DMCA Take Two: UK Government is to Propose Death Blow Opt-Out for AI Training

Americans are freedom loving people, and nothing says freedom like getting away with it.
Long Long Time, written by Guy Forsyth

Big Tech is jamming another safe harbor boondoggle through another government, this time for artificial intelligence. The defining feature of the DMCA scam is every artist in the known universe having to single-handedly monitor the entire Internet to catch each instance of theft in the act. Once caught, artists have to send a DMCA notice on a case by case basis, and then overcome what is 9 times out of 10 a BS counternotification. Then if they disagree with the BS counternotification, artists are faced with having to file a federal copyright infringement lawsuit which they don’t file because they can’t afford it.

And so it goes.

This is what an “opt-out” looks like. We have seen this movie before and we know how it ends–it’s called getting away with it. Let us be very clear with lawmakers: Notice and takedown and “opt out” is bullshit. It has never worked and has imposed a phenomenal cost on the artist community to the point that many if not most artists have just given up. The Future of Music Coalition and A2IM surveyed their members and determined that over half don’t even bother to look anymore because they can’t afford to run the search. The next largest group give up because they get no response from the notices.

Let’s understand–every time an artist gives up even looking for infringers, that’s a win for Big Tech. That’s why year after year, there are over a billion DMCA notices sent to a variety of infringers.

Ask yourself in all honesty, are you surprised? What head up the ass buffoon would ever think that an opt out would work? Unless the plan was to let Big Tech run wild and give both the biggest corporations in commercial history and the lawmakers a big fig leaf to cover up the theft?

That same approach is rearing its head again in both the US Congress and the UK. But this time it is being applied to artificial intelligence training and outputs. This is stark raving madness, drooling idiocy. At least with the DMCA an artist could look for an actual copy of their works that could be found by text-based search, audio fingerprints or just listening.

With AI, the whole point is to disguise the underlying work used to train the AI. The AI platform operator knows what works they used, which sites they scraped, or other ways to identify the infringed works. When sued, these operators have refused to disclose the training materials because they say that the sources of those materials are supposedly a trade secret and confidential.

Once a work is ingested into the AI, the output is also purposely distorted from the original. Again, impossible to conclusively identify. So what exactly are you opting out of? To whom do you send your little notice?

This entire opt-out idea is through the looking glass into the upside down world. Yet is is true.

The most current manifestation of this insanity is the UK government’s intention to pass legislation that would force artists to use an opt-out model, possibly on a work-by-work basis. And the worst part is that somehow they have been led to think that an opt-out is a protection for artists.

Orwellian.

Fortunately the UK government may seek public comment on this opt-out proposal. We will keep you posted on what the UK government actually proposes and how you can comment.

In the meantime, if you live in the UK, it’s not to early to contact your MP and ask them what the hell is going on. You may want to ask them why you can call the police when your car is being stolen but there’s nobody to call when your life’s work is being stolen. Particularly when the government protects the thieves.

Search is Ripping Us Off Again, this time for AI

By Chris Castle

In case you think that infringement of copyrights in AI training happens only to rock stars, photographers, record companies or movie studios, let me give you a personal anecdote that might cause you to reconsider. I asked Bing’s Copilot AI tool to list the deal points in a record producer agreement, and this is what I got back:

Copilot

Certainly! When negotiating a producer agreement, several key points should be considered. Here are some common negotiation points from the artist’s perspective:

  1. Scope of Engagement:
    1. The producer is generally engaged for one album project at a time.
    2. Clarify the scope of work, including the number of songs or recordings to be produced.
  2. Budget and Compensation:
    1. Determine the budget for the project (e.g., $10,000 in your case).
    2. Agree on the producer’s compensation, which may include an upfront fee, points on sales, or a combination.
  3. Ownership and Rights:
    1. Address ownership of the master recordings:
      1. Will the artist own and control the masters?
      2. Does the producer retain any rights?
  4. Credits and Royalties:
    1. Specify how the producer will be credited on releases.
    2. Discuss any royalties or backend points for the producer.
  5. Recording Schedule:
    1. Set a timeline for recording sessions.
    2. Define the two-week period for your project.
  6. Logistics:
    1. Determine where the recordings will take place.
    2. Outline the artist’s approval process.
    3. Define the producer’s deliverables.
  7. Termination Clause:
    1. Include provisions for termination if either party breaches the agreement.
    2. Address payment for work completed up to that point.

Remember that each negotiation is unique, and it’s essential to tailor the agreement to your specific needs and circumstances. Legal advice is recommended to ensure compliance with local laws and industry standards1 3 4.

