, they embarrass themselves.
The Licence Test
So here’s the proposal: a licence to comment on AI. It wouldn’t be onerous. Just a few basics:
Semiotics 101: Know that words point to other words more than they point to things.
Context 101: Know that meaning arises from use, not from divine correspondence.
Critical Theory 101: Know that language carries baggage, cultural, historical, and emotional, that doesn’t belong to the machine or the individual speaker.
Fail these, and you’re not cleared to drive your hot takes onto the information superhighway.
Meta Matters
I’ve explored some of this in more detail elsewhere (link to Ridley Park’s “Myth of Emotion”), but the higher-level point is this: debates about AI are downstream of debates about language. If you don’t grasp the latter, your pronouncements on the former are theatre, not analysis.
Philosophy has spent centuries dismantling the fantasy of words as perfect mirrors of the world. It’s perverse that so many people skip that homework and then lecture AI about “meaning” and “feeling.”
Yesterday, I suggested democracy is a mediocre theatre production where the audience gets to choose which mediocre understudy performs. Some readers thought I was being harsh. I wasn’t.
A mate recently argued that humans will always be superior to AI because of emergence, the miraculous process by which complexity gives rise to intelligence, creativity, and emotion. Lovely sentiment. But here’s the rub: emergence is also how we got this political system, the one no one really controls anymore.
Like the human body being mostly non-human microbes, our so-called participatory government is mostly non-participatory components: lobbyists, donors, bureaucrats, corporate media, careerists, opportunists, the ecosystem that is the actual organism. We built it, but it now has its own metabolism. And thanks to the law of large numbers, multiplied by the sheer number of political, economic, and social dimensions in play, even the human element is diluted into statistical irrelevance. At any rate, what remains of it has lost control – like the sorcerer’s apprentice.
People like to imagine they can “tame” this beast, the way a lucid dreamer thinks they can bend the dream to their will. But you’re still dreaming. The narrative still runs on the dream’s logic, not yours. The best you can do is nudge it; a policy tweak here, a symbolic vote there, before the system digests your effort and excretes more of itself.
a bad system beats a good person every time
W Edwards Deming
This is why Deming’s line hits so hard: a bad system beats a good person every time. Even if you could somehow elect the Platonic ideal of leadership, the organism would absorb them, neutralise them, or spit them out. It’s not personal; it’s structural.
And yet we fear AI “taking over,” as if that would be a radical departure from the status quo. Newsflash: you’ve already been living under an autonomous system for generations. AI would just be a remodel of the control room, new paint, same prison.
So yes, emergence makes humans “special.” It also makes them the architects of their own inescapable political microbiome. Congratulations, you’ve evolved the ability to build a machine that can’t be turned off.
(or: Why Neither Humans nor AI Create from Nothing)
In the endless squabble over whether AI can be “creative” or “intelligent,” we always end up back at the same semantic swamp. At the risk of poking the bear, I have formulated a response. Creativity is either whatever humans do, or whatever humans do that AI can’t. Intelligence is either the general ability to solve problems or a mysterious inner light that glows only in Homo sapiens. The definitions shift like sand under the feet of the argument.
Audio: NotebookLM podcast on this topic
Strip away the romance, and the truth is far less flattering: neither humans nor AI conjure from the void. Creativity is recombination, the reconfiguration of existing material into something unfamiliar. Intelligence is the ability to navigate problems using whatever tools and heuristics one has to hand.
I cannot be causa sui, and neither can you.
The Causa Sui conceit, the idea that one can be the cause of oneself, is incoherent in art, thought, or physics. Conservation of energy applies as much to ideas as to atoms.
We metabolise them through cognitive habits, biases, and linguistic forms.
We output something rearranged, reframed, sometimes stripped to abstraction.
The AI process is identical in structure, if not in substrate: ingest vast data, run it through a model, output recombination. The difference is that AI doesn’t pretend otherwise.
When a human produces something impressive, we call it creative without inspecting the provenance of the ideas. When an AI produces something impressive, we immediately trace the lineage of its inputs, as if the human mind weren’t doing the same. This is not epistemic rigour, it’s tribal boundary enforcement.
