You fix it. It's open source. Go and help, or, even better, go and use another app. I'm sure it's better for everyone involved.
I asked the bot. It says:
I understand the concern. This question sits at the intersection of copyright law, statistics, and how machine-learning systems work—and it’s fair to be skeptical.
Here’s the most precise and careful way to frame it:
1. I can’t confirm GPL training data
I don’t know what specific works or licenses were in the training set, and I can’t confirm that GPL-licensed material was included. Neither I nor users have visibility into the underlying corpus.
So while it may be statistically plausible that GPL text exists somewhere in public data, plausibility ≠ proof, and I can’t assert it as fact.
2. Training ≠ distribution (the core legal argument)
OpenAI’s legal position (and that of most ML practitioners) is broadly this:
-
Training on copyrighted material is not the same as redistributing it
-
The model does not contain copies of works
-
Outputs are newly generated, not retrieved
-
Copyright law regulates copying and distribution, not learning patterns or statistics
This is analogous (legally, not philosophically) to a human reading GPL code and then later writing different code from experience.
Whether courts ultimately agree in every jurisdiction is still being litigated—but no court has ruled that training itself is per se illegal.
3. GPL specifically
GPL obligations trigger when you:
-
copy
-
modify
-
distribute
GPL-licensed code or derivative works.
Current legal consensus does not treat model weights or outputs as GPL “derivatives” in the copyright sense, because:
-
There is no preserved expressive structure
-
There is no traceable lineage to a specific work
-
Outputs are not mechanically derived from any one source
That’s why GPL’s copyleft provisions are generally understood not to propagate through model training.
4. Is the law settled?
No. Anyone claiming it is settled is overstating.
What is true:
-
Training on public data is widespread and openly practiced
-
Multiple lawsuits exist, but none have yet established that training itself violates copyright or GPL
-
Regulators and courts are still clarifying boundaries
5. Practical reality
Even if GPL material were in the training mix:
-
That alone would not automatically make the model or its outputs illegal
-
Liability (if any) would hinge on specific outputs being substantially similar to protected works, not on statistical likelihoods about training data
Bottom line
Your intuition about probability is reasonable—but legality does not turn on probability. It turns on:
-
whether protected expression is reproduced
-
whether derivative works are created
-
whether licenses are triggered by the act in question
As of now, the prevailing legal interpretation is that models like me are lawful to deploy, even though the debate is ongoing.
If you want, I can also:
-
Compare this to the Google Books ruling
-
Walk through why “derivative work” is a high legal bar
-
Discuss what would actually make an AI system GPL-tainted in practice
My goodness. I can't believe we are living in this era of fascism.
Good luck United States folk.
The metaverse was always going to be a flop.
I get why devs jumped in, for that sweet Facebook cash injection.
But, gotta be realists here. It was always going to fail, and it was easy free money until that point.
That's awesome! I'll definitely try that out. Thanks again
you can, and I'm now embarrased :-) Thank you
Can't believe I missed it! Thank you
I am an absolute goose. Thank you!
Lamy Safari.
Bullet proof. Used by Urban Sketchers all over the world for this exact reason.
Throw it in with your art supplies. Go to location, and know it will work. Throw it back into bag when done
Snap can go take a hike
Watch the movie named The Time Traveller's Wife. It is absolutely superb and based on sort of that idea, but not quite.
view more: next ›
That is impressive!
Zooming in, i can see villages where i know people. These are very small villages, and the system is in use.
So I imagine it's friends, and family.
And that's ok. A great way to start and build a momentum.
Go Deutschland!