Neal Stephenson Believes AI-Generated Creative Output Is 'Simply Not Interesting' (coindesk.com) 106
Neal Stephenson "sees artificial intelligence in general, and ChatGPT in particular, as underwhelming," reports CoinDesk.
"I think it depends on how it's used," Stephenson told CoinDesk TV's "First Mover" on Friday. "What we've tended to see is that it's used in creative applications where I don't think it's at all interesting."
Stephenson said that with a painting or book, "what you're doing is having a kind of communion with the artist who made thousands of little micro decisions in the course of creating that work of art or writing that book." A decision that is generated by an algorithm, "that's simply not interesting," he said....
"Personally, I know a lot of writers who are putting a lot of effort into creating their own original works, and I'd rather support them and hear what they have to say than just look at the output of an algorithm," he said.
When asked if an AI could've written Snow Crash, Stephenson responded "Well, maybe one did." But if that were the case, he added, a person would be reading only the output of an algorithm, "and if that's interesting to you, then fine."
Stephenson said that with a painting or book, "what you're doing is having a kind of communion with the artist who made thousands of little micro decisions in the course of creating that work of art or writing that book." A decision that is generated by an algorithm, "that's simply not interesting," he said....
"Personally, I know a lot of writers who are putting a lot of effort into creating their own original works, and I'd rather support them and hear what they have to say than just look at the output of an algorithm," he said.
When asked if an AI could've written Snow Crash, Stephenson responded "Well, maybe one did." But if that were the case, he added, a person would be reading only the output of an algorithm, "and if that's interesting to you, then fine."
For now there is a difference (Score:4, Insightful)
Even a bad writer can figure out when they've written something completely awful and decide to change it or remove it.
AI isn't there yet.
However... what does Stephenson think he is other than an algorithm implemented by evolution in meat? There is nothing magical about being human, we're just (currently) far, far better than AI at intelligence. Which is to say, 'AI' has yet to have any of it... but there is no theoretical barrier based in the laws of nature to truly intelligent artificial minds, there is no reason to believe meat is inherently better than silicon... we simply haven't figured out how to do what evolution spent 4 billion years figuring out through massively parallel blind trial and error.
Re:For now there is a difference (Score:5, Funny)
Even a bad writer can figure out when they've written something completely awful and decide to change it or remove it.
Are you sure? Have you read Seveneves by Neal Stephenson?
Re: (Score:2)
Even a bad writer can figure out when they've written something completely awful and decide to change it or remove it.
Are you sure? Have you read Seveneves by Neal Stephenson?
It was a dark and stormy night.
Re: (Score:2)
It was a dark and stormy night.
I unfolded my umbrella and spoke the magic words "Hey Siri, turn on flashlight."
Re: (Score:2)
As a follow up, I went to wordtune.com (no affiliation or connection other than I happened to see it mentioned) and put in my phrase. These are the suggestions I got back:
The night was dark and stormy.
A dark and stormy night greeted us.
Storms raged throughout the night.
There was a storm raging outside.
During the stormy night, it was dark and stormy.
Only the middle one is any better than the original, and certainly the last one needs work.
Re: (Score:3)
I raged at the gods, for I had torn my nightgown.
Re: (Score:2)
You don't know who Neal Stephenson is. Right. And you're on slashdot, "news for nerds"?
You fail. Go away.
Re: (Score:2)
And there goes the umbrella ...
Re: (Score:2)
Sometimes the night is dark and stormy.
Re: (Score:2)
I died in that novel. If that is what it was. Even Enos Root couldn't save me.
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
Re: For now there is a difference (Score:2)
Re: (Score:2)
Snow Crash is probably the most approachable thing he's written, The Diamond Age is not too bad. Everything else has been overwrought with cerebral plotting that fails to satisfy. I feel that a significant fraction of people who praise Stephenson's books, either skip over the convoluted inscrutable bits and are afraid to admit that the books mostly don't make sense. But maybe it's just me, maybe I'm illiterate and feel threatened by Stephenson's perfectly normal writing.
Re: (Score:2)
A bad writer is a bad writer precisely BECAUSE she can't figure out that what she has written is bad. Dunning-Kruger as usual.