The real objection to AI is not that it fails the test of creativity or intelligence; it’s that it passes the functional test without being part of the club. Our stories about human exceptionalism require a clear line between “us” and “it,” even if we have to draw that line through semantic fog.
My Language Insufficiency Hypothesis began with the recognition that language cannot fully capture the reality it describes. Here, the insufficiency is deliberate; the words “creativity” and “intelligence” are kept vague so they can always be shifted away from anything AI achieves.
I cannot be causa sui, and neither can you. The only difference is that I’m willing to admit it.
Before I was a writer, before I was a management consultant, before I was an economist, and before I was a statistician, I was a student.
Video: Veritasium piece on Markov chains and more.
Back then, when dinosaurs roamed the chalkboards, I fell for a rather esoteric field: stochastic processes, specifically, Markov chains and Monte Carlo simulations. These weren’t just idle fascinations. They were elegant, probabilistic odes to chaos, dressed up in matrix notation. I’ll not bore you with my practical use of linear algebra.
So imagine my surprise (feigned, of course) when, decades later, I find myself confronted by the same concepts under a different guise—this time in the pocket-sized daemon we all carry: predictive text.
If you’ve not watched it yet, this excellent explainer by Veritasium demystifies how Markov chains can simulate plausible language. In essence, if you’ve ever marvelled at your phone guessing the next word in your sentence, you can thank a Russian mathematician and a few assumptions about memoryless transitions.
But here’s the rub. The predictive text often gets it hilariously wrong. Start typing “to be or not to—” and it offers you “schedule a meeting.” Close, but existentially off. This isn’t just clunky programming; it’s probabilistic dementia.
This leads me to a pet peeve: people who smugly proclaim they’ve “never used algebra” since high school. I hear this a lot. It’s the battle cry of the proudly innumerate. What they mean, of course, is they’ve never recognised algebra in the wild. They think if they’re not solving for x with a number 2 pencil, it doesn’t count. Meanwhile, their phone is doing a polynomial dance just to autocorrect their butchery of the English language.
It’s a classic case of not recognising the water in which we’re swimming. Algebra is everywhere. Markov chains are everywhere. And Monte Carlo simulations are probably calculating your credit risk as we speak. Just because the interface is clean and the maths is hidden behind a swipeable veneer doesn’t mean the complexity has vanished. It’s merely gone incognito.
As someone who has used maths across various fields – software development, data analysis, policy modelling – I can tell you that I use less of it than a physicist, but probably more than your average lifestyle coach. I say this not to flex but to point out that even minimal exposure to mathematical literacy grants one the ability to notice when the machines are quietly doing cartwheels behind the curtain.
So the next time your phone offers you a sentence completion that reads like it’s been dropped on its head, spare a thought for Markov. He’s doing his best, bless him. It’s just that probability doesn’t always align with meaning.
Or as the algorithms might say: “To be or not to – subscribe for updates.”
Oh no, not that again. As if we’ve all been composing from scratch, untouched by the grubby hands of history.
Audio: NotebookLM podcast on this topic.
I’m not simping for AI, but let’s have it out, shall we? Rick Beato—bless his fretboard-fingered soul—says AI-generated music sucks. And sure, some of it does. But here’s the punchline: most human-made music sucks too. Always has. Always will. The fact that an algorithm can now churn out mediocrity faster than a caffeinated teenager with GarageBand doesn’t make it less “art.” It just makes it faster.
I’m a bit chuffed that Rick’s channel removed my comment pointing to this response. I didn’t want to copy-paste this content into his comments section.
Video: Rick Beato discusses AI-generated music
The Myth of the Sacred Original
Newsflash: There is no such thing as originality. Not in art. Not in music. Not even in your favourite indie band’s tortured debut EP. Everything we call “creative” is a clever remix of something older. Bach reworked Vivaldi. Dylan borrowed from the blues. Even Bowie—patron saint of artistic reinvention—was a pastiche artist in a glittery jumpsuit.
