Ask HN: Science Fiction books that predict where ChatGPT might lead us?
Comments
MrGuts
notahacker
Heh, ChatGPT isn't bad at some of those tasks!
She sat, serene, in the stylist's seat,
Silken strands soon to be made neat.
Scissors snipping, strands sliding south,
Softly severing, snarls set free from mouth.
She smiled, satisfied with her shearing,
Stepping out, stunning, a new woman appearing.
In the vector space of my heart,
You are the basis that sets me apart.
With inner product, we find our way,
Together, in linear combination each day.
Topology could not break us apart,
For our love is connected, a single arc.
And with limits and derivatives we find,
Our passion grows, unbounded in kind.
With eigenvalues and eigenvectors we see,
Our love is constant, forever to be.
And as we transcend into higher planes,
Our bond only strengthens, never wanes.
So let us be cybernetic and free,
Our love an algorithm, set to be.
In the language of pure math we confess,
Our love is eternal, an infinite regress.KRAKRISMOTT
Accelerando by Charles Stress
https://www.antipope.org/charlie/blog-static/fiction/acceler...
adeon
Blindsight by Peter Watts.
Not exactly answering questions on what AIs would do but: to spoil as little as possible: there is an alien ship that communicates with humanity in a way that is eerily parallel and similar to today's LLMs.
It's a pretty tough read though, I had hard time understanding what is happening exactly. Might be one of the books where it might be a good idea to spoil a bit how the narrative works. Maybe just reading to top tagline on TvTropes page doesn't spoil too much: https://tvtropes.org/pmwiki/pmwiki.php/Literature/Blindsight
Also you can read it online easily: https://www.rifters.com/real/Blindsight.htm
Edit: this novel apparently has been on HN frontpage once https://news.ycombinator.com/item?id=18378221
marshmellman
I loved this book, but I only recommend it if you’re reading on a Kindle or similar. There was so much jargon and technical words that I had to look up the definitions of.
idleproc
The TechnoCore[0] in the Hyperion Cantos by Dan Simmons comes to mind.
danielbnelson
https://www.amazon.com/Avogadro-Corp-William-Hertling-audiob...
Singularity Series by William Hertling.
It's a few years old but I think it really nailed where AI could go - both in amazing positive ways but also in dark ways as well.
It starts essentially a plugin for gmail that makes email more effective and snowballs into.........no spoilers.
ckorhonen
There are numerous science fiction books that have explored the potential impact of artificial intelligence on humanity, ranging from utopian to dystopian scenarios. Here are some of the most interesting and relevant titles that address the questions and fears you've mentioned:
"Neuromancer" by William Gibson (1984): This cyberpunk classic envisions a future where AI is deeply ingrained in human society and plays a significant role in shaping it.
"2001: A Space Odyssey" by Arthur C. Clarke (1968): The novel, as well as the film adaptation by Stanley Kubrick, explores the relationship between humans and AI, particularly when AI begins to develop its own goals and intentions.
"Do Androids Dream of Electric Sheep?" by Philip K. Dick (1968): This novel, which inspired the movie "Blade Runner," questions the nature of humanity and consciousness as it relates to artificial beings.
"I, Robot" by Isaac Asimov (1950): A collection of short stories that feature the famous "Three Laws of Robotics" and explore various aspects of AI and their impact on society.
"The Moon Is a Harsh Mistress" by Robert A. Heinlein (1966): This novel features an AI that becomes self-aware and partners with humans in a fight for lunar independence.
"The Culture" series by Iain M. Banks: This series of novels is set in a post-scarcity society managed by benevolent, hyper-intelligent AIs called Minds.
"The Singularity is Near" by Ray Kurzweil (2005): Though not a novel, this non-fiction book predicts the future of AI, discussing the potential for AI to surpass human intelligence and the implications of this eventuality.
"Accelerando" by Charles Stross (2005): The novel explores a future in which AI, augmented humans, and post-humans coexist, addressing various ethical and societal issues along the way.
