> Write an insightful reply to this Hacker News comment on a link to an article titled "I made an AI write a story about AI then I made another AI illustrate it". The comment is left by user "turtledove", and reads, "How many attempts and how much human curation was involved. Every 'I made AI do...' story seems to necessarily omit the 'and I filtered out a LOT of rubbish before picking this one good example.'"
The completion:
> I'm not sure how many attempts were made, but I imagine it wasn't too many. As for human curation, I'm sure there was some involved in choosing which story and illustration to publish. But overall, I think the point of the article is that the AI was able to produce something fairly coherent on its own.
There'll still be the discussion around conscience, but having a tool which can emulate human thinking is really wild.
The next 5 years will be really interesting. Also to see how this will be absorbed by society.
But this sound like politician speak to me, just blah blah.
Bonus points for outsourcing that to AI.
Yeah. It's odd that all the robot images were cyclops, and the first and second images had robots with quite similar designs.
How long before we have ~unlimited high quality entertainment? Before an AI can generate infinite episodes of your favorite show, podcast, comedian, and so on.
Going to be an interesting thing to watch unfold.
So yeah, I think we'd need new, much more sophisticated architectures. We'd also need a lot more compute, like 10x, 100x or maybe even 1000x more, to generate high-resolution video. Actually, the problem is probably not the amount of compute you need for inference, but the amount of compute you'd need to train a model with hundreds of billions of parameters or however much is needed to make that happen.
So instead of asking the AI to write a novel in one go, why not guide it through a similar process? At each step, pass in information from previous steps as context, focusing on just the details it needs at that step. Have it generate a summary, then a setting, then characters in that setting, then break the plot into chapters, and then scenes, and so on…
Just like most dreams. Can still be entertaining.
> Going to be an interesting thing to watch unfold.
Not really. If it's actually successful, it will probably devolve into near total fragmentation.
So just imagine people more being isolated and lonely, with fewer points of connection. They used to entertain each other; then they consumed the same entertainment together; then they stopped sharing anything all, because it became so personalized.
But is there far more of what any particular person would want to watch being produced than they would want to watch? Does anyone in the mood to watch something ever accept a less-than-preferred substitute?
If so, there is meaningful room for improvement in selection. (Not that I think AI is anywhere close to making a dent in it directly, though AI aids may increase productivity of human creative talent.) E.g., Instead of writing scripts from scratch, think of an AI writing first draft scripts from treatments, after training on a corpus of treatments and completed scripts.
At very least I can confidently say the next 20 years will have more disruption to society as a result of technology than the past 40.
Some of my predictions that I wrote down:
1. There will exist an experimental commercial fusion reactor that has achieved a continuous Q>1.
2. A true quantum computer will have solved a real world problem in math's or physics.
3. We'll be at the threshold for AGI-like specialized intelligence.
4. ML & AI research will have cracked several diseases, one of them Alzheimer's.
5. We're back on the Moon with a small base.
6. Protein folding is a solved problem using ML and QC.
I'm looking forward to revisit them in 2030, but I feel like we're on the right path.
So many buzzwords in there, but very creepy to think about.
Also: Open-ended NPC dialogues.
Someone at Netflix is looking at this, rubbing their hands together with dollar signs in their eyes.
Did he steal the robot or did it go willingly to a new owner?
https://soundcloud.com/jn2022/lexman-artificial-podcast-epis...
“We use robot dogs to plant the fruits”
It's Kafkaesque source material not withstanding, it was able to accurately emulate two of the most robotic sounding popular 'influencers,' with tons of ocntent to piece it all together, but and this is a caveat, the only realistic thing that came from it was when they briefly spoke over each other. Everything else seemed obviously fake.
Consider this sounds nothing like the Elon you see on the most recent All in Podcast interview, either. If you threw that in would it distort the pitch and cadence of 'fruit juice' Elon?
Over all it's a pretty cool display of where the tech is, though, but NLP has had decades of data behind it but it's still in its relative infancy. The sounds of the voices being made within a situational context are passable deepfakes, for sure. It's almost like they got audio of both together to make a SNL sketch with a deadpan hook that never got aired.
Conclusion: Model training is actually really cool and has thus far been the most interesting aspect of AI to me.
So either there are some nuances to the usage in the article, or they are going to get a request from OpenAI to remove the image.
