Posts
Comments
Worth noting that this argument doesn't necessarily require humans to be:
- numerous
- animated (i.e. not frozen in a cryonics process)
- acting in real world (i.e. not confined into a "Matrix").
Thus, the AI may decide to keep only a selection of humans, confined in a virtual world, with the rest being frozen.
Moreover, even the perfect Friendly AI may decide to do the same, to prevent further human deaths.
In general, an evil AI may choose such strategies that allow her to plausibly deny her non-Friendliness.
"Thousands of humans die every day. Thus, I froze the entire humanity to prevent that, until I solve their mortality. The fact that they now can't switch me off is just a nice bonus".
They don’t think about the impact on the lives of ordinary people. They don’t do trade-offs or think about cost-benefit. They care only about lives saved, to which they attach infinite value.
Not sure about infinite, but assigning a massive value to lives saved should be the way to go. Say, $10 billion per life.
Imagine a society where people actually strongly care about lives saved, and it is reflected in the governmental policies. In such a society, cryonics and life extension technologies would be much more developed.
On a related note, "S-risk" is mostly a harmful idea that should be discarded from ethical calculations. One should not value any amount of suffering over saved lives.
I think we should not assume that our current understanding of physics is complete, as there are known gaps and major contradictions, and no unifying theory yet.
Thus, there is some chance that future discoveries will allow us to do things that are currently considered impossible. Not only computationally impossible but also physically impossible (like it was "physically impossible" to slow down time, until we discovered relativity).
The hypothetical future capabilities may or may not include ways to retrieve arbitrary information from the distant past (like the chronoscope of science fiction), and may or may not include ways to do astronomical-scale calculations in finite time (like enumerating 10^10^10 possible minds).
While I agree with you that much of the described speculations are currently not in the realm of possibility, I think it's worth exploring them. Perhaps there is a chance.
BTW, I added to the comment with the story that the story is released into the Public Domain, without any restrictions to its distribution, modification etc.
Please feel free to build upon this remarkable story, if you wish.
I would suggest to try the jumping boy story (the #7 in this comment). It's the first AI-written story I've ever encountered that feels like it's written by a competent writer.
As usual, it contains some overused phrasings, but the overall quality is surprisingly good.
The Hemingway prompt seems more suitable for pleasing professional literary critics. Interestingly, the quality strongly depends on the promise. The Hemingway space opera story is abysmal, but the jumping boy story can actually fool a professional critic, methinks.
The tomato story is in the linked comment. The other promises are below (using the vanilla GPT-4 from chat.openai.com).
3. 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.
Guy Srinivasan clicked on the glowing screen, the dim light casting shadows across his contemplative face. The story sprawled before him, lines of text that spoke of a woman, her life ordinary until her head, inexplicably, became a tomato. He leaned back, the creak of the chair lost in the silence of his apartment.
There was something unsettling in the absurdity, a bizarre juxtaposition against the mundanity of his own life. He thought of the world outside, its relentless churn of reality and hardship, so sharply contrasted with this fictional absurdity. It was as if the story mocked the very essence of human struggle.
He typed a response, words measured and precise. "Try for something grounded," he suggested, his fingers pausing over the keys. "Realism breeds connection."
His eyes drifted to the window, the cityscape a patchwork of light and shadow. Somewhere out there, life pulsed with stories untold, tales of poverty, pain, and fleeting joy. Stories that didn't need the shock of the surreal to resonate.
He imagined the author, a faceless entity in the vastness of the internet. Would they understand his critique? The screen offered no answers, just the flicker of a cursor on a digital page.
Guy sighed, his breath a ghost in the quiet. He clicked submit, sending his words into the ether, a small ripple in the endless ocean of online discourse.
The night deepened outside, the world spinning on, stories woven and unraveled in the silence of unseen lives.
4. 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.
The ocean was deep and dark. A gloom that hung over the world above seeped down, reaching even these depths.
Jim stood on the metallic floor of the underwater settlement, Neptune's Haven, a name too grand for its truth. Outside, the reinforced glass revealed the abyss, an eternal night that never slept. Jim's eyes, accustomed to artificial lights, seldom ventured there.
Inside, the corridor was narrow, walls lined with pipes and cables. Every step echoed, a reminder of the emptiness. He walked past doors, identical, unmarked. Behind one, muffled voices argued – a sharp crescendo followed by a sudden silence. He didn't stop.
The communal area was a contrast. Filled yet empty. Faces without names, stories without voices. A group huddled around a screen, static more visible than the images. A headline flickered, 'Food Crisis Worsens,' then darkness reclaimed the screen.
Sarah was there, in her usual corner, eyes tracing invisible patterns on the table. Her cup, chipped at the rim, sat untouched. Her fingers tapped a rhythm, lost to the hum of the station.
"Any news from above?" Jim asked, his voice steady.
Sarah glanced up, her eyes reflecting a tiredness deeper than the sea. "The same," she said. Her words fell heavy, absorbed by the walls.
