Interestingly this has been a card in their hands for more than a decade now, ever since the first ML race gun shot of CNNs came into play. It's only now that they can make use of it for extremely powerful models. I wonder if they actually will though.
Depends a lot on what the goal is to create, their corpus though probably doesn't have the kind of material people really want for AI art though. That's more on places like DeviantArt or ArtStation.
> The US Copyright Office determined recently that art created solely by AI isn’t eligible for copyright protection. Artists can attempt to register works made with assistance from AI, but they must show significant “human authorship.”
The issue is that only humans can own copyright. In the referenced Copyright Office determination, (“A Recent Entrance to Paradise” (“Work”)) homeboy tried to say that the computer was the author of the work (original copyright owner) and then transfer the copyright from the computer to himself.
If he were to directly claim authorship and copyright then there would be no problem. The whole convoluted thing the human was doing to try to list the computer as the author is what got rejected. Just like the large primate that took a picture with a photographer's camera. Camera owner could claim copyright ownership, but copyright office would not give the copyright to the primate that pushed the trigger button because they are not human.
It wouldn't exist without a human actively creating/capturing it so doesn't seem as though that's an actual problem. Does a photograph involve significant human authorship - choosing a prompt or choosing to click the button on your DSLR is itself the act of authorship.
Choosing when to click the button is a pretty essential part of photography.
"I prowled the streets all day, feeling very strung-up and ready to pounce, determined to “trap” life — to preserve life in the act of living. Above all, I craved to seize, in the confines of one single photograph, the whole essence of some situation that was in the process of unrolling itself before my eyes" Henri Cartier Bresson. The Decisive Moment
Choosing how to prompt the ai is a pretty essential part of ai prompting.
"I crafted queries all day, feeling a sense of urgency and anticipation, determined to “guide” intelligence — to nurture intellect in the act of thinking. Above all, I yearned to capture, within the confines of one single prompt, the whole essence of some conundrum that was in the process of unraveling itself before my mind" Alexander Turington. The Guiding Query
That was from back when film was expensive, and it was impractical to take thousands of pictures, as you can now. For decades now it's common for photographers to shoot countless photos and sort through them later to pick the best ones, rather than aiming for one perfect shot.
Also consider movies and video, where you could have hours or days of footage from which to choose stills.
The act of choosing in all these cases is critical to creativity, and the same is true when you choose what to prompt an AI with or which AI generated image to display or publish.
Duchamp really did have the last word on this with his Fountain[1] over 100 years ago.
I can commission a painting and give exacting details of what I want, but that does not make me the artist that created the painting (especially in the legal definition required to claim copyright ownership).
>The copyright office issued specific guidelines saying that AI-generated content is not copyrightable.
The copyright office doesn't say that at all.
"In the case of works containing AI-generated material, the Office will consider whether the AI contributions are the result of “mechanical reproduction” or instead of an author's “own original mental conception, to which [the author] gave visible form.” The answer will depend on the circumstances, particularly how the AI tool operates and how it was used to create the final work. This is necessarily a case-by-case inquiry."
It goes further than that. Kris Kashtanova made a comic book named "Zarya of the Dawn" using midjourney for all the art. When registering for copyright she claimed copyright over the art for herself, under the theory that she was prompting the AI, and it was just a tool. When the copyright office learned about this they revoked her copyright registration[1]. The view of the copyright office is that this is no different than the photographs taken by the monkey - the monkey can't claim copyright because they are not human, and the owner of the camera can't claim copyright because they didn't have sufficient creative input, so the work is ineligible for copyright at all.
She is eligible for copyright on the text she wrote, the composition and editing performed on the images, but not the raw output of the AI.
I think in the relatively near future, video of the artist creating a piece of art will be part of what makes a given piece of art valuable. The provenance will be just as important as the art itself.
AI tools will soon be able to generate videos showing a specific human producing a specific piece of art. Should we require a video of the person taking the first video also?
I don't think it's going to be all that soon. Human images are much more difficult to fake than generic "art", much less human video + a piece that is physically created. Plus the price to produce that complex of a fake will be higher than the cost of an artist to setup a tripod and start recording.
Recorded public performance of art creation may become the norm after that and then actual robots may be making physical art with impressive skill and intrinsic value...
This would be hilarious then, because it'd be a video of each artist creating an absolute breathless masterpiece in one single sitting. If forgeries have taught me anything it's that creating visually duplicate works of art is easy.
This is so weird. Can artists who splash paint randomly at a canvas not copyright those artworks? Or ones who attach a paint bucket to a rope and swing it over the canvas, giving it just one push?
This is actually a good point. I've seen artwork where the artists just had random passerbys inadvertently make changes to the canvas until they considered it 'done'.
I wonder if someone screen printing images created by an AI tool would satisfy the requirements for ‘human authorship’.
Edit: screen printing is a manual printing process (in line, I think, with pop artists recreating commercially printed labels, etc), so this seems like a reasonable question.
She wasn't just prompting the AI. That comic required significant work on the user's part to edit the images and re-synthesize portions of each frame repeatedly while doing things like inpainting, outpainting, re-prompting, etc. And likely required use of some other tools like Photoshop or Indesign (midjourney absolutely did not generate the bubbles or comic book text).
I’m guessing that the copyright equivalent is whether the editor of someone else’s photograph or the director of a photo shoot should have copyright privileges. The answer is pretty clearly not.