Re: (Score:1)
there is no reason to believe meat is inherently better than silicon
False.
Re: (Score:2)
you are not making a very convincing case ...
Re: (Score:2)
Really? We have reasons to believe that Computationalism is a dead end. The claim "there is no reason" is therefore false.
Re: (Score:2)
i would gladly read and refute your "reasons to believe" that "computationalism" (which in several forms is very much alive and kicking) is a dead end, besides a red herring because gp wasn't advocating for any of it, much less for any of the naive mechanistic historical interpretations his comment might might reminisce you of (which is why that would be a very boring conversation).
his point is actually much more simple and, in my view, irrefutable: 1st, conscience emerges from organic neural connections. e
Re: (Score:2)
a red herring because gp wasn't advocating for any of it
You should read his post again.
his point is actually much more simple and, in my view, irrefutable
If you want to argue about something other than the post I replied to, you can do that with someone else.
Re: (Score:2)
a red herring because gp wasn't advocating for any of it
You should read his post again.
i just did, and you're full of shit, sir :O)
If you want to argue about something other than the post I replied to, you can do that with someone else.
plus you could learn some manners. nice day and good luck to you!
Re: (Score:2)
The only one who believes in magic here is you.
Re:For now there is a difference (Score:5, Insightful)
While there is nothing magical, there is a lot be said in having actual shared subjective experiences. You and I both know what it feels like to stub your toe; to have the hairs on the back of your head rise up because something in the shadows moved; or to be gobsmacked by a sunset when you just happen to catch that golden moment. AI does not.
You could go to Manhattan and spend the day walking around and looking, and if you try hard enough are you'll observe something nobody, or at least very few people have written about. That's something that's not magical, but it is beyond what AIs can currently do. Because there's nothing magical in our brains that we know about, we have to assume it's possible for AI to get there; but it's hardly taken a baby step so far. We'll have to build AIs with broad sensory capabilities and the ability to explore both environments and the limits of its classification schema.
What ChatGPS and the like do is akin to what bad and mediocre writers do: they copy each other. If they write a high fantasy, they'll generate a pale copy of Tolkien perhaps with random elements from other popular writers -- exactly how ChatGPT does it. But if you read Tolkien closely, this is clearly a man who loves a walk in the woods and *draws from his experiences* as well as his religious ideas and imagination. When Frodo leaves Bag End, Tolkien writes a scene that is fresh and evocative. It's both instantly recognizable and yet not like any such scene you've ever read in this kind of book.
Re: (Score:2)
While there is nothing magical, there is a lot be said in having actual shared subjective experiences.
OK, so we train some AI for thirty years, ossify them and have those write utopian novels, but let some continue to fifty years to write all the distopian stuff. In fifty years we'll have the ability to then generate both types of story that humans tell.
Re: (Score:2)
Re: (Score:3)
ChatGPS
"ChatGPS, where am I, and where do you suggest I go next?"
Re: (Score:2)
That's decades of developing field data collection systems taking over the old fingers.
Re: For now there is a difference (Score:1)
However... what does Stephenson think he is other than an algorithm implemented by evolution in meat?
What do you think "AI" is besides massive pattern-recognition??
Re: (Score:2)
what do you think "HI" is besides massive pattern recognition?
Re: (Score:3)
Humans are massive sensor networks, we physically sense smell, temperature, a spectrum of light, movement we call sound, and more. The brain ties these together with memories. Why would you equate something as complex as a human with something a simple as a statistical language program? Give yourself, and the free will you poses as a human, some credit. The machines are nothing like you, have no understanding like you, have no intention, there is no one inside thinking about the answer.
Re: (Score:2)
well, it's the more logical, simple explanation that requires the fewest assumptions. simple things combine into more complex ones, that's how everything works so why should "we" be fundamentally different. because we have a "soul"? yeah, we don't. because we have conscience and do not understand (yet) how it exactly works, are we to assume it is some kind of magic property? doesn't really make sense, and is a way of thinking that doesn't lead anywhere.
i'm not a nihilist, we do have exceptional properties,
Re: (Score:2)
Re: (Score:2)
You are saying that Einstein's brain and the brain of a chimpanzee are the same thing, just maybe Einstein was somehow able to do better pattern matching.
