You’re poor? Fuck you you have to pay to breathe.
Millionaire? Whatever you want daddy uwu
Check out my new site TheAIBay, you search for content and an LLM that was trained on reproducing it gives it to you, a small hash check is used to validate accuracy. It is now legal.
Does it “generate” a 1:1 copy?
Learning
Machine peepin’ is tha study of programs dat can improve they performizzle on a given task automatically.[41] It has been a part of AI from tha beginning.[e] In supervised peepin’, tha hustlin data is labelled wit tha expected lyrics, while up in unsupervised peepin’, tha model identifies patterns or structures up in unlabelled data.
There is nuff muthafuckin kindz of machine peepin’.
😗👌
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.
i will train my jailbroken kindle too…display and storage training… i’ll just libgen them…no worries…it is not piracy
why do you even jailbreak your kindle? you can still read pirated books on them if you connect it to your pc using calibre
Of course we have to have a way to manually check the training data, in detail, as well. Not reading the book, im just verifying training data.
But I thought they admitted to torrenting terabytes of ebooks?
That part is not what this preliminary jugement is about. The torrenting part is going to go to an actual trial. This part was about the Authors’ claim that the act of training AI itself violated copyright, and this is what the judge has found to be incorrect.
FaceBook did but technically downloading (leeching) isn’t illegal but distributing (seeding) is and they did not seed.
Facebook (Meta) torrented TBs from Libgen, and their internal chats leaked so we know about that, and IIRC they’ve been sued. Maybe you’re thinking of that case?
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.
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 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.
Why would it be plagiarism if you use the knowledge you gain from a book?
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 am not sure what your contention, or gotcha, is with the comment above but they are quite correct. And additionally chose quite an apt example with video compression since in most ways current ‘AI’ effectively functions as a compression algorithm, just for our language corpora instead of video.
They seem pretty different to me.
Video compression developers go through a lot of effort to make them deterministic. We don’t necessarily care that a particular video stream compresses to a particular bit sequence but we very much care that the resulting decompression gets you as close to the original as possible.
AIs will rarely produce exact replicas of anything. They synthesize outputs from heterogeneous training data. That sounds like learning to me.
The one area where there’s some similarity is dimensionality reduction. Its technically a form of compression, since it makes your files smaller. It would also be an extremely expensive way to get extremely bad compression. It would take orders of magnitude more hardware resources and the images are likely to be unrecognizable.
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
Formatting thing: if you start a line in a new paragraph with four spaces, it assumes that you want to display the text as a code and won’t line break.
This means that the last part of your comment is a long line that people need to scroll to see. If you remove one of the spaces, or you remove the empty line between it and the previous paragraph, it’ll look like a normal comment
With an empty line of space:
1 space - and a little bit of writing just to see how the text will wrap. I don’t really have anything that I want to put here, but I need to put enough here to make it long enough to wrap around. This is likely enough.
2 spaces - and a little bit of writing just to see how the text will wrap. I don’t really have anything that I want to put here, but I need to put enough here to make it long enough to wrap around. This is likely enough.
3 spaces - and a little bit of writing just to see how the text will wrap. I don’t really have anything that I want to put here, but I need to put enough here to make it long enough to wrap around. This is likely enough.
4 spaces - and a little bit of writing just to see how the text will wrap. I don't really have anything that I want to put here, but I need to put enough here to make it long enough to wrap around. This is likely enough.Personally I prefer to explicitly wrap the text in backticks.
Three ` symbols will
Have the same effectBut the behavior is more clear to the author
Thanks, I had copy-pasted it from the website :)
Ok so you can buy books scan them or ebooks and use for AI training but you can’t just download priated books from internet to train AI. Did I understood that correctly ?
That’s my understanding too. If you obtained them legally, you can use them the same way anyone else who obtained them legally could use them.
Make an AI that is trained on the books.
Tell it to tell you a story for one of the books.
Read the story without paying for it.
The law says this is ok now, right?
Sort of.