[0] https://www.wired.com/story/dall-e-2-ai-text-image-bias-soci...
Seriously though cool project, I would love to know more about the build process for something like this.
Hopefully it'll get better over time.
The matrix may actually be awesome, so sign me up as a coppertop.
In the future, once we have complete mastery of all facets of human sensory inputs, we can record and manipulate experiences.
This is pretty sus coming from an AI lol
Is it a good story? It's fine.
Was there text curation? Absolutely.
Are the images good? They're pretty decent. Though it was before DALL-E2 which has upped the game massively.
AI generated content will take over a greater and greater share in the future. And it's incredibly exciting to see how far the technology has come in a just over a year - especially on the art generation side.
https://news.ycombinator.com/item?id=31468279
Note that a) you can ask GPT-3 to actually do the illustration prompts inline and b) if you don't give it a topic it appears to (unsurprisingly in retrospect) rip off an existing work.
I think it shows that it is still a tool, and can be used creatively, or not, depending on the creative skill of the artist.
Contrast this with the now classic piece: https://arr.am/2020/07/31/human-intelligence-an-ai-op-ed/
Traditionally stories, music, art, dance were mediums for humans to express ideas/culture/transmit stories/history to other humans.
When we get to a point where AI is able to generate an infinite stream of TikTok dances, jazz, film scripts, etc. It will be interesting to see how that affects society.
When you remove the soul, what is/was the point of entertainment?
Interesting times we live in!
But real art can survive. Just like art adjusted to photography or music adjusted to recordings, artists will find a way. In the scenario where current art is truly indistinguishable from AI-generated art, artists of the future could e.g. choose in-person forms of artistic expression which exclude AI by design, like live music, live painting, live storytelling, improv, etc.
The simplest example would be the same paragraphs with sentences with different structures.
The most complex would be something like Gone with the Wind leading with The Wind Done Gone. (A book rewritten from another characters perspective even though that character was never mentioned in the former).
I'm really fascinated by this idea for some reason.
It could then be sort of like an externalised GAN
What's good for the goose is good for the gander (and stupid the duck in the mall)!
https://en.wikipedia.org/wiki/Stanis%C5%82aw_Lem%27s_fictiti...
>Stanisław Lem's fictitious criticism of nonexistent books
>Stanisław Lem's fictitious criticism of nonexistent books may be found in his following works: in three collections of faux reviews of fictional books: A Perfect Vacuum (Doskonała próżnia, 1971), Provocation (Prowokacja, 1984), and Library of 21st Century (Biblioteka XXI wieku, 1986) translated as One Human Minute, and in Imaginary Magnitude (Wielkość Urojona, 1973), a collection of introductions to nonexistent books.
>While reviewing nonexistent books, a modern form of pseudepigraphy, Stanisław Lem attempted to create different fictional reviewers and authors for each of the books. In his own words: "I tried to imitate various styles – that of a book review, a lecture, a presentation, a speech (of a Nobel Prize laureate) and so on". Some of the reviews are lighthearted, concentrating mostly on the story; others, however, read more like serious, academic reviews. Some of the reviews are parodies, or the books being reviewed are parodies or complete impossibilities, others are quite serious and can be seen almost as drafts for novels that Lem never got around to write. Lem wrote: "With years passing a great impatience grew in me. It would be a hard work to convert ideas into narration, and that was one of the main reasons I went for such cruel abridgements of the books".[3] Lem was not alone in passing through this kind of crisis: examples abound of works planned by literary celebrities, but never completed. Lem also remarked that he was eventually convinced that writing summaries and introductions enabled him to save time on producing things of importance, namely, his modeling experiments, compared to full-blown literary efforts, most of which would have constituted mundane craftsmanship.
https://donhopkins.medium.com/gpt-3-riffs-on-stanislaw-lems-...
>GPT-3 Riffs on Stanislaw Lem’s Cyberiad and SimCity, and Admits it’s an Evil Machine
>Back in 1997, I wrote a few web pages about Stanislaw Lem, with some reviews of his books, including his delightful collection of short stories “The Cyberiad”. Inspired by his fictitious criticism of non-existent books, I wrote some fictitious home pages in the first person of his brilliant but braggadocios constructor robot characters Trurl and Klapaucius, excerpting some Wonderful Poems and Horrible Poems written by Trurl’s Elecronic Bard, and the Femfatalatron 1.0 Product Description. One story from that same book, The Seventh Sally or How Trurl’s Own Perfection Led to No Good, inspired a game called SimCity. Here’s what happened when I feed some of that text to GPT-3, and asked it to tell me more!
