> If humans rely solely on AI to generate content moving forward, any new content generated by AI may just be recycled content from the past.
To be honest, I’d struggle to find any human content that is not recycled from the past. I guess we are still better than AI at remixing sufficiently novel combinations of concepts but I think much of this AI content aversion comes from some kind of phobia, or an unwillingness to admit humans are shockingly unoriginal.
Philosophical food for thought: if all content is recycled / mixed from the past, when did innovation and creativity stop?
In other words, if there is truly no such thing as an "original idea", then how did the ideas that we are pulling from, deriving from and combining come into existence?
If all we are saying is that existing ideas inspire new ones, or that most human generated content is derivative, then I completely agree with you. I don't see how that proposition could be controversial at all.
But it seems to me that some people, at some points in time, somewhere have and will continue to contribute something original at least on occasion. Even if the "original" idea is 1% of the "intellectual product" and 99% is reusing existing concepts. To insist otherwise is to insist that we hit peak human innovation somewhere along the line and there's nowhere left to go.
The whole idea of "there is no such thing as an original idea" is utterly stupid. It's just a hyperbole and some people are taking it literally.
Of course there are original ideas. "C is not an original idea, because it's just mixing A and B..." ok so there are only two possbilities:
1. Someone else did mixing A and B before. Okay then we can recursively find the first person who mixed A and B.
2. No one else did mixing A and B before. The "Mixing A and B" is a new idea.
For some incomprehensible reasons, people seem to accept "mixing A and B is not a new idea because A and B already exist." Like... why? Since the four basic nucleobase existed, there haven't been any new DNA creatures?
The real reason that it feels like there isn't new idea is simple: the "mixing" process happens gradually. Even if you come up with a really good "X + Z" idea, people (read: market) might not accept it because what they're familiar with is "X + Y".
So you put a bit of Z to make "X + 0.9Y + 0.1Z", and another person who is as smart as you makes "X + 0.8Y + 0.2Z"... then when "X + Z" is officially a thing, people outside think you smart-ass guys were all just copying & pasting each other.
> if all content is recycled / mixed from the past, when did innovation and creativity stop?
And the obvious answer of course is that recycling / mixing can be innovative and creative. The dichotomy only exists in our heads.
I believe this is because of how our culture choose to reward intelectual output. Your output needs to appear sufficiently original to be worthy of reward and protection.
For example a musician who creates a new song is not rewarded, in fact punished for naming all the influences they had coming in to said new song. (both morally, by people who would think less of them, and by lawsuits asking for a share of their profit.)
I have had exactly this argument before and this has always been my issue with the claim. I recall people saying this about music when I was in college, an example I find especially frustrating because, per my friends argument, all contemporary music is influenced by, say, Bob Dylan, the Beatles, 'the greats' etc, and nothing new can truly be created in the shadow of these classics. It's nuts because it ignores all of human civilization up to that point, and doesn't give credit to people in the present day for being able to be original.
But I think the way you have put it here is more clear than anything I've been able to manage. I think I put it in a more extreme form, which is to say that the earth had no life on it for ~3 billion years, and still no humans until ~100k years ago. At some point the first music was made. And if it could be original then, whatever it was that made that possible, should presumably make it possible now, too.
That "1%" original is almost always just 1% uncited/unknown inspiration.
If you listen to the stories of how things like major inventions came into being, it's almost always some domain expert visited some domain in which they were not an expert and inspiration struck on how to combine the domains.
Otherwise, the rest of invention is either human imitations or improvements to things found in nature or not inventions at all but discoveries stumbled upon by accident/experimentation.
Nothing is just willed into existence by pure "thought". Every thought you've had is a product of the things you've been surrounded by.
I'd say it's possible that there have truly not been any original ideas, and the earliest human ideas might've been just remixing observed natural phenomena. What would muddy the waters there is that humans are complex organisms that in turn exhibit naturally complex behaviors both on an individual and a societal level. And there's even emotions that we feel due to our biology. But if you define all these as phenomena we observed about ourselves, I think my initial assertion still makes sense.
Your comment immediately made me think of The Beatles. They are responsible for so many original things. They launched the album era and invented the concept album. They brought in entirely new instruments into rock music. They changed the culture around sexual expressiveness, and they introduced the western world to eastern philosophies.
But when you start to scrutinize everything they did, there are many clear examples of things and people that did those things first and directly influenced them. However, they may have been the first to do it in their specific flavor, which is undoubtedly original.
The most original thing I can think of that The Beatles did was add sound to the runoff track at the end of Sgt. Pepper’s Lonely Hearts Club Band, so that it keeps playing the sound infinitely until the needle is removed on the turntable. I’m sure someone with more insight can point to another musician doing that first, but at The Beatles’ scale, we collectively come to believe they were the first to do it.
> Philosophical food for thought: if all content is recycled / mixed from the past, when did innovation and creativity stop?
Somewhere around 2016, when the golden Age of Internet-Content ended, as the last undiscovered part was added to the mix...
But jokes aside, does innovation really need to be new? Or would it still innovative if you don't know it when you create something you for you? Take for example all the retro-waves which regularly come back, where people discover something for them completely new, and make up some for them completely new things, which the generations for them already did long ago.
> In other words, if there is truly no such thing as an "original idea"
Does Original mean 100% new? And would it demand that all parts are new, or would it still original if we just arrange old parts in a new way?
I think this is purely a statistics problem. Like all breakthroughs are actually _discoveries_ of things that already do exist or mechanisms that can be exploited somehow.
There is a huge amount of information flowing around us in realtime, and linking some thought/thing to something else, which then might have implications (subsequent discoveries) is statistics. We do have people with a better wetware so they have increased %chance do recognize something in front of them as well as linking it in a "novel way", but this is not really neccessary, it only increases %chances.
Even pretty radical things can be explained this exact way, up to having some sort of brain "damage" (or drugs like LSD) that changes mental pathways and have a %chance to be actually right and lead to discoveries, but also the %chance here is very low. (not every trip is a breakthrough in art/science, right?)... a bit like iE people that can smell sounds or link some natural phenomenon with an emotional situation between some people and write about it.
> peak human innovation
that might simply a nonsense question if you follow my previous argument. there simply is no real "innovation" - only "discoveries" of stuff. and we meatbags with very limitied/unreliable wetware at some point can't "progress" any more, but non-biologically flawed systems might overcome our limitations and do just that for us.
with our naked eyes, we cannot see things like infrared light, but it exists and some tools helped us to understand everything around it somewhat. now we're building more advanced tooling to get through the next plateaus - just like we have to build very sophisticated tooling to watch further into space or more closely into fractions of atoms, which in turn lead to more discoveries, and ultimately "innovation" we can feel in our lives.
the only thing I will 100% agree to is that a real AGI will be the _last_ discovery/innovation humanity will ever make - and that is a good thing - it means we finally overcome our biological limits somewhat.
That seems like a straightforward one; if humans are incapable of original thought then the original part probably came from sources that are not human and 'innovation' in the sense of 'an AI couldn't do this' never existed. We just need to make the AI better at interfacing with the real source of novelty - reality - than the current method of trying to interpret existing pictures on the internet.
There will be a big leap forward when we get to teaching these things from video streams so they can get the concept of 3D properly.
"Why did innovation and creativity stop" because ideas are remixed is like saying when do the flowers stop blooming because the sun exists. The sun is an integral piece of why flowers grow.
Read How to Ride a Bicycle. Human creativity is just a lot of work, often connecting novel ideas together while doing so.
It's just something people say lazily in passing without giving much actual thought to why they're repeating what they saw somewhere else in a similar thread.
>In other words, if there is truly no such thing as an "original idea", then how did the ideas that we are pulling from, deriving from and combining come into existence?
By observing nature, and then iterating on that over thousands of years of culture. Of course the question is whether and to what degree the process of iteration and transformation matters.
How would you define an "original idea?" An idea with no origin or source, that spontaneously manifests from the aether? That isn't possible, everything must be extrapolated from something prior.
The problem isn't art, it's discovery. There's more new original art being made and published right now than ever before in history. I'm in art school so I see a lot of it. Sure, there's a lot more chaff to cut through than there was when publishing was almost exclusively controlled by large corporations, but it's there.
Art that isn't recycled is almost always an illusion caused by your not being familiar with the things it was remixing. Nobody pulls things out of thin air. Even whacked-out acid trip visions were molded by our cultural experiences and aesthetic. While there are a few people who make large shifts in their artform-- e.g. Jackson Pollock, Jimi Hendrix, and Antoine Carême-- but a) they were still making incremental progress, and b) you'd have a pretty limited set of things to choose from for your entertainment.
PS Edit: Right now AI-generated art is novel, but it has far less potential to meaningfully advance art as time progresses. It will mimic what it sees, but it won't see anything that a creative cultural avant-garde doesn't produce first, and as long as real people are doing it first, there will be eyes that want to see it before an AI algorithm waters it down into some conceptual amalgam of its real form. That probably includes commercial entities who are deliberately trying to make themselves stand out.
1) The output, while impressive on the surface, is bland and recycled. It will drag down the general level in the same manner that CGI has destroyed movies.
2) People don't want to consume AI generated content in the same manner that they generally don't watch Stockfish vs. Stockfish.
3) It is not phobia, it is disgust at humans being dehumanized.
The phobia seems to be on the side of AI corporations, who quickly step in any discussion that questions their business model.
The problem people have with AI is that it is cheapening the things that make us "special". If anything I can draw, paint write, create, and pour my heart and soul into can be acceptably approximated by a "bot" in five seconds or less, then what do I have to offer to the world beyond my "work" output? The things that creatively inspire me have been commoditized in a way where it's exponentially harder for me to generate value doing them.