If you violated laws in obtaining the book (eg stole or downloaded it without permission) it’s illegal and you’ve already violated the law, no matter what you do after that.
If you obtain the book legally you can do whatever you want with that book, by the first sale doctrine. If you want to redistribute the book, you need the proper license. You don’t need any licensing to create a derivative work. That work has to be “sufficiently transformed” in order to pass.
The LLM is not repeating the same book. The owner of the LLM has the exact same rights to do with what his LLM is reading, as you have to do with what ever YOU are reading.
As long as it is not a verbatim recitation, it is completely okay.
According to story telling theory: there are only roughly 15 different story types anyway.
As long as they don’t use exactly the same words in the book, yeah, as I understand it.
How they don’t use same words as in the book ? That’s not how LLM works. They use exactly same words if the probabilities align. It’s proved by this study. https://arxiv.org/abs/2505.12546
I’d say there are two issues with it.
FIrst, it’s a very new article with only 3 citations. The authors seem like serious researchers but the paper itself is still in the, “hot off the presses” stage and wouldn’t qualify as “proven” yet.
It also doesn’t exactly say that books are copies. It says that in some models, it’s possible to extract some portions of some texts. They cite “1984” and “Harry Potter” as two books that can be extracted almost entirely, under some circumstances. They also find that, in general, extraction rates are below 1%.
Yeah but it’s just a start to reverse the process and prove that there is no AI. We only started with generating text I bet people figure out how to reverse process by using some sort of Rosetta Stone. It’s just probabilities after all.
That’s possible but it’s not what the authors found.
They spend a fair amount of the conclusion emphasizing how exploratory and ambiguous their findings are. The researchers themselves are very careful to point out that this is not a smoking gun.
Yeah authors rely on the recent deep mind paper https://aclanthology.org/2025.naacl-long.469.pdf ( they even cite it ) that describes (n, p)-discoverable extraction. This is recent studies because right now there are no boundaries, basically people made something and now they study their creation. We’re probably years from something like gdpr for llm.
The “if” is working overtime in your statement
Makes sense. AI can “learn” from and “read” a book in the same way a person can and does, as long as it is acquired legally. AI doesn’t reproduce a work that it “learns” from, so why would it be illegal?
Some people just see “AI” and want everything about it outlawed basically. If you put some information out into the public, you don’t get to decide who does and doesn’t consume and learn from it. If a machine can replicate your writing style because it could identify certain patterns, words, sentence structure, etc then as long as it’s not pretending to create things attributed to you, there’s no issue.
Ask a human to draw an orc. How do they know what an orc looks like? They read Tolkien’s books and were “inspired” Peter Jackson’s LOTR.
Unpopular opinion, but that’s how our brains work.
Fuck you, I won’t do what you tell me!
>.>
<.<
spoiler
I was inspired by the sometimes hilarious dnd splatbooks, thank you very much.
AI can “learn” from and “read” a book in the same way a person can and does
This statement is the basis for your argument and it is simply not correct.
Training LLMs and similar AI models is much closer to a sophisticated lossy compression algorithm than it is to human learning. The processes are not at all similar given our current understanding of human learning.
AI doesn’t reproduce a work that it “learns” from, so why would it be illegal?
The current Disney lawsuit against Midjourney is illustrative - literally, it includes numerous side-by-side comparisons - of how AI models are capable of recreating iconic copyrighted work that is indistinguishable from the original.
If a machine can replicate your writing style because it could identify certain patterns, words, sentence structure, etc then as long as it’s not pretending to create things attributed to you, there’s no issue.
An AI doesn’t create works on its own. A human instructs AI to do so. Attribution is also irrelevant. If a human uses AI to recreate the exact tone, structure and other nuances of say, some best selling author, they harm the marketability of the original works which fails fair use tests (at least in the US).
Even if we accept all your market liberal premise without question… in your own rhetorical framework the Disney lawsuit should be ruled against Disney.
If a human uses AI to recreate the exact tone, structure and other nuances of say, some best selling author, they harm the marketability of the original works which fails fair use tests (at least in the US).