It’s not that she didn’t do (a lot) of work, but that the creation of the underlying work happened by AI. If it were human then it would hold the copyright, but it’s not so it doesn’t. The logical misstep is thinking, “because it can’t have copyright, someone else can.”
Exactly, generative AI, like the camera, is just a fancy way of transforming ideas from the real-world into a digital representation, but with a lot more parameters.
> That comic required significant work on the user's part to edit the images and re-synthesize portions of each frame repeatedly while doing things like inpainting, outpainting, re-prompting, etc. And likely required use of some other tools like Photoshop or Indesign (midjourney absolutely did not generate the bubbles or comic book text).
The issue is that the AI's output is deterministic, and the prompts it uses are commonly too short to be eligible for copyright, not least because someone else could plausibly use the same prompt independently. With the same seed, the AI would then produce the same image. Or produce a similar image in response to a similar prompt.
If you could copyright that, you then have an enforcement problem, because the usual way to show copying is similarity, but you can then have two images that are similar yet independent. And some light Photoshop work is not going to eliminate the similarity.
If someone builds a device that sprays paint onto a canvas based on some parameters, and then a person use those parameters, writes a small controller that sprays the paint a specific way, manually adjusts the position of the device over multiple sessions, and does their own touchups to create a piece of art, would they not hold the copyright on the resulting piece?
Yes, there is a deterministic component (although, to my knowledge, the AI tools aren't actually deterministic over their parameters). But the resulting work involves a lot of human creativity and intervention.
Suppose you have a printer with a programmable head which can be used to print out arbitrary images. Can you copyright the pictures it can print, even though the printing is done by machine? Obviously. But then it's not the machine choosing what you want on the page.
Perhaps my analogy wasn't clear. I meant, the painting device uses your parameters, but also supplies some modifications. Like a stenograph.
At the end of the day, generative AI, Stenograph, and this painting device are all tools.
If you shake a kaleidoscope and then take a picture through the lens, I'm pretty sure you have copyright on that photograph, even though someone else made the kaleidoscope
It's not the presence of a machine which makes it ineligible for copyright. It's the absence of some independent creative expression. If you add significant creative expression to what the machine does, that's not the same thing as the output of a machine produced from a minimal input.
"The issue is that the AI's output is deterministic"
Point a digital camera at a still scene under controlled lighting conditions and it's pretty deterministic also.
Anyway, it's easy enough to add randomness to the AI image generation process (and Midjourney does do that by default, as a matter of face), so the process need not be deterministic at all.
It's not about the physics of light, it's about what the artist chooses to have in the scene.
And it's not randomness that fixes it. Do you even want to get into the information theory problems if you could copyright the output of a random number generator?
What you need is for someone to be making creative choices with enough entropy to be considered original and not be reproducible by feeding a short sentence to an existing algorithm.
I really like how you put it. Good thought! But I don't quite agree that entropy is a criteria of originality. Because originality is not ranodmness, it's... distinctiveness.
If I commission an artist and give them exacting directions, they are still the artist and copyright owner of the work. They can then assign it to me, but I am not the artist simply because I commissioned the work and gave input.
I understand that the individual AI generated elements can’t be copyrighted, but in this case the final product is a huge amount more than that. It’s a collage of such elements, plus cropping, filtering, colour grading, composition in the page and overlay with speech bubbles and such. It seems to me that the end result should be copyrightable.
Then the fact the original elements aren’t covered isn’t a problem. You just delete them.
> “Zendaya leaving gates of Central Park,” Kashtanova entered into Midjourney, an AI program similar to ChatGPT that produces dazzling illustrations from written prompts. “Sci-fi scene future empty New York....”
> From these inputs and hundreds more emerged “Zarya of the Dawn,” an 18-page story about a character resembling the actress Zendaya who roams a deserted Manhattan hundreds of years in the future. Kashtanova received a copyright in September, and declared on social media that it meant artists were entitled to legal protection for their AI art projects.
It's an interesting argument, treating the AI more like a commissioned artist than like a technical tool.
But in the end, this seems like the opinion of one mostly irrelevant government office? Copyright protection is automatic in the US since 45 years now, you don't need the involvement of the copyright office at all. For establishing that you created the work, a letter from the copyright office refusing you is as good as a letter accepting your work, and in most cases it's redundant anyways. The only relevant opinion is that of the court where you sue someone else for copyright infringement.
The problem I have with this is who is the arbiter of what is "AI"? Couldn't I just claim I used "autonomous state machines" and not fall under this categorization?
It's also a literal pandora's box because somehow an AI itself can be copyright, but what it produces can't be? Surely it isn't very hard to have an AI that produces other AI? So who owns those?
This seems dumb. If she hadn’t told them how she created it, it would have been copyright? Is the copyright office going to start asking artists how they create their work now? This is just a bad decision on their part.
There are laws and rules for copyright, and when you claim copyright, you make a legal claim to the government that those rules apply to yourself and the piece in question. TDIL: When I make legal statements to the government, such as that copyright applies to a work I am submitting, those statements must be true.
What is weird about this is that even if AI works aren't protected by copyright, under Feist a collection of uncopyrightable information can be protected if they are selected coordinated and arranged. That is almost certainly met when creating a comic book or graphic novel.
