I think an important distinction here is distribution... did you tell someone else what you memorized? Is downloading a model akin to distributing that same information?
What if I don't download the model and I just communicate with it. Sort of like chatting with another human. That's not a copyright issue right? I mean that's how most LLMs are deployed today.
My understanding is that it depends on a judge/jury's subjective opinion on how similar the output is to something copyrightable. Perhaps intent may play a role as well.