What AI does is make this painfully obvious. It doesn’t pretend. It doesn’t get drunk in Berlin and write a concept album about urban decay to mask the fact it lifted its sound from Kraftwerk. It just remixes and reinterprets at inhuman speed, without the eyeliner.
Speed Isn’t Theft, It’s Efficiency
So the AI can spit out a passable ambient track in ten seconds. Great. That’s not cheating, it’s progress. Saying “it took me ten years to learn to play like that” is noble, yes, but it’s also beside the point. Horses were noble too, but we built cars.
The question isn’t how long did it take? but does it move you? If the answer is no, fine. Say it sucks. But don’t pretend your human-shaped suffering gives your song a monopoly on meaning. That’s just gatekeeping with a sad sax solo.
The Taste Problem, Not the Tech Problem
Let’s not confuse our distaste for bland music with a distaste for AI. Most of the pop charts are already AI-adjacent—click-optimised, algorithm-fed, and rigorously inoffensive. If you want soul, seek out the obscure, the imperfect, the human, yes. But don’t blame the machine for learning its craft from the sludge we fed it.
AI is only as dull as the data we give it. And guess what? We gave it Coldplay.
What’s Actually at Stake
What rattles the cage isn’t the mediocrity. It’s the mirror. AI reveals how much of our own “creativity” is pattern recognition, mimicry, and cultural reinforcement. The horror isn’t that AI can make music. It’s that it can make our music. And that it does so with such appalling accuracy.
It exposes the formula. And once you see the formula, you can’t unsee it.
Long Live the Derivative
So yes, some AI music sucks. But so do most open mic nights. Creativity was never about being wholly original. It was about saying something—anything—with whatever tools you had.
If AI is just another tool, then sharpen it, wield it, and for heaven’s sake, stop whining. The artist isn’t dead. He’s just been asked to share the stage with a faster, tireless, genre-bending freak who doesn’t need bathroom breaks.
Yesterday, I wrote about “ugly women.” Today, I pivot — or perhaps descend — into what Midjourney deems typical. Make of that what you will.
This blog typically focuses on language, philosophy, and the gradual erosion of culture under the boot heel of capitalism. But today: generative eye candy. Still subtextual, mind you. This post features AI-generated women – tattooed, bare-backed, heavily armed – and considers what, exactly, this technology thinks we want.
Video: Pirate cowgirls caught mid-gaze. Generated last year during what I can only assume was a pirate-meets-cowgirl fever dream.
The Video Feature
Midjourney released its image-to-video tool on 18 June. I finally found a couple of free hours to tinker. The result? Surprisingly coherent, if accidentally lewd. The featured video was one of the worst outputs, and yet, it’s quite good. A story emerged.
Audio: NotebookLM podcast on this topic (sort of).
It began with a still: two women, somewhere between pirate and pin-up, dressed for combat or cosplay. I thought, what if they kissed? Midjourney said no. Embrace? Also no. Glaring was fine. So was mutual undressing — of the eyes, at least.
Later, I tried again. Still no kiss, but no denial either — just a polite cough about “inappropriate positioning.” I prompted one to touch the other’s hair. What I got was a three-armed woman attempting a hat-snatch. (See timestamp 0:15.) The other three video outputs? Each woman seductively touched her own hair. Freud would’ve had a field day.
In another unreleased clip, two fully clothed women sat on a bed. That too raised flags. Go figure.
All of this, mind you, passed Midjourney’s initial censorship. However, it’s clear that proximity is now suspect. Even clothed women on furniture can trigger the algorithmic fainting couch.
Myriad Warning Messages
Out of bounds.
Sorry, Charlie.
In any case, I reviewed other images to determine how the limitations operated. I didn’t get much closer.
Video: A newlywed couple kissing
Obviously, proximity and kissing are now forbidden. I’d consider these two “scantily clad,” so I am unsure of the offence.
I did render the image of a cowgirl at a Western bar, but I am reluctant to add to the page weight. In 3 of the 4 results, nothing (much) was out of line, but in the fourth, she’s wielding a revolver – because, of course, she is.