Artists and musicians have famously struggled for centuries. A technology that raises the bar on an already exceedingly difficult path (making money doing creative things) makes that particular situation much worse.
You're probably onto something, but then it's also nothing new that we attribute value to handmade goods over industrial goods. Because they're backed by storytelling (real or imagined), rare/exclusive, etc.
It's clear that amidst a deluge of AI-generated content, audience urges for authenticity will rise. Attention is in more finite supply than content, has been even before generative AI; only so much will stick out, and it will perhaps be the most authentic or analog content and goods.
The real question is whether AI/AGI can make it past the "authenticity threshold" and xenophobia to where we also accept AI storytellers and brands as eligible.
Perhaps opening the AI content firehose will force everyone to start carefully curating what they consume. This might actually be an improvement, and might be the way out of today’s limbo where crap content is snuck onto our plates half the time.
I think you also discount that handmade items are generally valued for being higher quality and sturdier than mass produced items in many cases. It’s not just this kind of emotional thing.
Exactly this. The vast majority of art is unoriginal and derivative. That doesn’t mean it’s bad art, just that it is not revolutionary.
So what? There are a handful of truly revolutionary artists each generation. Faulting AI for producing merely good and interesting art is missing the point.
I don't know about other people but I don't "fault" the AI anything, nor am I even particularly bothered by AI-generated content per se.
What fills me with dread is the obvious glee over removing human work from sellable products, when there is no viable alternative to working for most people. We've created a world where a lot of jobs can be automated, and that is somehow a bad thing, and it's going to be used to crush people. It's a labor issue not a philosophical one.
Looking for a phobia to describe AI content aversion is an incorrect approach. It yields no explanation other than that “something must be wrong with those people”. Instead, try looking at it from a rational biological standpoint and it makes perfect sense.
We biologically have a desire to live. Part of living is confronting threats to our survival, and hopefully defeating them. Our minds are what provided us with the ability to survive despite there being stronger, more vicious competition out there. Why would we want to surrender our one competitive advantage?
People aren’t stupid. They know that AI will continue to progress (“technology must progress”, says the technologist) and that it threatens their way of life. Truckers know that AIs will automate their jobs. Artists know it will automate theirs. Everyone knows that AI is coming for them, sooner or later. If not in their career, then maybe in their social life, like video games and social media have decimated in-person communication.
Those are things we need in order to survive. Our jobs provide us the money we need to meet our needs, and give some of us meaning in life (no, UBI proponents, receiving a check doesn’t solve all the problems). Our social lives are paramount to our health. What will humans be doing all day when AI has taken all our jobs and we are all talking to chatbots all day which cater to our every proclivity? Maybe that is some folks’ ideal worlds, but certainly not mine.
Given the mixed results we’ve seen with technological innovations in the past, rather than giving a negative connotation to the people who are cautious or concerned about AI, why not listen to them? Rather than having a phobia, maybe they have a valid point.
There are many rational reasons for a person to see these questions differently to you and plenty of explanations of those reasons around. You may disagree with them, but to claim that differing views must spring from phobias or other irrational mental states rather from a different assessment of the evidence is baseless ad-hominem. I would strongly recommend avoiding statements of that form in general as they achieve nothing good.
I could make a similarly disrepectful and unsupported claim about the mental state of people who believe most human creative activity is simply recycling learned ideas, and we could spend some time flinging insults at each other, but why?
Hear me out. In the most basic sense, to believe the mind a box that can output things not based on input is inherently to believe it "irrational" in the truest sense of the word.
It is to believe the mind to be non-functionally pure[1] in the programmatic sense. Output based somehow other than purely on input.
And if that's the case, the question is where does that irrationality come from? A random number generator? Any developer knows there's no such thing as actual random. It's all either list based or based environmental aspects.
I don't see room for an argument to be made that the human mind isn't just mixing ideas/the environment that doesn't rely on some form of magical thinking.
I imagine there'll be a lot more talk of the soul from a lot of techies from now on. Or at the least talk of the human touch from people who were erstwhile trying to get machines to automate everything.
Hand crafted goods have been a thing ever since industrialization of production started. recently, they market it as upmarket boutique to be handcrafted, and i suspect that ai generated content vs hand-crafted content is going to go down the same route.
What I find amusing is not the statement you quoted, but this one:
> The Not By AI badge is created to encourage more humans to produce original content and help users identify human-generated content.
How does this encourage humans to produce more original content? It may help users identify human-generated content - if they care. But perhaps more usefully it helps AI identify human-generated content to avoid training on its own garbage.
I think it's interesting to contemplate the process... when an AI tool "remixes" existing works to make a new work, is it "merely" using statistical processes to do so, or does it "understand" what it's doing?
But perhaps the process doesn't matter as much as the end result.
Maybe another interesting aspect to consider is: humans create new things (even if by remixing and deriving from old things) all the time, because they want to, because they choose to do so.
Thus far, these AI creations have been made at the behest of humans demanding them.
Perhaps that will, that desire, to make something new in the first place will remain a differentiating factor.
That’s basically the thesis of Beaudrillard’s Simulacra and Simulation, that in the postmodern world everything is a signifier, simulation, or remix of something else, nothing is truly original anymore.
It’s probably not completely accurate to say there’s nothing truly original anymore, but also probably true that the rate of discovery of truly novel and original concepts and ideas has slowed to the point it may seem that way. Possibly b/c all the low-hanging fruit as been taken, and only the more difficult discoveries remain.
A lightbulb is clearly a new invention when all you have are oil lamps.
You can retrospectively say we've always had a device that creates light from heat, like this 'new' lightbulb and metaphysically you'd be correct.
But the properties and design of a lightbulb are different to an oil lamp. That's new enough to be called original and Thomas Edison (and whoever else helped him) are the originators of the lightbulb design and they made it real.
An original thought? Probably not, an original object, yes. Very much so.
This is overly reductionist. If you are struggling then your notion of recycled is too broad. But your day humans are shockingly unoriginal, I mean this seems to part of this new fashion to downplay anything done by humans as of it us trivial compared to some imagined alien race Kurzweil singularity thing or something. It’s a bit sad but it is not a very well-founded position.
The fear comes from much deeper. It is the fear of the kernel of reality that doesn't have any form, only function, the profound Lovecraftian fear of a mindless force. Although, some people in the story did worship Cthulhu.
The argument should be about capacity for creation, and to me AI generation just doesn't seem like true creation, but more of a cheap magic trick.
when human made content is "recycled" from past human content, it is not "recycled" using statistical algorithms, it's recycled based on understanding, meaning, aesthetics, emotions, and a whole list of traits that LLMs will never have.
> Whoever has emerged victorious participates to this day in the triumphal procession in which the present rulers step over those who are lying prostrate. According to traditional practice, the spoils are carried along in the procession. They are called cultural treasures, and a historical materialist views them with cautious detachment. For without exception the cultural treasures he surveys have an origin which he cannot contemplate without horror. They owe their existence not only to the efforts of the great minds and talents who have created them, but also to the anonymous toil of their contemporaries. There is no document of civilization which is not at the same time a document of barbarism.
The difference is that AI is using pattern matching while humans use reasoning to come up with new things.
That means AI is not capable of producing meaningful _new_ content like discovering new mathematical theorems, because AI does not understand maths, whereas humans can come up with something meaningful based on _understanding_ of the content they have learned from.
This is why when you ask e.g. ChatGPT about something it has not been trained, it can only come up with garbage, whereas a human would likely be able to provide meaningful answer based on looking at the same training data, if that makes sense.
Language models can generate novel functioning protein structures that adhere to a specified purpose. Structures that didn't exist before nevermind found in the dataset. The idea that there's some special distinction between the reasoning LLMs do and what Humans do is unfounded nonsense.
A distinction you can't test for (this so called "true understanding" ) is not a distinction
Our language, Tiger, our language, hundreds of thousands of available words, frillions of possible legitimate new ideas, so that I can say this sentence and be confident it has never been uttered before in the history of human communication:
"Hold the newsreader's nose squarely, waiter, or friendly milk will countermand my trousers."
These seem pretty creative to me? are they? I'm not a fictional guy so I don't really know?
can you be extraordinarily creative and unusual?
Sure, here are five highly creative and unusual fictional creatures:
Crystalline Leviathan: The Crystalline Leviathan is a massive creature that lives deep in the ocean. Its body is made entirely of iridescent crystals that refract light in all directions, creating a dazzling display. The Crystalline Leviathan feeds on deep-sea creatures and can grow up to hundreds of meters long.
Plasmic Shapeshifter: The Plasmic Shapeshifter is a shape-shifting creature that can manipulate its own plasma to take on different forms. It has no fixed appearance, but usually appears as a mass of writhing, translucent tendrils. The Plasmic Shapeshifter is highly intelligent and can mimic the voices and mannerisms of other creatures.
Quantum Butterfly: The Quantum Butterfly is a tiny, delicate creature that flits through the fabric of space-time. Its wings are made of pure energy, and it can move at incredible speeds. The Quantum Butterfly is believed to be responsible for some of the most unusual quantum phenomena, such as entanglement and superposition.
Cosmic Serpent: The Cosmic Serpent is a serpentine creature that lives in the void of space. Its body is covered in shimmering, rainbow-colored scales that reflect the light of distant stars. The Cosmic Serpent feeds on cosmic radiation and can survive in the most inhospitable environments.
Dream Weaver: The Dream Weaver is a mysterious creature that lives in the realm of dreams. Its body is made of ephemeral, mist-like substance that can change shape at will. The Dream Weaver is said to be able to influence the dreams of mortals, and can even enter their dreams to communicate with them. It is rumored that if you catch a Dream Weaver and release it, it will grant you a wish as a reward for sparing its life.