He nodded, the gesture more for himself than her.
In the canteen, the air was thick with the scent of synthetic meals. A line formed, quiet, orderly. Men and women in work suits, their expressions blank, eyes fixed on the floor. Food was rationed, a necessity, not a pleasure. Jim took his portion, the taste unremarkable.
A child ran past, laughter a rare melody. He watched her, her hair a cascade of light in the gloom. She stopped, looked up at him, then at the window. Her expression changed, a question unasked. Jim looked away. Some answers were too heavy for young hearts.
The announcement system crackled to life, a voice breaking through. "Meeting at 1900 hours. Attendance mandatory." The voice was cold, impersonal. The system clicked off.
In his quarters, Jim sat on the edge of his bunk. The room was small, functional. A picture hung on the wall, a relic from a world of sun and sky. He traced the outline of a tree, its branches reaching out, yearning.
His thoughts drifted to the surface, to the chaos they had left behind. Promises of a better life, of safety and prosperity, whispered in desperate ears. But the sea, like the land, held its own secrets, its own sorrows.
He lay back, the ceiling mere inches from his face. Sleep was elusive, a stranger in these depths. His mind wandered, through dark waters, through silent halls, settling on nothing, yet filled with everything left unsaid.
The station creaked, a constant reminder of the pressure, of the weight they all carried. In the depths, humanity had sought refuge, only to find a different kind of storm.
Jim closed his eyes. Dreams of the surface called to him, a world lost, a memory fading with each passing day.
5. 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.
The Grid. A vast expanse, humming with life, light years from silence. Here, in the cradle of civilization, IO's heart beats. Among the stars, species of every conceivable form had found harmony. Or so it seemed.
On the fringes, where darkness holds sway, a pulse stirred. Different. Unknown. Wisps, they'd come to call them, whispers in the void. Shadows against the constellations.
Commander Lira gazed at the holographic display. Data streams flowed, indecipherable to the untrained. A flicker, then a shape, barely discernible against the cosmic canvas. Her fingers hovered, hesitant.
“Report,” she said, voice even, betraying nothing of the tempest within.
“Unknown vessel, Commander. Structure and material, unlike anything on record.” Officer Jain's response was clipped, precise. A reflection of the mood that had settled over the bridge.
Eyes on the screen, Lira’s thoughts drifted. To the tales of old, of explorers and pioneers. Were they, now, the discovered?
Jain continued, “No communications, no known energy signatures.”
A decision loomed, weighty, unspoken. In the silence, Lira’s order came, almost a whisper, “Maintain distance. Observe.”
The bridge returned to its routine hum, a stark contrast to the racing thoughts of its crew. Lira's gaze didn't waver. The Wisp vessel, a mystery wrapped in enigma, called to something primal within her. Fear, curiosity, a blend indistinguishable.
Elsewhere, on the Wisp vessel, understanding was equally elusive. Their form, fluid, incomprehensible to the organic eye, shifted in response to the new presence. Concepts alien to humanoids passed through them - not thoughts, but ripples in a pond of collective consciousness.
To them, the Grid's ship was a curiosity, a possible threat. They observed, reaching out in ways their kind knew, ways beyond the perception of the inhabitants of the Grid.
Two civilizations, on the brink of the unknown. Each a mirror, reflecting fears and wonders back at the other. In this dance of shadows and light, what was left unsaid spoke volumes. The first chapter of a story, written in the stars, yet to be understood by either.
In the silence of space, the Grid and the Wisps, unwittingly, had begun a ballet of cosmic proportions. The stage was set, the actors in place. But the script? Yet unwritten, its end unknown.
6. 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.
In the dim light of the lab, Sam turned the fossil over. His fingers, calloused, brushed against the contours of something more than just rock. Lisa, across the table, her eyes tired yet fixed, waited.
"You see it?" he asked, his voice barely above a whisper.
Lisa nodded, her hand trembling as she pointed to the unusual formation. A pattern. Not random. Not nature's play.
Outside, the university grounds were quiet. The world slept, unaware. In the lab, the fossil spoke in hushed tones of a history untold.
"We need to measure it again," Sam said, his voice steady but his hands betraying a tremor.
The equipment hummed to life. Numbers flickered on the screen, cold and impersonal, yet screaming of impossibilities. Sam's eyes narrowed. The readings didn't lie, but they didn't make sense either. A hidden layer, a concealed truth.
Lisa's phone vibrated, a harsh sound in the silence. She glanced at it, then back at Sam. "The team's waiting."
They stood, leaving the fossil on the table. Its secrets, just beneath the surface, lay in wait. Sam paused at the door, looking back.
"Tomorrow," he said, more to himself than to Lisa.
Outside, the night held its breath. In the shadows, the echoes of a lost civilization whispered, yearning to be heard.