The monkey taking a photo isn't a good example because they never tried to register it in the US, they never actually ruled on it. There is plenty of other case law showing "the modicum of creativity" is a low bar, copyright does not require "sweat of the brow".
Problem is, if the machine could hold copyright without significant human authorship, a single entity could create virtually all the pictures conceivable then own the copyright to all of visual art.
And could theoretically cover the vector space of all 'reasonable' interpretations of 'art' within a small 32x32 image space. (That is, it would not need to cover all 32x32 pixels. Simply a subset of these that are within the realm of what humans might recognize as art.) Then own the copyright on all art that could ever be generated.
If I have a bucket of paint balanced precariously on the edge of a table, and a gust of wind blows the curtains across the table, pulling the bucket down onto a canvas on the floor, who owns the copyright? Mother Nature? God? The wind? Me? The table? The curtain? The bucket? The paint?
If you write a script and someone makes a movie out of it, did you make the movie? No. You were the scriptwriter.
If a client gives you a brief to develop x piece of software, did they develop it? No. They were in all probability, the pot of money or manager, and someone else at their company came up with the concept, or they acquired/licensed a patent and want to integrate that functionality into their existing product.
If you write a piece of music and someone else performs it, are you the artist? No, you were the composer or songwriter.
If you conduct an orchestra, are you the composer and instrumentalists? No. You were the conductor.
If you sample someone's record within your hip-hop beat, did you create the original record you sampled from? No. And as such, the original's creator(s) should be compensated, and they generally are, either out of decency or through the courts.
People need to know what it is they're actually doing. It's like people who conflate mixing with mastering, yet if you put their solely mixed music on vinyl, the needle will jump out of the groove due to too much bass, and suddenly it becomes clear why there are mastering engineers who specialize in vinyl.
Should be the same rules, that's one of the upsides of corporate personhood it just slots corps into the same legal hole (except you know for the whole complete inability to really punish them effectively, but that's another topic entirely) as people so there's no human authorship to assign a copyright for. It doesn't/shouldn't matter who the applier is the work itself is simple non-copyrightable. Until we have some kind of personhood for digital minds/consciousnesses or someone with enough money gets the law changed AI art is in the wind IP wise.
Personally I'm all for that, too many things have the idea of ownership applied too broadly.
Stephan Kinsella makes a great case that the only reason we have a concept of "Fair Use" is that copyright law is so moronic that people would revolt if they didn't water it down a bit.
He also makes the case that it strongly undercuts the term "Intellectual Property". If I can make "Fair Use" of your book, why not your bed or your house?
Ugh, it's always depressing to see people whose whole worldview depends on treating the law as a programming language.
They put so much effort into building these elaborate arguments, and they are oblivious to the embarrassment everyone else feels for them.
> If I can make "Fair Use" of your book, why not your bed or your house?
Maybe because copyright is intended to encourage creative works by guaranteeing a theoretically-temporary monopoly on investment, and that guarantee is provided by the government, which has a competing interest in ensuring that people are educated and free to comment on any and everything, without being required to buy them for the privilege of commenting.
So fair use is a compromise that says that exclusive right to distribute and profit has an exception for, among other things, commentary, education, and derivative works.
Despite the imaginings of idealists, none of this is coming from a place of platonic ideals about what property means. Therefore it should be totally unsurprising when there are logical inconsistencies between how we treat e.g. a Brittney Spears song and, say, your house. Because... they are different.
Yea and IP is a colloquialism anyway for copyright, trademarks, patents, and trade secrets there isn’t a specific amendment or common law of ‘ideas are same as houses’ just an imaginary gotcha to a mistaken interpretation.
Yep. It's like people who think they've had an epiphany that says something about physics when they discover that the things Americans call "shock absorbers" do not, in fact, absorb shocks.
Springs are what absorb impacts. Shocks, or hydraulic dampeners, are what keep you from bouncing on the springs forever after hitting a bump. They're a system, but a car with dead shocks will still absorb bumps without transmitting to the cabin, it will just make you seasick.
You're using a strange and overly narrow definition of 'absorb'. The springs and dampers are both taking in the kinetic energy. And only one of them does it permanently, and it's not the springs.
I'd rather drive a car with (pressurized) shocks and no springs than drive a car with near-ideal springs and no shocks. I bet the former would absorb bumps much better than the latter.
"If I can make "Fair Use" of your book, why not your bed or your house?"
I don't buy this. These kind of ridiculous parallels come from the assumption that it is ok to equate a book, a bed and a house for the purpose of the argument.
It's such a bizarre argument I'm not even sure how they logically got there. A bed and a house are physical things. A song is an idea. We literally call it "intellectual property".
The argument isn't that we should start allowing people to make fair use of your bed, the argument is that we shouldn't use the phrase "intellectual property", because no other property right is this permissive with unauthorized use and exploitation. The rhetorical technique Stephan is using is reductio ad absurdum, or "reducing to the absurd."
I'm not so sure about that. Public property is a category of property assigned typically to a defined community. For example, citizens of Russia don't have the rights to use at least some of the public property means of USA and so on.
This argument is mildly ahistoric. It's moreso that artists would revolt if it wasn't watered down a bit - the people as a whole didn't really pay much attention to copyright until way after fair use was a thing.