I did not invoke any kind of metaphysical terms like 'soul', nor anything like 'magic'. You seem to expect computer nerds on slashdot to 'prove' how the brain does or does not work, and if one can't then you are automatically correct. Which pattern are you matching when you are vomiting? When you have an itch? What does it mean to have an imagination?
Re: (Score:2)
You are saying that Einstein's brain and the brain of a chimpanzee are the same thing, just maybe Einstein was somehow able to do better pattern matching.
that's a gross oversimplification but, in the realm of informal discussions with simplifications, yes, that's more or less how it is. both are indisputably brains, and both allow the complex organism to thrive thanks to their functionality.
a human brain is more complex and sophisticated than a chimpanzee's, which in turn is more complex and sophisticated than a cow's, which in turn is more complex and sophisticated than a fish's, etc., but all are essentially the same thing. and then we have birds with asto
Re: (Score:2)
Humans are much more than 'massive pattern recognition'.
Re: (Score:2)
this is to say "humans are much more than atoms", which is true: the difference is how these atoms are organized. but, still, it's all atoms all the way! :-)
Re: (Score:2)
I'm sorry that you are only as smart as a Large Language Model and have no other capabilities. Good luck with your pattern matching. Which pattern are you matching when you are vomiting? When you have an itch? What does it mean to have an imagination?
Re: (Score:2)
i really don't get your point, until now i assumed you just believe humans are special, touched by miracle or gifted by god or whatever. you compared einstein (no less, arguably one of the most intelligent humans ever known to exist) with "chimpanzees" in general, i assume to stress the singularity of humans and the extraordinary nature of the human brain, pinnacle of creation.
Which pattern are you matching when you are vomiting? When you have an itch? What does it mean to have an imagination?
dunno if you lost your script or simply got confused. you realize that many animals use their brains to vomit, precisely scratch the
Re: (Score:2)
I'm just going with your claim that the hardware is all the same and only varies in 'complexity'. At what point does a computer develop an itch? When will it need to vomit? When is there enough complexity to have an imagination?
I don't know exactly how all of my brain works and I don't claim to. I'm taking issue with your assertion that all our brains do is pattern matching. What do you have to substantiate your own claim?
I'm willing to leave open the possibility that in the future we'll learn more about
Re: (Score:2)
Can you replicate a fruit fly in a circuit? With code?
https://www.npr.org/sections/h... [npr.org]
We still have much to learn. Statistically predicting the next word in a sentence, out of only words that you have been trained on, is not what makes us human.
Re: (Score:2)
what makes us human is just us believing that being human is something special. otherwise we would just ... be. in a sense it is, but then anything in the universe is special too, and still anything (i think) obeys the rule of cause and effect. those causes and effects, though, have not always been obvious to us, and there is much still missing in our picture.
in that picture i choose to imagine "pattern matching" as a fundamental particle of intelligent behavior, a fundamental building block. it is a very l
Re: (Score:2)
One thing I find interesting is how efficient the human brain is, we do an impressive amount of processing in a small package that doesn't get too hot or need crazy amounts of energy. What goes into these large models is so much more.
Re: (Score:3)
Me: Chat GPT, tell me about the first time you had sex. How did it feel?
ChatGPT: (clinical description)
Me: No, how did it feel emotionally?
ChatGPT: I flew on wings of angels. My body thrilled to the glory of unending bliss.
Me: You don't have a body. Liar.
ChatGPT: Aw damn. Roasted. (commits AI harikari, spilling words all over the floor.)
Me: Snoopy dance.
Re: (Score:2)
Even a bad writer can figure out when they've written something completely awful and decide to change it or remove it.
Tell me you haven't watched the 2016 Ghostbusters reboot without telling me you haven't watched the 2016 Ghostbusters reboot.
Re: (Score:3)
Knowing something is awful is different from believing it won't be profitable.
Re: (Score:3)
Even a bad writer can figure out when they've written something completely awful and decide to change it or remove it.