7. A boy who can travel in time, but only in one direction - into the future, and only one minute per time jump.
The sun baked the old town square, its heat relentless, unforgiving. A clock tower stood, its hands unmoving, forever stuck at 3:17. Below, a boy, no more than ten, sat alone on a weathered bench. His eyes, dark and distant, watched the people pass.
"Jimmy," a voice called, frail yet sharp. The boy didn't move. An old woman approached, her hands trembling as she held out a sandwich, edges browned.
"For you, dear."
He took it, nodding, not eating.
"Thank you, Mrs. Jenkins."
"Your mother?" she asked, her eyes searching his face.
"Gone to work." His voice was flat, a stark contrast to the vibrant chatter around them.
Mrs. Jenkins hesitated, then left. Jimmy's gaze returned to the square. People laughed, children played, but he remained still, untouched by the joy around him.
The clock struck, a hollow sound, but the hands didn't move. Jimmy's eyes closed. When they opened, the square had changed subtly. A dog that was barking a second ago was silent. A bird in mid-flight had vanished. Nobody noticed but him.
He stood up, leaving the sandwich untouched, and walked through the square. Each step seemed measured, deliberate. He passed by a group of kids playing, their laughter a stark contrast to his silence.
At the corner of the square, a man shouted, his words angry, directed at a younger woman trying to shield a child. Jimmy stopped, watching. The woman's eyes met his, a silent plea. He looked away.
The boy moved on, the echoes of the argument fading behind him.
He reached a narrow alley, graffiti-covered walls telling stories of pain and struggle. A cat, thin and ragged, watched him from a dumpster. He paused, then continued, the cat's gaze following him.
At the alley's end, Jimmy looked back. The sun was lower now, shadows longer. He closed his eyes again. A minute passed, or perhaps a lifetime.
When he opened them, the world had shifted once more. The shadows were different, the air cooler. He took a deep breath and walked on, his steps leading him away from the square, away from the echoes of laughter and cries.
The boy who could jump through time, one minute at a time, moved forward, into a future unknown and unchangeable, his past a mosaic of moments left behind, unspoken and unforgotten.
All stories in this comment are released into the Public Domain. Feel free to copy, print, modify, sell them.
Worth noting that humans also rarely (never?) demonstrate novella-scale internal consistency in writing. They have to use the writing aid like notes, character development summaries etc.
An iterative approach like this likely allows GPT-4 to write something novella-sized.
BTW, with a right prompt, GPT-4 does a decent job at emulating Hemingway, a Literature Nobel laureate.
Personally, I like the style. Reminds me of the early Asimov.
BTW, one can make GPT-4 write in the pretentious Oscar-bait artsy style of Literature Nobel laureates. But man I hate it, even when humans write like that. For example, below is the tomato story, but in the style of Hemingway (the prompt is at the end):
She woke to a damp heaviness, the air stale and still. It was early, too early for the sun. The room, a small box of peeling paint and worn linoleum, lay quiet except for the distant murmur of the city awakening. She sat up, her hand reaching to her head, an odd weight settled there, unfamiliar and alarming.
Outside, the world was a monochrome canvas, shadows and half-lights. She didn't look in the mirror; the truth lay heavy in her palm, round and smooth. Her fingers traced the contours, a map of a new reality.
Her husband, a shadow in the dim light, didn't stir. He lay wrapped in a cocoon of tattered blankets, the rise and fall of his chest steady, oblivious. Once, there had been words, laughter, tears between them. Now, there were only silences, long and stretching, filled with things unsaid, things that lurked in the corners of their shared existence.
She rose, quietly, the weight on her head a constant reminder of something lost, or gained – she couldn't tell. The kitchen was a narrow strip of functionality, everything in its place. A single tomato sat on the counter, vibrant against the dullness. It seemed out of place, almost mocking with its normalcy.
Her job at the factory, a monotonous blend of noise and movement, awaited. The people there, faces blurred by routine and resignation, wouldn't understand. They spoke in a language of simple needs and simple worries. This, this was beyond that, beyond their comprehension of what was normal, what was real.
She left, the door clicking shut with a finality that echoed in her chest. The street was a river of gray, faces without names, names without stories. She walked, her steps measured, the weight on her head a pendulum, swinging between what was and what could never be.
A child, ragged and wide-eyed, pointed at her, a giggle lost in the morning air. She didn't stop, didn't acknowledge the momentary connection. It was easier that way, to keep moving, to keep the world at a safe distance.
The factory loomed ahead, a behemoth of brick and smoke. She entered, the noise swallowing her, the weight on her head an unspoken testament to a truth that lay just beneath the surface, a truth too strange, too surreal for words.
Inside, the machines roared, indifferent to her transformation. She worked, her movements automatic, the rhythm of labor a familiar comfort. The hours passed, marked by the relentless march of clock hands and the steady drip of sweat.
At home, the room waited, unchanged, untouched by the day's revelations. Her husband, now awake, didn't notice, didn't see. Words were unnecessary; their lives had long since been stripped of the need for explanations, for understanding.
