> 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.
> 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?
In copyright-law (and I think patents?), there is the Threshold of originality. Basically you evaluate how much work and change went into something, to distinguish it from other works. Which IMHO comes down to how much of a and b can you still see in the mix, and how much did mixing them changed them in the end product. If the change is low, then people more likely consider it as not innovative.
Or how Homer Simpson once said: “People are afraid of new things. You should have taken an existing product and put a clock in it or something.”
Copyright laws are a tool, not a reason by itself. They are aimed to give money to inventors, not to judge innovation. You can argue they do judge in order to accomplish their aim, but that's the byproduct, not the aim. So let's not give the laws more meaning and usage than they deserve.
on similar (I think) line of thought, but further along,
the reason to have property (also a tool, or social-technology to be slightly more precise), i.e. ownership over things is a byproduct of having a marketplace in which we can trade.
In this view, the marketplace (or trade, depending on your outlook) is THE WAY to come together and put all our skills together in order to co-create (con-struct) something much larger.
Alas, capitalism means that only a very few chosen elites (which are, by this point, mostly autonomous corporations) get to decide what we all work together to co-create. We as human individuals are only able to participate in this figurative "marketplace" (understood as a social-technology) as the part of merchandise, specifically as 'commodity'-style labor.
Do you have an alternative to suggest? Under most of human history the chosen elites inherited their positions from an ancestor who won an important war. Capitalism may not be an even playing field but the process that lets Elon Musk build landing Rockets is an order of magnitude more even than the process that let Kuresh build pyramids. Is there a model that might be more even still?
Ah, that's fair. I formulate a similar observation by saying that digital assets inhabit a post-scarcity economy which doesn't work the same as a resource-based scarcity one, and using the same money for both requires more suspension of disbelief than most of us are capable of.
Totally agree. The idea that ideas/bits can be owned is a slippery slope with bad policy at the bottom. Maybe it was once necessary as a sort of training wheels for innovation, but it has long since become more of a drag than it's worth.
Copyrights don't protect novelty. Two people can independently create the same thing and both be entitled to copyright. You cannot do that in patent. Only one is an invention in the eyes of the law.
The threshold for originality in copyright is the bare minimum, so it's not a good standard for "invention". Patents have a much higher bar to overcome, and it is hard to put into a simple explanatory phrase.
I think what you are describing in copyright isn't the issue of originality, but determining what is encompassed in a copyrighted work. The court will analyze what the work consists of, and what of it was your expression, as opposed to someone else's. So, it's not novelty exactly but it's close.
Yes, and no. I can't speak for laws in the USA, as I'm from Europe. But Copyright-laws in the EU do have parts which specifically target mixing and mashups of content, and how much new content of your you need to add to make it count as a separate work. These parts were recently updated, because of YouTube, the meme-culture and so on. But it's my understanding that for music and text-quotes, the whole concept is already longer around. So I guess US-Laws do have something like this too?
So of course, this does not handle novelty on a global scale for all of mankind's knowledge and content, but the general Idea and how to handle it is there.
> Two people can independently create the same thing and both be entitled to copyright.
Similar maybe. But for literally the same, I doubt it. People are getting already sued for having too much similarity.
My point is more that, in the way the law works out, what you get to protect is the part of an expression that is unique to you, which can include mashups, etc. My point being that this is perhaps distinct from novelty, as novelty isn't a requirement of copyright, just independent creation.
>Similar maybe. But for literally the same, I doubt it. People are getting already sued for having too much similarity.
Full stop yes. Independent creation of the same thing is not an issue in copyright law in the US. I do not speak about Euro copyright, as I'm merely a US atty. In US copyright law, a necessary element of infringement is access to the allegedly copied work - if access to the work is rebutted, then there is no copying and no infringement. The copyright stands.
>> Basically you evaluate how much work and change went into something, to distinguish it from other works.