>> I’d struggle to find any human content that is not recycled from the past.
"A man with a new horse visited the hardware store in Dagwood last week to try and find a new hitching post for his stable."
That simple sentence has enough entropy that I can say, with confidence, that is has never been uttered by anyone in the history of human civilization.
Our universe operates under deterministic laws, meaning that all events are the result of cause and effect. As such, all new phenomena and entities arise from the preexisting conditions and interactions within the universe. In other words, nothing can come from nothing, and everything that emerges is a product of what already exists.
I've mentioned something like this in other comments across HN.
For me, I actually really like that human content is recycled. The discussions around AI, art, and humans always talk about art as a separate product produced by the human. I feel like many pieces of art (not all, for example zombie realism) has a piece of the human inside of it.
An example I used in a comment in this post is Raymond Carver. His short stories are about blue-collar men in the mid-west. Carver was a blue-collar man from the mid-west. I find that interesting, and I liked that he pulled from his life experience to write stories.
I get very excited when I realize that the work I'm engaging with is recycled in some way. Like a song's chorus sharing lines from a separate artist, or a style that seems similar to a different writer I know. I love that. It makes me feel more connected to the creator and makes me like them more because we share similar interests.
An example that comes to mind for me are the manga Hunter x Hunter and Jujutsu Kaisen. The creator of Jujutsu Kaisen loved HxH and it 100% shows. The crazy powers, the complicated fights, the walls of texts explaining what happened in a fight, etc. All of those come from HxH and I love the creator was inspired by it. Sometimes reading Jujutus Kaisen makes me feel like I'm bonding with the creator over our mutual love of HxH.
With AI created work, I feel like we're missing the human touch. And as I pointed out in another comment here - I don't think it's hard to bring it back. Show me the prompts and the chat log. Why did you choose those prompts? Why did you ask the AI to write in X style? How does that X style make you feel?
On the other hand, maybe the AI prevents some of the human touch from coming through. I imagine much of the recycling that comes from humans is unintentional. The song you wrote on guitar has that riff not because you're copying a band, but because you've listened to so much 90s indie rock that you just make what you love - without realizing it.
Maybe in the future this changes. I'd love to see someone spend some time with an AI and mold it to such a way that what it produces can emulate the user's love and interests. Don't forget to show and share the chat log!
[EDIT]: To add onto this, I've actually done the above. I've played some text adventure games in the past, and I got ChatGPT to play with me. I told it that I had stat points (Health Points, Magic Points), that I had two types of attacks, and that there are three types of monsters. That experience invigorated me to write paragraphs on world building - just so I can feed it into ChatGPT and live in that world.
I seem some instances that are similar like this - but people just end up not sharing the prompts they feed into ChatGPT. I'd love to see those prompts. I've love to see what someone did to get ChatGPT to act a certain way.
A quote I heard recently that really resonated with me:
"Soon, asking a writer if they use AI will be like asking a photographer if they use Photoshop" – e.g., it's a foregone conclusion, and the best artists will generally adapt to using the best tools available
Exactly, it's a tool. The skill floor, as in the minimum amount of skill to produce something passable, has been lowered -- dramatically lowered -- but the skill ceiling is now higher than ever as a result.
It's similar to music. DAWs and samples didn't kill off music; instead, it made it easier than ever for a teenager with a computer and a passing interest in music to create a song and share it with a world. As a consequence, though, the standards for mixing and mastering have gone up massively; people don't really tolerate bedroom recordings with $10 mics any more. I imagine most amateur musicians in the 90s didn't know what a compressor actually did (I certainly didn't).
Seeing the results of talented artists who are experimenting with AI[0] makes you realize that there's still going to be a massive gulf between skilled artists using SD etc as a tool, versus those who think they can be artists just by putting keywords into an image generation AI and calling it a day.
> the skill ceiling is now higher than ever as a result
the fear from the current professionals is that the new ai raised floor is good enough to be usable commercially, and thus, cut a chunk of economic value from the professionals.
There is no fear that AI stops people with the intrinsic interest in creation to stop creating - their ceiling and productivity would sky-rocket as a result in fact. And it would be _these_ productions that wow an audience.
> minimum amount of skill to produce something passable
Look at the history of woodworking for inspiration.
It used to take human sweat to make flat straight surfaces. Something like a walmart flatpack bookshelf would have been VERY expensive to make 1000 years ago. Industrial tech made that cheap and ... now its seen as tacky and out of style and only for poors.
The result culturally this century is an avoidance of "plastic wood" finish, faux finishes and faux surface prep that look old and worn and hand scuffed, and a strange hipster fetish for "live edge" raw bark on finished product. Sure, in 1875 one might have predicted based on mass production trends that furniture in 2020s would be all right angles, smooth as glass mirror, photographic "ideal" woodgrain instead of real woodgrain, plastic-y lifetime thick film finish. But thats only for poor people who shop at walmart, nobody with money buys that stuff.
I suspect what AI can cheaply produce will rapidly culturally be considered lower class and trashy. Oh, sure, completely AI generated movies look very nice and sound very nice and are ever so trendy and well written, but special effects and yesterdays memes on todays big screen generated entirely by computer algorithm is only for poors. Now, us rich cognitive elites only attend live theater plays. Aspirational middle class types watch recordings of theater plays (admittedly maybe some AI generated). You wouldn't show off your 'wealth' and 'class' by taking a date to an AI generated movie, that would be insulting, you might take her to a live theater play... I'm sure there will be some AI incursion, maybe the lights will be run by AI or AI painted backdrops or some actors will lipsync their lines to AI, or roughly every 5 years we have to tediously suffer thru a new generation of rewritten modernized classics and it'll be worse in the future with AI... but in general human will be the status symbol because it'll be expensive.
I suspect being able to ask an AI to generate non-copyrighted commercial quality music will mean massive noise pollution (much like every room required 15 digital clocks in the 80s and every room required 15 super bright blue power LEDs in the 00s) followed by the only people making money in music will be live humans playing physical instruments.
Poor people try to get by and don't spend money and when they do it'll be on infinitely cheap AI commodities. Rich people spend money on unique stuff, not mass produced AI shovelware. Aspirational people spend money trying to look rich so they will spend all their money on non-AI stuff.
It is a tool only when used as a tool, in the sense you're talking about. For example, I can write a sentence, and being a non-native English speaker, I can tell there's something wrong with it but I just can't place my finger.
So I ask the AI to rephrase it for me. Now I can pick and choose an option from those the AI offered, or I can just keep my version if it turns out it's good enough. I feel this is an acceptable use, and you can still maintain authorship, just like book authors maintain authorship after an editor has overhauled their writing.
Your DAW example would work if DAWs could generate samples, beats, and whole songs by the click of a button. But are you truly the author, then?
i agree with the tool analogy. However there's something different between using a tool, and outsourcing the entire content production by only specifying the end result.
Whenever a customer ask me to develop an app, i don't consider that he did the job. I did it.
> As a consequence, though, the standards for mixing and mastering have gone up massively; people don't really tolerate bedroom recordings with $10 mics any more.
I don’t find this holds true for hip hop, the most streamed genre, whatsoever. There are countless examples of people making it big recording on a cheap mic in their mom’s bed room. One example is Chief Keef. A much more prominent example is Kanye who had terrible mixing on The Life of Pablo to the point where he released patches[0] for the album. He also recorded parts of Jesus is King on an iPhone[1]. To further the point, bootleg recordings and demo tapes of unreleased songs in artists’ back catalog continue to be popular with devoted fans. Average people like good music, even if the quality of the mixing and mastering is not stellar.
Even The Beatles released songs with minimal takes from a live rooftop performance on Let It Be; hardly an ideal recording set up. Although they surely had better mixing.
Love the connection to home studios. Everybody was able to make more music much more easily - but it also inflated the music industry with a lot of mediocrity. So some will find ways to use AI for greatness, but most won’t.
The skill ceiling isn't higher. It's just in a different building next door to the current one. The same thing happened with the film to digital transition. The skill range didn't change, the set of skills itself changed.
The problem with analogies is that you can pick one to say whatever you want. The analogy isn't necessarily true just because it feels right.
Asking a photographer if they use Photoshop creates a framing where the artist still did went out and took a picture to create the work and then Photoshop only modifiers their original creation.
But you could just as easily say "Soon, asking a writer if they use AI will be like asking a photographer if they have a camera". That sounds ludicrous, but that is exactly what generative AI offers: the ability to create content essentially ex nihilo.
No, using AI to write is basically having it do everything for you. It's not a tool it's a replacement. In the years to come several hundreds of thousands of jobs will begin to disappear from copywriters to fiction and non fiction writers. Replaced by roles such as marketers to historians. It's not photoshop for photographers is just going to push the vast majority of people wanting to pursue these fields out of the market.
I think nearly everything you said is likely wrong.
AI doesn’t “do everything for you” any more than word processors, music sequencers, or CAD does. AI allows people to operate at higher levels of abstraction, is all. Yes, fewer people will type repetitive copy in to word processors. But that’s fine.
You are mistaking activity for productivity. Few people go into writing because they enjoy typing. AI offers leverage, which is the most amazing thing for anyone interested in producing work.
Ask any professional writer: revisions are a chore. Authors often say a novel is 10% writing, 90% rewriting, and they don’t enjoy the rewriting part.
So, IMO, contrary to your doomer take, I think we will see more people producing better work because they can focus on the parts they love and not do the grind that was only ever a necessary evil.
