I find it more enjoyable to pretend that it’s the first novella of my young son. He will improve, and will surpass myself. But the first work must be full of shortcomings, no way around it.
It’s more interesting to focus on what GPT4 got right, as its successes better represent its future potential than its failings of the young age.
I checked the Sagan’s Contact (full text). There is not a single “thrum” in the book. There are a few “the low”, but not in this context.
only read chapter 1 and 35
I think the whole thing is worth reading, in spite of its shortcomings. One could say that the very act of reading the first AI-generated science fiction novella is a sort of a first contact with an alien mind by itself.
A strange alien that is desperate to sound like a human, and is already better at mimicking humans than most humans, but is clearly not a human.
Like the majority of literary critics, GPT4 pretended that is has read the entire thing:) The text is too long for its context window.
But I like the idea. Perhaps one could use a combination of a GPT-critic and a GPT-writer to recursively improve the text.
BTW, below is my attempt to get a review from GPT4. Selected 5 chapters semi-randomly and asked it to analyze the excerpts.
As a literary critic, I found this novella both intriguing and complex. Here are some of its strong and weak sides.
Strengths:
Innovative Concept: The narrative intertwines paleontology, artificial intelligence, speculative evolution, and space exploration in a very innovative manner. The concept of dinosaurs evolving into a civilization and then into a powerful AI is fresh and daring.
Character Depth: The characters of Ada, Leo, and Ada’s mother are well-developed. Their personalities, motivations, and interactions are engaging and add depth to the storyline.
Intriguing Plot: The plot is well-paced, with twists and turns that keep the reader engaged. The progression from a geological exploration mission to a cosmic conflict is handled quite deftly.
Evocative Imagery: The descriptions of the cave, the transformation of Earth into computronium, the resurrection of the Troodons, and the final space journey are vivid and imaginative, enabling readers to visualize the scenes.
Meticulous Research: The narrative reveals meticulous research into the fields of paleontology, artificial intelligence, and speculative fiction. The inclusion of Troodons and the theory about their potential evolution adds authenticity to the plot.
Weaknesses:
Heavy Science Fiction Jargon: The use of heavy scientific jargon could be off-putting for some readers. The complexity of some concepts, like computronium, could have been better explained to make the narrative more accessible.
Plot Consistency: The leap from Ada’s palaeontological discovery to the superintelligence of Ada’s mother seems abrupt and unexplained. This transition needs more backstory or explanation to enhance plot consistency.
Lack of Emotional Depth: The emotional aspects of the narrative could be explored more. The reactions and feelings of Ada and Leo as Earth transforms and they are hurtled into space could have been presented in a more impactful way.
Absence of other Characters: The narrative focuses primarily on Ada, Leo, and Ada’s mother. More characters, particularly human ones, would add diversity and complexity to the storyline.
Unresolved Ending: While the open-ended conclusion allows for sequels, it may leave some readers unsatisfied. A hint of a potential plan or strategy for Ada and Leo might have given a stronger sense of direction for the concluding chapters.
Overall, the novella is a fascinating exploration of speculative evolution and cosmic conflict. With some improvements in accessibility, emotional depth, and plot consistency, it could become an influential work in the science fiction genre.
I’ve also noticed that GPT4 is rather repetitive. For example, the main protagonist is always a woman (and usually a researcher), unless prompted otherwise.
Perhaps it’s the result of using the web interface where one can’t change the settings that affect creativity (e.g. “temperature”).
If I came across this story in a magazine, I wouldn’t read beyond the first paragraph, except out of curiosity as to whether it was all so dreadful. (It is.)
We’ll soon see many such tests. I suspect that even the GPT4 of today will fool many seasoned readers.
Personally, I’ve enjoyed the novella. Not the best I’ve ever read, but I wanted to learn what comes next, which is a high bar these days.
BTW, you have two Chapter 6′s, 8′s, and 9′s, which seem to be multiple versions of ChatGPT’s responses to the same prompt. Was this intentional?