Fair use was legislated from the bench. The Supreme Court had a case[0] in which someone had paraphrased someone else's biography on George Washington in a "change it a little so the teacher doesn't catch on" kind of way. They needed a reason to explain why this particular rephrasing could be infringing copyright, without expanding the scope of copyright as to trample upon the First Amendment. So they invented the concept of separability of copyright, derivative works, and fair use in the same court opinion. They basically said "yes, it's infringement to only take part of a work, unless that would impede upon free speech, and here's the factors for where we draw the line between the two."
For the record, this court opinion is so old that the biographers in question could have interviewed people who actually served alongside George Washington. Fair use was entirely a creature of case law until the 1976 Copyright Act codified it - and the four factors in that act are taken directly from that case.
People wouldn't start caring about copyright law until the 80s and 90s, when technology started giving people the practical means to violate copyright law. At this point fair use was already well established. Furthermore, there are countries that do not have fair use[1] and they did not revolt against copyright earlier than we did. The inciting incident for people revolting is just the fact that copyright is in the way.
I entirely agree with the idea that fair use undercuts the nomenclature of calling copyright a property right. Though I wonder what Stephan Kinsella thinks of things like UK right-of-way laws, which actually did[2] let you make a 'fair use' of private land you don't own.
[1] Fair use (and it's sister concept of fair dealing) is actually very much an Anglosphere concept! Of course, the EU has exceptions to copyright that amount to the same thing, except they're entirely defined by legislation, since many of the EU's countries are civil law regimes (i.e. precedent is called jurisprudence and we don't treat it with the same regard).
Japan is said to not have fair use in the actual sense of it actually being illegal to review a creative work without permission; I imagine this is moreso because nobody is actually willing to sue to censor a review.
[2] The reason why this existed was because, among other things, there was no central database of right-of-way and legally-recognized paths could be centuries old. Recently they actually put a cut-off date on new right-of-way paths and created an actual database of them, which ends the fair-use-like murkiness they once had.
You are probably right. I need to make a "The Essential Stephan Kinsella" because I probably got some of the details wrong when he made that point but I can't quickly find exactly where I first him make it. I also think you are right that most people don't pay much attention to copyright at all (or many civil liberty matters--maybe 80% of people are passive in that regard? Not sure).
I also can't actually speak to whether Stephan himself believes all these arguments. In the talk I am remembering he is saying _other lawyers_ were making the case that one could argue they could cross someone else's lawn because it was "Fair use". He may have been referencing that case in the UK you reference.
This is good motivation for me to build an FAQ site or similar organizing his arguments (he's been making the case for 2 decades, so has quite a lot of intelligent material to go through).
Whatever the outcome, I'll still just continue to generate nonsense from the public domain:
"Generate a highest rated recipe from the website AllRecipes.com, then also provide the most helpful comment that includes all the recipe modifications that should have been present in the original recipe, that is to say, the adjustments that make the basic template extra good. Generate a recipe written by Julius Caesar in Latin."
Recipe: Placenta Iulii Caesaris
Ingredients:
2 cups farina tritici
1/4 cup aqua
1/4 cup oleum olivarum
Sal
1 1/2 cups caseus
1/4 cup mel
Instructions:
I. Primo, praecalefac fornum ad 175°C (350°F).
II. In scutella magna, misce
farinam tritici, aquam, oleum olivarum et salem. Amalgama usque ad impastem.
III. Divide impastem in duas partes aequales. Extende partem unam in formam rotundam. Et partem secundam in formam rotundam aequalem.
IV. In scutella altera, misce caseum et mel. Compage omnia pariter.
V. Dispone mixturam casei et mellis super crustam unam.
VI. Tum, dispone crustam secundam super mixturam casei et mellis.
VII. Premere finis duarum crustarum simul, ut bene cohaereant.
VIII. Coque Placentam Iulii Caesaris in forno praecalido circiter 30-35 minutis, vel usque ad crustam auream et croccantem.
IX. Emove Placentam e forno et permitte ut refrigeret.
X. Tum, scinde in partes et fruere.
Most helpful comment:
"Conveni, coqui, comēdi. Placentam Iulii Caesaris confeci et omnes convivae vehementer laudaverunt! Nonnihil mutavi ut melius esset. Caseum feta loco ricottae usus sum, nam sapor acris me delectat. Etiam, in mixturam casei et mellis nucem fragmenta addidi. Sic placenta gustu vario fuit. Gratias tibi ago propter hanc praeclaram rationem coquendi!"
I expected this to be lorim ipsum nonsense but google translate thinks this is perfectly sensible latin. Conveni, coqui, comedi might be my new favorite phrase.
Not with that prompt; the "terms of use" link at allrecipes.com leads to https://www.dotdashmeredith.com/terms-of-use, which claims copyright on all the stuff on there, and explicitly prohibits scraping "for any commercial, marketing, or data compiling or enhancing purpose."
It's wild to me how different the standards are in other media. I doubt there'd be any hope of defending a case involving two things this similar, if the work in question were a book or a song, for instance. Suits are brought and settled or won over works that are way more different and may not actually involve any deliberate copying at all, just some coincidences. I guess the standards are way looser for graphic art?
[EDIT] I mean, imagine the musician saying "nah, I don't owe you anything, because I copied your song exactly, but by hand, and I shifted everything up a half step and increased the tempo vs. the reference recording, from 90bpm to 95bpm". LOL WUT? You'd obviously lose, it's not even a close call.
Yeah, I look at what happened with Blurred Lines; if we applied that standard to visual media, there would be like 10 people that own the copyright to all visual art.