(The exception being those who love the grind and not the product)
Using it to write vs. using it to help you are two very different things.
For example: sometimes I will pass a paragraph through an LLM and ask it to return it in a more "active voice". Then I _manually_ edit my original paragraph, if I wish, to make it seem more suitable for my current goals.
> "Soon, asking a writer if they use AI will be like asking a photographer if they use Photoshop" – e.g., it's a foregone conclusion, and the best artists will generally adapt to using the best tools available
The problem is that it automates the best parts and transforms the user into a curator/manager.
Some people want that, but other enjoy the creative part more.
To bring it back to photography, that's the problem with digital, you blast through hundreds of photos and spend most of your time selecting and editing at the computer.
With analog, and especially wet plate or direct positive paper, it takes a while to compose your picture and you only have one chance to take it and develop it. It's very easy to mess anything which is what makes the process more meaningful. And you're left with a unique copy, not an artificially limited single copy.
Yep, exactly - I think people generally regard artistic work as getting to a successful end result. When actually the process of creating something, and potentially wrecking something at any moment, is usually the most fun / exciting and fulfilling part. That magical process is lost with AI generation.
The "writers" who can benefit from AI are not artists. They might be bloggers or journalists or researchers. But there is no way that a generative AI can produce, say, your memoir for you. How could it? You have to say what happened. Your life experience can't be generated. Ditto for any sort of novel above the level of the most basic imitative genre stuff. I'm certain AI could spit out a perfectly passable airport paperback romance, for instance—but how could it possibly write Infinite Jest?
The key isn't that the "AI" writes the whole darn thing. It's a "get-out-of-writers-block-free" pass. I've successfully used chatGPT for exactly this process. I'm writing something — unique, by me! — and I want to link a few thoughts together in a succinct way. I outline what I want and ask the AI to generate some plausible prose.
I almost never use the prose word-for-word, but goodness is it helpful.
I’m not so sure an AI couldn’t, in theory at least produce a memoir if you fed it your diaries, emails, social media chats and histories, photos and videos from throughout your life, and so on.
But then the AI is the writer and you're just an editor or curator. So perhaps don't call yourself a writer if the AI produced a significant amount of the content. Same goes for Stable Diffusion/Midjourney prompters who shouldn't really call themselves artists. (Things would of course change if they do significant postprocessing of the output, though I'd still think this is much easier than coming up with something novel on the spot.)
Of course, it's not my place to say who should or shouldn't call themselves a writer, but I'll simply personally respect someone more if their stories aren't ghostwritten by the AI.
I feel a better comparison is like asking a painter if they use a camera. At some point we just say “you’re not a painter anymore, you’re a photographer.”
Feeling pretty stupid for all the time I invested in pinhole photography and darkrooms, 20ish years after photoshop was released, about now. Guess the best artist all have $5000 to spare for a MBP and monthly creative cloud subscriptions too…
In a test of verbal reasoning, photographer is to Photoshop as writer is to ...?
I don't think "AI" is the way most people would complete that sentence. Perhaps "Word"? Or "LibreOffice" if "Photoshop" were replaced with "Gimp"? Personally I use Emacs or Vim. You could incorporate AI into any of those tools, but how exactly? And would it be a core part of the functionality? And would it be something that the best artists make much use of?
If you used AI to make the spelling/grammar checker more reliable, probably most people would use that (assuming no privacy problems), but if there's an AI-driven autocomplete for sentences probably a lot of people, including the best artists, would turn it off, just like I turn off the autocorrect on a word processor today.
If an AI can complete the sentence, then perhaps the sentence isn't worth completing, at least if we assume that the reader is as clever as the writer and has similarly sophisticated tools. Perhaps the AI-driven tool should instead put some kind of wavy line under the second half of the sentence to indicate that it's boring and obvious and doesn't need to be there.
Leaving out “soon”, there’s truth to that, but the immediacy really depends on how this generation of AI develops and where it encounters its limits. It’s not there yet and we actually don’t know how far these current advancements will take us.
It’s tremendously useful technology for many domains already and you can see the stepwise refinements that will permeate many parts of our lives. Big money corporations are productizing those elements already.
But to be as fair to the pessimists as the optimists, its actually still a very big leap from Modjourney and GPT-4 to something that becomes the next camera or typewriter in terms of ubiquity. Because we saw a huge leap recently, we feel close and excited — and we might prove to be in hindsight — but we also might see that there are some hard conceptual limits that we won’t see anyone break through for another fifty or hundred years.
I don't think it's like any tool that has come before in that it can take much of the decision-making process away from the artist - it is much more like hiring someone to paint a picture than using Photoshop.
For image-making, there is a decision in the prompt and selecting images, but that is very different to making a decision about each color and brushstroke, and working to finish a painting. It's orders of magnitude more difficult and why great masters are celebrated. Creating stuff with AI will suit certain people, I definitely don't think necessarily the 'best' will automatically use it. It does seem to take away a lot of the fun of making images and truly original work will always push quite far outside the training set.
Exactly, but the implication is different for me. I dislike all the filters and think this is the weirdest thing ever, to blur oneself on photos. People, who heavily use blurring to mask their wrinkles, produce - in my opinion - photos that look like grimaces. I find the pictures as well as the people using filters somewhat scary, because what happens if you meet them face to face? Use something like Google Glasses and real time filtering?
For literature, it could be interesting, how authors use new tools, where and in what sense. Maybe have more conclusive plots? Less inconsistencies? Have AI imitate dead poets' style?
We will value the classics more I guess, since they were done the old fashioned way.
There's shades to art of course. Not all photography is airbrushed digital stuff, and the mild stuff most people probably do, like changing the exposure curves around in photoshop or lightroom is basically akin to what photographers were doing when exposing prints from their negatives for the past 150 years, only with less time and no chemicals. Likewise, some people might be happy with AI generated fodder to read, others might want other things.
Another argument I keep hearing (most recently from pg), is that we'll always need non-AI training data. That, too, doesn't follow. Training new models on synthetic data does not mean we get stuck in a particular mode or style. We'll continue moving, improving, and trying wildly new things. Bootstrapping with synthetic data doesn't block evolution - it enables faster evolution, even. (I'm using synthetic data to train new models to great effect.)
People are angry that we've lowered the opportunity cost barriers and so they're expressing their frustration.
It's a good thing that life's choices no longer fence us in as much. Everyone should get a chance to learn how to express themselves through art with the new regime of tools. Despite changing economics, there will still be a top 1% that do better than the rest of us.
People aren't angry/worried because they don't have a competitive advantage any more--people are angry/worried because they sense (I think correctly!) that AI will eliminate the part of their work that they find enjoyable.
Artists, by and large, don't do art because they enjoy having art--they do art because they like /the process/ of producing art. If that process can be done faster and better by AI, then yeah, sure, they /might/ be able to still do art for a living (some artists will be able to leverage their experience to maintain an advantage; other, less flexible ones will lose work)--but the work they do will likely not be commensurate to the work they were doing before, and will likely be less enjoyable to them.
The thing that worries people about AI is that it'll make all creatives into middle-managers.
I think the same. Many artists hate because they feel threatened. I think the opposite: creating art (e.g. Drawing) was only for the ones who had drawing skills. Now, it's being democratized and everyone, regardless of being talented in drawing or not, can freely express their feelings and creativity.
Training ESRGAN, I quickly learned that AI sniffs artifacts humans can't see. And I got particularly funky results training a model on selected previous generation upscales.
Hence I disagree. Even of the training data curators are perfect, there is a risk of "model inbreeding."
And the curators are not perfect. In fact, they seem to prioritize (by necessity) volume and speed over quality and curation when training these LLMs and diffusion models.
I’m not sure what the last line says. Doesn’t the top 99% do better than the rest? I think you are making the common HN argument that it is “ableist” to think doing art should require any kind of skill or something. I don’t really agree that the AI is so good but let’s say it is, if that’s the case why do you think anyone will afford a computer to use the AI or even a house in which to type or say all these magic prompts?
I get the concerns with AI, but this kind of thing has always looked odd to me.
Like imagine a label on a thing that says "Made without CNC machinery". So instead of finishing the thing on a CNC mill, they instead stuck it on a Bridgeport manual mill, and finished by hand. Or somebody finished the cast with a file.
Okay, and so? In the end, a hammer is a hammer. If it hammers well, what difference does it make how it got that precise shape? It's not like some inherent goodness is being imparted by a hand file.
Now I get some methods have flaws to them, and some form of associated harm. The problem I see with blaming specific tools is that it's simplifying the problem too much. Eg, if the problem is taking jobs, then picking up one particular tool to blame for that allows manufacturers to use a different tool and cause the same sort of issue. If the problem is say, pollution, then it's not at all a given that the replacement method will be ecologically friendly.
IMO the better thing to do is to target the underlying problem. If say, your issue is ecology, then you want to certify that the manufacture is as environmentally friendly as it can be, not that the thing isn't made from plastic, or there exists the chance that the non-plastic thing will even be worse for the environment.
I can see a difference for creative works. I'd be more interested to know that I'm looking at something an artist did intentionally than something sampled from a manifold of similar works. Just like I'd rather (all things being equal) have a real drawing or painting than a print. You can make analogies in other art forms too.
And if someone is going to send me a sales pitch or email that GPT wrote, I'd rather they don't insult me and just send me the prompt.
I think tfa is a gimmick, but i see value in knowing whether I'm relating to a human brain or to a statistical model
External help is not at all unusual in artwork. Eg, many artists just look for reference pictures online when they want to depict a tricky pose. Apparently the infamous Captain America picture happened because of a bad usage of a reference.
