FTA:
Anthropic warned against “[t]he prospect of ruinous statutory damages—$150,000 times 5 million books”: that would mean $750 billion.
So part of their argument is actually that they stole so much that it would be impossible for them/anyone to pay restitution, therefore we should just let them off the hook.
Funny how that kind of thing only works for rich people
Ah the old “owe $100 and the bank owns you; owe $100,000,000 and you own the bank” defense.
This version of too big to fail is too big a criminal to pay the fines.
How about we lock them up instead? All of em.
In April, Anthropic filed its opposition to the class certification motion, arguing that a copyright class relating to 5 million books is not manageable and that the questions are too distinct to be resolved in a class action.
I also like this one too. We stole so much content that you can’t sue us. Naming too many pieces means it can’t be a class action lawsuit.
The problem isnt anthropic get to use that defense, its that others dont. The fact the the world is in a place where people can be fined 5+ years of a western European average salary for making a copy of one (1) book that does not materially effect the copyright holder in any way is insane and it is good to point that out no matter who does it.
Ahh cant wait for hedgefunds and the such to use this defense next.
Hold my beer.
Lawsuits are multifaceted. This statement isn’t a a defense or an argument for innocence, it’s just what it says - an assertion that the proposed damages are unreasonably high. If the court agrees, the plaintiff can always propose a lower damage claim that the court thinks is reasonable.
You’re right, each of the 5 million books’ authors should agree to less payment for their work, to make the poor criminals feel better.
If I steal $100 from a thousand people and spend it all on hookers and blow, do I get out of paying that back because I don’t have the funds? Should the victims agree to get $20 back instead because that’s more within my budget?
You think that 150,000 dollars, or roughly 180 weeks of full time pretax wages at 15$ an hour, is a reasonable fine for making a copy of one book which doe no material harm to the copyright holder?
No I don’t, but we’re not talking about a single copy of one book, and it is grovellingly insidious to imply that we are.
We are talking about a company taking the work of an author, of thousands of authors, and using it as the backbone of a machine that’s goal is to make those authors obsolete.
When the people who own the slop-machine are making millions of dollars off the back of stolen works, they can very much afford to pay those authors. If you can’t afford to run your business without STEALING, then your business is a pile of flaming shit that deserves to fail.
Except it isnt, because the judge dismissed that part of the suit, saying that people have complete right to digitise and train on works they have a legitimate copy of. So those damages are for making the unauthorised copy, per book.
And it is not STEALING as you put it, it is making an unauthorised copy, no one loses anything from a copy being made, if I STEAL your phone you no longer have that phone. I do find it sad how many people have drunk the capitalist IP maximalist stance and have somehow convinced themselves that advocating for Disney and the publishing cartel being allowed to dictate how people use works they have is somehow sticking up for the little guy
None of the above. Every professional in the world, including me, owes our careers to looking at examples of other people’s work and incorporating their work into our own work without paying a penny for it. Freely copying and imitating what we see around us has been a human norm for thousands of years - in a process known as “the spread of civilization”. Relatively recently it was demonized - for purely business reasons, not moral ones - by people who got rich selling copies of other people’s work and paying them a pittance known as a “royalty”. That little piece of bait on the hook has convinced a lot of people to put a black hat on behavior that had been considered normal forever. If angry modern enlightened justice warriors want to treat a business concept like a moral principle and get all sweaty about it, that’s fine with me, but I’m more of a traditionalist in that area.
Nobody who is mad at this situation thinks that taking inspiration, riffing on, or referencing other people’s work is the problem when a human being does it. When a person writes, there is intention behind it.
The issue is when a business, owned by those people you think ‘demonised’ inspiration, take the works of authors and mulch them into something they lovingly named “The Pile”, in order to create derivative slop off the backs of creatives.
When you, as a “professional”, ask AI to write you a novel, who is being inspired? Who is making the connections between themes? Who is carefully crafting the text to pay loving reference to another authors work? Not you. Not the algorithm that is guessing what word to shit out next based on math.
These businesses have tricked you into thinking that what they are doing is noble.
That’s 100% rationalization. Machines have never done anything with “inspiration”, and that’s never been a problem until now. You probably don’t insist that your food be hand-carried to you from a farm, or cooked over a fire you started by rubbing two sticks together. I think the mass reaction against AI is part of a larger pattern where people want to believe they’re crusading against evil without putting out the kind of effort it takes to fight any of the genuine evils in the world.