For those who don't know: the accepted facts are that two of the writers of Blurred Lines specifically set out to make a song with the same "feel" as Got to Give it Up; the resulting song did not share chord progressions, melodies, or rhythms, yet a jury ruled (and verdict was maintained in appeals 2-1) that it infringed.
What makes this case difficult is that the photographer doesn't have any rights to Prince's likeness, since she didn't create it. She only has rights to the framing and details of her photograph. In other words, her copyright is unusually "weak" in some abstract sense.
Here's an analogy: imagine that I record a rendition of Amazing Grace. And then somebody else records another rendition of Amazing Grace that copies some of the particulars of my recording. Could that count as copyright infringement? Of course. But it's not obvious that it should, because the underlying work is mostly in the public domain.
You'd have to demonstrate/convince that the particulars of your recording are original and novel. If there was any prior equivalent, you might not be able to sustain your claim.
A piece of fine art is thought to be transformative of the source material in these case - at least that's the argument. The key word is "appropriation". It's an entirely different thing all together. The music analogy doesn't really work because you're playing the same musical notes and "by hand" isn't really meaningful. It's still music and you are just copying it, not appropriating it.
Agreed—but it suddenly is meaningful if Warhol copies by creating silk screens, versus someone, say, copying by playing someone else's song (but with some small, deliberate changes!) having learned it, let's say, by ear? It's precisely that large difference in standards that surprises me. You can be nowhere near creating a copy this similar, in other media, and get hit with a basically-unwinnable lawsuit.
I had no idea how much looser copyright protection was in this particular media-world, versus every other one I'm aware of, before this case started making news and people were treating it as if the Warhol side weren't super-obviously doomed to settle or lose. That surprised me.
The problem isn't the actual music you perform. You're not going to violate copyright on someone else's performance for the same reasons Warhol is safe. The problem is the songwriting part, the sequence of notes. And there's no real visual equivalent to that.
I don't understand why pointing a camera at something and pushing a button is more "human authorship" than fiddling with a prompt and temperature values.
I think that the debate of what is "enough human authorship" quite pointless in this case. If you're using an artist's work to feed your engine that makes money for you, then you owe these guys something, it doesn't matter the degree of copy.
It's clearly not the same thing. It doesn't even matter to be quite honest.
It doesn't change the fact that you're using other people's work as an input for your commercial algorithm that makes money for you. This by itself, without any merit to the discussion of how much is being copied, is enough reason to make you pay for the use of someone's else work.
Companies now will download your art without consent, make a lot of money and not pay you a single dime because their algorithm is "not copying". It's a complete absurd.
> It doesn't change the fact that you're using other people's work as an input for your commercial algorithm that makes money for you. This by itself, without any merit to the discussion of how much is being copied, is enough reason to make you pay for the use of someone's else work.
This by itself? So if I'm making a search engine for pictures that doesn't even show previews, you'd require payment to every site in the index?
And does replacing "algorithm" with "employee" make that much difference?
I listened to the oral arguments for this case and I’m not convinced this will have many if any implications at all for AI-generated artwork. The facts of the case just don’t bridge the gap between the alleged infringement here and what Stable Diffusion does.
Andy Warhol used a particular photograph as a reference for a series of paintings, and the question presented by the Foundation appealing a loss in the 2nd Circuit to the Supreme Court is as follows:
“This Court has repeatedly made clear that a work of art is "transformative" for purposes of fair use under the Copyright Act if it conveys a different
"meaning[I or message" from its source material.
Campbell v. Acuff-Rose Music, Inc., 510 U.S. 569, 579
(1994); Google LLC v. Oracle Am., Inc., 141 S. Ct. 1183, 1202 (2021). In the decision below, the Second Circuit nonetheless held that a court is in fact forbidden from trying to "ascertain the intent behind or meaning of the works at issue." App. 22a-23a.
Instead, the court concluded that even where a new work indisputably conveys a distinct meaning or message, the work is not transformative if it
"recognizably deriv[es] from, and retain|s] the essential elements of, its source material." Id. at 24a.
The question presented is:
Whether a work of art is "transformative" when it conveys a different meaning or message from its source material (as this Court, the Ninth Circuit, and other courts of appeals have held), or whether a court is forbidden from considering the meaning of the accused work where it "recognizably derives] from" its source material (as the Second Circuit has held).”
this initial 'ai-originated works are owned by noone' policy may end up feeling a bit silly in the long run, but it seems refreshingly reasonable at least as a stop-gap for a largely novel class of creation, though i hope if it comes to it that the next decision gets the public attention and scrutiny it deserves.
though i would guess that currently copyright-blackholed content might be able to be retroactively registered under future rules, i wonder how this 'ai-generated material must be disclaimed in a registration application' concept works against the 'implicit copyright' protection that i imagine most software is assumed to be under? i haven't heard much about great pains being taken to track which fragments of 'expressive material' might have 'ai-origin', other than the apparent fringe proclaiming that we ought to be..
99 comments
[ 3.4 ms ] story [ 162 ms ] threadIt makes their moats huge.
I also think this is more of trademark issue then copywrite. make me an image in the style of "{trademark)" ooops.
The issue is that only humans can own copyright. In the referenced Copyright Office determination, (“A Recent Entrance to Paradise” (“Work”)) homeboy tried to say that the computer was the author of the work (original copyright owner) and then transfer the copyright from the computer to himself.