Source(s)

1. An Artist’s Guide to Negotiating Record Producer Agreements – Medium

2. Negotiating a Music Producer Agreement: 7 Key Issues

3. 5 Things to Look for in a Music Producer Agreement – Lawyer Drummer

4. How to Negotiate: Steps, Phrases & Tips to Win the Deal – Selling Signals

Notice that Copilot lists “Source(s)” and that source #1 is an article from the Medium website.

My article.

I’ve written a number of articles about negotiating producer agreements and I can categorically say I haven’t given permission or been asked to give permission for any of those articles to be scraped and used to train AI. So how did it come to be in Copilot’s training materials? 

My guess is that Medium (and probably a lot of other sites) were crawled by Bing’s spider and that copies of Medium pages were stored in Bing’s (or Microsoft’s) data centers. When Microsoft launched its Copilot AI tool, one could imagine that the temptation would have been strong to use those copies as part of the training tools for Copilot. In fact, the Verge reports that “companies around the web are using your site and its data to build massive sets of training data, in order to build models and products that may not acknowledge your existence at all.” Can you say Section 230 or DMCA? Maybe there will be a question at the April 11 House Energy & Commerce hearing on Section 230.

So Google-style “innovation” has a self-destructive flavor consistent with their oikophobic capitalism. Greater Silicon Valley’s view of culture in general and copyright in particular is as sources of wealth extracted by destruction–you know, creative destruction, permissionless innovation, etc. (It’s no wonder Google was inexorably attracted to defense contracting despite all the “don’t be evil” hoorah. After all, what creates massive wealth faster than convincing governments to pay big money to blow things up that must be replaced by ever more big money to blow even more things up.)

Are you surprised then that two of the biggest operators in the AI space are the search engine operators Google and Microsoft? This is another example of how Big Tech helps itself to your data and work product without you even knowing it’s happening. So now what? I now know I’m being ripped off, and I’m wondering if Medium is in on it.

The Verge tells us:

The ability to download, store, organize, and query the modern internet gives any company or developer something like the world’s accumulated knowledge to work with. In the last year or so, the rise of AI products like ChatGPT, and the large language models underlying them, have made high-quality training data one of the internet’s most valuable commodities. That has caused internet providers of all sorts to reconsider the value of the data on their servers, and rethink who gets access to what. 

Ya think?

@SchneiderMaria Rolls Over YouTube in Her Copyright Infringement Case

By Chris Castle

It’s been just over two years since Maria Schneider sued YouTube for copyright infringement. But the court has now cleared a path for her to actually proceed with her main case by dismissing–emphatically–YouTube’s motion to dismiss for failure to state a claim.

According to Reuters:

Schneider sued YouTube in 2020 on behalf of a proposed class of small copyright owners, arguing the platform only protects large copyright owners from infringement while allowing pirated content from others in order to draw in users. The group said major companies have access to YouTube’s advanced Content ID software to scan for and automatically block infringing content, while individual creators are left “out in the cold.”

But that’s not the critical part. Maria’s lawsuit alleges that YouTube YouTube removed copyright management information (CMI) in violation of 17 U.S.C. § 1202(b)–potentially intentionally.

The amended complaint states that YouTube knew that files containing audio and/or video works routinely contain CMI, that CMI is valuable for protecting copyright holders, and that the distribution of works with missing CMI on YouTube has induced, enabled, facilitated, and concealed copyright infringement. The plausible inference from these and similar allegations is that YouTube removed the CMI from plaintiffs’ works with knowledge that doing so carried a “substantial risk” of inducing infringement. 

One could see how anyone who intentionally removes one brick from the complex wall that protects big infringers like YouTube from truly massive liability for copyright infringement would be in a whole heap of trouble for inducing infringement (which gets you into Grokster land).

Personally, it’s my view that this is exactly what YouTube and Google do on a massive scale and that they should pay the class damages that will dwarf all the fines these people have already paid for everything from violations of the Controlled Substance Act to competition law violations. Truly Carl Sagan level damages…billions and billions.

We’re lucky Maria’s on the side of the angels. Fight on.

Guest Post: What is the Intention of Justice? Notice and Stay Down is the Government’s Responsibility

By Chris Castle

ARTHUR

Let’s get back to justice…what is justice? What is the intention of justice? The intention of justice is to see that the guilty people are proven guilty and that the innocent are freed. Simple isn’t it? Only it’s not that simple.

From …And Justice for All, written by Valerie Curtin and Barry Levinson.