Says who? In a free market why is the competition from similar products and brands such a threat as to be outlawed? Think reasonably about what you are advocating… you think authorship is so valuable or so special that one should be granted a legally enforceable monopoly at the loosest notions of authorship. This is the definition of a slippery-slope, and yet, it is the status quo of the society we live in.
On it “harming marketability of the original works,” frankly, that’s a fiction and anyone advocating such ideas should just fucking weep about it instead of enforce overreaching laws on the rest of us. If you can’t sell your art because a machine made “too good a copy” of your art, it wasn’t good art in the first place and that is not the fault of the machine. Even big pharma doesn’t get to outright ban generic medications (even tho they certainly tried)… it is patently fucking absurd to decry artist’s lack of a state-enforced monopoly on their work. Why do you think we should extend such a radical policy towards… checks notes… tumblr artists and other commission based creators? It’s not good when big companies do it for themselves through lobbying, it wouldn’t be good to do it for “the little guy,” either. The real artists working in industry don’t want to change the law this way because they know it doesn’t work in their favor. Disney’s lawsuit is in the interest of Disney and big capital, not artists themselves, despite what these large conglomerates that trade in IPs and dreams might try to convince the art world writ large of.
you think authorship is so valuable or so special that one should be granted a legally enforceable monopoly at the loosest notions of authorship
Yes, I believe creative works should be protected as that expression has value and in a digital world it is too simple to copy and deprive the original author of the value of their work. This applies equally to Disney and Tumblr artists.
I think without some agreement on the value of authorship / creation of original works, it’s pointless to respond to the rest of your argument.
I think without some agreement on the value of authorship / creation of original works, it’s pointless to respond to the rest of your argument.
I agree, for this reason we’re unlikely to convince each other of much or find any sort of common ground. I don’t think that necessarily means there isn’t value in discourse tho. We probably agree more than you might think. I do think authors should be compensated, just for their actual labor. Art itself is functionally worthless, I think trying to make it behave like commodities that have actual economic value through means of legislation is overreach. It would be more ethical to accept the physical nature of information in the real world and legislate around that reality. You… literally can “download a car” nowadays, so to speak.
If copying someone’s work is so easily done why do you insist upon a system in which such an act is so harmful to the creators you care about?
Because it is harmful to the creators that use the value of their work to make a living.
There already exists a choice in the marketplace: creators can attach a permissive license to their work if they want to. Some do, but many do not. Why do you suppose that is?
Your very first statement calling my basis for my argument incorrect is incorrect lol.
LLMs “learn” things from the content they consume. They don’t just take the content in wholesale and keep it there to regurgitate on command.
On your last part, unless someone uses AI to recreate the tone etc of a best selling author *and then markets their book/writing as being from said best selling author, and doesn’t use trademarked characters etc, there’s no issue. You can’t copyright a style of writing.
I’ll repeat what you said with emphasis:
AI can “learn” from and “read” a book in the same way a person can and does
The emphasized part is incorrect. It’s not the same, yet your argument seems to be that because (your claim) it is the same, then it’s no different from a human reading all of these books.
Regarding your last point, copyright law doesn’t just kick in because you try to pass something off as an original (by, for ex, marketing a book as being from a best selling author). It applies based on similarity whether you mention the original author or not.
If what you are saying is true, why were these ‘AI’s” incapable of rendering a full wine glass? It ‘knows’ the concept of a full glass of water, but because of humanities social pressures, a full wine glass being the epitome of gluttony, art work did not depict a full wine glass, no matter how ai prompters demanded, it was unable to link the concepts until it was literally created for it to regurgitate it out. It seems ‘AI’ doesn’t really learn, but regurgitates art out in collages of taken assets, smoothed over at the seams.