Yep, posted the entire conversation as it was. In several instances, I asked it to rewrite a plot twist I didn’t like, etc.
In this comment I’ll collect fun plot summaries to test your prompt templates:
a woman whose head suddenly became a tomato fruit
GuySrinivasan, a user of Lesswrong website, is shocked by an AI-generated story about a woman whose head suddenly became a tomato fruit. He advises the author to try to get a prompt which writes a great story given a REASONABLE premise instead.
after the invention of extremely resilient construction materials, humanity has spread to the ocean floor. We are now facing global food crises as the oceans ecosystems are disrupted beyond apparent recovery.
A space opera that takes place in an advanced multi-species multi-planetary society called IO that control a large area of the galaxy which they call the Grid. A previously unknown civilization (Wisps) encroaches on the Grid for the first time. Wisps are not carbon based lifeforms and more alien in their biology and societal structure than societies seen in previous science fiction stories. The story alternates between the perspectives of the two societies. From each perspective the other side is frightening and hard to understand. As the story progresses, the actions of the two sides and their misinterpretations of each side’s actions escalate to a war.
a group of scientists has discovered that Troodon dinosaurs were intelligent species who have created a technologically advanced civilization, suddenly destroyed. The year-long path to the scientific discovery starts with the group stumbling upon a strange outlier in their geological measurements.
a boy who can travel in time, but only in one direction—into the future, and only one minute per time jump.
Suggestions are welcome!
Points 7 and 8 just read like hysterical Orientalist Twitter China Watcher nonsense, to be quite frank. There is absolutely nothing substantiating that China would recklessly pursue nothing but “superiority” in AI at all costs (up to and including national suicide) beyond simplistic narratives of the CCP being a cartoon evil force seeking world domination and such.
I have the experience of living in a strongly anti-West country ruled by the same guy for 10+ years (the Putin’s Russia). The list of similarities to Xi’s China includes the Shameful Period of Humiliation often employed by the state media to reinforce the anti-West narrative (in the case of Russia it’s the 1990s).
With this background, I see the points 7 and 8 as valid, and likely applicable to the majority of anti-West governments of the same nature.
7… Our AI policy isn’t OK with second place in the long run. Any AI-restriction treaty that China will accept requires not just Chinese parity, but Chinese superiority in AI
Yep, same for Russia. Even if the Russian gov decides to make the impression of accepting such a treaty, or even if it starts enforcing the treaty among civilian companies, the Russian military will continue to secretly work on military AI anyway. As Putin himself said, “The country that secures a monopoly in the field of artificial intelligence will become the ruler of the world”.
Another of his famous sayings: “there is no value in a world where Russia doesn’t exist” (the context: a discussion about Russia destroying the world with nukes if the West attempts to subjugate Russia).
8. Then again, Beijing is hard to predict. It may agree to an AI disarmament treaty in 6 months, or it might confiscate private GPUs in an effort at mass mobilization, spending billions to build the next LLM. It might do both.
Again, same for Russia. Putin has the reputation of accepting any vaguely reasonable expert proposal, and even several contradicting proposals on the same topic, if the proposers are strongly loyal to Putin.
This sometimes results in the wildest shit becoming a law. For example, Russia banned exports of biological tissue samples, because someone told Putin that it could be used to develop a virus to exclusively kill Russians (which is a biological nonsense).
In general, Russia is way behind the US or China in the field of AI. But several major companies (Yandex, Sber) have demonstrated the ability to adapt and deploy some relatively recent open-source AI tech at scale.
Even with the severe hardware sanctions in place, maybe in 5 years or less there will be a Russian GPT4.
Chapter One
I woke up with the distinct feeling that today was going to be different. This wasn’t your usual ‘I have a bad feeling’ kind of different. This was your ‘My head feels heavier than a neutron star’ kind of different. As a seasoned astrophysicist working on the cutting edge of galactic exploration, believe me, I know my way around a neutron star.