Law out of balance is no law at all.  I suggest that the DMCA is just this imbalance and the unbalanced DMCA has created other imbalances that in turn transferred wealth from the many to the few.  One of the biggest dangers to our society currently and in the future is erosion of the third estate (or the “musician’s middle class”) into the concentration of wealth in fewer and fewer hands.  This erosion is accompanied by its inevitable trend toward authoritarianism enforced by the mandarin class of Silicon Valley.  Not to mention the policy laundering operations funded by transferred wealth like the Chan Zuckerberg Initiative (that’s the Chan Zuckerberg who asked Xi Jinping to name her then-unborn child).  

Serfing in the Apocalypse 

This kind of neo-feudal concentration of wealth is most obvious in the tech oligarchy, especially in companies like Facebook, Google and Spotify with their dual class supervoting stock that concentrates the corporate decision making and wealth not in the shareholders but in the hands of Mark Zuckerberg, Sergey Brin, Larry Page, Eric Schmidt, Daniel Ek and Martin Lorentzen.  And then there’s Amazon with the world’s richest man, Jeff Bezos—the future space mogul.  (Bezos’ Blue Origin and Google’s adventures in biometrics and AI in China are examples of the second order knock-on effects of the Internet oligarchy become defense contractors.) 

I also suggest that one of the driving forces that has accelerated this concentration of wealth and power over the last twenty years has been the 1998 Digital Millennium Copyright Act.  Unless substantially reversed, the DMCA will continue to accelerate the wealth transfer from creators to oligarchs.  It must also be said that state actors or near state actors like TikTok either profit from, promote or protect massive online piracy based in DMCA-type alibis.  This topic is another conversation, but anyone who has dealt with the huge pirate sites has felt the cold hand of truly bad guys with top cover.  In addition to the tech oligarchs, Russian oligarchs think the DMCA idea is really pretty groovy.

The DMCA Alibi

You’ve probably heard the expression “notice and takedown” applied to copyright online.  It was the DMCA that created the “notice and takedown” alibi regime for piracy and near-piracy.   These notices have come to be called “DMCA notices” and the Congressional plan that implemented that call and response has unambiguously failed.  You may have also heard the expression “value gap.”   The “value gap” is shorthand for illicit profits made from exploiting the DMCA loophole which itself is a prima facie case of law out of balance.  The “value gap” is the predictable consequence of “notice and takedown.”

Google alone has received nearly five billion DMCA notices just in the current reporting period.  That’s 5,000,000,000.  I’m still waiting to see the conga line of Members of Congress and Senators who say that was exactly what they intended (and many who were involved in drafting the DMCA are still serving).  I’m also waiting to hear lawmakers acknowledge that when something happens 5,000,000,000 times, it’s a feature not a bug just like the Ford Pinto’s exploding gas tank.  No one ever asked them until Senator Thom Tillis began a series of hearings before the Senate Judiciary Committee’s Subcommittee on Intellectual Property earlier this year.

If we’re lucky, in coming days Senator Tillis will be introducing a legislative overhaul of this gaping wound reflecting the many hearings he’s chaired this year to investigate the DMCA imbalance that created one of the biggest wealth transfers in history.  That wealth transfer is not only caused by the perpetual state of piracy or near piracy created by the DMCA, it is also caused by the cost of enforcing copyright that has fallen on all creators in all copyright categories.  Not to mention the sheer scale of the burden imposed by lawmakers on creators.  Hopefully Senator Tillis’s investigation will bear fruit and will right the imbalance.

And as we have exhaustively endured for over 20 years, law out of balance is no law at all.   In the music business, performers—like all creators—have been effectively powerless to stop this latest great imbalance in justice created by the copyright infringement safe harbor disaster and piracy force multiplier.  That value gap has hollowed out the performer community (as well as record companies) after 20 years of wealth transfer to the Big Tech oligarchs from commoditizing the recordings that performers created.  And Big Tech have used their DMCA-driven profits to hire even more lobbyists around the world to create even more loopholes in the human rights of artists in the endless maelstrom of Malthusian decline.  That decline manifests itself in the ennui of learned helplessness of creators around the world as companies like Google seek to impose Google’s version of notice and takedown around the world.

Notice and Staydown

But—there is a new term in our lexicon that hopefully will appear in new legislation from Senator Thom Tillis: Notice and stay down. What does it mean?  It’s a mid point between a pure negligence standard and the intent of the DMCA to provide a responsible alternative dispute resolution system.  Instead of the endless whack a mole iterations of catch me if you can posting and reposting of infringing works, online service providers would be required to actually do the right thing and keep the infringing work off of their service.  It’s really just a properly enforced repeat infringer policy.  It’s hard to believe that adults persist in this whack a mole but they do.  There’s big money in those moles that don’t actually stay whacked.