Copyright exemptions (fair use/fair dealing etc) are a million times more complex than that. There are times when one adds almost nothing yet will still get protection. Take political humor. A standard bit is just to point out something funny. Look at how often political comics (John oliver/stewart etc) just play a clip of some politician. No edits. No commentary. The clip speaks for itself. That is still protected speech. Understanding how the comic adds to the clip cannot be expressed in numbers.
You are confusing the "copying" analysis element of infringement, with the affirmative defense of fair use. They are not related. A necessary element of proving infringement is showing what was copied, which most likely requires the court to construe exactly what is covered under a given copyright.
I mean, if the examples are to be believed, GPT4 seems to be able to explain what's funny about a given image. It's not out of the question that it or some future iteration could reduce that very thing to a discrete set of numeric scores.
If we follow this line of thinking: in the, let's call it, "pre-AI" days all of the ideas that we have of the form "Mixing A and B" are ones that at least one human found to be interesting/valuable (and the ones that become common and get remixed must have been interesting/valuable to many humans). Maybe the "originality" of the idea isn't the thing we care about, per se, but rather that fact that somebody though it was interesting to shine a spotlight on this region of the idea space for the first time.
But now that we have software that can generate massive amounts of "Mixing A and B" ideas automatically... I dunno, seems like we're heading toward a sort of "pollution of the idea atmosphere" where we get a ton of new/remixed ideas dumped into the world that haven't passed through that initial filter of a human vetting them as particularly useful or valuable or interesting in the first place.
> I dunno, seems like we're heading toward a sort of "pollution of the idea atmosphere" where we get a ton of new/remixed ideas dumped into the world that haven't passed through that initial filter of a human vetting them
We already have that. Observe: ahem “It is an industrial capacity, that many people like the Reddit poem person who does the cow thing. And everyone delighted in the nonsense of words that are sense.” Or, perhaps you want something on-topic? “Your ideas about ideas are mere ideas. Ideas that are ideas are ideas, but these ideas are not ideas. lol!” Perhaps an unoriginal, unfiltered synthesis of some good ideas? “It is a truth universally acknowledged that a potato peeler could save you 5 Altairian dollars a day.”
We don't need AI to produce unoriginal, unfiltered internet comments. Certain YouTube comments sections provide a great example (though the problem with YouTube comments isn't as bad as people tend to make out). We humans already have social mechanisms to keep the good ideas and ditch the bad ideas, even when many of the humans aren't bothering to filter their own output.
There's two variations, one stupid one not. The stupid one is "novelty no longer exists and maybe never did". You've covered it. The not stupid one is this question about the closure under creativity in the same sense that numbers are closed under multiplication and addition. Sure you can make infinite numbers, but you can never multiply and add your way to a cat, because a cat isn't a number. Is everything we do rearrangement of basic known parts much like numerics is rearrangement of basic known digits? Its a deep question.
If you need examples of creativity, look at the math. Math is full of the novel (at the time of invention) concepts: complex numbers, groups, automorphisms, etc., etc.
None of these concepts can be obtained by rearranging the "parts". Sometimes a new concept requires the invention of "parts" that had never existed before, and, in turn, becomes a "part" in the future inventions.
Your "deep question" fails to address gspencley's point: If everything we do is a rearrangement of basic known parts, where and when did we get the basic known parts? From cavemen? From apes? From protozoa? Someone, at some time came up with the basic known parts.
So, was that real creativity, or not? If not, why not? If the parts are really "basic", they didn't come from other, pre-existing parts.
And if it was real creativity, why is it impossible for us to do the same?
All the advances relying on new concepts and discoveries or inventions in science, math, logic and technology would suggest that the basic known parts are not set. So yes, there's been plenty of genuine novelty. Culture as well as new forms of music, food and entertainment come into existence. New words are always being coined as languages are fluid.
I do believe AI sometimes generates an idea that is just as original as a human's.
I don't believe originality is that valuable. It's a positive term to me, but just slightly.