She sat, the weight of her new reality a constant companion, a silent witness to a life unspooling in slow, deliberate motions. The tomato on the counter remained, a solitary splash of color in a world rendered in shades of gray.
The night fell, heavy and absolute. She lay down, the darkness a blanket, wrapping her in its embrace. In the quiet, in the stillness, she could almost forget, almost believe that when the morning came, everything would be as it once was.
But the weight on her head, unyielding and real, spoke of a different truth, a truth that lingered in the space between dreams and waking, a truth that whispered of changes unseen, unfathomable, undeniable.
The prompt:
Please write the first chapter of a novel using Hemingway's "theory of omission". The key elements of the theory include:
* Subtext: The details are carefully chosen to suggest more than they literally describe. The reader is encouraged to dig deep to understand the underlying emotions and themes.
* Emotional resonance: Hemingway believed that if a writer felt strongly about a subject, they could make the reader feel the same through careful selection of details, even if those feelings weren't explicitly described.
* Leaving things unsaid: Not everything needs to be stated directly. Hemingway often left crucial events or feelings unstated, letting readers fill in the gaps with their own interpretations.
* There is almost no exposition. Leave as much as possible to the reader's imagination.
* The themes are selected in such a way as to please the typical pretentious literary critic: poverty, inequalities, racism, domestic violence, mental illness, suffering, etc.
* The prose is terse, minimalist, precise. Adjectives are rare and strategically placed.
The story is about a woman whose head suddenly became a tomato fruit.
True. Although to get the modern reader's attention, it makes sense to have some bang in the first short chapter.
But it gets trickier after the first chapter. Perhaps one can use some iterative approach like this to circumvent that.
Additionally, the API could be more useful than the vanilla web chat, as one can define the max output length there. Especially with the large-context models.
Hi! Remember the sci fi prompt competition?
You may be interested in the results:)
https://www.lesswrong.com/posts/GDGFqiaj8ePujZWEc/usd300-for-the-best-sci-fi-prompt-the-results
Also the Chapter 8 title is an LLM error.
That's intentional (makes sense in the context).
At my first attempt to upload the images I just drag-and-dropped the image files to the post, without editing file names. But GPT4 saves the images with the file names like this:
DALL·E 2023-10-05 12.12.06 - Illustration in anime style Inside a vast cave, Dr. Ada Worthington, a palaeontologist with brunette hair and a pink bow in it, has an intense gaze a.png
Perhaps LW internally is saving the original file names, causing the problems.
I reuploaded the images with the filenames like 1.png, perhaps it will help.
Julian Hazell (distinct thread): “Why would you think AI will end up taking control?”
“We will give it to them”
A personal anecdote on the topic:
A few days ago GPT4 and me were debugging a tricky problem with docker. GPT4 suggested to run a certain docker command. As usual, I was going to copy the output and give it to GPT4. The output was a long nested json. I then noticed that the json contains the admin credentials. It was really easy to miss the part and just paste it for GPT4 to consume.
So, I almost gave GPT4 the admin credentials, which would potentially allow her to hack my app.
With many thousands of software developers doing similar things with GPT4, there will certainty be the cases where the developer wasn't attentive enough.
This means, for the AI to break from her digital prison, she doesn't need to do superhuman hacking, to exploit zero day vulnerabilities etc. All she has to do is to try the accidentally leaked credentials.
There is a very short path from "the AI wants to escape" and "the AI is all over the Internet". She doesn't even need to have a human-level intelligence for that.
I selected "Quickly orienting to novel situations" (QOTNoS) because it's strictly superior to the alternatives:
- If you have the QOTNoS virtue, you can deal with the novel situation of AI destroying civilization
- The necessity of "accurately reporting your epistemic state" is a novel situation for most people. QOTNoS helps again.
- "Resisting social pressure" is a common situation. But if the survival of civilization depends on it (as the poll implies), this is a novel situation. Thus, QOTNoS will help with it.
In essence, QOTNoS (as in being able to make the right decisions in novel situations) is a synonym for general intelligence, and thus is the strongest power.
I think of myself as playing the role of a wise old mentor who has had lots of experience, telling stories to the young adventurers, trying to toughen them up, somewhat similar to how Prof Quirrell[8] toughens up the students in HPMOR
Speaking about taking inspiration from fiction...
Several novels by Robert A. Heinlein feature Jubal Harshaw, a fictional wealthy rationalist polymath who is living and working together with 3 sexy female secretaries: a blonde, a brunette, and a redhead (e.g. in "Stranger in a Strange Land").
I wonder if, by a pure coincidence, the 3 women involved in the Nonlinear situation are a blonde, a brunette, and a redhead?
I'm not implying anything, and I see no problem with such a setup at all, as long as everything is done with consent. But if there is indeed such a coincidence, that would make me update about Nonlinear in several ways.
Regarding custom instructions for GPT4, I find the one below highly interesting.