How in the world did we arrive at the status quo?  A page of history is worth a volume of logic to fully understand this leading edge of the Great Reset.  

The Great Copyright Reset

In the late 1990s, the large ISPs had a legitimate concern about this Internet thing. If ISPs (like Verizon or AT&T) are providing ways for the many to connect with each other over the Internet, they were inevitably empowering essentially anonymous users to send digitized property to each other by means of that same technology.  That property might take the form of an email file attachment (or link to a file) that contained a copy of a sound recording, movie or an image.  ISPs wanted to be protected from responsibility for things like copyright infringement they had nothing to do with.  (This knowledge predicate is where the games begin.)

The ISPs needed a zone in which they could operate, a zone that came to be called the “safe harbor.” The deal essentially was that if you didn’t know or have a reason to know there was bad behavior going on with your users, or didn’t have knowledge waiving like a red flag, then the government would provide a little latitude to reasonable people acting reasonably.

This safe harbor idea was a great privilege conferred upon online service providers and balanced the democratizing nature of the Internet with the need to enforce the law against bad actors.  Lawmakers were caught up with the idea of bringing people together.  What they didn’t realize sufficiently was some of those people previously only met on Death Row.

Artists’ rights to protect themselves were not entirely extinguished by this new safe harbor for big companies but were severely burdened. Record labels and film studios had to devote substantial resources to whack a mole that could have been spent on their core businesses–making records and movies.  If a copyright owner thought there was infringement going on that didn’t qualify for the safe harbor, then the intention was that individual artists shouldn’t have to file a lawsuit, they could just send a simple notice to the service provider. If it turned out that there was a bona fide dispute over the particular use of the work, then the parties could go to court and hash it out if necessary. The notice part of “notice and takedown” was perceived as an inexpensive remedy that would be available to artists who did not want to take on a lawsuit as well as ISPs with litigation budgets.  The Congress did not factor in the charlatans who would come later like Google and Facebook, neither of which existed in 1998.

This is documented in the legislative history from 1998, i.e., both before Google and and Facebook and before the Electronic Frontier Foundation discovered Morpheus or Mrs. Lenz:

This ‘‘notice and takedown’’ procedure is a formalization and refinement of a cooperative process that has been employed to deal efficiently with network-based copyright infringement.

Section 512 does not require use of the notice and take-down procedure. A service provider wishing to benefit from the limitation on liability under subsection (c) must ‘‘take down’’ or disable access to infringing material residing on its system or network of which it has actual knowledge or that meets the ‘‘red flag’’ test, even if the copyright owner or its agent does not notify it of a claimed infringement. 

Sounds very civilized, don’t it? Sounds like something that could be considered to be just. How could something that sounded so right go so wrong so fast?  Notice and takedown has become notice and shakedown after the charlatans arrived.

The Inevitable Notice and Shakedown

The one thing that nobody thought was that it was the intention of Congress that there would be ad networks, multinational corporations and international piracy rings whose business model is in large part built on exploiting the “notice and takedown” loophole in that safe harbor.  

These organizations ignored the DMCA’s knowledge predicate and repeat infringer requirements and adopted what is essentially a “catch me if you can” version that allows them to infringe until they get caught by the copyright owner and then continue to infringe if they are not sued–the exact opposite of what the DMCA intended.  What once was a reasonable exception was almost immediately tainted as a massive loophole that the government has done little to nothing to correct much less enforce.

The “safe harbor” is no longer a loophole, it has graduated to a full blown design defect as indiscriminately harmful as any exploding gas tank.  So now when artists ask that some common sense be applied to this grotesque distortion of the law-supposedly passed in part for the benefit of artists-some would tell artists that it’s not up to government to tell them what the law means. As Kafka-esque as that sounds.

Will You Believe Me or Your Lying Eyes?

Isn’t it obvious that having to send a notice for the same work on the same service hundreds of thousands of times an absurd burden? In other words — is the government actually defending whack a mole with a straight face? Did the government actually intend that 5,000,000,000 take down notices in a year are a new normal?  If they did, evidence of that intent is not in the statute or the legislative history.  Would Congress offer protection to an exploding gas tank after they already knew it was a threat because it was designed that way?