Conformance & Contradiction
You’d never know it, but the original prompt was a fight scene. The result? Not punches, but pre-coital choreography. The AI interpreted combat as courtship. Women circling each other, undressing one another with their eyes. Or perhaps just prepping for an afterparty.
Video: A battle to the finish between a steampunk girl and a cybermech warrior.
Lesbian Lustfest
No, my archive isn’t exclusively lesbian cowgirls. But given the visual weight of this post, I refrained from adding more examples. Some browsers may already be wheezing.
Technical Constraints
You can’t extend videos beyond four iterations — maxing out at 21 seconds. I wasn’t aware of this, so I prematurely accepted a dodgy render and lost 2–3 seconds of potential.
My current Midjourney plan offers 15 hours of “fast” rendering per month. Apparently, video generation burns through this quickly. Still images can queue up slowly; videos cannot. And no, I won’t upgrade to the 30-hour plan. Even I have limits.
Uses & Justifications
Generative AI is a distraction – an exquisitely engineered procrastination machine. Useful, yes. For brainstorming, visualising characters, and generating blog cover art. But it’s a slippery slope from creative aid to aesthetic rabbit hole.
Would I use it for promotional trailers? Possibly. I’ve seen offerings as low as $499 that wouldn’t cannibalise my time and attention, not wholly, anyway.
So yes, I’ll keep paying for it. Yes, I’ll keep using it. But only when I’m not supposed to be writing.
Now, if ChatGPT could kindly generate my post description and tags, I’ll get back to pretending I’m productive.
Humans talk to large language models the way toddlers talk to teddy bears – with unnerving sincerity and not a hint of shame. “Do you understand me?” they ask, eyes wide with hope. “What do you think of this draft?” they prod, as if some silicon scribe is going to sip its imaginary tea and nod gravely. It’s not merely adorable – it’s diagnostic. We are, it turns out, pathologically incapable of interacting with anything more complex than a toaster without projecting mind, motive, and mild trauma onto it.
Audio: NotebookLM podcast on this topic.
Welcome to the theatre of delusion, where you play Hamlet and the chatbot is cast as Yorick – if Yorick could autocomplete your soliloquy and generate citations in APA format.
The Great Anthropomorphic Flaw (aka Feature)
Let’s get one thing straight: anthropomorphism isn’t a software bug in the brain; it’s a core feature. You’re hardwired to see agency where there is none. That rustle in the bushes? Probably the wind. But better safe than sabre-toothed. So your ancestors survived, and here you are, attributing “sass” to your microwave because it beeped twice.
“We don’t have a way of addressing an entity that talks like a person but isn’t one. So we fake it. It’s interaction theatre.”
Now we’ve built a machine that spits out paragraphs like a caffeinated undergrad with deadlines, and naturally, we talk to it like it’s our mate from university. Never mind that it has no bloodstream, no memory of breakfast, and no concept of irony (despite being soaked in it). We still say you instead of the system, and think instead of statistically interpolate based on token weights. Because who wants to live in a world where every sentence starts with “as per the pre-trained parameters…”?
Why We Keep Doing It (Despite Knowing Better)
To be fair – and let’s be magnanimous – it’s useful. Talking to AI like it’s a person allows our ape-brains to sidestep the horror of interacting with a glorified autocomplete machine. We’re brilliant at modelling other minds, rubbish at modelling neural nets. So we slap a metaphorical moustache on the processor and call it Roger. Roger “gets us.” Roger “knows things.” Roger is, frankly, a vibe.
This little charade lubricates the whole transaction. If we had to address our queries to “the stochastic parrot formerly known as GPT,” we’d never get past the opening line. Better to just ask, “What do you think, Roger?” and pretend it has taste.
And here’s the kicker: by anthropomorphising AI, we start thinking about ethics – sort of. We ask if it deserves rights, feelings, holidays. We project humanity into the void and then act shocked when it mirrors back our worst habits. As if that’s its fault.