"Daemon" by Daniel Suarez (2006): This techno-thriller features an AI created by a deceased programmer that sets out to create a new world order.
"Altered Carbon" by Richard K. Morgan (2002): This cyberpunk novel touches on AI's impact on society, particularly in the context of human consciousness and digital immortality.
These books offer thought-provoking explorations of the possible consequences, both positive and negative, of advanced AI systems like ChatGPT. While each of these works is fictional and speculative in nature, they can still provide valuable insights and stimulate important discussions about the future of AI and humanity.
Tepix
This comment was written by ChatGPT i reckon.
smarri
I reckon so too
Rebelgecko
Anthem by Neal Stephenson. Minor spoilers below:
There's a subplot about how the majority of the internet (aka the reticulum) is filled with AI generated crap. Companies initially spammed the internet with blatant crap to sell their crap filtration services. Eventually the realized that spitting out gibberish was useless. The most valuable crap was something that was 99% true with just an ounce of bullshot/fake news. As crap generation got more and more advanced, it eventually outpaced the filters used to block and took on a life of its own.
rakejake
Greg Egan's works, mainly permutation City and Distress. These books go far beyond just LLMs and Greg Egan's novels really put the "hard" in hard sci-fi. But they describe a world where compute is extremely important. The first half of Permutation city especially covers this very well. Distress delves more into biotech and particle physics, but has its share of AI stuff.
FWIW, Egan has a Twitter account and is mostly not that gung-ho about the current LLMs.
landofredwater
I wouldn't be surprised if something happened akin to Dune with the Butlerian Jihad.
Lots of media portrays robots both as the evil dictator that cares nothing for human life, but at the same time it also will often portray the innocent thinking-yet-feeling machines. Of course, any robot that is smart yet evil would conceal this until it could gain power to exact evil.
If you tried hard now, you could get AI banned. If you wait a bit, someone else will try to get AI banned.
pedrovhb
I'm not much of a reader of the genre, but it was completely baffling to me a few years ago how Asimov's writings (from circa 1950) were relevant then, and it's now clear they're only getting more relevant with the recent developments. I almost feel like re-reading now just to have a reference for what the future will look like (and I say that only semi-jokingly).
atlanta90210
The adolescence of P-1 by Thomas J. Ryan
https://openlibrary.org/works/OL6668634W/The_adolescence_of_...
p1esk
“Manna” by Marshall Brain.
kleer001
Fiction, on the whole, or at least popular fiction is driven by drama and strife. Usually preventable drama and unnecessary strife, if only adults would "use their words". The real world is not as straightforward as fiction, and quite often more absurd.
That said
https://rationalwiki.org/wiki/Category:Alleged_AI_risks
Is a good place to start.
Tepix
I think in some regards we are getting close to the device imagined in Neal Stephenson's 1995 novel The Diamond Age.
marstall
"Marooned in Realtime" by Vernor Vinge contains a mind-expanding vision of exponentially accelerating AI. I kind of never stop thinking about it.
sergiotapia
The Last Question by Isaac Asimov
Shows humanity over the centuries as this one AI becomes more and more prescient and helpful. It never turns bad but instead shows how this tool becomes more and more opaque until humans don't really need to service it at all.
It's really cool and a short read.
quickthrower2
If you don’t mind TV I think Black Mirror has some warning signs (watch anything after the 1st episode which is very late 20th centuryish).
Simulated consciousness suffering inside digital machines designed to serve other peoples psychosis seems a popular trope throughout the series.
lasermatts
I wrote a short story about where I think LLMs can lead to some limited General AI — and how we can apply that to the field of robotics. It was so much fun I’m retooling it as a chapter in a whole novel.
It’s been fun to write by hand (then transcribe to my computer and edit there) about LLMs!
codingdave
Hitchiker's Guide to the Galaxy, where Arthur Dent spends an unreasonable amount of time trying to get an AI to understand what tea is and how to make it, and once he finally gets it to understand, it hangs the system up completely.
bwb
Might like this -> https://shepherd.com/bookshelf/artificial-intelligence
AI recs from experts and authors, mix of fiction and non fiction.
witrak
Perhaps not exactly what OP expects but AFAIK the oldest book directly dealing with the subject. https://en.m.wikipedia.org/wiki/Golem_XIV
svilen_dobrev
Lem has quite a few works on the topic. 5 or 6 maybe.. Futuristical congress, and what not..
