Was I an AI all along?

by Ana Lopez

We started a cult over the weekend. It was one of those things that happens when you decide to stop drinking for a few weeks. It’s an avocado-oriented octopus cult called Octo-guacamolians. But that’s not important now. What is importantly, we put the parameters of cult into GPT-4, and it came with some remarkably cohesive and reasonable rites, rituals, and, well, all the other aspects of cult. Later that same weekend, I reflected on what I’ve been doing for much of my life and started to wonder if I was a proto-AI for a while.

A publisher saw the post and asked if I wanted to write a book on macro photography. I said yes, and then had to learn how to actually do macro photography.

You see, I was in an interesting situation there for a while. I wrote a stack of books on photography, starting with one on macro photography, followed by a bunch of others. Portraits, travel photography, etc. In the weird times before we settled on “mirrorless” for the current range of image capture devices, there was a hot moment when no one really knew what to call them, so we called them Compact Mirrorless Cameras (CoSyCa) and so on – and brilliantly I thought I’d call the whole genre EVIL – electronic viewfinder, interchangeable lens. The publisher agreed, and we even ended up publishing a book called EVIL photography. Those were the days of experimentation, a brave, brand new world where no one really knew what was what, where was true, or if anything really mattered.

The story of my book on macro photography was very interesting; in 2005 I built a macro lens out of a Pringles can (actually it was just a handy tube to reverse a 50mm lens, but… it worked!), which ended up on slashdot, digg, and all those pre-Reddit-era link aggregation sites. In the process I accumulated loads of traffic and learned the hard way why we use AWS and such these days – in the mid noughties we had our own servers which meant my host was very grumpy that there was suddenly a ton of traffic to this one particular page and threatened to disconnect the server because it was taking up too many resources. Ah, the heady days of the early internet.

Anyway, a publisher saw the post and asked if I wanted to write a book on macro photography. I said yes, and then had to learn how to actually do macro photography. The beauty of book publishing is that it takes a long time. So I bought a new camera, wrote a letter to Canon saying I was writing a book on macro photography, asking them to please send me some macro lenses, and went to my local bookstore and bought a bunch of books and magazines about macro. I spent the next four months watching porn (that was my day job – long story) and taking macro shots, educating myself and taking notes as I went along. I ended up distilling all my notes and lessons into my first book.

All subsequent books were essentially the same: I learned everything I could about a subject, distilled it, and wrote it down, illustrating with photographs I took along the way. Are these the best macro/travel/portrait shots you’ve ever seen? Probably not. But my publishers would tell me that was okay; I had the rare gift of learning the thing, doing the thing, then teaching it and stringing together sentences that mostly made sense in a way that book buyers seemed to appreciate.

In addition to writing my own books, I’ve also ghostwritten a couple of books (most of which I can’t say anything due to NDAs and contracts, ssssh), but they were the same thing, just in a different way. I took in as much information as I could and then distilled it into a coherent form, adapting my style as best I could to something the other person would plausibly have written. I’ve written books on venture capital, photography and some much more esoteric subjects.

As I started learning more about how the AIs work – how they can mimic other artists’ forms and even other writers’ writing styles – I found myself having an existential crisis. This thing that I’ve been doing for over 20 years can now be done by computers.

As a college student, I had some internet friends who were dilletantes who played words and made the stupidest prose we could, in the style of Franz Kafka, Werner Herzog, and the OMG! EXCITING! KAWAII! styles that swept across the internet. As a writer, it was fun and educational to get a sense of how much flexibility there is, stylistically and creatively, in writing words.

I must admit I was afraid to ask GPT-4 to try out some of the writing prompts I remember from the old days.

I asked it to “Write 100 words about the joy of kittens in the style of Werner Herzog”:

The joy of kittens is a fleeting, visceral experience, just a glimpse into the chaos of existence. As they frolic, we are reminded of our own primal desire to play, to explore the unfathomable cosmos. These tiny creatures embody the fragility of life, their innocence carrying the weight of time’s relentless progression. But in their eyes lurks an indomitable spirit, a force that defies the entropic nature of the universe. It is in these ephemeral moments that we are repelled from the crushing indifference of the cosmos, our hearts swell with warmth, as we are engulfed in the ecstasy of their presence.

I asked it to “Write 100 words about the joy of kittens in the style of Franz Kafka”:

In the shadowy corners of existence, one can find solace in the humble presence of kittens. Their delicate spinning, woven into the fabric of reality like an intricate tapestry, is an enigmatic paradox of innocence and pristine nature. The joy they evoke, a fleeting moment of tranquility from the existential weight we carry, is an elusive treasure that escapes our grasp like a whisper in the wind. The dance of feline innocence, reflected in their quivering eyes, a window into the depths of their souls, fills the emptiness of human desire with a warm, ephemeral glow, temporarily making the unbearable burden of existence bearable.

And my heart broke a little.

God, this is good.

This unassuming little AI was seemingly effortlessly able to do what my compatriots and I had toiled for hours. The consequences of that are terrifying on so many levels. Fake news, fake reviews, anything fake, can now be rolled out on an industrial scale, and all good enough to be just about plausible.

It is often said that humans will do their job until machines can come along that can do it well enough for less money. That’s true for most of the field of robotics – it is possible (perhaps) to build a car by hand, but robots have taken over much of production for a reason.

When I was asked to write books on various topics, I think about how similar my instructions were to the kind of prompts I now give to GPT. “Hey Haje, could you write a book about travel photography? Same style as your portrait bookbut focused on lighter gear and taking pictures along the way?” All right. Yes sir, I can.

And in the midst of all this, I am reminded of the time I received a copy of a book with my name on the cover, but which I did not write.

And in the midst of all this, I am reminded of the time I received a copy of a book with my name on the cover, but which I did not write. My book publisher had repurposed most of the copy I wrote for a book that flopped, had an editor rewrite parts of it, and then republished it with a completely different title and angle. Somehow that also happened while the publisher was being acquired or sold, or going through a management change, so no one really told me this was happening. The first time I knew this book existed was when a FedEx box of five copies showed up on my doorstep, followed (a few days later) by (ironically) my pre-check. Legally they were free: I had canceled the rights to my book and they were able to turn it into cartoons, bobbleheads, movies or dance performances. At least, that’s how I read “all media” – but it turns out that “any media” can also mean “another book.” Stupid me.

In today’s world of generative AI, all of the above doesn’t sound completely outrageous. But I’d be lying if I said I didn’t have a huge, Texas-sized portion of déjà vu as I watch AI unfold before our very eyes.

What bothers me is whether humans are still better than our robot overlords. And that’s what really scares me. A generative AI with full access to the internet can better research, write and post every human being. It can mimic any style of writing and can even throw typos into the mix to throw you off its scent, should it decide it’s necessary. There are still some supposed tell-tale signs of AI-generated text, but as a writer I have to admit I don’t know what I’m looking for, and I’ll be fooled just as much as anyone. point.

The really scary thing is how we got to GPT-4 so quickly, and how many numbers are left before we hit infinity. In other words, GPT-4’s shortcomings will be shredded by what comes next, and as a writer, I feel I have every reason to worry.

Oh, that cult we formed? We made it together over a delicious meal of pallet wine (yes, really – wine bought by the pallet, which I did not participate in, per my previous comment about not drinking) and Mexican food. Introducing The Octo-guacamolians: a group dedicated to the worship of an eight-armed avocado god named Guacamoctopus. They hold weekly rituals that involve creating intricate guacamole mandalas and underwater dance performances.

I mean. If it didn’t exist before, it exists now.

Was I an AI all along? by Haje Jan Kamps originally published on businessupdates.org

Related Posts