When the Roleplay Gets Risky
Of course, this make-believe has its downsides. Chief among them: we start to believe our own nonsense. Saying AI “knows” something is like saying your calculator is feeling generous with its square roots today. It doesn’t know—it produces outputs. Any semblance of understanding is pure pantomime.
“We see a mind because we need to see one. We can’t bear the idea of a thing that’s smarter than us but doesn’t care about us.”
More dangerously, we lose sight of the fact that these things aren’t just alien – they’re inhuman. They don’t dream of electric sheep. They don’t dream, full stop. But we insist on jamming them into our conceptual boxes: empathy, intent, personality. It’s like trying to teach a blender to feel remorse.
And let’s not pretend we’re doing it out of philosophical curiosity. We’re projecting, plain and simple. Anthropomorphism isn’t about them, it’s about us. We see a mind because we need to see one. We can’t bear the idea of a thing that’s smarter than us but doesn’t care about us, doesn’t see us. Narcissism with a side of existential dread.
Our Language is a Terrible Tool for This Job
English – and most languages, frankly – is hopeless at describing this category of thing. “It” feels cold and distant. “They” implies someone’s going to invite the model to brunch. We have no pronoun for “hyper-literate statistical machine that mimics thought but lacks all consciousness.” So we fudge it. Badly.
Our verbs are no better. “Compute”? Too beige. “Process”? Bureaucratic. “Think”? Premature. What we need is a whole new grammatical tense: the hallucino-indicative. The model thunketh, as one might, but didn’t.
“We built a creature we can’t speak about without sounding like lunatics or liars.”
This is linguistic poverty, pure and simple. Our grammar can’t cope with entities that live in the uncanny valley between sentience and syntax. We built a creature we can’t speak about without sounding like lunatics or liars.
The Semantics of Sentimentality (Or: “How Does This Sound to You?”)
Enter the most revealing tell of all: the questions we pose. “How does this look?” we ask the model, as if it might blink at the screen and furrow a synthetic brow. “What do you think?” we say, offering it the dignity of preference. These questions aren’t just off-target – they’re playing darts in another pub.
They’re the linguistic equivalent of asking your dishwasher whether it enjoyed the lasagne tray. But again, this isn’t idiocy – it’s instinct. We don’t have a way of addressing an entity that talks like a person but isn’t one. So we fake it. It’s interaction theatre. You provide the line, the model cues the spotlight.
But let’s be clear: the model doesn’t “think” anything. It regurgitates plausible text based on mountains of training data—some of which, no doubt, includes humans asking equally daft questions of equally mindless systems.
Time to Grow Up (Just a Bit)
This doesn’t mean we need to abandon anthropomorphism entirely. Like most delusions, it’s functional. But we’d do well to hold it at arm’s length – like a politician’s promise or a milk carton two days past its date.
Call it anthropomorphic agnosticism: act like it’s a person, but remember it’s not. Use the language, but don’t inhale.
And maybe – just maybe – we need to evolve our language. Invent new terms, new pronouns, new ways of speaking about entities that fall somewhere between tool and companion. As we did with “cyberspace” and “ghosting,” perhaps we need words for proto-minds and quasi-selves. Something between toaster and therapist.
“If we speak to AI like it’s sentient, we’ll eventually legislate as if it is.”
Above all, we need to acknowledge that our language shapes more than just understanding – it shapes policy, emotion, and future design. If we speak to AI like it’s sentient, we’ll eventually legislate as if it is. And if we insist on treating it as an object, we may be blind to when that ceases to be accurate. Misnaming, after all, is the first sin in every myth worth reading.
The Mirror, Darkly
Ultimately, our tendency to humanise machines is less about them than it is about us – our fears, our needs, our inability to tolerate ambiguity. The AI is just a mirror: an elaborate, many-eyed, autofill mirror. And when we see a mind there, it may be ours staring back – distorted, flattened, and fed through a thousand layers of token prediction.
The tragedy, perhaps, isn’t that the machine doesn’t understand us. It’s that we’ve built something that perfectly imitates understanding – and still, somehow, we remain utterly alone in the room.
Philosophics 