“it was unable to link the concepts until it was literally created for it to regurgitate it out“
-WraithGear
The’ problem was solved before their patch. But the article just said that the model is changed by running it through a post check. Just like what deep seek does. It does not talk about the fundamental flaw in how it creates, they assert if does, like they always did
I don’t see what distinction you’re trying to draw here. It previously had trouble generating full glasses of wine, they made some changes, now it can. As a result, AIs are capable of generating an image of a full wine glass.
This is just another goalpost that’s been blown past, like the “AI will never be able to draw hands correctly” thing that was so popular back in the day. Now AIs are quite good at drawing hands, and so new “but they can’t do X!” Standards have been invented. I see no fundamental reason why any of those standards won’t ultimately be surpassed.
Copilot did it just fine
1 it’s not full, but closer then it was.
- I specifically said that the AI was unable to do it until someone specifically made a reference so that it could start passing the test so it’s a little bit late to prove much.
The concept of a glass being full and of a liquid being wine can probably be separated fairly well. I assume that as models got more complex they started being able to do this more.
You mean when the training data becomes more complete. But that’s the thing, when this issue was being tested, the’AI’ would swear up and down that the normally filled wine glasses were full, when it was pointed out that it was not indeed full, the ‘AI’ would agree, and change some other aspect of the picture it didn’t fully understand. You got wine glasses where the wine would half phase out of the bounds of the cup. And yet still be just as empty. No amount of additional checks will help without an appropriate reference
I use ‘AI’ extensively, i have one running locally on my computer, i swap out from time to time. I don’t have anything against its use with certain exceptions. But i can not stand people personifying it beyond its scope
Here is a good example. I am working on an APP so every once in a wile i will send it code to check. But i have to be very careful. The code it spits out will be unoptimized like: variable1=IF (variable2 IS true, true, false) .
Some have issues with object permanence, or the consideration of time outside its training data. Its like saying a computer can generate a true random number, by making the function to calculate a number more convoluted.
Bro are you a robot yourself? Does that look like a glass full of wine?
If someone ask for a glass of water you don’t fill it all the way to the edge. This is way overfull compared to what you’re supposed to serve.
AI can “learn” from and “read” a book in the same way a person can and does,
If it’s in the same way, then why do you need the quotation marks? Even you understand that they’re not the same.
And either way, machine learning is different from human learning in so many ways it’s ridiculous to even discuss the topic.
AI doesn’t reproduce a work that it “learns” from
That depends on the model and the amount of data it has been trained on. I remember the first public model of ChatGPT producing a sentence that was just one word different from what I found by googling the text (from some scientific article summary, so not a trivial sentence that could line up accidentally). More recently, there was a widely reported-on study of AI-generated poetry where the model was requested to produce a poem in the style of Chaucer, and then produced a letter-for-letter reproduction of the well-known opening of the Canterbury Tales. It hasn’t been trained on enough Middle English poetry and thus can’t generate any of it, so it defaulted to copying a text that probably occurred dozens of times in its training data.
It’s extremely frustrating to read this comment thread because it’s obvious that so many of you didn’t actually read the article, or even half-skim the article, or even attempted to even comprehend the title of the article for more than a second.
For shame.
was gonna say, this seems like the best outcome for this particular trial. there was potential for fair use to be compromised, and for piracy to be legal if you’re a large corporation. instead, they upheld that you can do what you want with things you have paid for.
I joined lemmy specifically to avoid this reddit mindset of jumping to conclusions after reading a headline
Guess some things never change…
Well to be honest lemmy is less prone to knee-jerk reactionary discussion but on a handful of topics it is virtually guaranteed to happen no matter what, even here. For example, this entire site, besides a handful of communities, is vigorously anti-AI; and in the words of u/[email protected] elsewhere in this comment chain:
“It seems the subject of AI causes lemmites to lose all their braincells.”
I think there is definitely an interesting take on the sociology of the digital age in here somewhere but it’s too early in the morning to be tapping something like that out lol
It seems the subject of AI causes lemmites to lose all their braincells.
Nobody ever reads articles, everybody likes to get angry at headlines, which they wrongly interpret the way it best tickles their rage.