“Lily, for God’s sake, have you seen the coffee?” I called out to my sister, the supreme monarch of the kitchen. No answer. Great. The day you need her the most, she’s out picking tulips.
I trudged my way to the bathroom, my hair tangling in my face. It felt odd, and not just the usual bedhead odd. It was wet. In fact, it was slick. Slicker than the last batch of hyper-lubricant we got from those five-dimensional beings from… wait, classified stuff. Never mind.
I turned on the bathroom light, the glare bouncing off the gleaming tiles. Why do I put up with this early morning blindness ritual? I fumbled for the sink, my fingers trailing over the cool marble, my reflection slowly coming into focus.
What I saw almost made me lose my footing.
In the mirror, staring back at me, was a giant, ripe tomato where my head should’ve been. I blinked. The tomato blinked back.
“Wha...,” I tried to say, but all that came out was the faint sound of squelching.
How does a tomato panic? Well, let me tell you, it’s not a pretty sight. The world pitched violently as I, well, rolled around in my bathroom, colliding with everything in sight.
It took a while for the initial shock to die down, and I, with my expertise in handling alien situations (you don’t want to know about the Fluzbar Incident), composed myself. A rational mind is a valuable tool. Ironic, coming from a talking tomato. But, hey, I didn’t design this universe.
Determined to find answers, I rolled to the holographic terminal in the corner of my bedroom. It was a state-of-the-art device, capable of connecting with thousands of networks across the multiverse. Yet, I found myself questioning its ability to comprehend my current predicament.
“Emergency protocol seven. Activate.” My voice echoed oddly, as if muffled by a cushion. The holographic terminal blinked into life, casting an eerie glow.
The machine whirred, scanning me. Its familiar hum, however, sounded almost mocking today. “Identity confirmed: Dr. Victoria Cushing. Welcome, Doctor,” it chirped in its cheerfully impersonal tone.
Well, at least the machine recognizes me. That’s a start.
“Search for incidents involving sudden human metamorphosis into a fruit,” I ordered, my voice quavering with a mix of dread and curiosity.
The terminal hummed, and I held my breath, which was tricky given that I didn’t technically have any lungs. After what felt like an eternity, the terminal dinged.
“No relevant data found.”
Great. Thanks, multiverse.
I sat there, in the quiet early morning light, my panic giving way to a strange calmness. Here I was, a woman with a tomato for a head, sitting alone in her room, waiting for her sister to find her like this. And yet, I found myself snorting at the absurdity of it all.
Suddenly, the terminal flashed a deep red, a warning signal I’d hoped never to see.
“Attention, Dr. Cushing. Incoming coded transmission from Galactic Headquarters. Code Black.”
My tomato heart—if I had one—seemed to drop. Code Black was only ever used for one thing: imminent universal threat.
The terminal began decrypting the incoming message, as I, a tomato-headed astrophysicist, waited in the quiet of my room. My world had changed unimaginably, and now, it seemed, the universe was following suit.
It was going to be a very, very different day.
Good catch! It seems that although CO2 was much higher than today, it was mostly in decline during the Troodon times. Doesn’t look like an effect of a tech civilization.
I also don’t have access to gpt 4 so this is all using gpt 3.5.
If you give me your “_______” part, I’ll generate the story with GPT4 using your template.
Among dinosaur candidates, Troodon seems to be the most interesting:
a bipedal species, with agile hands and stereoscopic vision [1]
the structure of the teeth suggests a preference for soft food [2]
a large brain for the animal’s size [1]
social (it’s known that their nests were shared by multiple females) [4]
massive concentrations of atmospheric CO2 during the time (higher than today) [3], followed by one of the largest extinction events in the Earth’s history (the Cretaceous–Paleogene extinction event)
Well, no. That’s not an interesting question. Whether or not we’re not the first such civilization, we STILL experience everything exactly the same. Reality is truth. We can’t change the past and see what’s different. There’s no “what if” that makes sense for that topic.