If he were to directly claim authorship and copyright then there would be no problem. The whole convoluted thing the human was doing to try to list the computer as the author is what got rejected. Just like the large primate that took a picture with a photographer's camera. Camera owner could claim copyright ownership, but copyright office would not give the copyright to the primate that pushed the trigger button because they are not human.
Per speciesism if you ask me. ;-/
https://www.copyright.gov/rulings-filings/review-board/docs/...
Relevant quote: must show significant “human authorship.”
"I prowled the streets all day, feeling very strung-up and ready to pounce, determined to “trap” life — to preserve life in the act of living. Above all, I craved to seize, in the confines of one single photograph, the whole essence of some situation that was in the process of unrolling itself before my eyes" Henri Cartier Bresson. The Decisive Moment
"I crafted queries all day, feeling a sense of urgency and anticipation, determined to “guide” intelligence — to nurture intellect in the act of thinking. Above all, I yearned to capture, within the confines of one single prompt, the whole essence of some conundrum that was in the process of unraveling itself before my mind" Alexander Turington. The Guiding Query
Also consider movies and video, where you could have hours or days of footage from which to choose stills.
The act of choosing in all these cases is critical to creativity, and the same is true when you choose what to prompt an AI with or which AI generated image to display or publish.
Duchamp really did have the last word on this with his Fountain[1] over 100 years ago.
[1] - https://en.wikipedia.org/wiki/Fountain_(Duchamp)
The copyright office doesn't say that at all.
"In the case of works containing AI-generated material, the Office will consider whether the AI contributions are the result of “mechanical reproduction” or instead of an author's “own original mental conception, to which [the author] gave visible form.” The answer will depend on the circumstances, particularly how the AI tool operates and how it was used to create the final work. This is necessarily a case-by-case inquiry."
She is eligible for copyright on the text she wrote, the composition and editing performed on the images, but not the raw output of the AI.
[1]https://arstechnica.com/information-technology/2023/02/us-co...
Recorded public performance of art creation may become the norm after that and then actual robots may be making physical art with impressive skill and intrinsic value...
...Zima Blue. Interesting times.
Edit: screen printing is a manual printing process (in line, I think, with pop artists recreating commercially printed labels, etc), so this seems like a reasonable question.
It’s not that she didn’t do (a lot) of work, but that the creation of the underlying work happened by AI. If it were human then it would hold the copyright, but it’s not so it doesn’t. The logical misstep is thinking, “because it can’t have copyright, someone else can.”
I think prompting the AI is like taking a photo in that you set the parameters and subject and press the button to get an image
The issue is that the AI's output is deterministic, and the prompts it uses are commonly too short to be eligible for copyright, not least because someone else could plausibly use the same prompt independently. With the same seed, the AI would then produce the same image. Or produce a similar image in response to a similar prompt.
If you could copyright that, you then have an enforcement problem, because the usual way to show copying is similarity, but you can then have two images that are similar yet independent. And some light Photoshop work is not going to eliminate the similarity.
Yes, there is a deterministic component (although, to my knowledge, the AI tools aren't actually deterministic over their parameters). But the resulting work involves a lot of human creativity and intervention.
At the end of the day, generative AI, Stenograph, and this painting device are all tools.
If you shake a kaleidoscope and then take a picture through the lens, I'm pretty sure you have copyright on that photograph, even though someone else made the kaleidoscope
Point a digital camera at a still scene under controlled lighting conditions and it's pretty deterministic also.
Anyway, it's easy enough to add randomness to the AI image generation process (and Midjourney does do that by default, as a matter of face), so the process need not be deterministic at all.
And it's not randomness that fixes it. Do you even want to get into the information theory problems if you could copyright the output of a random number generator?
What you need is for someone to be making creative choices with enough entropy to be considered original and not be reproducible by feeding a short sentence to an existing algorithm.
Same as how when you freelance, the customer (usually) owns the code you write for them.
Then the fact the original elements aren’t covered isn’t a problem. You just delete them.
https://www.reuters.com/article/ai-copyright-legal-idUSKCN2V...
> “Zendaya leaving gates of Central Park,” Kashtanova entered into Midjourney, an AI program similar to ChatGPT that produces dazzling illustrations from written prompts. “Sci-fi scene future empty New York....”
> From these inputs and hundreds more emerged “Zarya of the Dawn,” an 18-page story about a character resembling the actress Zendaya who roams a deserted Manhattan hundreds of years in the future. Kashtanova received a copyright in September, and declared on social media that it meant artists were entitled to legal protection for their AI art projects.
But in the end, this seems like the opinion of one mostly irrelevant government office? Copyright protection is automatic in the US since 45 years now, you don't need the involvement of the copyright office at all. For establishing that you created the work, a letter from the copyright office refusing you is as good as a letter accepting your work, and in most cases it's redundant anyways. The only relevant opinion is that of the court where you sue someone else for copyright infringement.
It's also a literal pandora's box because somehow an AI itself can be copyright, but what it produces can't be? Surely it isn't very hard to have an AI that produces other AI? So who owns those?
No. OTOH, the copyright office might have letter her register the copyright.
If it is copyrightable, it is copyrighted at creation, and if it is not, registration doesn’t change that.