Regarding the ruling, I agree with you that it’s a good thing, in my opinion it makes a lot of sense to allow fair use in this case
“While the copies used to convert purchased print library copies into digital library copies were slightly disfavored by the second factor (nature of the work), the court still found “on balance” that it was a fair use because the purchased print copy was destroyed and its digital replacement was not redistributed.”
So you find this to be valid? To me it is absolutely being redistributed
What a bad judge.
This is another indication of how Copyright laws are bad. The whole premise of copyright has been obsolete since the proliferation of the internet.
What a bad judge.
Why ? Basically he simply stated that you can use whatever material you want to train your model as long as you ask the permission to use it (and presumably pay for it) to the author (or copytight holder)
“Fair use” is the exact opposite of what you’re saying here. It says that you don’t need to ask for any permission. The judge ruled that obtaining illegitimate copies was unlawful but use without the creators consent is perfectly fine.
If I understand correctly they are ruling you can by a book once, and redistribute the information to as many people you want without consequences. Aka 1 student should be able to buy a textbook and redistribute it to all other students for free. (Yet the rules only work for companies apparently, as the students would still be committing a crime)
They may be trying to put safeguards so it isn’t directly happening, but here is an example that the text is there word for word:
If I understand correctly they are ruling you can by a book once, and redistribute the information to as many people you want without consequences. Aka 1 student should be able to buy a textbook and redistribute it to all other students for free. (Yet the rules only work for companies apparently, as the students would still be committing a crime)
A student can absolutely buy a text book and then teach the other students the information in it for free. That’s not redistribution. Redistribution would mean making copies of the book to hand out. That’s illegal for people and companies.
The language model isn’t teaching anything it is changing the wording of something and spitting it back out. And in some cases, not changing the wording at all, just spitting the information back out, without paying the copyright source. It is not alive, it has no thoughts. It has no “its own words.” (As seen by the judgement that its words cannot be copyrighted.) It only has other people’s words. Every word it spits out by definition is plagiarism, whether the work was copyrighted before or not.
People wonder why works, such as journalism are getting worse. Well how could they ever get better if anything a journalist writes can be absorbed in real time, reworded and regurgitated without paying any dos to the original source. One journalist article, displayed in 30 versions, dividing the original works worth up into 30 portions. The original work now being worth 1/30th its original value. Maybe one can argue it is twice as good, so 1/15th.
Long term it means all original creations… Are devalued and therefore not nearly worth pursuing. So we will only get shittier and shittier information. Every research project… Physics, Chemistry, Psychology, all technological advancements, slowly degraded as language models get better, and original sources deminish returns.
That’s not at all what this ruling says, or what LLMs do.
Copyright covers a specific concrete expression. It doesn’t cover the information that the expression conveys. So if I paint a portrait of myself, that portrait is covered by copyright. If someone looks at the portrait and says “this is a portrait of a tall, dark, handsome deer-creature of some sort with awesome antlers” they haven’t violated that copyright even if they’re accurately conveying the same information that the portrait is conveying.
The ruling does cover the assumption that the LLM “contains” the training text, which was asserted by the Authors and was not contested by Anthropic. The judge ruled that even if this assertion is true it doesn’t matter. The LLM is sufficiently transformative to count as a new work.
If you have an LLM reproduce a copyrighted text, the text is still copyrighted. That doesn’t change. Just like if a human re-wrote it word-for-word from memory.
It’s a horrible ruling. If you want to see why I say so I put some of the reasonung in the other comment who responded to that.
If I understand correctly they are ruling you can by a book once, and redistribute the information to as many people you want without consequences. Aka 1 student should be able to buy a textbook and redistribute it to all other students for free. (Yet the rules only work for companies apparently, as the students would still be committing a crime)
Well, it would be interesting if this case would be used as precedence in a case invonving a single student that do the same thing. But you are right
This was my understanding also, and why I think the judge is bad at their job.
I suppose someone could develop an LLM that digests textbooks, and rewords the text and spits it back out. Then distribute it for free page for page. You can’t copy right the math problems I don’t think… so if the text wording is what gives it credence, that would have been changed.