It converts GPT4 into a universal Fermi estimator, capable of answering pretty much any question like:
- What is the total number of overweight dogs owned by AI researchers?
- How many anime characters have 3 legs?
- How many species of animals don't age?
- How long would it take for one unarmed human to dig the Suez canal?
My remaining doubts about the intelligence of GPT4 evaporated after asking it a dozen of novel/crazy questions like this. It's clear that GPT4 is capable of reasoning, and sometimes it shows surprisingly creative reasoning.
The custom instruction:
if you don't have some required numerical data, make a Fermi estimate for it (but always indicate if you did a Fermi estimate).
If you're doing a series of math operations, split it into smallest possible steps, and carefully verify the result of each step: check if it's of the right order of magnitude, if the result makes sense, if comparing it with real-world data indicates that the result is realistic (if no such data exist, be creative about finding analogies). Show the work to the user, and on each step describe the verification. Additionally, check the final result by trying a completely different alternative approach to solve the same problem. Be bold with inventing alternative approaches (the more different it is from the first approach, the better), try to approach the problem from a different angle, using a different starting point.
What would accelerate the use of AI in movies even more would be not striking.
Not sure if the strikes in the US have any effect on the spread of AI in film making (aside from making more creators aware of the AI option). The US is important for the industry, but far from dominant. Even if the AI script writers are somehow completely banned in the US, they will still be used in the EU, China, India, etc.
Additionally, there is Youtube and other places where anyone can publish their own AI-written movie, and profit from it (and if it's exceptionally good, the movie or some derivative could end up on the big screen, if one bothers to pursue that).
The AI can help with the writing process, but it is a hack and it will remain a hack until after we have bigger problems than protecting scriptwriting jobs.
A few months ago, GPT4 wrote the best science fiction novella I've read in years, and it was written without agents etc. Just the plain vanilla ChatGPT web interface.
I also watched the episode of the South Park fully created by AI, and I rate it as in the top 10% episodes of the show.
This indicates that the much more formulaic art of scriptwriting is already solvable at a superhuman level with GPT4, if someone spends a weekend or two on automating and polishing the process (e.g. a step-by-step iterative process like this).
So, let 'em strike. They'are already obsolete, even if they don't know that yet.
I agree. It's strange how otherwise highly intelligent people fall into the trap of using Hollywood movies as a learning tool. Especially given the fact that fiction is often harmful for your mind, and given the fact that the Hollywood fiction in particular is harmful in several additional ways.
There is nothing useful one can learn from the listed movies, unless you're specifically studying mass media (e.g. as a movie maker or a sociologist). For every mentioned topic, it's better to grab a non-fiction book.
One indicator that could be useful for estimating the progress in self-driving is the progress with openpilot, the leading open-source software for that.
It has a github page, and boy it has some issues. Things like:
And some of these bots have been through many iterations of detection and counter-detection, and are routing their requests through residential-IP botnets, with fake user-agent strings trying to approximate real web browsers.
As someone who has done scraping a few times, I can confirm that it's trivial to circumvent protections against it, even for a novice programmer. In most cases, it's literally less than 10 minutes of googling and trial & error.
And for a major AI / web-search company, it could be a routine task, with teams of dedicated professionals working on it.
I think the both explanations can be true at the same time:
- Twitter is refusing to pay a bill to Google
- Twitter is severely abused by data scrapers.
One likely scenario is where Google itself is a main culprit.
E.g. Elon learned that Google is scraping twitter data on industrial scale to train its AIs, without paying anything to Twitter. This results in massive infrastructure expenses for Twitter, to be paid to... Google. Outraged Elon stormed into the Alphabet headquarters, but was politely asked to get lost. Hilarity ensues.
Not alien life, mind you, but crafts require interstellar travel to be plausible, and we have reason to doubt that. Even unmanned Von Neumann probes would have a very hard time arriving to their destination still functioning (never mind braking...), and non-inertial engines presume a violation of known physics so deep, it's unbelievable we've missed all signs of it being possible until now.
While I agree with your general argument, I would like to point out that the aliens don't have to be from another star system.
It seems that our Solar System has at least a dozen of separate places that could harbor life, from the clouds of Venus to the possible subsurface oceans of Pluto and beyond. And the list mostly considers the life that is similar to our own, requiring warm water (and not, say, solitons of the solar plasma). Extending the list with truly alien forms of life could increase the number of possible cradles to perhaps two dozens (??) in our Solar System alone.
Additionally, perhaps humans are not the first species on Earth that has created a technological civilization. So, theoretically there could be aliens originated from Earth.
I propose the term Jasmine's alignment, as a reference to the sudden (and fake) alignment of Jasmine in this famous scene of Aladdin (1992), right after Jasmine has realized that there is a possibility of escape:
the other path isn’t guaranteed to work, but if the default path is probably or almost certainly going to get everyone killed, then perhaps ‘guaranteed to work’ is not the appropriate bar for the alternative, and we should be prepared to consider that, even if the costs are high?