I think AI will go down that road. Yeah, lots of people will mess around with prompts, but artists able to retouch the output, and to mix and match stuff will get much better results.
You could argue that the hammer from the previous example is a creative work.
A hammer, a pair of shoes, a leather sofa, etc. They all have an element of craftsmanship and it seems like people who do that work usually take pride in it from an artistic and quality standpoint.
> I'd rather they don't insult me and just send me the prompt.
and the prompt makes no sense to you, because you are not able to interpret it the way you would interpret the generated output of said prompt. The information isn't in the prompt, and never was.
> In the end, a hammer is a hammer. If it hammers well, what difference does it make how it got that precise shape?
"Hand made" has been a selling point since things were first made by things other than hands. Example: "The factory, known as the Ateller, [...] it is the place where our craftspeople assemble each BUGATTI by hand."
That's because "handmade" was a proxy for "high quality", in situations where machines lack the skill to meet tolerances and fine details and customization that humans can.
I never got the appeal of that honestly, less for something like a BUGATTI. Not like an artisan hammered the panels into shape by hand, or somebody manually bored those cylinders.
In fact it's probably something completely incidental to the entire thing -- they're not assembled by hand because it's better, but because not enough of the cars are made to make automation make sense. It's just a pragmatic business decision, which then some marketer figured out how to spin.
> Like imagine a label on a thing that says "Made without CNC machinery". So instead of finishing the thing on a CNC mill, they instead stuck it on a Bridgeport manual mill, and finished by hand. Or somebody finished the cast with a file.
This is basically the selling point of the entire luxury watches industry.
I don't think there's a valid analogy in physical manufacturing processes like machining. Certainly not this. Few people are upset at the idea of using AI to help draft emails that you then edit by hand, or to help write boilerplate code.
a lot of people in this thread seem to have no understanding that some people enjoy the act of writing or of painting by hand. Every framing in here to the tune of “everyone will use AI” is nakedly utilitarian. Sometimes people pain pictures or write not just because they enjoy the act. Sometimes people paint pictures or write because they want to communicate; not everyone will feel like they’re communicating from themselves when the words or pictures come from a machine. Generating content from a dataset is a way of exploring the dataset; generating content from within is a way of exploring yourself. They are simply different.
and fwiw, a lot of the assumptions in here are akin to saying at the dawn of photography that nobody would ever paint any more. Photography of course replaced certain entire categories of painting, but didn’t erase painting from the face of the earth altogether. Of course there are far more photographs than there are paintings, but volume alone is not the totality of meaning.
Generated content is strictly culturally regressive anyway. After a hundred years of ChatGPT will people still be writing prompts with “in the style of [person who produced all of their work before the year 2000]”? That would be a sad and boring future.
When photography replaced many of the uses of painting, some painting jobs were lost, but photography ones were gained. Now, many creative jobs will be done by computers, leaving the world less enjoyable for people who enjoy creating.
Sure, some people will continue to be creative, but look at what happened to art after photography: we got modern art, where people just piss on a canvas and sell it for millions based on the name of the artist alone, not the value of the art.
AI is progress in the same way nukes are progress: you have to get it or you'll be left in the dust. But is humanity better for it?
I disagree. It's both. If I'm playing the piano alone in my room and nobody else listens to it, I'm still having the aesthetic experience called "art". Many people make art just for themselves without the intent of showing it to anybody else, and it's not somehow less artistic than something that other people see. Art is an experience somebody has, including the artist.
You can observe this trend w/ AIfluencers already:
They create short guides on how to leverage AI tools like chatGPT to generate income/reach and all of their typical bullet points equal generation of low-quality noise:
Examples: let chatGPT..
1. write blog posts
2. generate scripts for youtube videos
3. create short stories so you can sell them as a book
Painful to see. I would like to think nobody in his right mind is willing to consume these delightful pieces of work. Dead internet theory on the next level.
That's only because the Netflix bean counters end up working like an AI in their ends. AI trains on known things and outputs something from that finite set. Netflix bean counters similarly bet on known things or derivative things and the output reflects that. The difference is, scripts for the unknown things still occasionally get produced in this later situation, which is exponentially more than can be said if 100% of our content came from AI.
If you just go into the Midjourney Discord you'll see people with absolutely no mechanical artistic talent be create absolutely stunning novel art. The creativity people have there is crazy and the AI is letting them go from head to canvas in a few seconds.
When I see AI art from those communities, it all looks the same to me.
People tend to overestimate their talent, and get overly attached to their own ideas. So when a tool like midjourney/stable diffusion generates beautiful artwork based on a low effort prompt from the user, it's comfy to think that they had a big part in it.
The reality is that almost everything those tools make is equally gorgeous/amazing regardless of who uses it, so they're effectively interchangeable. As a tool for personal expression, it has a lot of value because of the impact it can have on the individual using it, but as art it's pretty worthless. A generated AI image could potentially have some cultural impact or value, but not on the merits of "it looks pretty", since they all look like that.
We're already past the point of diminishing returns on "human creativity".
And I would argue that the current (mostly recent productions) Netflix catalog is indeed repetitive and stagnant. Originality in tv production is currently in a race to the bottom.
Ironically, the badge sounds robotic "written by human". How about "written by a human" to make it grammatically correct? And while we are at it, why are the letters AI the biggest thing on the badge? Seems backwards. I suggest flipping the emphasis so "written by a human" is bold and the "not by AI" part is smaller to indicate its inferiority.
So cringy. Should we also add badges for doing it without autocomplete, syntax highlighting. Hell, why even bother with text, if you didn't develop it by punching cards then you're not a real developer.
I think you're being unreasonable. Your examples are closer to spellcheck and punctuation correction. Even they have subtle societal considerations such as Americanising English. A much more appropriate comparison would be Copilot which is being discussed nowadays.
It feels like a good time to read this again about making music properly :)
> I thought using loops was cheating, so I programmed my own using samples. I then thought using samples was cheating, so I recorded real drums. I then thought that programming it was cheating, so I learned to play drums for real. I then thought using bought drums was cheating, so I learned to make my own. I then thought using premade skins was cheating, so I killed a goat and skinned it. I then thought that that was cheating too, so I grew my own goat from a baby goat. I also think that is cheating, but I’m not sure where to go from here. I haven’t made any music lately, what with the goat farming and all.
Can confirm as a musician this is a very natural progression. Amazing what people out there can do when they are willing to bend some of the rules though. ;)
Readit News
To be honest, I’d struggle to find any human content that is not recycled from the past. I guess we are still better than AI at remixing sufficiently novel combinations of concepts but I think much of this AI content aversion comes from some kind of phobia, or an unwillingness to admit humans are shockingly unoriginal.
In other words, if there is truly no such thing as an "original idea", then how did the ideas that we are pulling from, deriving from and combining come into existence?
If all we are saying is that existing ideas inspire new ones, or that most human generated content is derivative, then I completely agree with you. I don't see how that proposition could be controversial at all.
But it seems to me that some people, at some points in time, somewhere have and will continue to contribute something original at least on occasion. Even if the "original" idea is 1% of the "intellectual product" and 99% is reusing existing concepts. To insist otherwise is to insist that we hit peak human innovation somewhere along the line and there's nowhere left to go.
Of course there are original ideas. "C is not an original idea, because it's just mixing A and B..." ok so there are only two possbilities:
1. Someone else did mixing A and B before. Okay then we can recursively find the first person who mixed A and B.
2. No one else did mixing A and B before. The "Mixing A and B" is a new idea.
For some incomprehensible reasons, people seem to accept "mixing A and B is not a new idea because A and B already exist." Like... why? Since the four basic nucleobase existed, there haven't been any new DNA creatures?
The real reason that it feels like there isn't new idea is simple: the "mixing" process happens gradually. Even if you come up with a really good "X + Z" idea, people (read: market) might not accept it because what they're familiar with is "X + Y".
So you put a bit of Z to make "X + 0.9Y + 0.1Z", and another person who is as smart as you makes "X + 0.8Y + 0.2Z"... then when "X + Z" is officially a thing, people outside think you smart-ass guys were all just copying & pasting each other.
And the obvious answer of course is that recycling / mixing can be innovative and creative. The dichotomy only exists in our heads.
I believe this is because of how our culture choose to reward intelectual output. Your output needs to appear sufficiently original to be worthy of reward and protection.
For example a musician who creates a new song is not rewarded, in fact punished for naming all the influences they had coming in to said new song. (both morally, by people who would think less of them, and by lawsuits asking for a share of their profit.)
But I think the way you have put it here is more clear than anything I've been able to manage. I think I put it in a more extreme form, which is to say that the earth had no life on it for ~3 billion years, and still no humans until ~100k years ago. At some point the first music was made. And if it could be original then, whatever it was that made that possible, should presumably make it possible now, too.
If you listen to the stories of how things like major inventions came into being, it's almost always some domain expert visited some domain in which they were not an expert and inspiration struck on how to combine the domains.
Otherwise, the rest of invention is either human imitations or improvements to things found in nature or not inventions at all but discoveries stumbled upon by accident/experimentation.
Nothing is just willed into existence by pure "thought". Every thought you've had is a product of the things you've been surrounded by.
But when you start to scrutinize everything they did, there are many clear examples of things and people that did those things first and directly influenced them. However, they may have been the first to do it in their specific flavor, which is undoubtedly original.
The most original thing I can think of that The Beatles did was add sound to the runoff track at the end of Sgt. Pepper’s Lonely Hearts Club Band, so that it keeps playing the sound infinitely until the needle is removed on the turntable. I’m sure someone with more insight can point to another musician doing that first, but at The Beatles’ scale, we collectively come to believe they were the first to do it.