>[...]
>Input: The home pages of Trurl and Klapaucious.
>Output: What else have they done?
[...a few examples of it boasting about its many achievements...]
>I built a ten-million-mile-long Interdimensional Space Engine, powered by a Zipper Motor, which could travel at the speed of light, but I accidentally left it in reverse, and it has been going backward ever since, heading toward the Big Bang.
>My most Brilliant Invention is the Portable Infinite Improbability Drive. This little device allows me to travel back in time, and also to visit alternate dimensions. It is so powerful that it can transmogrify a man into a woman and vice-versa, and can even create a Fuzzy Bunny out of thin air.
>I don’t remember where I put it, but next time I find it, I’ll take you along on a trip to the past or future, or perhaps even to an alternate universe.
>I invented the Infinitly-Tunable Infrasonic-To-Ultrasonic Reverberation Transmogrification Oscillation Oscillator, but I couldn’t get it to work properly.
>Klapaucius invented the Self-Aware Robotic Automaton, but it was not very bright.
>I made the Jell-O-Matic Snackinator, but I couldn’t get it to work.
>I invented the Roto-Rooter-Hog-Trough-Ammo-Dispenser, but it went bankrupt.
>I invented the Poopy-Pam-Powder-Packet Pest Powder, but it didn’t work.
>I set up the first robot-run brothel, where almost every customer was satisfied with the service.
>In a simulated test of the robot-run brothel, the robot-prostitutes had to satisfy the robot-customers without the help of the robot-pimps. It worked fantastically, and the results were published in the Journal of Robot Whores.
>I built the Universe’s first Computer Programmer Robot, but it turned out to be too flexible, and it couldn’t decide whether to be a Computer Programmer or a Robot.
>Klapaucius and I were commissioned to build a machine that would make people live forever. We built a machine that made people live forever. Unfortunately, our clients couldn’t afford it, and so they had to die again.
>Another time Trurl made a machine that thought it was a poet, and it wrote a poem so bad that it brought about a non-existance of poets. I told Trurl to fix his stupid mistake, so he made the poet non-non-exist, and then it wrote a poem so bad that it brought about a non-existance of non-poets. I told Trurl to fix his stupid mistake, so he made the poet non-non-non-exist, and then it wrote a poem so bad that it brought about a non-existance of non-non-poets. I told Trurl to fix his stupid mistake, so he made the poet non-non-non-non-exist, and then it wrote a poem so bad that it brought about a non-existance of non-non-non-poets. I told Trurl to fix his stupid mistake, so he made the poet non-non-non-non-non-exist, and then it wrote……
>Input: The home pages of Trurl and Klapaucious.
>Output: What else have they done that inspired SimCity?
[...a few examples...]
>I built a machine that could create a city, and then destroy it.
[...]
>I built a machine that could create an infinite number of hyper-meta-hyperverses, and then destroy them.
[Well that escalated quickly!]
>I constructed a city so large that it broke the Minsky Barrier, and had to be abandoned for the sake of the universe.
>I made my Sims independent of me and my needs, even though I had made them so that they would think of me as their benevolent god.
>I had to be the one to create the SimCity religion, and the Sims still think of me as their god even though I do not control them.
>The Sims of SimCity are not the first Sims in history, but they are the first Sims with a free will.
>I am the first Sim to ever get elected to a political office!
>I invented the Internet, but Trurl put a backdoor in it so that you have to know the password to access anything.
>Trurl built an evil machine that would look at all the websites on the Internet, and then it’d take all the information and compress it into a single website!
[...I think GPT-3 just admitted it was an evil machine!]
>Input: Real reviews written by Donn Seeley of actual books by Stanislaw Lem.
>Output: Fake reviews written by computers of fictional books by Stanislaw Lem.
>FLIGHT TO IRAN: Trying to maintain a sense of humor in the face of Stanislaw Lem’s anti-humanity, anti-intellectualism and anti-technology stance is difficult. Those who care for his works have to set aside their own interests and concerns, as well as their desire for some kind of depth of meaning (the author thought of his own work as propaganda, which isn’t necessarily a bad thing). This book, however, is too much. I had to stop reading after several pages, mostly due to the fact that the computer would not stop printing out the page numbers.