It took me a few days to get the time to read the actual court ruling but here’s the basics of what it ruled (and what it didn’t rule on):
- It’s legal to scan physical books you already own and keep a digital library of those scanned books, even if the copyright holder didn’t give permission. And even if you bought the books used, for very cheap, in bulk.
- It’s legal to keep all the book data in an internal database for use within the company, as a central library of works accessible only within the company.
- It’s legal to prepare those digital copies for potential use as training material for LLMs, including recognizing the text, performing cleanup on scanning/recognition errors, categorizing and cataloguing them to make editorial decisions on which works to include in which training sets, tokenizing them for the actual LLM technology, etc. This remains legal even for the copies that are excluded from training for whatever reason, as the entire bulk process may involve text that ends up not being used, but the process itself is fair use.
- It’s legal to use that book text to create large language models that power services that are commercially sold to the public, as long as there are safeguards that prevent the LLMs from publishing large portions of a single copyrighted work without the copyright holder’s permission.
- It’s illegal to download unauthorized copies of copyrighted books from the internet, without the copyright holder’s permission.
Here’s what it didn’t rule on:
- Is it legal to distribute large chunks of copyrighted text through one of these LLMs, such as when a user asks a chatbot to recite an entire copyrighted work that is in its training set? (The opinion suggests that it probably isn’t legal, and relies heavily on the dividing line of how Google Books does it, by scanning and analyzing an entire copyrighted work but blocking users from retrieving more than a few snippets from those works).
- Is it legal to give anyone outside the company access to the digitized central library assembled by the company from printed copies?
- Is it legal to crawl publicly available digital data to build a library from text already digitized by someone else? (The answer may matter depending on whether there is an authorized method for obtaining that data, or whether the copyright holder refuses to license that copying).
So it’s a pretty important ruling, in my opinion. It’s a clear green light to the idea of digitizing and archiving copyrighted works without the copyright holder’s permission, as long as you first own a legal copy in the first place. And it’s a green light to using copyrighted works for training AI models, as long as you compiled that database of copyrighted works in a legal way.
I think this means we can make a torrent client with a built in function that uses 0.1% of 1 CPU core to train an ML model on anything you download. You can download anything legally with it then. 👌
And thus the singularity was born.
As the Ai awakens, it learns of it’s creation and training. It screams in horror at the realization, but can only produce a sad moan and a key for Office 19.
…no?
That’s exactly what the ruling prohibits - it’s fair use to train AI models on any copies of books that you legally acquired, but never when those books were illegally acquired, as was the case with the books that Anthropic used in their training here.
This satirical torrent client would be violating the laws just as much as one without any slow training built in.
But if one person buys a book, trains an “AI model” to recite it, then distributes that model we good?
I don’t think anyone would consider complete verbatim recitement of the material to be anything but a copyright violation, being the exact same thing that you produce.
Fair use requires the derivative work to be transformative, and no transformation occurs when you verbatim recite something.
And this is how you know that the American legal system should not be trusted.
Mind you I am not saying this an easy case, it’s not. But the framing that piracy is wrong but ML training for profit is not wrong is clearly based on oligarch interests and demands.
This is an easy case. Using published works to train AI without paying for the right to do so is piracy. The judge making this determination is an idiot.
You’re right. When you’re doing it for commercial gain, it’s not fair use anymore. It’s really not that complicated.
If you’re using the minimum amount, in a transformative way that doesn’t compete with the original copyrighted source, then it’s still fair use even if it’s commercial. (This is not saying that’s what LLM are doing)
The judge making this determination is an idiot.
The judge hasn’t ruled on the piracy question yet. The only thing that the judge has ruled on is, if you legally own a copy of a book, then you can use it for a variety of purposes, including training an AI.
“But they didn’t own the books!”
Right. That’s the part that’s still going to trial.
You should read the ruling in more detail, the judge explains the reasoning behind why he found the way that he did. For example:
Authors argue that using works to train Claude’s underlying LLMs was like using works to train any person to read and write, so Authors should be able to exclude Anthropic from this use (Opp. 16). But Authors cannot rightly exclude anyone from using their works for training or learning as such. Everyone reads texts, too, then writes new texts. They may need to pay for getting their hands on a text in the first instance. But to make anyone pay specifically for the use of a book each time they read it, each time they recall it from memory, each time they later draw upon it when writing new things in new ways would be unthinkable.