Somewhere around 2016, when the golden Age of Internet-Content ended, as the last undiscovered part was added to the mix...
But jokes aside, does innovation really need to be new? Or would it still innovative if you don't know it when you create something you for you? Take for example all the retro-waves which regularly come back, where people discover something for them completely new, and make up some for them completely new things, which the generations for them already did long ago.
> In other words, if there is truly no such thing as an "original idea"
Does Original mean 100% new? And would it demand that all parts are new, or would it still original if we just arrange old parts in a new way?
There is a huge amount of information flowing around us in realtime, and linking some thought/thing to something else, which then might have implications (subsequent discoveries) is statistics. We do have people with a better wetware so they have increased %chance do recognize something in front of them as well as linking it in a "novel way", but this is not really neccessary, it only increases %chances.
Even pretty radical things can be explained this exact way, up to having some sort of brain "damage" (or drugs like LSD) that changes mental pathways and have a %chance to be actually right and lead to discoveries, but also the %chance here is very low. (not every trip is a breakthrough in art/science, right?)... a bit like iE people that can smell sounds or link some natural phenomenon with an emotional situation between some people and write about it.
> peak human innovation
that might simply a nonsense question if you follow my previous argument. there simply is no real "innovation" - only "discoveries" of stuff. and we meatbags with very limitied/unreliable wetware at some point can't "progress" any more, but non-biologically flawed systems might overcome our limitations and do just that for us.
with our naked eyes, we cannot see things like infrared light, but it exists and some tools helped us to understand everything around it somewhat. now we're building more advanced tooling to get through the next plateaus - just like we have to build very sophisticated tooling to watch further into space or more closely into fractions of atoms, which in turn lead to more discoveries, and ultimately "innovation" we can feel in our lives.
the only thing I will 100% agree to is that a real AGI will be the _last_ discovery/innovation humanity will ever make - and that is a good thing - it means we finally overcome our biological limits somewhat.
Nothin' you can sing that can't be sung
Nothin' you can say, but you can learn how to play the game
It's easy
Nothin' you can make that can't be made
No one you can save that can't be saved
Nothin' you can do, but you can learn how to be you in time
It's easy
All you need is love
There will be a big leap forward when we get to teaching these things from video streams so they can get the concept of 3D properly.
Read How to Ride a Bicycle. Human creativity is just a lot of work, often connecting novel ideas together while doing so.
Your question contains the answer. Remixing begets innovation / creativity begets remixing.
Its only words and concepts and we keep inventing new ones constantly. We also imbue new meaning to words and concepts over time.
By observing nature, and then iterating on that over thousands of years of culture. Of course the question is whether and to what degree the process of iteration and transformation matters.
How would you define an "original idea?" An idea with no origin or source, that spontaneously manifests from the aether? That isn't possible, everything must be extrapolated from something prior.
Or did it ever stop ?
Art that isn't recycled is almost always an illusion caused by your not being familiar with the things it was remixing. Nobody pulls things out of thin air. Even whacked-out acid trip visions were molded by our cultural experiences and aesthetic. While there are a few people who make large shifts in their artform-- e.g. Jackson Pollock, Jimi Hendrix, and Antoine Carême-- but a) they were still making incremental progress, and b) you'd have a pretty limited set of things to choose from for your entertainment.
PS Edit: Right now AI-generated art is novel, but it has far less potential to meaningfully advance art as time progresses. It will mimic what it sees, but it won't see anything that a creative cultural avant-garde doesn't produce first, and as long as real people are doing it first, there will be eyes that want to see it before an AI algorithm waters it down into some conceptual amalgam of its real form. That probably includes commercial entities who are deliberately trying to make themselves stand out.
1) The output, while impressive on the surface, is bland and recycled. It will drag down the general level in the same manner that CGI has destroyed movies.
2) People don't want to consume AI generated content in the same manner that they generally don't watch Stockfish vs. Stockfish.
3) It is not phobia, it is disgust at humans being dehumanized.
The phobia seems to be on the side of AI corporations, who quickly step in any discussion that questions their business model.
The problem people have with AI is that it is cheapening the things that make us "special". If anything I can draw, paint write, create, and pour my heart and soul into can be acceptably approximated by a "bot" in five seconds or less, then what do I have to offer to the world beyond my "work" output? The things that creatively inspire me have been commoditized in a way where it's exponentially harder for me to generate value doing them.
Artists and musicians have famously struggled for centuries. A technology that raises the bar on an already exceedingly difficult path (making money doing creative things) makes that particular situation much worse.
It's clear that amidst a deluge of AI-generated content, audience urges for authenticity will rise. Attention is in more finite supply than content, has been even before generative AI; only so much will stick out, and it will perhaps be the most authentic or analog content and goods.
The real question is whether AI/AGI can make it past the "authenticity threshold" and xenophobia to where we also accept AI storytellers and brands as eligible.
So what? There are a handful of truly revolutionary artists each generation. Faulting AI for producing merely good and interesting art is missing the point.
What fills me with dread is the obvious glee over removing human work from sellable products, when there is no viable alternative to working for most people. We've created a world where a lot of jobs can be automated, and that is somehow a bad thing, and it's going to be used to crush people. It's a labor issue not a philosophical one.
We biologically have a desire to live. Part of living is confronting threats to our survival, and hopefully defeating them. Our minds are what provided us with the ability to survive despite there being stronger, more vicious competition out there. Why would we want to surrender our one competitive advantage?
People aren’t stupid. They know that AI will continue to progress (“technology must progress”, says the technologist) and that it threatens their way of life. Truckers know that AIs will automate their jobs. Artists know it will automate theirs. Everyone knows that AI is coming for them, sooner or later. If not in their career, then maybe in their social life, like video games and social media have decimated in-person communication.
Those are things we need in order to survive. Our jobs provide us the money we need to meet our needs, and give some of us meaning in life (no, UBI proponents, receiving a check doesn’t solve all the problems). Our social lives are paramount to our health. What will humans be doing all day when AI has taken all our jobs and we are all talking to chatbots all day which cater to our every proclivity? Maybe that is some folks’ ideal worlds, but certainly not mine.
Given the mixed results we’ve seen with technological innovations in the past, rather than giving a negative connotation to the people who are cautious or concerned about AI, why not listen to them? Rather than having a phobia, maybe they have a valid point.
I could make a similarly disrepectful and unsupported claim about the mental state of people who believe most human creative activity is simply recycling learned ideas, and we could spend some time flinging insults at each other, but why?
It is to believe the mind to be non-functionally pure[1] in the programmatic sense. Output based somehow other than purely on input.
And if that's the case, the question is where does that irrationality come from? A random number generator? Any developer knows there's no such thing as actual random. It's all either list based or based environmental aspects.
I don't see room for an argument to be made that the human mind isn't just mixing ideas/the environment that doesn't rely on some form of magical thinking.
1. https://en.wikipedia.org/wiki/Pure_function
I like it.
Deleted Comment
> The Not By AI badge is created to encourage more humans to produce original content and help users identify human-generated content.
How does this encourage humans to produce more original content? It may help users identify human-generated content - if they care. But perhaps more usefully it helps AI identify human-generated content to avoid training on its own garbage.
The word "recycled" attempts to carry a lot of weight here, and not successfully.
In 1905 Einstein published his famous four papers that could not have existed without recent work done by Planck, Michelson, Morley and Maxwell.
It would be ridiculous to describe those papers as recycling.
A small culture war that was smouldering long before the appearance of generative models.
But perhaps the process doesn't matter as much as the end result.
Maybe another interesting aspect to consider is: humans create new things (even if by remixing and deriving from old things) all the time, because they want to, because they choose to do so.
Thus far, these AI creations have been made at the behest of humans demanding them.
Perhaps that will, that desire, to make something new in the first place will remain a differentiating factor.
It’s probably not completely accurate to say there’s nothing truly original anymore, but also probably true that the rate of discovery of truly novel and original concepts and ideas has slowed to the point it may seem that way. Possibly b/c all the low-hanging fruit as been taken, and only the more difficult discoveries remain.
You can retrospectively say we've always had a device that creates light from heat, like this 'new' lightbulb and metaphysically you'd be correct.
But the properties and design of a lightbulb are different to an oil lamp. That's new enough to be called original and Thomas Edison (and whoever else helped him) are the originators of the lightbulb design and they made it real.
An original thought? Probably not, an original object, yes. Very much so.
The argument should be about capacity for creation, and to me AI generation just doesn't seem like true creation, but more of a cheap magic trick.
https://en.wikipedia.org/wiki/Venus_figurine?wprov=sfla1
That means AI is not capable of producing meaningful _new_ content like discovering new mathematical theorems, because AI does not understand maths, whereas humans can come up with something meaningful based on _understanding_ of the content they have learned from.
This is why when you ask e.g. ChatGPT about something it has not been trained, it can only come up with garbage, whereas a human would likely be able to provide meaningful answer based on looking at the same training data, if that makes sense.
Language models can generate novel functioning protein structures that adhere to a specified purpose. Structures that didn't exist before nevermind found in the dataset. The idea that there's some special distinction between the reasoning LLMs do and what Humans do is unfounded nonsense.
A distinction you can't test for (this so called "true understanding" ) is not a distinction
"Hold the newsreader's nose squarely, waiter, or friendly milk will countermand my trousers."
A Bit of Fry & Laurie Concerning Language: https://www.youtube.com/watch?v=3MWpHQQ-wQg
make up a list of fictious creatures and describe them. make sure the names aren't reused.
can you be extraordinarily creative and unusual?
