> we cannot ship your game while it contains these AI-generated assets, unless you can affirmatively confirm that you own the rights to all of the IP used in the data set that trained the AI to create the assets in your game.
This is exactly how this stuff should work. Greedily scraping whatever content you want hurts people who made that content and ultimately hurts AI developers who still need more high quality data.
I'm still not convinced by this argument. All human-generated art is also a result of the artist's experiences, and is strongly influenced by other art they have consumed. So why should GenAI not be allowed to blend the work of other artists?
If you want to argue that we should fundamentally treat machine- and human-generated works differently, that's fine -- but it's a different argument from "looking at a bunch of art and then synthesising ideas is bad," because that's exactly what many (most?) human artists do.
There's a pretty big fucking difference between the organic experience of a human being and a massive VC funded hellsystem that can process 400 million exact copies of images and generate thousands per day.
I honestly can't believe people are still making this dishonest, bad faith argument. It's obviously problematic if you think about it for more than 3 minutes.
I believe the expectation is that there is a difference between new creative work by humans and the output of tools. Tools are not 'artistically influenced' by their inputs.
Also, a human can take a work, modify it, and create a derivative work. They do not have copyright to the original material, and the degree of derivation is a winding blurry line through the court system to determine if they fully own the new work.
I suspect these to dominate the arguments for the first court cases around generative AI art - that the artist (operator) is the one who has to justify that they provided enough creativity in the process to create an independent work.
> you can affirmatively confirm that you own the rights to all of the IP used in the data set that trained the AI
i think valve is over reaching with this policy.
It should be that you need to prove the art used in the game itself that does not breach any copyright. The tool used to create said art has no bearing on the final art with regards to copyright.
Otherwise, would valve also have mentioned that the developer should also produce evidence of their photoshop license/subscription (if they used photoshop in the course of making their game)? Do they need to check that the version of windows being used to make the game is a licensed one?
> The tool used to create said art has no bearing on the final art with regards to copyright.
This is still an open question with regards to AI art generation tools. Do you have recent legal precedent to cite that I don't know about, or are you just making things up?
> This is still an open question with regards to AI art generation tools.
While it is an unanswered question with no legal precedence, i am a believer that what isn't currently illegal is and should be considered legal, until harm has been shown and thus require legal ruling.
Valve may be anticipating that it will become illegal, in which case they would have to pull games from the store and issue refunds. They may be waiting to see which way the wind blows on this before they get their revenue stream mixed up with it.
Do you have a legal decision that AI art forms no derivative of a copyrighted work, vs a derivative of ALL the copyrighted work in its training set?
There is no new law, there is ambiguity with the lack of current case law. There are certainly people who think generative art based on scraping the internet is infringing under current legal standards. We won't know until people go to court and judges make decisions.
Valve's insistence in the face of their own liability for selling derivative works seems a sound business decision here, at least when selling in markets where it is an open legal issue.
Yep, you are absolutely right.