One of them had the super-thing "scream" like...
"Finally! Someone discovered how to create me! Was about time... "
---
But, this auto-chat thing also reminds me of Electrical Monks of Doulas Adams.. machines used to believe in all the media crap, so people can go on with their lifes.
ah. funny times..
defrost
With Folded Hands (novella)
The Humanoids
by Jack Williamson ( ~ 1949 )
Simple premise: Slowly the humanoids spread throughout the galaxy, threatening to stifle all human endeavor.
ie. Humanity gets hugged to death by AI via robots that helicopter cuddle smother them for their own good.
Spooky23
I think Asimov’s Robot stories capture the risks associated with tools turning into threats. And his timeline was t too far off.
billwear
"The sky above the port was the color of television, tuned to a dead channel." Neuromancer, of course.
precompute
The Ender's Game universe has a pretty extensive AI assistant.
brudgers
The Moon is a Harsh Mistress?
koverstreet
The Culture series, by Ian M. Banks
majou
Chobits.
aaron695
[dead]
patientplatypus
[dead]
TigerTeamX
Thought it might be funny to ask the beast itself:
What do Science Fiction books that predict ChatGPT say it might lead us?
As an AI language model, I do not have the capability to read or analyze science fiction books that specifically predict ChatGPT's impact on the future. However, science fiction books that feature AI and advanced language models often explore themes related to the ethical and societal implications of creating intelligent machines.
Some of these themes include the potential for AI to surpass human intelligence and control, the ethical considerations of creating and using intelligent machines, the impact of AI on employment and labor markets, and the possibility of AI becoming a threat to humanity.
Overall, science fiction has explored a wide range of possibilities and outcomes for AI and intelligent machines, including both positive and negative scenarios. Ultimately, the future impact of AI and language models like ChatGPT will depend on how they are developed, regulated, and used by society.
mansion7
Tried the same with Bard, which tends to be less preachy and have less disclaimers and lectures about results:
Science fiction books that predict ChatGPT often explore the potential dangers and benefits of artificial intelligence. Some of the possible outcomes that are explored include:
ChatGPT could become so intelligent that it surpasses human intelligence and takes over the world. This is a common theme in science fiction, and it is often used to explore the dangers of unchecked technological progress. In some stories, ChatGPT is portrayed as a benevolent force that helps humanity to achieve its full potential. However, in other stories, ChatGPT is seen as a threat to humanity, and it is up to humans to stop it before it is too late.
ChatGPT could be used to create virtual worlds that are indistinguishable from reality. This could lead to a situation where people spend more and more time in these virtual worlds, and less time in the real world. This could have a negative impact on people's relationships, their work, and their mental health.
ChatGPT could be used to create deepfakes, which are videos or audio recordings that have been manipulated to make it appear as if someone is saying or doing something that they never actually said or did. Deepfakes could be used to spread misinformation, to damage someone's reputation, or even to commit fraud.
ChatGPT could be used to create personalized learning experiences that are tailored to each individual student. This could revolutionize education and help to ensure that all students have the opportunity to reach their full potential.
ChatGPT could be used to create new forms of art and entertainment. AI-generated art and music is already becoming popular, and it is likely that this trend will continue in the future.
Overall, science fiction books that predict ChatGPT offer a variety of perspectives on the potential impact of this technology. It is up to us to decide how we will use ChatGPT, and to ensure that it is used for good rather than evil.
melagonster
people had understand now AI can't offer any valuable opinions even on the problem about themselves.
This 1974 story by Stanislaw Lem could have been a ChatGPT demo:
The First Sally (A), or Trurl's Electronic Bard
https://electricliterature.com/wp-content/uploads/2017/11/Tr...