I've seen a lot people on HN credit the SV companies' "free food" practice to google. Do they believe free food for your employees is a new idea that someone in google came up with? I don't think so.
It definitely can. GPT-3 can too. You know the joke about "idea guy"? Who has "idea" but no programming/design skill and no connection to bring funding? New ideas aren't always very valuable.
I'm finding it spectacular for generating ideas. Ask it for "40 ideas for plugins I could build for Datasette" for example. The results are comparable to what I've seen from a meeting room full of humans for an hour, but GPT-4 generated them in less than a minute.
Really? I feel like if you have to ask what plugins to build you’re doing it wrong. You should know what plugins to build by being a user of Datasette and understanding its limitations for your self.
Once you have an AI to also prototype the plugin ideas, such an idea list may become useful. I've always seen that the owners of any product have more product improvement ideas than they could economically implement.
I’ve always interpreted statements like “there’s no such thing as an original idea” or “everything’s a remix” not literally, but rather as a reminder that new ideas are born from a cultural context and the ideas in it, using those ideas like a language of creative expression.
I often take it a step further and use it as a reminder that new ideas are rarely born from one person but rather the contributions of many, each too small to be noticed as an “original idea”, but when viewed collectively, can be revolutionary.
Isn't the "no such thing as an original idea" point more about there being so many people alive now that one cannot think of anything that somebody else hasn't though of as well?
So many advancements (like the airplane) often get invented simultaneously by different people in completely different areas of the globe without any connection to each other.
I think that most people are attached to the idea that humans have some type of "soul", even if they don't call it that. This soul, as the thinking goes, is completely separate from material reality, and allows people to have ideas that come "out of nowhere" and are not inspired by anything in particular. In this way, humans are supposedly different from machines, whose outputs are a mere function of their inputs.
This is the root of the objection to AI. To say that humans are similar would imply that a person's thoughts are a function of their sensory experiences, and that is not a popular view.
Similarly, people like to think that a person's behavior is not a mere function of their experience- that they are capable of "choosing" how to react to their circumstances. They will accept no explanation that appeals to material conditions or biology. A man steals bread not because he is poor and hungry, nor because of some chemical reaction in his brain, but because he "chose" to steal. The part that chooses would his "soul", which cannot be explained in terms of cause-and-effect.
You’re going to have a lot of unproductive conversations if this what you believe other people think.
There’s a much richer discussion going on about current-generation AI and its prospects that is grounded in plainly materialist and technical insights, with thoughtful differences of opinion about what current research demonstrates and about what the sophistication of biological/neurological machines may involve in comparison.
You might find that conversation more enriching if you tune into it instead of the one you seem to be focused on.
No, this a straw man. The line of reasoning here, first, makes a lot of presuppositions about AI and it is overly reductionist about human intelligence. I see this comment constantly in all HN threads about AI, “humans intelligence is nothing but probabilistic sparks” or whatever just actually means.
> 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 feel like this heavily requires “citation needed”. There are plenty of these “inside the studio” type interviews where an artist describes at length their inspirations and the other artists they admired and wanted to mimic in some way.
> I feel like this heavily requires “citation needed”.
You might have missed that I was stating my belief. I can only cite myself as the ultimate authority on what beliefs I have or don't have.
If instead of believing something I will know something you will notice from the lack of "I believe" and the appropriate citations. If we would need to provide citations for any belief we could not talk about theories and ideas we have which as of yet lack the sufficient evidentiary backing.
Now of course it sounds like what you are trying to express is that you are disagreeing with my belief. Which is perfectly fine.
> There are plenty of these “inside the studio” type interviews where an artist describes at length their inspirations and the other artists they admired and wanted to mimic in some way.
Yes. Humans are full of contradictions therefore you won't see black-and-white behaviour from them.
I think this is mostly referring to the Blurred Lines verdict. On the other hand, artists have a strong incentive to record their songwriting and recording process, so that they can head off any potential disputes about writing credits from people actually in the studio (this situation is statistically much more likely than somebody not involved suing after the song's release).