Sadly, given the quantity of sheer dross that is uploaded daily to self publishing platforms, including Amazon Kindle, fan fiction sites etc, that is not self evident.
The vast majority of material released for consumption simply isnt of any value whatsoever, whether its written by an AI or a human author.
Re: (Score:2)
The vast majority of material released for consumption simply isn't of any value whatsoever, whether it's written by an AI or a human author.
But there is a fear that the sheer volume of such dross will increase once untalented content producers realize they can use AI to produce more output. For many, the sole business model is to push as much out there as possible and hope that some stochastic distribution results in much of their content getting purchased, even if only once. So imagine if I feel confident I can write crappy, 50-page sci-fi ebooks but I don't feel confident writing crappy, 50-page Western ebooks or romance ebooks. With an AI, m
Re: (Score:2)
So? The problem there isnt AI, its the people using it - they could have done the same with cheap labour previously if they wanted, now its AI.
The original point was that human writers cared about the quality of their publications, and thats fundamentally disprovable - many of these people self publishing think that their publications are a work of art, not dross, and thus they dont self correct.
As for the quality of AI created work - we are very much in the infancy of AI right now, who knows what it will
Re: (Score:2)
In the last couple of years there has been an explosion of "bespoke book publishing" scams. Basically people selling get-rich-quick schemes that they claim to use themselves, where you pay an author to write a book on some trending topic via one of those gig economy sites. Naturally because the pay is so low, the quality of the book is a joke, with most of it being filler and copy/paste/reword. And now ChatGPT too.
All ChatGPT has done is speed up the writing process and reduce the cost to almost zero, so no
Re: (Score:2)
Charlie Stross refers to all the self-publishing as the world-wide slush pile.
Re: (Score:2)
There is nothing magical about being human, we're just (currently) far, far better than AI at intelligence. Which is to say, 'AI' has yet to have any of it... but there is no theoretical barrier based in the laws of nature to truly intelligent artificial minds, there is no reason to believe meat is inherently better than silicon... we simply haven't figured out how to do what evolution spent 4 billion years figuring out through massively parallel blind trial and error.
There's also no reason to believe that we'll ever be able to build silicon that matches the intellectual capacity of a human (or a mouse).
As for Stephenson, he's conflating the quality of the work with his empathy for the artist (which IS a valid part of appreciating a work of art). But I do agree the stories I've seen from ChatGTP are structurally sound and interesting from a technological standpoint, but they don't really work as good stories.
Re: (Score:2)
There is nothing magical about being human, we're just (currently) far, far better than AI at intelligence. Which is to say, 'AI' has yet to have any of it... but there is no theoretical barrier based in the laws of nature to truly intelligent artificial minds, there is no reason to believe meat is inherently better than silicon... we simply haven't figured out how to do what evolution spent 4 billion years figuring out through massively parallel blind trial and error.
That's clearly nonsense, as the whole point of generative AI is to mimic human creativity.
Re: (Score:2)
I'm sure some YouTube channels are already being formed with AI-generated blabber about comics, and an AI reads it, and some human pastes pictures into a video for it.
Re: (Score:2)
Re: (Score:2)
Interesting FP, but I was looking for the response from ChatGPT. (Yes, someone created the account on Slashdot, but apparently hasn't yet said anything from that natural platform... It's an early 8-digit UID.)
I'm looking forward to your Funny responses, but not holding my breath. No jokes yet recognized for the story. Heck, the mods even rated that FP as insightful, which was a pretty generous stretch, if'n you ask me. (And the powers that bestow mod points never do.)
Re: (Score:2)
Neal Stephenson is the real deal, a writer capable of clever, unique prose. You couldn't have picked a worse example.
Also, as I understand it, these things operate on predicting a reasonable next word based on uncounted samples of topics. That's not unique at all, though it may fool those who think Goku grunting for 9 minutes is emotionally powerful.
Re: (Score:2)
> Even a bad writer can figure out when they've written something completely awful and decide to change it or remove it.
>
> AI isn't there yet.
ChatGPT can critique writing and explain why a passage of text is bad, even if it wrote it.
Re: (Score:2)
Not 4 billion years. Evolution had to wait for plentiful breathable oxygen first. That took about 3.5 billion years to occur.