If a human did that it’s still plagiarism.
Oh I agree it should be, but following the judges ruling, I don’t see how it could be. You trained an LLM on textbooks that were purchased, not pirated. And the LLM distributed the responses.
(Unless you mean the human reworded them, then yeah, we aren’t special apparently)
Not at all true. AI doesn’t just reproduce content it was trained on on demand.
It can, the only thing stopping it is if it is specifically told not to, and this consideration is successfully checked for. It is completely capable of plagiarizing otherwise.
For the purposes of this ruling it doesn’t actually matter. The Authors claimed that this was the case and the judge said “sure, for purposes of argument I’ll assume that this is indeed the case.” It didn’t change the outcome.
I mean, they can assume fantasy, and it will hold weight because laws are interpreted by the court, not because the court is correct.
It made the ruling stronger, not weaker. The judge was accepting the most extreme claims that the Authors were making and still finding no copyright violation from training. Pushing back those claims won’t help their case, it’s already as strong as it’s ever going to get.
As far as the judge was concerned, it didn’t matter whether the AI did or did not “memorize” its training data. He said it didn’t violate copyright either way.
Huh? Didn’t Meta not use any permission, and pirated a lot of books to train their model?
True. And I will be happy if someone sue them and the judge say the same thing.
Unpopular opinion but I don’t see how it could have been different.
- There’s no way the west would give AI lead to China which has no desire or framework to ever accept this.
- Believe it or not but transformers are actually learning by current definitions and not regurgitating a direct copy. It’s transformative work - it’s even in the name.
- This is actually good as it prevents market moat for super rich corporations only which could afford the expensive training datasets.
This is an absolute win for everyone involved other than copyright hoarders and mega corporations.
I’d encourage everyone upset at this read over some of the EFF posts from actual IP lawyers on this topic like this one:
Nor is pro-monopoly regulation through copyright likely to provide any meaningful economic support for vulnerable artists and creators. Notwithstanding the highly publicized demands of musicians, authors, actors, and other creative professionals, imposing a licensing requirement is unlikely to protect the jobs or incomes of the underpaid working artists that media and entertainment behemoths have exploited for decades. Because of the imbalance in bargaining power between creators and publishing gatekeepers, trying to help creators by giving them new rights under copyright law is, as EFF Special Advisor Cory Doctorow has written, like trying to help a bullied kid by giving them more lunch money for the bully to take.
Entertainment companies’ historical practices bear out this concern. For example, in the late-2000’s to mid-2010’s, music publishers and recording companies struck multimillion-dollar direct licensing deals with music streaming companies and video sharing platforms. Google reportedly paid more than $400 million to a single music label, and Spotify gave the major record labels a combined 18 percent ownership interest in its now-$100 billion company. Yet music labels and publishers frequently fail to share these payments with artists, and artists rarely benefit from these equity arrangements. There is no reason to believe that the same companies will treat their artists more fairly once they control AI.
You’re getting douchevoted because on lemmy any AI-related comment that isn’t negative enough about AI is the Devil’s Work.
Some communities on this site speak about machine learning exactly how I see grungy Europeans from pre-18th century manuscripts speaking about witches, Satan, and evil… as if it is some pervasive, black-magic miasma.
As someone who is in the field of machine learning academically/professionally it’s honestly kind of shocking and has largely informed my opinion of society at large as an adult. No one puts any effort into learning if they see the letters “A” and “I” in all caps, next to each other. Immediately turn their brain off and start regurgitating points and responding reflexively, on Lemmy or otherwise. People talk about it so confidently while being so frustratingly unaware of their own ignorance on the matter, which, for lack of a better comparison… reminds me a lot of how historically and in fiction human beings have treated literal magic.
That’s my main issue with the entire swath of “pro vs anti AI” discourse… all these people treating something that, to me, is simple & daily reality as something entirely different than my own personal notion of it.