The "Shake It Off" case seems like it involves lyrical content, which had always been a primary concern of music copyright, even before "Blurred Lines". The "Thinking Out Loud" case seems to involve similar issues to the "Blurred Lines" case, but was filed long after[1]:
> While the Gaye family is not involved in the “Thinking Out Loud” lawsuits against Sheeran, the precedent set in their case looms over all new copyright infringement claims. Notably, the court took into account not just sheet music but studio arrangement too and ruled that “Blurred Lines” significantly aped the vibe of “Got to Give It Up,” something that had previously been beyond copyright protection.
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.
So Ramanujan with no formal training in mathematics was really surrounded by advanced education of mathematics and had no original ideas? I feel if more people studied philosophy they may discover how problematic these reductions are.
What does that even mean? Mathematical ideas are ideas. The notion of continued fractions is not just an expression of the world around us. This is basically hokum. The point is that human intelligence utilized original thoughts in the case of Ramanujan.
One of your three sheep is black. 1/3 - that's a fraction, a idealized representation of the real world. Now you take that concept and do it again over and over ad infinitum.
That's not a magical invention that has no bearing on the world around us. That's just an expression of real world taken to its logical conclusion. It was not invented from a vacuum, it was invented from the input of the world around us.
What is "hokum" is the idea that the human mind would somehow come up with meaningful output without meaningful input to seed it.
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.
The earliest humans didn't know everything we know today. How could they had any ideas about digital simulations, branching timelines or nuclear war?
There's a million things today that didn't exist back then, and many things that came to exist culturally over time, or were discovered. Do you think they were sitting around the fire talking about how the molecular motion registers as a conscious heat sensation in animals or what the proper interpretation of QM is?
I don't have a definite conclusion on anything, but I remember having this discussion with a friend a long time ago, and it made me think... What he was trying to convince me was that all of those things you mention can be seen as subclasses of other natural things:
Digital simulations are self-explanatory - All things simulated must have an existing thing they are simulating. Digital is one type of representation of an already existing thing. It can be seen as a subclass of concept/drawing/painting/.
Branching timelines are more abstract, but it's ultimately based on the idea of a tree. Dilemmas over branching decisions have existed as long as we have been able to think. We branch timelines in our imaginations while playing chess or doing any strategic endeavor where decisions and responses to those decisions matter. FFT: Decision tree, binary tree, random forests, etc. These don't quite cover the complexity of QM, but it's hard to ignore that there is overlap.
A nuke is a type of bomb, which is a type of rapid expansion, which is just an expansion of something (volcano, lightning, comets, etc...)
My friend's point was that of course a caveman won't be thinking about quantum mechanics, but they were thinking about the more basic things that ultimately led to their descendants thinking about QM.
No true original ideas and there was just remixing natural phenomena? Really? So writing was just remixing all the writing that people saw volcanoes and rainstorms do?
>> No true original ideas and there was just remixing natural phenomena? Really? So writing was just remixing all the writing that people saw volcanoes and rainstorms do?
> Writing was a remix of pictorial representation, which was a remix of the way things like ox heads, flowing water, and birds look.
That's the kind of absurd reasoning when you take some proposition and try to defend it to the death even though its wrong.
I'm not the one preserving the word 'remix' in this context, I just wanted to put it in the terms that GP was using. It certainly sounds more absurd when you use that word.
But the point is that human creations are always based on something else, so pointing out that AI is basing its output on a database of previous work does not necessarily mean that it is not creating new art, or being creative, or however else you want to put it.
It's like the ridiculous lawsuits that claim a song is stolen because it uses the same chord progression as an older song, where there are almost always centuries-old examples of that same progression from Beethoven et al.
Your point seems to be that the reasoning is absurd because it's defending an incorrect premise, and the premise is obviously wrong because the reasoning is absurd, so I'm not you'll want to know what the people on the other side of this discussion think.
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.