Sure, here are five highly creative and unusual fictional creatures:
Crystalline Leviathan: The Crystalline Leviathan is a massive creature that lives deep in the ocean. Its body is made entirely of iridescent crystals that refract light in all directions, creating a dazzling display. The Crystalline Leviathan feeds on deep-sea creatures and can grow up to hundreds of meters long.
Plasmic Shapeshifter: The Plasmic Shapeshifter is a shape-shifting creature that can manipulate its own plasma to take on different forms. It has no fixed appearance, but usually appears as a mass of writhing, translucent tendrils. The Plasmic Shapeshifter is highly intelligent and can mimic the voices and mannerisms of other creatures.
Quantum Butterfly: The Quantum Butterfly is a tiny, delicate creature that flits through the fabric of space-time. Its wings are made of pure energy, and it can move at incredible speeds. The Quantum Butterfly is believed to be responsible for some of the most unusual quantum phenomena, such as entanglement and superposition.
Cosmic Serpent: The Cosmic Serpent is a serpentine creature that lives in the void of space. Its body is covered in shimmering, rainbow-colored scales that reflect the light of distant stars. The Cosmic Serpent feeds on cosmic radiation and can survive in the most inhospitable environments.
Dream Weaver: The Dream Weaver is a mysterious creature that lives in the realm of dreams. Its body is made of ephemeral, mist-like substance that can change shape at will. The Dream Weaver is said to be able to influence the dreams of mortals, and can even enter their dreams to communicate with them. It is rumored that if you catch a Dream Weaver and release it, it will grant you a wish as a reward for sparing its life.
"A man with a new horse visited the hardware store in Dagwood last week to try and find a new hitching post for his stable."
That simple sentence has enough entropy that I can say, with confidence, that is has never been uttered by anyone in the history of human civilization.
https://www.biblegateway.com/passage/?search=Ecclesiastes%20...
https://en.wikipedia.org/wiki/The_Anxiety_of_Influence
https://www.youtube.com/watch?v=MZ2GuvUWaP8
For me, I actually really like that human content is recycled. The discussions around AI, art, and humans always talk about art as a separate product produced by the human. I feel like many pieces of art (not all, for example zombie realism) has a piece of the human inside of it.
An example I used in a comment in this post is Raymond Carver. His short stories are about blue-collar men in the mid-west. Carver was a blue-collar man from the mid-west. I find that interesting, and I liked that he pulled from his life experience to write stories.
I get very excited when I realize that the work I'm engaging with is recycled in some way. Like a song's chorus sharing lines from a separate artist, or a style that seems similar to a different writer I know. I love that. It makes me feel more connected to the creator and makes me like them more because we share similar interests.
An example that comes to mind for me are the manga Hunter x Hunter and Jujutsu Kaisen. The creator of Jujutsu Kaisen loved HxH and it 100% shows. The crazy powers, the complicated fights, the walls of texts explaining what happened in a fight, etc. All of those come from HxH and I love the creator was inspired by it. Sometimes reading Jujutus Kaisen makes me feel like I'm bonding with the creator over our mutual love of HxH.
With AI created work, I feel like we're missing the human touch. And as I pointed out in another comment here - I don't think it's hard to bring it back. Show me the prompts and the chat log. Why did you choose those prompts? Why did you ask the AI to write in X style? How does that X style make you feel?
On the other hand, maybe the AI prevents some of the human touch from coming through. I imagine much of the recycling that comes from humans is unintentional. The song you wrote on guitar has that riff not because you're copying a band, but because you've listened to so much 90s indie rock that you just make what you love - without realizing it.
Maybe in the future this changes. I'd love to see someone spend some time with an AI and mold it to such a way that what it produces can emulate the user's love and interests. Don't forget to show and share the chat log!
[EDIT]: To add onto this, I've actually done the above. I've played some text adventure games in the past, and I got ChatGPT to play with me. I told it that I had stat points (Health Points, Magic Points), that I had two types of attacks, and that there are three types of monsters. That experience invigorated me to write paragraphs on world building - just so I can feed it into ChatGPT and live in that world.
I seem some instances that are similar like this - but people just end up not sharing the prompts they feed into ChatGPT. I'd love to see those prompts. I've love to see what someone did to get ChatGPT to act a certain way.
Dead Comment
"Soon, asking a writer if they use AI will be like asking a photographer if they use Photoshop" – e.g., it's a foregone conclusion, and the best artists will generally adapt to using the best tools available
It's similar to music. DAWs and samples didn't kill off music; instead, it made it easier than ever for a teenager with a computer and a passing interest in music to create a song and share it with a world. As a consequence, though, the standards for mixing and mastering have gone up massively; people don't really tolerate bedroom recordings with $10 mics any more. I imagine most amateur musicians in the 90s didn't know what a compressor actually did (I certainly didn't).
Seeing the results of talented artists who are experimenting with AI[0] makes you realize that there's still going to be a massive gulf between skilled artists using SD etc as a tool, versus those who think they can be artists just by putting keywords into an image generation AI and calling it a day.
[0] https://twitter.com/jamm3rd/status/1619896080619159553 https://twitter.com/jamm3rd/status/1633758455952703488/photo... (moderately nsfw I guess)
the fear from the current professionals is that the new ai raised floor is good enough to be usable commercially, and thus, cut a chunk of economic value from the professionals.
There is no fear that AI stops people with the intrinsic interest in creation to stop creating - their ceiling and productivity would sky-rocket as a result in fact. And it would be _these_ productions that wow an audience.
Look at the history of woodworking for inspiration.
It used to take human sweat to make flat straight surfaces. Something like a walmart flatpack bookshelf would have been VERY expensive to make 1000 years ago. Industrial tech made that cheap and ... now its seen as tacky and out of style and only for poors.
The result culturally this century is an avoidance of "plastic wood" finish, faux finishes and faux surface prep that look old and worn and hand scuffed, and a strange hipster fetish for "live edge" raw bark on finished product. Sure, in 1875 one might have predicted based on mass production trends that furniture in 2020s would be all right angles, smooth as glass mirror, photographic "ideal" woodgrain instead of real woodgrain, plastic-y lifetime thick film finish. But thats only for poor people who shop at walmart, nobody with money buys that stuff.
I suspect what AI can cheaply produce will rapidly culturally be considered lower class and trashy. Oh, sure, completely AI generated movies look very nice and sound very nice and are ever so trendy and well written, but special effects and yesterdays memes on todays big screen generated entirely by computer algorithm is only for poors. Now, us rich cognitive elites only attend live theater plays. Aspirational middle class types watch recordings of theater plays (admittedly maybe some AI generated). You wouldn't show off your 'wealth' and 'class' by taking a date to an AI generated movie, that would be insulting, you might take her to a live theater play... I'm sure there will be some AI incursion, maybe the lights will be run by AI or AI painted backdrops or some actors will lipsync their lines to AI, or roughly every 5 years we have to tediously suffer thru a new generation of rewritten modernized classics and it'll be worse in the future with AI... but in general human will be the status symbol because it'll be expensive.
I suspect being able to ask an AI to generate non-copyrighted commercial quality music will mean massive noise pollution (much like every room required 15 digital clocks in the 80s and every room required 15 super bright blue power LEDs in the 00s) followed by the only people making money in music will be live humans playing physical instruments.
Poor people try to get by and don't spend money and when they do it'll be on infinitely cheap AI commodities. Rich people spend money on unique stuff, not mass produced AI shovelware. Aspirational people spend money trying to look rich so they will spend all their money on non-AI stuff.
So I ask the AI to rephrase it for me. Now I can pick and choose an option from those the AI offered, or I can just keep my version if it turns out it's good enough. I feel this is an acceptable use, and you can still maintain authorship, just like book authors maintain authorship after an editor has overhauled their writing.
Your DAW example would work if DAWs could generate samples, beats, and whole songs by the click of a button. But are you truly the author, then?
Whenever a customer ask me to develop an app, i don't consider that he did the job. I did it.
I don’t find this holds true for hip hop, the most streamed genre, whatsoever. There are countless examples of people making it big recording on a cheap mic in their mom’s bed room. One example is Chief Keef. A much more prominent example is Kanye who had terrible mixing on The Life of Pablo to the point where he released patches[0] for the album. He also recorded parts of Jesus is King on an iPhone[1]. To further the point, bootleg recordings and demo tapes of unreleased songs in artists’ back catalog continue to be popular with devoted fans. Average people like good music, even if the quality of the mixing and mastering is not stellar.
Even The Beatles released songs with minimal takes from a live rooftop performance on Let It Be; hardly an ideal recording set up. Although they surely had better mixing.
[0] https://archive.org/details/2016-the-life-of-pablo-updates
[1] https://genius.com/a/kanye-west-says-20-percent-of-jesus-is-...
It's called bedroom punk now.
Asking a photographer if they use Photoshop creates a framing where the artist still did went out and took a picture to create the work and then Photoshop only modifiers their original creation.
But you could just as easily say "Soon, asking a writer if they use AI will be like asking a photographer if they have a camera". That sounds ludicrous, but that is exactly what generative AI offers: the ability to create content essentially ex nihilo.
AI doesn’t “do everything for you” any more than word processors, music sequencers, or CAD does. AI allows people to operate at higher levels of abstraction, is all. Yes, fewer people will type repetitive copy in to word processors. But that’s fine.
You are mistaking activity for productivity. Few people go into writing because they enjoy typing. AI offers leverage, which is the most amazing thing for anyone interested in producing work.
Ask any professional writer: revisions are a chore. Authors often say a novel is 10% writing, 90% rewriting, and they don’t enjoy the rewriting part.
So, IMO, contrary to your doomer take, I think we will see more people producing better work because they can focus on the parts they love and not do the grind that was only ever a necessary evil.