Whack a mole is not automatic-it requires human intervention. As we saw in BMG’s precedent setting and victorious lawsuit against the ISP Cox Communications over Cox’s grotesque failure to enforce its repeat infringer policy, a person has to decide to repost the infringing file even while knowing the file is or is very likely an infringement. Whack a mole actually defies the entire purpose of the safe harbor-whack a mole is not a little latitude for reasonable people acting reasonably.

Whack a mole is a design defect.  Is it just that Congress should protect any design defect?

Let’s get back to justice. Not only does the status quo require creators to tell lawmakers (including courts) what their law means, the U.S. Government has utterly failed artists with the fundamental justification for the Sovereign common to our jurisprudence and political theory. 

Crucially, it must be acknowledged that the government has failed to protect artists.  The government has failed to enforce the laws, essentially overseeing and giving legitimacy to one of the largest wealth transfers of all time from the hands of the many into the overflowing pockets of the few.  All based on an extreme interpretation by Google and its ilk of the government’s laws.  Direct challenges to these interpretations involve costly and protracted litigation — with the inescapable whack a mole continuing all the while.

It would not be unreasonable for artists to think that the whole thing smacks of crony capitalism, particularly when one of the biggest beneficiaries of the loophole is a major lobbying influence like Google. While some ISPs have at least tried to address the issue, the Googles of this world are noticeably absent.

So I would beg pardon here-I do not feel that it should be necessary for artists to tell the Congress what would be acceptable in the way of parameters for “notice and stay down”, at least not initially. I think artists have the undisputed right to ask-actually to demand-of the Congress, what was their intention?

Enter the Foxes

Don’t underestimate the knock-on effects of the DMCA wealth transfer that funds self-preservation for the DMCA beneficiaries.  Who can forget Google’s dominance of the Obama Administration?  It’s clear that like Google learned from Microsoft, Facebook has learned from Google (and both joined forces to try to defeat the European Copyright Directive, so expect more of the same foxes coming for the henhouse when Senator Tillis introduces his bill).  

We note the irony that the ethics czar for the Biden transition team is from Facebook, as is the director of legislative affairs a former Facebook lobbyist.  A former Facebook board member co-chairs the transition team and there is a sprinkling of other former Facebook board members in other roles.  Three transition team members are former Chan Zuckerberg Initiative employees.  And Google’s Eric “Uncle Sugar” Schmidt will have a leading role.  

Once they get into power, you can expect that DMCA reform will get exponentially harder, but the Tech Transparency Project will have even more work to do.

Senator Tillis Could Make Real Progress Toward Reversing the DMCA Cronyism

The safe harbor is the government’s law. They wrote it. They voted for it. They represented voters—including creators—when they did so. They presumably have some idea what it is supposed to mean. Many who voted for it are still in the Congress. The Congress needs to come clean on what they intended. Isn’t that the better place to start? Why should artists have to tell the Congress what the Congress’s intention was?

If it was the intention of the Congress (and President Clinton who signed the law) that the current state of whack a mole was the plan all along, then let them say that — and perhaps more importantly, point to where they told the electorate that was their intention at the time the DMCA was passed in the Congress and signed into law.  If it is not their intention, then it should be reversed with no daylight.

Google alone is on track to receive over five billion take down notices this year alone. If this was the Congressional intention, then let them say that. If their intention was there should be no upper limit on the number of takedown notices any one company could receive in a year, then let them say that. And explain themselves.

And let’s be clear-Google does not appear to view these billions of notices as a design defect, although that would be a perfectly reasonable conclusion. And neither do Facebook or Twitter. One has to believe that if a company the size of Google viewed billions of notices as a problem, they could fix that problem. They haven’t. In fact the number of notices grows exponentially every year. Perhaps they view billions of DMCA notices as a feature set.  Because along with the billions of notices comes a fortune for Google just like Facebook, Twitter and the rest.  Big Tech’s defenders would say of Pirate Bay and Megavideo, they’re just like Google.  Yes, that’s right.  Google is just like them and they are just like Google.  Serfing on the DMCA apocalypse.

What is the intention of justice? That the guilty are proven guilty. But if lawmakers won’t tell us what it means to be guilty much less prosecute the politically connected wrongdoers, then what justice is that?

Notice and stay down is a reasonable reaction to whack a mole, and one that is entirely consistent with the original intent of the DMCA notice and takedown regime that has gone so far wrong. Hopefully Senator Tillis will be leading the charge.

It might actually be that simple.  Notice and stay down.

As Arthur told the jury, “If he’s allowed to go free, then something really wrong is going on here.”