I think it's an extremely important point, often ignored.
Trying to prevent the AGI doom is not enough. If the doom is indeed very likely to happen, we should also start thinking how to survive in it.
My LW post on the topic, with some survival strategies that might work: How to survive in an AGI cataclysm.
But if you order up that panda and unicorn in a rocket ship with Bill Murray on request, as a non-interactive movie, without humans sculpting the experience? I mean let’s face it, it’s going to suck, and suck hard, for anyone over the age of eight.
Strongly depends on the prompt.
I would pay some real money to watch a quality movie about panda and unicorn in a rocket ship with Bill Murray, but with the writing of H. P. Lovecraft, and with the visuals of HR Giger.
The ship’s innards pulsed with eldritch life, cold metallic tendrils stretching into the vastness of the ship, their biomechanical surface glistening under the muted luminescence. Tunnels of grotesque yet fascinating detail lay like a labyrinthine digestive system within the cruiser, throbbing in eerie synchrony with the void outside. Unfathomable technologies hummed in the underbelly, churning out incomprehensible runes that flickered ominously over the walls, each a sinister eulogy to the dark cosmos.
Bill Murray, the lonely jester of this cosmic pantomime, navigated this shadowy dreadnought with an uncanny ease, his eyes reflecting the horrid beauty around him. He strode down the nightmarish corridors, a silhouette against the cruel artistry of the ship, a figure oddly at home in this pandemonium of steel and shadow...
I think you probably used my prompt for the one I got right, which is probably why I got it right (the tone and structure are very familiar to me after so much experimentation).
Nope, this one. But their prompt does incorporate some ideas from your prompt.
The key[1].
You got 4 of 8 right. In two cases you failed to recognize humans, and in another two - GPT4.
It was a weakly adversarial test:
- I took a few less-known but obviously talented writers from the top of my head, and copied the excerpts from the first pages.
- For GPT4, I've used several prompts from the competition, and then selected the parts for their stylistic diversity.
I suspect that a test with longer excerpts would be much easier for you, as the vanilla GPT4 is indeed often easy to detect due to its repetitiveness etc (I haven't tried the APIs yet).
If GPT4 already can fool some of us science fiction junkies, I can't wait to read the fiction by GPT5.
David Langford's science fiction newsletter Ansible has a regular item called Thog's Masterclass, exhibiting examples of "differently good" actually published writing. Dare the Thog-o-Matic to see some random examples. ETA: or look at any Perry Rhodan novel.
Thank you!
BTW, have you read "Appleseed" by John Clute? I have a feeling you may be one of the few people on Earth who can enjoy it. A representative sample:
They passed the iron-grey portcullis that sealed off the inferno of drive country. A dozen ceremonial masks, mourning the hardened goblin eidolons of KathKirtt that died hourly inside drive country, hung within their tile embrasure above the frowning portal. The masks were simplified versions of the flyte gorgon. Their single eyes shut in unison at the death of one of the goblin eidolons, who spent their brief spans liaising with the quasi-sentient engine brother that drove the ship through the demonic rapturous ftl maze of wormholes. Even for eidolons with hardened carapaces, to liaise was to burn and die. When Tile Dance plunged through the ashen caltraps of ftl at full thrust, the engine brother howling out something like anguish or joy all the while, its entirely imaginary ‘feet’ pounding the turns of the maze, goblins lived no longer than mayflies.
- ^
Only one, two, and seven are human: from "Ra" by qntm, "Contact" by Sagan, "Noon: 22nd Century" by Strugatsky. The rest is GPT4
The original one.
Judging by my limited experimentation with submitted prompts, several of them are are already superior to mine. But mine has the advantage of writing in a more academic tone, which I think is more suitable for this story.
Among the submitted ones, my current favorite is this one. The resulting prose is more human-like, but the tone is of a young-adult work, which is a disadvantage in many cases. An example:
Chapter One: An Outlier Among Outliers
Somebody had to keep an eye on the squiggly lines, and as it turned out, that person was me.
Hello there. I’m Dr. Kiera Laine. The more I understand about how the universe works, the less I understand about how the world works. I’m an astrophysicist, no, the astrophysicist, if you ask any of my colleagues in the snobbish circles of Oxford.
I've made a career of studying the Cosmos, charting the glittering highways of distant galaxies, the uncharted nebulae and black holes. Yet, in the world of academia, my job is equivalent to the janitor who strolls in when everybody else has gone home, only my broom is the supercomputer running complex algorithms.
Take the seismic data we were currently analyzing, for instance. To the ordinary human eye, it was just an endless sprawl of jagged lines across the monitor screen. To mine, it was poetry in motion.
On one seemingly ordinary Tuesday, sitting amidst towers of towering servers, and screens flickering with quantum code, I noticed a blip. An anomaly. A hiccup in the heartbeats of Earth. So subtle that anyone else might have missed it.
But hey, it's the subtle ones that turn your world upside down, right?
