makingStuffForFun

makingStuffForFun @lemmy.ml 5d ago

Techmino is excellent

makingStuffForFun @lemmy.ml 1w ago

100% behind this. Public code, should be public code.

I should be able to access services without an American corporation having my data (Google, apple).

1

makingStuffForFun @lemmy.ml 2w ago

Omg that's a valid concern. This is exactly what xero are doing right now. Finding every little place they can charge and adding fees for developers left, right and centre. A megalomaniac leader has led xero to complete enshitification, and, with the wrong leader, steam could end up on the same place.

makingStuffForFun @lemmy.ml 2w ago

It's absolutely mind boggling. The power of the people.

1

makingStuffForFun @lemmy.ml 2w ago

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!

2

makingStuffForFun @lemmy.ml 2w ago

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.

2

makingStuffForFun @lemmy.ml 3w ago

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
distributeGPL-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