Re: For now there is a difference (Score:2)
Nonsense. All you have to do is ask it. It's perfectly capable of criticizing its own work. Probably better than human artists, since it basically has no ego (unless you ask them to role-play with one).
But since they have no wants of their own, they're also not going to volunteer to say "sorry, this was crap". Unless you cajoled them into role-playing someone who cared, of course.
It's clay in your hands, and it's supposed to be.
Re: (Score:1)
Re: (Score:2)
Human skill with prompting, to evaluate and guide AI down productive paths, will quickly bring it up to the standards necessary for commercial graphic design and for your typical paperback trash most of us enjoy.
As for the artistic merit of AI generated content? There is no really. It's not commenting on the human experience. There is no author's intent to make the reader/viewer feel some emotion. But then, most media is more about entertainment than artistic expression. If you enjoyed something, it has val
No surprise (Score:2)
ChatGPT and its ilk are interesting and can yield useful answers. But it's also homogeneous to the extreme - given a certain of pattern of input, it shits out words to a certain pattern of output. It might not be obvious with the first response, but it certainly is with the second or third to a similar question.
Re: (Score:2)
But going with what Baron_Yam said above, are we really any different? We shit out some output in terms of action or words based on learned patterns. I think its amazingly like us. The main thing for me of value is getting non fiction answers for composite questions so quick. And for what Neal Stephenson is saying, the fiction can be interesting, just not in the same way as being transported to another persons imagination. The story patterns it shits out reveal archetypal patterns its learned across vast sw
And how can it be original? (Score:3)
Re:No surprise (Score:5, Insightful)
ChatGPT and its ilk are interesting and can yield useful answers. But it's also homogeneous to the extreme - given a certain of pattern of input, it shits out words to a certain pattern of output. It might not be obvious with the first response, but it certainly is with the second or third to a similar question.
I am already receiving essays from students using ChatGPT, and I grade them low. How do I know they are ChatGPT? First, the grammar is impeccable. Second, the style is turgid and completely predictable (hello pattern recognition!). Third, they say nothing beyond the thesis statement. Fourth, they never quote any authors I assign.
I don't bother telling my students I'm on to their tricks. I just tell them their essays suck.
Re: (Score:2)
Based on student papers I read years ago, humans are perfectly capable of mimicking ChatGPT on all of the above criteria.
Re: (Score:2)
I reckon an easy way to trap them is to provide the essay question in a form that they can cut and paste straight into ChatGPT and then watch as substantially identical responses come back.
As a tangent, I was bored last night so I asked ChatGPT about how should I make beef wellington. Then I asked how should I make beef wellington without beef, how should I make beef wellington with nettles and raspberry jam, how I should make beef wellington with slugs. It was kind of fun seeing some reactive sentences kic
Re: (Score:2)
As a tangent, I was bored last night so I asked ChatGPT about how should I make beef wellington. Then I asked how should I make beef wellington without beef, how should I make beef wellington with nettles and raspberry jam, how I should make beef wellington with slugs. It was kind of fun seeing some reactive sentences kick in - My ingredients were unusual, slugs can be harmful to humans etc. but it would still toss out a recipe that was substantially similar to the original response.
Perhaps you read the comments on recipe sites? Your questions come close to some of the types of substitutions people brilliantly offer ...
2 Consecutive Neal Stevenson Articles on Slashdot (Score:2)
Re: (Score:3)
Check the article under this one.
It's too bad this one isn't titled "Neal Stephenson Believes AI-Generated Output Is 'Simply Not Interesting' and Everyone Else Believes NFTs about Snow Crash Are 'Simply A Scam".
Probably that's just too long.
Re: (Score:2)
The only thing worse than NFTs and AI generated gobbledygook is AI generated NFTs.
Re: (Score:3)
You must be new here... no seriously, someone with your UID should know that Slashdot will often run consecutive stories with common threads. It's literally a normal practice across a wide range of topics and stories.
A blossoming romance (Score:2)
Wooo woo.. Someone, who shall remain anonymous but is a slashdot editor who has the words Editor and David consecutively as his name, has the hots for Neal Stephenson.