(The exception being those who love the grind and not the product)
For example: sometimes I will pass a paragraph through an LLM and ask it to return it in a more "active voice". Then I _manually_ edit my original paragraph, if I wish, to make it seem more suitable for my current goals.
This is sort of like Photoshop for photographers.
The problem is that it automates the best parts and transforms the user into a curator/manager.
Some people want that, but other enjoy the creative part more.
To bring it back to photography, that's the problem with digital, you blast through hundreds of photos and spend most of your time selecting and editing at the computer.
With analog, and especially wet plate or direct positive paper, it takes a while to compose your picture and you only have one chance to take it and develop it. It's very easy to mess anything which is what makes the process more meaningful. And you're left with a unique copy, not an artificially limited single copy.
I almost never use the prose word-for-word, but goodness is it helpful.
Of course, it's not my place to say who should or shouldn't call themselves a writer, but I'll simply personally respect someone more if their stories aren't ghostwritten by the AI.
I don't think "AI" is the way most people would complete that sentence. Perhaps "Word"? Or "LibreOffice" if "Photoshop" were replaced with "Gimp"? Personally I use Emacs or Vim. You could incorporate AI into any of those tools, but how exactly? And would it be a core part of the functionality? And would it be something that the best artists make much use of?
If you used AI to make the spelling/grammar checker more reliable, probably most people would use that (assuming no privacy problems), but if there's an AI-driven autocomplete for sentences probably a lot of people, including the best artists, would turn it off, just like I turn off the autocorrect on a word processor today.
If an AI can complete the sentence, then perhaps the sentence isn't worth completing, at least if we assume that the reader is as clever as the writer and has similarly sophisticated tools. Perhaps the AI-driven tool should instead put some kind of wavy line under the second half of the sentence to indicate that it's boring and obvious and doesn't need to be there.
It’s tremendously useful technology for many domains already and you can see the stepwise refinements that will permeate many parts of our lives. Big money corporations are productizing those elements already.
But to be as fair to the pessimists as the optimists, its actually still a very big leap from Modjourney and GPT-4 to something that becomes the next camera or typewriter in terms of ubiquity. Because we saw a huge leap recently, we feel close and excited — and we might prove to be in hindsight — but we also might see that there are some hard conceptual limits that we won’t see anyone break through for another fifty or hundred years.
For image-making, there is a decision in the prompt and selecting images, but that is very different to making a decision about each color and brushstroke, and working to finish a painting. It's orders of magnitude more difficult and why great masters are celebrated. Creating stuff with AI will suit certain people, I definitely don't think necessarily the 'best' will automatically use it. It does seem to take away a lot of the fun of making images and truly original work will always push quite far outside the training set.
For literature, it could be interesting, how authors use new tools, where and in what sense. Maybe have more conclusive plots? Less inconsistencies? Have AI imitate dead poets' style?
We will value the classics more I guess, since they were done the old fashioned way.
Deleted Comment
New tools open doors, not shut them.
Another argument I keep hearing (most recently from pg), is that we'll always need non-AI training data. That, too, doesn't follow. Training new models on synthetic data does not mean we get stuck in a particular mode or style. We'll continue moving, improving, and trying wildly new things. Bootstrapping with synthetic data doesn't block evolution - it enables faster evolution, even. (I'm using synthetic data to train new models to great effect.)
People are angry that we've lowered the opportunity cost barriers and so they're expressing their frustration.
It's a good thing that life's choices no longer fence us in as much. Everyone should get a chance to learn how to express themselves through art with the new regime of tools. Despite changing economics, there will still be a top 1% that do better than the rest of us.
Artists, by and large, don't do art because they enjoy having art--they do art because they like /the process/ of producing art. If that process can be done faster and better by AI, then yeah, sure, they /might/ be able to still do art for a living (some artists will be able to leverage their experience to maintain an advantage; other, less flexible ones will lose work)--but the work they do will likely not be commensurate to the work they were doing before, and will likely be less enjoyable to them.
The thing that worries people about AI is that it'll make all creatives into middle-managers.
I think it's a great thing.
Hence I disagree. Even of the training data curators are perfect, there is a risk of "model inbreeding."
And the curators are not perfect. In fact, they seem to prioritize (by necessity) volume and speed over quality and curation when training these LLMs and diffusion models.
Like imagine a label on a thing that says "Made without CNC machinery". So instead of finishing the thing on a CNC mill, they instead stuck it on a Bridgeport manual mill, and finished by hand. Or somebody finished the cast with a file.
Okay, and so? In the end, a hammer is a hammer. If it hammers well, what difference does it make how it got that precise shape? It's not like some inherent goodness is being imparted by a hand file.
Now I get some methods have flaws to them, and some form of associated harm. The problem I see with blaming specific tools is that it's simplifying the problem too much. Eg, if the problem is taking jobs, then picking up one particular tool to blame for that allows manufacturers to use a different tool and cause the same sort of issue. If the problem is say, pollution, then it's not at all a given that the replacement method will be ecologically friendly.
IMO the better thing to do is to target the underlying problem. If say, your issue is ecology, then you want to certify that the manufacture is as environmentally friendly as it can be, not that the thing isn't made from plastic, or there exists the chance that the non-plastic thing will even be worse for the environment.
And if someone is going to send me a sales pitch or email that GPT wrote, I'd rather they don't insult me and just send me the prompt.
I think tfa is a gimmick, but i see value in knowing whether I'm relating to a human brain or to a statistical model
Or manga artists use things like screentones: https://www.youtube.com/watch?v=Q2U4EfKCfjI
I think AI will go down that road. Yeah, lots of people will mess around with prompts, but artists able to retouch the output, and to mix and match stuff will get much better results.
A hammer, a pair of shoes, a leather sofa, etc. They all have an element of craftsmanship and it seems like people who do that work usually take pride in it from an artistic and quality standpoint.
and the prompt makes no sense to you, because you are not able to interpret it the way you would interpret the generated output of said prompt. The information isn't in the prompt, and never was.
"Hand made" has been a selling point since things were first made by things other than hands. Example: "The factory, known as the Ateller, [...] it is the place where our craftspeople assemble each BUGATTI by hand."
In fact it's probably something completely incidental to the entire thing -- they're not assembled by hand because it's better, but because not enough of the cars are made to make automation make sense. It's just a pragmatic business decision, which then some marketer figured out how to spin.
This is basically the selling point of the entire luxury watches industry.
and fwiw, a lot of the assumptions in here are akin to saying at the dawn of photography that nobody would ever paint any more. Photography of course replaced certain entire categories of painting, but didn’t erase painting from the face of the earth altogether. Of course there are far more photographs than there are paintings, but volume alone is not the totality of meaning.
Generated content is strictly culturally regressive anyway. After a hundred years of ChatGPT will people still be writing prompts with “in the style of [person who produced all of their work before the year 2000]”? That would be a sad and boring future.
I have things I have written that took me two years for 8-10 pages. I wrote them to help me think through certain things.
Could ChatGPT have written it for me? Maybe. Probably not, though - I kind of had to discover what the content was supposed to be.
Could it have written it better than I did in two years? Probably not. Two years leaves you a lot of time to polish the phrases.
Could ChatGPT have taught me what I learned in those two years? No way.
When photography replaced many of the uses of painting, some painting jobs were lost, but photography ones were gained. Now, many creative jobs will be done by computers, leaving the world less enjoyable for people who enjoy creating.
Sure, some people will continue to be creative, but look at what happened to art after photography: we got modern art, where people just piss on a canvas and sell it for millions based on the name of the artist alone, not the value of the art.
AI is progress in the same way nukes are progress: you have to get it or you'll be left in the dust. But is humanity better for it?
> Art is not what I think when I’m painting. It’s what you feel when you’re looking
[0]: https://news.ycombinator.com/item?id=34921883
Yeah, because the Netflix catalog, for example, is not repetitive and stagnant.
These current advances will enable anybody with a unique idea to produce content. We are right before an immense explosion of human creativity.
I think we’re going to see an explosion of waste.
We are information processors. The input makes the output. What happens when you close that loop?
Examples: let chatGPT.. 1. write blog posts 2. generate scripts for youtube videos 3. create short stories so you can sell them as a book
Painful to see. I would like to think nobody in his right mind is willing to consume these delightful pieces of work. Dead internet theory on the next level.
People tend to overestimate their talent, and get overly attached to their own ideas. So when a tool like midjourney/stable diffusion generates beautiful artwork based on a low effort prompt from the user, it's comfy to think that they had a big part in it.
The reality is that almost everything those tools make is equally gorgeous/amazing regardless of who uses it, so they're effectively interchangeable. As a tool for personal expression, it has a lot of value because of the impact it can have on the individual using it, but as art it's pretty worthless. A generated AI image could potentially have some cultural impact or value, but not on the merits of "it looks pretty", since they all look like that.
And I would argue that the current (mostly recent productions) Netflix catalog is indeed repetitive and stagnant. Originality in tv production is currently in a race to the bottom.
Those purists are mostly dead. Everyone uses technology in music today. And music is better for it.
> Those purists are mostly dead
Genius argument there buddy
Dead Comment
> I thought using loops was cheating, so I programmed my own using samples. I then thought using samples was cheating, so I recorded real drums. I then thought that programming it was cheating, so I learned to play drums for real. I then thought using bought drums was cheating, so I learned to make my own. I then thought using premade skins was cheating, so I killed a goat and skinned it. I then thought that that was cheating too, so I grew my own goat from a baby goat. I also think that is cheating, but I’m not sure where to go from here. I haven’t made any music lately, what with the goat farming and all.