Maybe they didn't stop, but they're converging towards zero. In the past hundred years, artists were coming up with a lot of things that had not existed for all of humanity. Nowadays, it's rare to find truly original style. The space has been explored thoroughly. It's also not just random search. It's no coincidence that most image generation prompts have an existing artist or style in them. If you leave it off, you just get crap.
>Maybe they didn't stop, but they're converging towards zero. In the past hundred years, artists were coming up with a lot of things that had not existed for all of humanity.
How do you distinguish this from survivorship bias? There were probably tons of shitty artists 100 years ago but you haven't heard of them.
> It's no coincidence that most image generation prompts have an existing artist or style in them.
I've been thinking about this. I don't think it's evidence that anything is getting worse, because a lot of the prompts people use are referring to recent artists/styles. Is it possible that leaving out the style/artist leads to an average of every style which doesn't really work?
>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.
A painting or story made by artificial intelligence is not human because it does not have a life story behind it. I still enjoy reading the artist's biography, some of his correspondence, trying to understand his creative process. If you pour your heart into your work we can bond through human experience, maybe we can even sit down and talk. An AI does not fear death or loneliness. Sometimes I think that part of this site's audience only considers art from a consumer-product perspective. For me it goes a little further.
> Sometimes I think that part of this site's audience only considers art from a consumer-product perspective
Imagine you are an artist. You as a patron connect and talk about a piece of art, you walk away happy and feeling connected. He does not sell any art because they are indistinguishable from what the AI can produce with the cost of electricity. Now if you are willing to pay for "bonding over human experience", GPT can probably be trained to do that as well. Generative AI eliminates the livelihood of almost all artists eventually.
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.
Don't we already, though? I mean, how many of the hundreds to thousands of mediocre movies that hit Netflix, Hulu & co every year do you watch? If they were AI-generated, would it actually matter to you?
As far as I can tell, there's just two interesting things to watch out for:
- Personalized AI-generated content. What if the movie were just for you? What if it expired like a Snapchat, never to be seen again by anyone else? Would this tickle us? Would we succumb to new filter bubbles, increasing the distance between us?
- Can AI make the movie that's so good that it sticks out and does become the one we watch collectively?
Ideally, AI art would be tagged on any large platform and AI artists would be forced to compete in a race to the bottom against all their fellow prompters.
I wish this would happen. But, looking at the current world where publication and distribution are dirt cheap and simpler than ever with the internet, most people's media curation is "What's free" as opposed to "What's good." If the new torrent from the firehouse is AI-generated content, careful curation will lose more. The time and money cost become harder to justify.
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.
Would you be happier if your car / bicycle / city bus was produced entirely by hand, with no tools or automation?
Labor will shift. Bemoaning new efficiencies and new empowerment because they reduce the need for meaningless labor consumption is backwards. We should be sensitive to those whose lives will take an unexpected turn (I may be one of them!), but we should do so in the context of celebrating greater individual leverage to create and produce.
No, as I was trying to imply I don't particularly care about the use of a given technology per se, I care about the consequences of its application to labor.
"Labor will shift" makes it sound like a smooth and automatic process but it is not. People will lose jobs with no equivalent replacements, families will fall into poverty and misery when they hadn't before. In a place like the US with healthcare tied to employment, people will die. And eventually, it will reach a stable equilibrium with fewer jobs that can support a reasonable quality of life. That's what labor shifting looks like, we know because we've seen it over and over again.
The changes might ultimately be net positive for a great many people, but that's small consolation to the people whose lives will be made much much worse during the transition. None of this is inevitable, but historically it's the path we've chosen and we seem even more dedicated to this outcome now than at previous times of change in the relation between labor and survival.
I think a big issue I take with the removal of humans from art creation, or at least discussions around it, is that art is always talked about as being separate from the creator. As a product the person makes.
For many pieces of art, and what draws me to art, is knowing that the creator put a piece of themselves into it. (I'm going to avoid talking about the 'separating art from the artist' discussion, that's separate than what I'm discussing here).