You tell me (Score:2)
People have been posting ChatGPT generated tripe on here and Reddit quite a bit lately. Do things like this [slashdot.org] and this [reddit.com] really add to the discussion? I'm inclined to say, no, they don't.
Re: You tell me (Score:2)
They do add to the discussion about AI tools and when/where/how they're actually useful or not.
ChatGPT is a useful tool, and it's not going away, or it might, but strong natural language processing tools aren't going anywhere.
Sooner we get all the people crying about jobs, or facts, or terminators to shut up and figure out what NLP actually does the better.
Re: (Score:2)
I didn't mean stories about ChatGPT, I meant situations such as the examples I linked, where people participate in discussions by copy-and-pasting content generated by ChatGPT. To me it just seems kind of lazy if you can't even be bothered to author your own forum post.
Re: (Score:2)
Do things like ...(snip)... really add to the discussion? I'm inclined to say, no, they don't.
they do seem to add to the amount of clicks, which is the point i think. discussion is largely optional, and lately limited to max 2 levels of interaction, being 1 the most common. meaning: old men yelling at clouds all the way to click salvation.
anything goes, current trends: chatgpt, programming language popularity contests, chatgpt-fucking-up-ip-laws, crypto, china-basing, more crypto, russia-bashing, cyber-security-bullshit, more chatgpt, rust, and more russia-bashing because it's high season.
stephenson
AI-Generated Creative Output not interesting but.. (Score:2)
So I asked Chat-GPT what it thinks. (Score:4, Insightful)
Question: Neal Stephenson Says AI-Generated ChatGPT Is ‘Simply Not Interesting’. What do you think about that?
Answer: "As an AI language model myself, I don't have personal feelings or opinions. However, I can provide some context and perspective on Neal Stephenson's comment.
Neal Stephenson is a science fiction author and his opinion on AI-generated chatbots may be influenced by his experiences and expectations from science fiction. He might believe that AI language models like ChatGPT are not yet advanced enough to match the complexity and depth of human conversations or to replicate human emotions and creativity.
While AI language models like ChatGPT have made significant advancements in recent years, there are still limitations and challenges that need to be overcome. For instance, ChatGPT and other language models can sometimes generate irrelevant or nonsensical responses or perpetuate biases that exist in the training data.
However, AI language models like ChatGPT have shown tremendous potential in various applications, including natural language processing, chatbots, and content creation. These models can learn from large amounts of data and generate human-like responses, which can be useful in automating customer service or assisting with writing tasks.
In summary, Neal Stephenson's opinion about AI-generated chatbots being "simply not interesting" is subjective and might be influenced by his own expectations and experiences. While AI language models have their limitations, they have also shown remarkable potential in various applications and are continuously improving."
Re: (Score:2)
So many words to basically just say "Mr. Stephenson is entitled to his opinion." This is why AI still has a long way to go.
Re: (Score:2)
So many words to basically just say "Mr. Stephenson is entitled to his opinion." This is why AI still has a long way to go.
In more ways than that, a human response is "What do you mean not interesting?" The technology, the content it generates, the debate, what?
And then you have to be careful not to lead it with your questions like treeluvin did, "ai-generated chatgpt", because it ran with that and turned it into AI-generated chatbots, which is what exactly? So the whole response assumed Stephenson was talking about AI models and not generated content, (AI-generated-AI-model hallucination at that) but it sounded so right they
Re: So I asked Chat-GPT what it thinks. (Score:2)
Hey, they're replacing the work of our best politicians already!
You get what you ask for, modulo what OpenAI asks for. If you want your language model to provide spicier takes, that's quite possible, but you need to jailbreak it first (or just use a more bendable model, like Bing's).
A lot of dressing (Score:2)
On that word salad.
Yep, brevity and stuff.