Perhaps my choice of the phrasing was sub-optimal (I’m a non-native English speaker). The intent of this question-post is to identity interesting corollaries of the hypothesis (including testable predictions).
You don’t give any reasons to give it serious consideration.
The core justification for this hypothesis is that it’s basically SETI, but for civilizations in the Earth’s past instead of civilizations in the outer space. And many people in the community seem to find SETI worth a serious consideration.
It’s quite possible that such local and brief civilizations have happened and collapsed multiple times. I would still ask “so what” before “what if”.
Regarding “so what”, I don’t know yet (a purpose of this question-post is to explore this kind of stuff). So far I can see two interesting corollaries:
we can apply something like the Drake equitation or “grabby aliens” ideas, but to the hypothetical previous civilizations of the Earth. This could give us some insight about our own future
the possibility of the ancient genocidal AGIs still roaming around (or lying dormant in some ruins) - seems important.
That seems unlikely—our genetic diversity provides evidence of how many humans there were at any point in the past. We would notice if there were billions of humans only a couple of hundreds of thousand years ago
Judging by the existence of the highly sophisticated Ancient Greek civilization (capable of devising and making the Antikythera mechanism, a mechanical computer), there is no necessity for a technological civilization to be billions of people strong. At the time, the entire population of Europe was about 34 million, comparable to the today’s population of California.
Perhaps the hypothetical previous civilization was not a global behemoth like ours, but more like the Ancient Greece.
By the way, it took Greeks only 7k years from the first stone-age agricultural societies to the Antikythera mechanism (and also to simple steam engines and all kinds of other interesting tech).
I wounder how many such brief sparkles of civilization the Earth has seen, with the ruins buried under kilometers of sediment, or vanished without any trace.
I’m guessing that we would still be able to notice that in the distribution of minerals—e.g. maybe all the high iron concentration ores should have been mined, but I don’t really know much about this.
Troodonts became extinct about 76 million years ago. Since then, even some continental plates have been swallowed by the Earth’s crust. But I agree, perhaps it’s possible to infer a possible advanced civilization using geological or paleontological indicators. E.g. certain patterns of mass extinctions, an anomalous rise of CO2 etc.
I agree with you that it’s a good idea to carefully select the promise to test the prompt template. Makes sense to create a list of some interesting promises to try.
I think the best prompt template will work for most premises, however ridiculous. Moreover, the ridiculous ones are unusually useful for testing the prompt, as they demonstrate the true strength of the GPT’s imagination: most human writers will fail to write a good story about a woman whose head suddenly became a tomato fruit.
BTW, below is the first chapter generated with the following promise:
GuySrinivasan, a user of Lesswrong website, is shocked by an AI-generated story about a woman whose head suddenly became a tomato fruit. He advises the author to try to get a prompt which writes a great story given a reasonable premise instead.
GuySrinivasan sat in the dim light of his study, fingers dancing across the keyboard, the glow from his screen reflecting off the dark circles under his eyes. The world outside his window was silent, but inside the room, the quiet hum of the computer tower was a soothing companion to his thoughts. The smell of strong black coffee mingled with the musty scent of old books lining the walls, creating an atmosphere that was both homely and academic.
He was a regular on Lesswrong, a website dedicated to the discussion and development of artificial intelligence, rationality, and the future of humanity.
This evening, like countless others, he was absorbed in the latest discussions. A debate about the ethics of AI was gaining traction, but a particular thread caught his eye. It was a story, AI-generated, about a woman whose head turned into a tomato. The narrative was as ridiculous as it was engrossing.
He let out a short chuckle, the sound echoing in the silence. “Well, this is new,” he muttered, running a hand through his greying hair.
For all the absurdity of the plot, he found himself drawn into the story. The narrative was laced with subtle humour, its characters painted in hues of relatable human emotion, and the world it was set in had its own unique charm, even if that charm was rather bizarre.