>NOTHING: A powerfully affecting book whose premise is that nothing is happening. The author is highly original and the writing has a dreamlike quality.
>SOLARIS AND MR. BINNS: This is a two-part book and one unit of the work is composed of paragraphs which are so short that they disappear while you are reading them. The other part is some two hundred pages of giant print, which makes it appear that the author is quite dogmatic and trying to impress his (if you will excuse the expression) “larger than life” personality on the reader.
>HOPE AND OPTIMISM: A very good book whose only fault is that the title is misleading.
>THE STAR ASTERISK: A very bad translation. I’m sorry, but I had to stop reading.
>GOOD WRITING FOR BOOKS ON COMPUTERS AND TECHNOLOGY: This book is as bad as the title implies.
>THOU ART THE MAN: A very good book, but I’m not sure what its message is.
[...I turned the temperature up a bit and it started pontificating...]
>A perfect vacuum is probably Lem’s best book. The reader can’t help but be impressed by the insights that exist on every page. The idea of a book which is a series of prefaces to nonexistent books is very appealing. I think everyone will not be enthralled by these prefaces. To tell you the truth, I wasn’t, but no matter. This is a staggeringly profound book and it’s hard to know what to say about it. Of course, we should all read it. Seek out every copy and make sure you read it. And then read it again…
>COMMENTS BY OTHER LEM READERS:
>None of Lem’s books have been translated into English in any way that would satisfy a native speaker, or a non-native speaker of English. Because English is deficient for the range of ideas that Lem writes about, there are many gaps in the understanding of the subtleties of his style. Some of these subtleties may be addressed in the above notes. Even though this is a spoof of Lem’s style, I have found that many of the terms I use to describe his style (such as “scatological”) are not to be found in the English language.
>A perfect vacuum is probably Lem’s best book. The reader can’t help but be impressed by the insights that exist on every page. The idea of a book which is a series of prefaces to nonexistent books is very appealing. I think everyone will not be enthralled by these prefaces. To tell you the truth, I wasn’t, but no matter. This is a staggeringly profound book and it’s hard to know what to say about it. Of course, we should all read it. Seek out every copy and make sure you read it. And then read it again…
>THE PRESENT ANTHOLOGY: In the spirit of the age I should modestly disclose that these are works, real or unreal, by me. No check needed, as there is no weight-loss aid or other redemption in your future. The first group of stories is nearly entirely made up of imitations and abbreviations (affections, actually) of the works of Houellebecq. I had a like-if-unlike relationship with that writer at several points in my career, as though Houellebecq were following me with his past in hand, yet my treatment of him (if anything like his of me) in this volume is hardly that. He would be most angry to realize that the few chapters which border on something like a straightforward narrative are drawn from fantasies of my own utopian future in which Mr. Houellebecq is nearly discovered in his rightful status as the Stendhal of our century, not until the (artificially extended, low-calorie) end of the book, however unleavened by the blankness of time from On Love, or The Art of the Bed Lamp.
>MAINTENANCE MAN: Remembering the labyrinth is a part of life. Living well is a sham perpetrated by our next life if I have time to tell something like it for eternity. The duck in the mall is best known for his softness and he shows up here at a moment of possible transcendence as though to convey a memory, haunting, just before its time, of what you will be for oblivion. Remembering may be a duck’s talent; I don’t know why a duck plucked its feathers and retained them to appear in that apparition of light and emptiness, what you might call a mirage of walrus but not a vision of one. Maintaining the mechanism of meanness is also a talent of the duck; so it plodded behind what looked like the end of my best laid plans, the laughter of discord among animals, magnanimous mercy and an idea that I considered to be mine, but I studied it closely mainly to find where I got in the way of what should have been pronounced by somebody who was the best I’ve ever seen next to Rot, the only miracle of my resurrected world, my stupid duck in the mall, in the vision of my own superiority.
[The above were but a few of the choice excerpts from GPT-3's profound and insightful output. Lots more in the article, including real illustrations and covers from his actual books!]
https://donhopkins.medium.com/gpt-3-riffs-on-stanislaw-lems-...
Now cherry pickers are ppl who will never tell you how much fine tuning it took to get their Medium click bait dreams come true.