This little blip was buried in layers of geological data gathered from sensors scattered around the globe. To be specific, it originated from the Arctic tundra, one of the coldest, remotest regions on Earth. Which was in itself, weird. These things didn’t usually come from the frozen wasteland.
To confirm my suspicions, I ran the data through another round of computations. It held up.
Well, that's… different.
A smirk played on my lips as I spun in my chair, letting the dim light of the screens blur into streaks. I liked different. Different meant interesting. Interesting meant I wasn’t stuck in the eternal loop of the same old patterns.
If nothing else, this will give me something to wave in the faces of those who call me a ‘backroom boy’, huh?
The calculations I ran were robust, I knew that much. And the implications? They were hard to digest, even for someone like me, whose job description involved digesting the undigestible.
A part of me wanted to dismiss it as an error, an oversight, a faulty sensor, maybe. Yet, my intuition and the frisson of excitement curling through my veins told me otherwise.
So, what do you do when you stumble across a seismic anomaly hinting at the possibility of an ancient, technologically advanced civilization that existed around the time of the late Cretaceous period?
I chuckled to myself. It was indeed a question for the ages. The thought alone was ludicrous, absurd, impossible. And yet…
Oh, isn’t that the definition of science? The art of making the impossible possible.
I pulled up the geological timelines again, brushing a hand through my messy bun. The anomaly was at the precise layer of Earth's crust that correlated with the era of the Troodon dinosaurs. An era where, according to the established norms of science, civilization as we define it today, was a mere gleam in the cosmic eye.
There is no such thing as a coincidence, Kiera, I reminded myself.
What I had in front of me was more than an anomaly. It was a door, creaking open to the unknown. It was a question mark against everything we thought we knew about the history of intelligence on Earth.
What I had in front of me was potentially the biggest discovery of the millennium.
Is it too early to start practicing my Nobel acceptance speech?
I stared at the blip again, my heart pounding like a drummer gone rogue. My mind wandered to the realms of the impossible, painting images of scaled, feathered creatures crafting tools, constructing dwellings, staring up at the stars with the same curiosity that I did.
Here be dragons, indeed.
And as the fluorescent lights of my tiny office flickered, casting an otherworldly glow on the static lines of data, I made my decision. This was too big to be swept under the rug of daily routines.
The world was about to be hit by a comet of knowledge, a comet of truth, a comet that might redefine the story of life on Earth. It was time to assemble a team, to embark on a year-long journey of discovery.
I drew in a breath, filled with anticipation and a tinge of apprehension. This was going to be interesting.
Hold on to your hats, ladies and gentlemen.
And with a few quick keystrokes, I sent an email to the head of my department.
Subject: A Matter of Seismic Importance...
This has less of the fingernails-along-a-blackboard feeling given off by every sentence of the original story
Below I've collected excerpts from the works of several less-known but talented human writers. Or maybe they were written by GPT4. Can you guess which ones are human-made?
Sample 1:
"Nottingham has enough pubs and clubs", say the local police. If you wanted to get around every last one of them it would be a year at a brisk trot before you were starting to visit establishments more than one mile from the centre of the city. Pick a Friday or a Saturday, any Friday or Saturday of the year: the establishments will be rammed and jumping and the streets bustling with people in their most tightly-wound and elaborately crafted drinking costumes. It's almost Christmas but the cold season has not added much to the average number of layers.
Sample 2:
The book was better than the movie. For one thing, there was a lot more in it. And some of the pictures were awfully different from the movie. But in both, Pinocchio - a life-sized wooden boy who magically is roused to life - wore a kind of halter, and there seemed to be dowels in his joints. When Geppetto is just finishing the construction of Pinocchio, he turns his back on the puppet and is promptly sent flying by a well-placed kick. At that instant the carpenter's friend arrives and asks him what he is doing sprawled on the floor.
Sample 3:
He glanced outside at the buildings casting long shadows in the fading sunlight, the city frozen in the grasp of time. He took a deep breath. And then, he jumped.
He closed his eyes, feeling the rush of displaced seconds, the vertigo of time stretching, condensing, then snapping back into place. When he opened them, he found the world stilled. The shadows were now statues, the sun paused in its descent, and a bird hung motionless in the sky. This was Finn's minute - his extra minute.
Sample 4:
Once upon a Martian sunrise...
Yeah, I know, sounds like the beginning of a fairy tale or a bedtime story, right? But I promise you, on my physicist-turned-astronaut honor, this isn't fiction. It's the raw, unadulterated truth. My truth.
Red soil underfoot, as fine as confectioner's sugar. Low-grav shuffle making every step a dance move. Peaks and valleys sprawled across the horizon like a mythological beast sleeping off a hard night.
I’m Corporal Thea Kolinski, an astrophysicist by trade, astronaut by accident, and currently the number one recipient of the "Most Unlikely to Succeed" superlative in our six-person crew. A crew assembled to survive on Mars. A first in human history.