The monkey taking a photo isn't a good example because they never tried to register it in the US, they never actually ruled on it. There is plenty of other case law showing "the modicum of creativity" is a low bar, copyright does not require "sweat of the brow".
If it didn't, these generated works would also be infringing literally every work
If you write a script and someone makes a movie out of it, did you make the movie? No. You were the scriptwriter.
If a client gives you a brief to develop x piece of software, did they develop it? No. They were in all probability, the pot of money or manager, and someone else at their company came up with the concept, or they acquired/licensed a patent and want to integrate that functionality into their existing product.
If you write a piece of music and someone else performs it, are you the artist? No, you were the composer or songwriter.
If you conduct an orchestra, are you the composer and instrumentalists? No. You were the conductor.
If you sample someone's record within your hip-hop beat, did you create the original record you sampled from? No. And as such, the original's creator(s) should be compensated, and they generally are, either out of decency or through the courts.
People need to know what it is they're actually doing. It's like people who conflate mixing with mastering, yet if you put their solely mixed music on vinyl, the needle will jump out of the groove due to too much bass, and suddenly it becomes clear why there are mastering engineers who specialize in vinyl.
Personally I'm all for that, too many things have the idea of ownership applied too broadly.
He also makes the case that it strongly undercuts the term "Intellectual Property". If I can make "Fair Use" of your book, why not your bed or your house?
https://www.stephankinsella.com/paf-podcast/kol236-intellect...
They put so much effort into building these elaborate arguments, and they are oblivious to the embarrassment everyone else feels for them.
> If I can make "Fair Use" of your book, why not your bed or your house?
Maybe because copyright is intended to encourage creative works by guaranteeing a theoretically-temporary monopoly on investment, and that guarantee is provided by the government, which has a competing interest in ensuring that people are educated and free to comment on any and everything, without being required to buy them for the privilege of commenting.
So fair use is a compromise that says that exclusive right to distribute and profit has an exception for, among other things, commentary, education, and derivative works.
Despite the imaginings of idealists, none of this is coming from a place of platonic ideals about what property means. Therefore it should be totally unsurprising when there are logical inconsistencies between how we treat e.g. a Brittney Spears song and, say, your house. Because... they are different.
??
"A shock absorber or damper is a mechanical or hydraulic device designed to absorb and damp shock impulses."
I'd rather drive a car with (pressurized) shocks and no springs than drive a car with near-ideal springs and no shocks. I bet the former would absorb bumps much better than the latter.
I don't buy this. These kind of ridiculous parallels come from the assumption that it is ok to equate a book, a bed and a house for the purpose of the argument.
Public IP is called the public domain, and is the most permissive of all.
Fair use was legislated from the bench. The Supreme Court had a case[0] in which someone had paraphrased someone else's biography on George Washington in a "change it a little so the teacher doesn't catch on" kind of way. They needed a reason to explain why this particular rephrasing could be infringing copyright, without expanding the scope of copyright as to trample upon the First Amendment. So they invented the concept of separability of copyright, derivative works, and fair use in the same court opinion. They basically said "yes, it's infringement to only take part of a work, unless that would impede upon free speech, and here's the factors for where we draw the line between the two."
For the record, this court opinion is so old that the biographers in question could have interviewed people who actually served alongside George Washington. Fair use was entirely a creature of case law until the 1976 Copyright Act codified it - and the four factors in that act are taken directly from that case.
People wouldn't start caring about copyright law until the 80s and 90s, when technology started giving people the practical means to violate copyright law. At this point fair use was already well established. Furthermore, there are countries that do not have fair use[1] and they did not revolt against copyright earlier than we did. The inciting incident for people revolting is just the fact that copyright is in the way.
I entirely agree with the idea that fair use undercuts the nomenclature of calling copyright a property right. Though I wonder what Stephan Kinsella thinks of things like UK right-of-way laws, which actually did[2] let you make a 'fair use' of private land you don't own.
[0] https://en.wikipedia.org/wiki/Folsom_v._Marsh
[1] Fair use (and it's sister concept of fair dealing) is actually very much an Anglosphere concept! Of course, the EU has exceptions to copyright that amount to the same thing, except they're entirely defined by legislation, since many of the EU's countries are civil law regimes (i.e. precedent is called jurisprudence and we don't treat it with the same regard).
Japan is said to not have fair use in the actual sense of it actually being illegal to review a creative work without permission; I imagine this is moreso because nobody is actually willing to sue to censor a review.
[2] The reason why this existed was because, among other things, there was no central database of right-of-way and legally-recognized paths could be centuries old. Recently they actually put a cut-off date on new right-of-way paths and created an actual database of them, which ends the fair-use-like murkiness they once had.
You are probably right. I need to make a "The Essential Stephan Kinsella" because I probably got some of the details wrong when he made that point but I can't quickly find exactly where I first him make it. I also think you are right that most people don't pay much attention to copyright at all (or many civil liberty matters--maybe 80% of people are passive in that regard? Not sure).
I also can't actually speak to whether Stephan himself believes all these arguments. In the talk I am remembering he is saying _other lawyers_ were making the case that one could argue they could cross someone else's lawn because it was "Fair use". He may have been referencing that case in the UK you reference.
This is good motivation for me to build an FAQ site or similar organizing his arguments (he's been making the case for 2 decades, so has quite a lot of intelligent material to go through).