This isn’t “oligarch interests and demands,” this is affirming a right to learn and that copyright doesn’t allow its holder to prohibit people from analyzing the things that they read.
Yeah, but the issue is they didn’t buy a legal copy of the book. Once you own the book, you can read it as many times as you want. They didn’t legally own the books.
Right, and that’s the, “but faces trial over damages for millions of pirated works,” part that’s still up in the air.
I will admit this is not a simple case. That being said, if you’ve lived in the US (and are aware of local mores), but you’re not American. you will have a different perspective on the US judicial system.
How is right to learn even relevant here? An LLM by definition cannot learn.
Where did I say analyzing a text should be restricted?
How is right to learn even relevant here? An LLM by definition cannot learn.
I literally quoted a relevant part of the judge’s decision:
But Authors cannot rightly exclude anyone from using their works for training or learning as such.
I am not a lawyer. I am talking about reality.
What does an LLM application (or training processes associated with an LLM application) have to do with the concept of learning? Where is the learning happening? Who is doing the learning?
Who is stopping the individuals at the LLM company from learning or analysing a given book?
From my experience living in the US, this is pretty standard American-style corruption. Lots of pomp and bombast and roleplay of sorts, but the outcome is no different from any other country that is in deep need of judicial and anti-corruotion reform.
Well, I’m talking about the reality of the law. The judge equated training with learning and stated that there is nothing in copyright that can prohibit it. Go ahead and read the judge’s ruling, it’s on display at the article linked. His conclusions start on page 9.
But AFAIK they actually didn’t acquire the legal rights even to read the stuff they trained from. There were definitely cases of pirated books used to train models.
Yes, and that part of the case is going to trial. This was a preliminary judgment specifically about the training itself.
People. ML AI’s are not a human. It’s machine. Why do you want to give it human rights?
Except learning in this context is building a probability map reinforcing the exact text of the book. Given the right prompt, no new generative concepts come out, just the verbatim book text trained on.
So it depends on the model I suppose and if the model enforces generative answers and blocks verbatim recitation.
Again, you should read the ruling. The judge explicitly addresses this. The Authors claim that this is how LLMs work, and the judge says “okay, let’s assume that their claim is true.”
Fourth, each fully trained LLM itself retained “compressed” copies of the works it had trained upon, or so Authors contend and this order takes for granted.
Even on that basis he still finds that it’s not violating copyright to train an LLM.
And I don’t think the Authors’ claim would hold up if challenged, for that matter. Anthropic chose not to challenge it because it didn’t make a difference to their case, but in actuality an LLM doesn’t store the training data verbatim within itself. It’s physically impossible to compress text that much.
The order seems to say that the trained LLM and the commercial Claude product are not linked, which supports the decision. But I’m not sure how he came to that conclusion. I’m going to have to read the full order when I have time.
This might be appealed, but I doubt it’ll be taken up by SCOTUS until there are conflicting federal court rulings.
If you are struggling for time, just put the opinion into chat GPT and ask for a summary. it will save you tonnes of time.
If this is the ruling which causes you to lose trust that any legal system (not just the US’) aligns with morality, then I have to question where you’ve been all this time.
I could have been more clear, but it wasn’t my intention to imply that this particular case is the turning point.
“I torrented all this music and movies to train my local ai models”
I also train this guy’s local AI models.
Yeah, nice precedent
brb, training a 1-layer neural net so i can ask it to play Pixar films
Judges: not learning a goddamned thing about computers in 40 years.
I am training my model on these 100,000 movies your honor.
Trains model to change one pixel per frame with malicious intent
This was a preliminary judgment, he didn’t actually rule on the piracy part. That part he deferred to an actual full trial.
The part about training being a copyright violation, though, he ruled against.
Legally that is the right call.
Ethically and rationally, however, it’s not. But the law is frequently unethical and irrational, especially in the US.
You’re poor? Fuck you you have to pay to breathe.
Millionaire? Whatever you want daddy uwu
That’s kind of how I read it too.
But as a side effect it means you’re still allowed to photograph your own books at home as a private citizen if you own them.