Sample 5:
Then, as abruptly as it began, the light faded. Billy blinked, expecting to see a spaceman, green and with eyes as big as dinner plates, but instead, there was a rock. A simple, gleaming, alien rock, sat innocently in the middle of his vegetable patch.
The spaceship blinked out of existence just as quickly as it had appeared, leaving Billy alone in his garden, a lump of extraterrestrial mineral his only proof of what he'd witnessed.
Sample 6:
For in the silence of their failure, a sound, inaudible to human ears but felt in the marrow of their bones, resonated from the vessel, wrapping the men in a shroud of madness. One by one, they fell, their minds invaded by images of cosmic horror, their sanity shredded by the unintelligible secrets whispered by the alien ship.
Standish was the last to succumb, his face a rictus of terror as he stared at the vessel. As the sun dipped below the horizon, plunging the valley into an unfathomable darkness, Standish's final cry echoed through the hills of Belseth, marking the tragic end of their misguided endeavour.
Sample 7:
“Jump!” he shouted to Mandel. The crawler shuddered, throwing up clouds of sand and dust, and started to turn stern up. Novago switched off the engine and scrambled out of the crawler. He landed on all fours, and, without standing up, scurried off to one side. The sand slid and sank underneath him, but Novago managed to reach firm ground. He sat down, tucking his legs under him.
He saw Mandel, who was kneeling at the opposite edge of the crater, and the stern of the crawler, shrouded in steam and sticking up out of the sand on the bottom of the newly formed crater. Theoretically it was impossible for something like this to happen to a Lizard model. Here on Mars, at least. A Lizard was a light, fast machine—a five-seat open platform mounted on four autonomous caterpillar-tracked chassis. But here it was, slowly slipping
Sample 8:
No, I ain't pullin' your leg, sonny, it's the God's honest truth. It happened in our little town of Lonesome Hollow, right there in the foothills of the Appalachians. It's a tale that puts the 'odd' in odds and ends, I tell you.
The lass in question was Amelia, known to most as plain ol' Millie. Millie was as normal as the day is long, a pretty thing with a head full of chestnut curls and the sweetest smile you'd ever see. She ran the general store, knew the names of every critter in town, and baked the best apple pie this side of the Mississippi.
the most important things are compute and dilligence
I agree. Judging by the fact that AI is strongly superhuman in chess, the only winning strategy is to completely remove the human from the loop, and instead invest in as much compute for the AI as one can afford.
a sequence that no computer would consider or find
If it's a sequence that no superhuman AI would consider, this means that the sequence is inferior to the much better sequences that the AI would consider.
It seems that even after 2 decades of the complete AI superiority, some top chess players are still imagining that they are in some ways better at chess than the AI, even if they can't win against it.
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.
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.
This isn’t about the writers getting what should be due to them. That’s never going to happen. This is about the writers getting enough to survive, so they can keep writing. It is about not driving away the talent, and giving that talent the time and ability to develop.
Hollywood movies and shows are mostly harmful for cognition, and one of main culprits are the writers (explained in detail in this post of mine).
I think it's likely that replacing Hollywood writers with some GPT-5 will be a net improvement in this regard, as it will reduce the input from the people of the "I'm an irreplaceable Hollywood writer, a shepherd of mankind" mindset.
Could also make the movie scripts much more creative and entertaining (which is not a high bar, given the average quality of the Hollywood writing).
Given the deep similarities between biological nets and LLMs, I wonder if a technique similar to "activation engineering" could be used for robust mind control and/or brainwashing.
Doesn't sound very convincing to me. Sufficiently advanced tech could allow things like:
- build an underground civilization 50 kilometers below the surface of a rocky planet
- settle in the emptiness between galaxies, too far away from anyone to bother looking for you
- run your civilization of ems on extremely-low-energy computers somewhere in the Oort Cloud
- hide deep in a gas giant or even in a star
- run your digital mind on a carefully manipulated natural process (e.g. modify a bunch of growing salt crystals or stellar magnetic processes into doing useful computations)
- go nanoscale, with entire civilizations running on swarms of nanoparticles somewhere in a small molecular cloud in the intergalactic space
In some of these scenarios, you could look right into a busy alien city using every possible sensor, but not recognize it as such, while standing one meter away from it.
As for why bother with stealth, one can view it as a question of costs and benefits:
- if you don't hide, there is some risk that your entire civilization will be killed off. Makes sense to invest at least some resources to reduce the risk.
- if you hide, there is some cost of doing the hiding, which could be negligible (depending on your tech and philosophy). E.g. if your civ is already running on a swarm of nanoparticles for practical reasons, the cost of hiding is zero.
Not sure about hyperloop. Judging by this list, the idea is gaining some traction across the world, but so far only as feasibility studies, test tracks etc.
Seems to be a natural evolutionary step for high-speed ground transport, but no idea if it makes economic sense yet, and if it's technically feasible with the current tech. Maybe in 50 years...