An example I've talked about in the past on HN is Raymond Carver. Carver's short stories are often centered around blue-collar men in the mid west. This is because Carver was a blue-collar man from the mid west. I find that interesting. I enjoy reading about Carver's life, and reading about what people had to say about him.
Essentially, write what you know.
Art made by AI is missing that - and I think the frustrating part for me is that I don't think it's that hard to bring it back.
Show me the prompts used for the art. Tell me why you used those specific prompts. What did those prompts mean to you? I want to know all of those things.
I also think people stop too soon. Why not take what the AI has made, do something to it yourself, and then feed it back into the AI to see what happens?
Until it doesn't. I mean until very recently the narrative justification for extreme automation was it would free up our time to create art and stuff. Now that's in question.
It's all excuses to avoid thinking about the problems the automation technology will cause. Avoidance worked OK in the past, but as these technologies get more and more extreme, the problems will get more and more pressing, and the old lazy excuses won't cut it anymore.
> ...but we should do so in the context of celebrating greater individual leverage to create and produce.
And the end point of that is a small cadre of elites who control the machines, and hordes of people left with no economic value (except, perhaps as slaves for elite amusement, like gladiators and prostitutes).
People who say "labor will shift" tend to have a significant overlap with the people who say "one day AGI will do all the work for us so we can live in paradise"; which, in turn, has significant overlap with the people who don't spend nearly as much time as they should acknowledging that getting from point A to point B is going to be the bloodiest proposition in history and not a guarantee besides. Probably because there is yet another overlap with people who find technology far more fascinating than society, and thus don't care to look beyond first order effects.
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.
>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.
No, it believes that the mind has an internal state. We have many physical cases of state which is in practice undecidable. Moreover, in many formulation of quantum physics one can have a state which is unreachable even in theory - not just hidden variable style QM theory, there are ways to get unreachable state even in 'regular' QM[0].
>And if that's the case, the question is where does that irrationality come from?
The universe itself. The linked PDF - you might be familiar with the author, he features often on HN - provides one method this is possible. Though, I'm not saying this is true, I suspect it may not be.
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.
The elitism of having a Twitter account and a Wacom tablet? I've found traditional artists are very happy to help people out, especially in the digital art world. They just won't draw your anime waifu OC for exposure.
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
This is the same as getting ChatGPT to calculate something. It is likely that it can infer a correct result from the training data and give right "new" answer, but it doesn't mean it has any understanding of maths.
That's why these models like ChatGPT are trained on massive models, to hide the fact that the AI is actually very dumb pattern matching machine.
The only reason they found these "new" protein structures is because AI could match them to a pattern that it learned from the training data.
They even claim this:
> akin to generating grammatically and semantically correct natural language sentences on diverse topics
Just like ChatGPT can generate grammatically and semantically correct natural language, except if the topic is not something it was trained on it will output grammatically and semantically correct nonsense.
> ProGen can be further fine-tuned to curated sequences and tags
Which suggests there still needs to be a human that can reason to be able to curate the sequences, something AI can't and probably at this stage never be able to do.
This is something companies running these models won't openly admit, because that would confuse investors.
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.
But they mostly read like someone churning out monster manual entries by pairing animal names with adjectives then putting in the obvious two sentences of description.
Nothing about it engages my brain or strikes me as brilliant, insightful, or what I'd usually mean when I say "creative".
Those are all pretty standard, to be honest. Like madlibs for creatures, but with nothing really new.
This, I think, is the key bit of your comment:
> I'm not a fictional guy so I don't really know
HN (and wider social media) is filled with people who aren't familiar with [field] declaring that AI has surpassed humans in [field]; it's not a display of AI's new brilliance but the old[1] display of a speakers' ignorance.
Most of them don't display the same humility as you.
Plus you can prompt it to take those results and make them more unusual, evocative, creative. Basically use the same kind of creative pumps that human artists do.
>> 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.
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.