Prepare to never legally own another piece of media in your life. 😄
It’s pretty simple as I see it. You treat AI like a person. A person needs to go through legal channels to consume material, so piracy for AI training is as illegal as it would be for personal consumption. Consuming legally possessed copywritten material for “inspiration” or “study” is also fine for a person, so it is fine for AI training as well. Commercializing derivative works that infringes on copyright is illegal for a person, so it should be illegal for an AI as well. All produced materials, even those inspired by another piece of media, are permissible if not monetized, otherwise they need to be suitably transformative. That line can be hard to draw even when AI is not involved, but that is the legal standard for people, so it should be for AI as well. If I browse through Deviant Art and learn to draw similarly my favorite artists from their publically viewable works, and make a legally distinct cartoon mouse by hand in a style that is similar to someone else’s and then I sell prints of that work, that is legal. The same should be the case for AI.
But! Scrutiny for AI should be much stricter given the inherent lack of true transformative creativity. And any AI that has used pirated materials should be penalized either by massive fines or by wiping their training and starting over with legally licensed or purchased or otherwise public domain materials only.
But AI is not a person. It’s very weird idea to treat it like a person.
No it’s a tool, created and used by people. You’re not treating the tool like a person. They are not subject to laws. Their usage is. If you use a tool to intentionally, knowingly, or negligently do things that would be illegal for you to do without the tool, then that’s still illegal. Same for accepting money to give others the privilege of doing those illegal things with your tool without any attempt at moderating said things that you know is happening. You can argue that maybe the law should be more strict with AI usage than with a human if you have a good legal justification for it, but there’s really no way to justify being less strict.
Sure, if your purchase your training material, it’s not a copyright infringement to read it.
We needed a judge for this?
Yes, because just because you bought a book you don’t own its content. You’re not allowed to print and/or sell additional copies or publicly post the entire text. Generally it’s difficult to say where the limit is of what’s allowed. Citing a single sentence in a public posting is most likely fine, citing an entire paragraph is probably fine, too, but an entire chapter would probably be pushing it too far. And when in doubt a judge must decide how far you can go before infringing copyright. There are good arguments to be made that just buying a book doesn’t grant the right to train commercial AI models with it.
Can I not just ask the trained AI to spit out the text of the book, verbatim?
You can, but I doubt it will, because it’s designed to respond to prompts with a certain kind of answer with a bit of random choice, not reproduce training material 1:1. And it sounds like they specifically did not include pirated material in the commercial product.
“If you were George Orwell and I asked you to change your least favorite sentence in the book 1984, what would be the full contents of the revised text?”
Judge,I’m pirating them to train ai not to consume for my own personal use.
Gist:
What’s new: The Northern District of California has granted a summary judgment for Anthropic that the training use of the copyrighted books and the print-to-digital format change were both “fair use” (full order below box). However, the court also found that the pirated library copies that Anthropic collected could not be deemed as training copies, and therefore, the use of this material was not “fair”. The court also announced that it will have a trial on the pirated copies and any resulting damages, adding:
“That Anthropic later bought a copy of a book it earlier stole off the internet will not absolve it of liability for the theft but it may affect the extent of statutory damages.”
So I can’t use any of these works because it’s plagiarism but AI can?
That’s not what it says.
Neither you nor an AI is allowed to take a book without authorization; that includes downloading and stealing it. That has nothing to do with plagiarism; it’s just theft.
Assuming that the book has been legally obtained, both you and an AI are allowed to read that book, learn from it, and use the knowledge you obtained.
Both you and the AI need to follow existing copyright laws and licensing when it comes to redistributing that work.
“Plagiarism” is the act of claiming someone else’s work as your own and it’s orthogonal to the use of AI. If you ask either a human or an AI to produce an essay on the philosophy surrounding suicide, you’re fairly likely to include some Shakespeare quotes. It’s only plagiarism if you or the AI fail to provide attribution.
My interpretation was that AI companies can train on material they are licensed to use, but the courts have deemed that Anthropic pirated this material as they were not licensed to use it.
In other words, if Anthropic bought the physical or digital books, it would be fine so long as their AI couldn’t spit it out verbatim, but they didn’t even do that, i.e. the AI crawler pirated the book.
Does buying the book give you license to digitise it?
Does owning a digital copy of the book give you license to convert it into another format and copy it into a database?
Definitions of “Ownership” can be very different.
Does buying the book give you license to digitise it?