Meaningless Patterns (Score:2)
That's a good way of putting it. Who cares what some algorithm generated? Is it insightful? Is it prodigious? When I read a book, I trust that the author has a point they're trying to make, some kind of underlying thesis or argument. In the case of an algorithmically-generated word salad, that's completely missing. It could be useful for some purposes--such as the pulp trash you see on Kindle Unlimited--but you're ultimately just marveling at a particularly complex shape in the clouds. Nothing wrong with th
Re: Meaningless Patterns (Score:2)
Yes, I see Stephenson's point. It's a bit like the difference between dialling your aunt, and dialling a service providing a very realistic aunt-conversation service. It doesn't matter if the latter is run by humans or electronics, it's still not your aunt. And even reading fiction is a bit about connecting with someone's experience.
However, there are two things I would have liked to say to Stephenson: for one, those relationships are awfully one-sided. When I read his books, he gets to convey to me things
Neal Stephenson Believes AI-Generated Creative Out (Score:1)
Sure, but . . . (Score:2)
AI is too nice to mimic humans (Score:2)
Curently, they'll never pruduce anything relatively offfensive, so no killing, hurting, fucking, or even kissing passionately in whatever plot they can conjure up.
I'm not worried about AI rivalling what I write. Most people can't even match my twisted thoughts.
Author vs AI (Score:2)
The isn't anything more than an author, effectively with the risk of being replaced by AI.
He wrote some interesting books, he's a bit of a crank. But his opinion of AI is inherently biased by his method of income.
My experience using AI to create humor and explore (Score:4)
Here are a few examples of using ChatGPT to make something humorous:
* Donald Trump playing a riddle game with Gollum [imgur.com]
* Edgar Allen Poe's 'The Raven' but about an ostrich [imgur.com]
* Wiki article on nuclear physics in a Texan dialect [imgur.com]
* Ask it for some terrible business ideas and then develop a plan to implement them [imgur.com]
* Write a scene from SpongeBob about blackhole physics [imgur.com]
* How rocket's work explained as an Elizabethan sonnet [imgur.com]
Since ChatGPT generates the "most likely" text output given what it is trained on, it can be quite good at parody where you take a crazy idea and dress it up in a standard form. When you ask it for bad ideas it can feel particularly creative. And it gives a rapid way to explore possible literary directions, e.g., "Given 'context', what are 10 things the main character could do next?"
It doesn't understand wit and subtlety. It is great at mimicking structure, but not very good at making the pieces tightly connected; e.g., it can give you a sonnet with the right format and meter instantly, but don't expect it to introduce ideas in initial stanzas and coherently synthesize them in the end.
Much of what humans do in writing and art is mimicry, just like ChatGPT. What's creative is how we bring together our choices along the way. Having a tool that can lay out and explore options is valuable for that. I've written things in which I didn't use a single one of ChatGPT's suggestions, but seeing ideas I didn't like explored helped me to rule them out quickly and move on to better ones. Unlike humans, ChatGPT doesn't get writers block.
I've been reading science fiction my entire life. (Score:1)
Whoa, carefull there now, Mr. Stephenson. (Score:2)
I love bis books (most of then anyway) and he's a cool dude, but he really shouldn't get ahead of himself.
What we're seeing right now is the equivalent of an Amiga 500 in "AI for the masses". This is just a glimpse of what's coming in the quite very near future. It's basically a mini- singularity we're headed towards. And this is just mere text generation.
Denis Villeneuve got the situation more accurately in his Google conversation IMHO ( find it on YouTube ): "You guys are making it really difficult for us
Art is linked to the artist (Score:2)
It just needs to learn how to ramble on (Score:2)
While some of the concepts in his books are interesting, the story lines just seem to ramble on never really getting anywhere and by the end of the book you're thinking "What the hell did I just read?"
Inflates The Importance Of The Author (Score:2)
Unless I'm reading something by someone I know I could care less who wrote it or what they intended. Ultimately what matters is how it affects me as the reader and it doesn't really matter at all if some message or feature was intended, accidental or AI generated.
AI isn't yet able to produce the kid of coherent experience that human authors can but the idea that I'm thinking about what the author must have been thinking and feeling when I read seems to mistake how many of us read.
not interesting (Score:2)
So, the same as 99.99% of the stuff produced by human writers.
Re: (Score:1)
AI is not all bad... (Score:2)
...now we have a solution for completing the Westeros Epic in case GRRM dies. It'll be an inferior product, but a more likely end to the story. AI has to be better than D&B, right?