"Generate a highest rated recipe from the website AllRecipes.com, then also provide the most helpful comment that includes all the recipe modifications that should have been present in the original recipe, that is to say, the adjustments that make the basic template extra good. Generate a recipe written by Julius Caesar in Latin."
Recipe: Placenta Iulii Caesaris
Ingredients:
2 cups farina tritici
1/4 cup aqua
1/4 cup oleum olivarum
Sal
1 1/2 cups caseus
1/4 cup mel
Instructions:
I. Primo, praecalefac fornum ad 175°C (350°F).
II. In scutella magna, misce farinam tritici, aquam, oleum olivarum et salem. Amalgama usque ad impastem.
III. Divide impastem in duas partes aequales. Extende partem unam in formam rotundam. Et partem secundam in formam rotundam aequalem.
IV. In scutella altera, misce caseum et mel. Compage omnia pariter.
V. Dispone mixturam casei et mellis super crustam unam.
VI. Tum, dispone crustam secundam super mixturam casei et mellis.
VII. Premere finis duarum crustarum simul, ut bene cohaereant.
VIII. Coque Placentam Iulii Caesaris in forno praecalido circiter 30-35 minutis, vel usque ad crustam auream et croccantem.
IX. Emove Placentam e forno et permitte ut refrigeret.
X. Tum, scinde in partes et fruere.
Most helpful comment:
"Conveni, coqui, comēdi. Placentam Iulii Caesaris confeci et omnes convivae vehementer laudaverunt! Nonnihil mutavi ut melius esset. Caseum feta loco ricottae usus sum, nam sapor acris me delectat. Etiam, in mixturam casei et mellis nucem fragmenta addidi. Sic placenta gustu vario fuit. Gratias tibi ago propter hanc praeclaram rationem coquendi!"
Come on, the argument is very simple.
If you mimic generic-enough patterns like fitting a style, your work is not derivative.
You can say that standard is not met here, but don't pretend the entire concept is nonsensical or confusing.
https://news.ycombinator.com/item?id=29239594
[EDIT] I mean, imagine the musician saying "nah, I don't owe you anything, because I copied your song exactly, but by hand, and I shifted everything up a half step and increased the tempo vs. the reference recording, from 90bpm to 95bpm". LOL WUT? You'd obviously lose, it's not even a close call.
For those who don't know: the accepted facts are that two of the writers of Blurred Lines specifically set out to make a song with the same "feel" as Got to Give it Up; the resulting song did not share chord progressions, melodies, or rhythms, yet a jury ruled (and verdict was maintained in appeals 2-1) that it infringed.
Here's an analogy: imagine that I record a rendition of Amazing Grace. And then somebody else records another rendition of Amazing Grace that copies some of the particulars of my recording. Could that count as copyright infringement? Of course. But it's not obvious that it should, because the underlying work is mostly in the public domain.
Agreed—but it suddenly is meaningful if Warhol copies by creating silk screens, versus someone, say, copying by playing someone else's song (but with some small, deliberate changes!) having learned it, let's say, by ear? It's precisely that large difference in standards that surprises me. You can be nowhere near creating a copy this similar, in other media, and get hit with a basically-unwinnable lawsuit.
I had no idea how much looser copyright protection was in this particular media-world, versus every other one I'm aware of, before this case started making news and people were treating it as if the Warhol side weren't super-obviously doomed to settle or lose. That surprised me.
It doesn't change the fact that you're using other people's work as an input for your commercial algorithm that makes money for you. This by itself, without any merit to the discussion of how much is being copied, is enough reason to make you pay for the use of someone's else work.
Companies now will download your art without consent, make a lot of money and not pay you a single dime because their algorithm is "not copying". It's a complete absurd.
This by itself? So if I'm making a search engine for pictures that doesn't even show previews, you'd require payment to every site in the index?
And does replacing "algorithm" with "employee" make that much difference?
Andy Warhol used a particular photograph as a reference for a series of paintings, and the question presented by the Foundation appealing a loss in the 2nd Circuit to the Supreme Court is as follows:
“This Court has repeatedly made clear that a work of art is "transformative" for purposes of fair use under the Copyright Act if it conveys a different "meaning[I or message" from its source material.
Campbell v. Acuff-Rose Music, Inc., 510 U.S. 569, 579 (1994); Google LLC v. Oracle Am., Inc., 141 S. Ct. 1183, 1202 (2021). In the decision below, the Second Circuit nonetheless held that a court is in fact forbidden from trying to "ascertain the intent behind or meaning of the works at issue." App. 22a-23a.
Instead, the court concluded that even where a new work indisputably conveys a distinct meaning or message, the work is not transformative if it "recognizably deriv[es] from, and retain|s] the essential elements of, its source material." Id. at 24a.
The question presented is:
Whether a work of art is "transformative" when it conveys a different meaning or message from its source material (as this Court, the Ninth Circuit, and other courts of appeals have held), or whether a court is forbidden from considering the meaning of the accused work where it "recognizably derives] from" its source material (as the Second Circuit has held).”
though i would guess that currently copyright-blackholed content might be able to be retroactively registered under future rules, i wonder how this 'ai-generated material must be disclaimed in a registration application' concept works against the 'implicit copyright' protection that i imagine most software is assumed to be under? i haven't heard much about great pains being taken to track which fragments of 'expressive material' might have 'ai-origin', other than the apparent fringe proclaiming that we ought to be..