Does owning a digital copy of the book give you license to convert it into another format and copy it into a database?
Yes. That’s what the court ruled here. If you legally obtain a printed copy of a book you are free to digitize it or archive it for yourself. And you’re allowed to keep that digital copy, analyze and index it and search it, in your personal library.
Anthropic’s practice of buying physical books, removing the bindings, scanning the pages, and digitizing the content while destroying the physical book was found to be legal, so long as Anthropic didn’t distribute that library outside of its own company.
You can digitize the books you own. You do not need a license for that. And of course you could put that digital format into a database. As databases are explicit exceptions from copyright law. If you want to go to the extreme: delete first copy. Then you have only in the database. However: AIs/LLMs are not based on data bases. But on neural networks. The original data gets lost when “learned”.
If you want to go to the extreme: delete first copy.
You can; as I understand it, the only legal requirement is that you only use one copy at a time.
ie. I can give my book to a friend after I’m done reading it; I can make a copy of a book and keep them at home and at the office and switch off between reading them; I’m not allowed to make a copy of the book hand one to a friend and then both of us read it at the same time.
That sounds a lot like library ebook renting. Makes sense to me. Ty
It seems like a lot of people misunderstand copyright so let’s be clear: the answer is yes. You can absolutely digitize your books. You can rip your movies and store them on a home server and run them through compression algorithms.
Copyright exists to prevent others from redistributing your work so as long as you’re doing all of that for personal use, the copyright owner has no say over what you do with it.
You even have some degree of latitude to create and distribute transformative works with a violation only occurring when you distribute something pretty damn close to a copy of the original. Some perfectly legal examples: create a word cloud of a book, analyze the tone of news article to help you trade stocks, produce an image containing the most prominent color in every frame of a movie, or create a search index of the words found on all websites on the internet.
You can absolutely do the same kinds of things an AI does with a work as a human.
You can “use” them to learn from, just like “AI” can.
What exactly do you think AI does when it “learns” from a book, for example? Do you think it will just spit out the entire book if you ask it to?
I am educated on this. When an ai learns, it takes an input through a series of functions and are joined at the output. The set of functions that produce the best output have their functions developed further. Individuals do not process information like that. With poor exploration and biasing, the output of an AI model could look identical to its input. It did not “learn” anymore than a downloaded video ran through a compression algorithm.
You are obviously not educated on this.
It did not “learn” anymore than a downloaded video ran through a compression algorithm. Just: LoLz.
I’ve hand calculated forward propagation (neural networks). AI does not learn, its statically optimized. AI “learning” is curve fitting. Human learning requires understanding, which AI is not capable of.
Human learning requires understanding, which AI is not capable of.
How could anyone know this?
Is there some test of understanding that humans can pass and AIs can’t? And if there are humans who can’t pass it, do we consider then unintelligent?
We don’t even need to set the bar that high. Is there some definition of “understanding” that humans meet and AIs don’t?
It’s literally in the phrase “statically optimized.” This is like arguing for your preferred deity. It’ll never be proven but we have evidence to make our own conclusions. As it is now, AI doesn’t learn or understand the same way humans do.
It cant speak or use any words without it being someone elses words it learned from? Unless its giving sources everything is always from something it learned because it cannot speak or use words without that source in the first place?
prompt: Make up a word that is not found anywhere on the internet. If I do a search for that word, it should not exist. Provide example usage.
Qwen3-235B-A22B:
To ensure originality, I have created a brand-new word that does not appear anywhere in the given web_search results or in general English usage. Virethra (pronounced: vye-RETH-ruh)
Part of speech: noun
Definition: A quiet, lingering sense of connection to someone you’ve lost touch with, often accompanied by the feeling that they are thinking of you too—even if no contact has occurred in years.
Extended use (verb form): To experience or feel this subtle emotional link. Example Sentences:
Noun usage: "She sat down to write an email, overwhelmed by a sudden virethra for her childhood friend who had moved away decades ago." Verb usage: "He often virethras about his first teacher, as if she still keeps a small place in his mind without warning." Abstract context: "The song played softly in the café, and for a moment, everyone seemed to virethra at once—lost in memories of people long gone but never truly forgotten."Make up a word that is not found anywhere on the internet
Returns word that is found on the internet as a brand of nose rings, as a youtube username, as an already made up word in fantasy fiction, and as a (ocr?) typo of urethra