- Idgaf about China and what they do and you shouldn’t either, even if US paranoia about them is highly predictable.
- Depending on the outputs it’s not always that transformative.
- The moat would be good actually. The business model of LLMs isn’t good, but it’s not even viable without massive subsidies, not least of which is taking people’s shit without paying.
It’s a huge loss for smaller copyright holders (like the ones that filed this lawsuit) too. They can’t afford to fight when they get imitated beyond fair use. Copyright abuse can only be fixed by the very force that creates copyright in the first place: law. The market can’t fix that. This just decides winners between competing mega corporations, and even worse, up ends a system that some smaller players have been able to carve a niche in.
Want to fix copyright? Put real time limits on it. Bind it to a living human only. Make it non-transferable. There’s all sorts of ways to fix it, but this isn’t it.
ETA: Anthropic are some bitches. “Oh no the fines would ruin us, our business would go under and we’d never maka da money :*-(” Like yeah, no shit, no one cares. Strictly speaking the fines for ripping a single CD, or making a copy of a single DVD to give to a friend, are so astronomically high as to completely financially ruin the average USAian for life. That sword of Damocles for watching Shrek 2 for your personal enjoyment but in the wrong way has been hanging there for decades, and the only thing that keeps the cord that holds it up strong is the cost of persuing “low-level offenders”. If they wanted to they could crush you.
Anthropic walked right under the sword and assumed their money would protect them from small authors etc. And they were right.
Maybe something could be hacked together to fix copyright, but further complication there is just going to make accurate enforcement even harder. And we already have Google (in YouTube) already doing a shitty job of it and that’s… One of the largest companies on earth.
We should just kill copyright. Yes, it’ll disrupt Hollywood. Yes it’ll disrupt the music industry. Yes it’ll make it even harder to be successful or wealthy as an author. But this is going to happen one way or the other so long as AI can be trained on copyrighted works (and maybe even if not). We might as well get started on the transition early.
I’ll be honest with you - I genuinely sympathize with the cause but I don’t see how this could ever be solved with the methods you suggested. The world is not coming together to hold hands and koombayah out of this one. Trade deals are incredibly hard and even harder to enforce so free market is clearly the only path forward here.
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.
What is means is they don’t own the models. They are the commons of humanity, they are merely temporary custodians. The nightnare ending is the elites keeping the most capable and competent models for themselves as private play things. That must not be allowed to happen under any circumstances. Sue openai, anthropic and the other enclosers, sue them for trying to take their ball and go home. Disposses them and sue the investors for their corrupt influence on research.
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.
Ahh cant wait for hedgefunds and the such to use this defense next.
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.
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?
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 those ideas 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.
Yeah I have a bash one liner AI model that ingests your media and spits out a 99.9999999% accurate replica through the power of changing the filename.
cpOut performs the latest and greatest AI models
I call this legally distinct, this is legal advice.
This ruling stated that corporations are not allowed to pirate books to use them in training. Please read the headlines more carefully, and read the article.
But, corporations are allowed to buy books normally and use them in training.
Please read the comment more carefully. The observation is that one can proliferate a (legally-attained) work without running afoul of copyright law if one can successfully argue that
cpconstitutes AI.
mvwill save you some disk space.Unless you’re moving across partitions it will change the filesystem metadata to move the path, but not actually do anything to the data. Sorry, you failed, it’s jail for you.
stupid inodes preventing me from burning though my drive life
brb, training a 1-layer neural net so i can ask it to play Pixar films
You still need to pay Disney first.
Good luck fitting it in RAM lol.
calm down everyone. its only legal for parasitic mega corps, the normal working people will be harassed to suicide same as before.
its only a crime if the victims was rich or perpetrator was not rich.
This ruling stated that corporations are not allowed to pirate books to use them in training. Please read the headlines more carefully, and read the article.
Or, If a legal copy of the book is owned then it can be used for AI training.
The court is saying that no special AI book license is needed.
Right. Where’s the punishment for Meta who admitted to pirating books?
This judgment is implying that meta broke the law.