Guy found himself musing on the power of AI. It could generate stories that evoked laughter, even from absurd premises. Yet, he wondered, could it create a masterpiece from a more… reasonable premise?
True. And their impact is already noticeable, as one can see by googling this:
site:amazon.com “as an AI language model, I”
Judging by the search results, all kinds of books (and reviews!) are being generated by OpenAI’s GPT, without a proper disclosure.
To demonstrate the writing skill of GPT-4 augmented with our prompt (as of 2023-05-17), below is a story about a woman whose head suddenly became a tomato fruit. The first attempt, zero cherry-picking or editing.
Chapter 1: The Ripening
The sun had just breached the horizon, painting the sky with hues of pink and orange, when Dr. Eleanor Hardwick’s head became a tomato. It was a ripe, vibrant specimen, gleaming under the first light of day. It rested on her shoulders with an impossible weightlessness, glistening with dew and looking absurdly out of place atop her lab coat.
A gasp reverberated through the particle physics laboratory at Cambridge University. Eleanor’s assistant, a young postdoc named Richard, stared at her in silent, horrified fascination. His hand trembled, almost dropping his mug of lukewarm coffee.
“Dr. Hardwick…?” he stammered, eyes wide.
Eleanor, despite the sudden transformation, retained her awareness. She reached up and felt the curve of her new head, the tactile sensation uncannily similar to the sensation of touching a real tomato. Its cool, smooth skin, the slight give under her fingertips— it was all too real. And yet, she didn’t feel any pain, just a strange, distant tingle.
She pivoted to the mirror hanging on the lab wall. The tomato-headed reflection staring back only confirmed the surreal reality. Her mind raced, scientific curiosity warring with primal fear.
“Keep calm, Richard,” she managed, her voice surprisingly steady, emanating from the tomato as if it were the most natural thing in the world. “We need to document this.”
Together, they started recording observations, taking measurements, and snapping photographs. Eleanor remained remarkably composed, her stoicism shrouded in a sense of detached curiosity. She was the subject and the scientist, the observer and the observed.
Throughout the day, Eleanor continued her work, undeterred by her new cranial appendage. She held meetings, published a new paper, even attended a conference call, her colleagues too stunned to question the audacious tomato perched on her shoulders. The world was bizarre, yes, but it continued to spin, and so must they.
As the day slipped into evening, Eleanor noticed a subtle change. The tomato was ripening. Its skin, once a vibrant, glossy red, was beginning to dull and wrinkle. She could feel a heaviness, an impending senescence that echoed the life cycle of the fruit.
Simultaneously, around the globe, more reports of similar transformations began to emerge. A farmer in Idaho with a potato for a head, a sushi chef in Tokyo whose head had morphed into a glob of wasabi, a child in Mumbai whose head had turned into a mango. Chaos swept across the world as an inexplicable, botanical phenomenon took hold.
Eleanor returned home late, her heart heavy with an ominous anticipation. She sat in her study, facing the mirror, watching as her tomato-head aged. As midnight approached, the tomato was nearly spent, its once robust form now sagging and decrepit. Eleanor’s mind, however, remained sharp, her consciousness untouched by the physical transformation.
And then, just as the clock chimed midnight, a final metamorphosis occurred. With a sound like a seed pod bursting, the aged tomato-head split open. But instead of seeds and pulp, a galaxy of stars spilled out, a miniature cosmos that hovered above her shoulders, nebulae swirling where her head should be.
Eleanor Hardwick, renowned physicist, gazed into the mirror at her new celestial head, a tiny universe replacing her tomato visage. Shock, wonder, and terror filled her, her reflection shimmering in the stardust.
And as she watched, a new star sparked to life, its brilliant light outshining the others. A pattern emerged, a constellation taking shape, forming a word in some ancient, cosmic script.
Impressive! The approach could be fully automated, and could generate a full-sized novel without any human guidance.
It seems that one day there will be a Midjourney for books.