> What happens is a human obtains "a free copy" of a copyrighted work, processes it using a machine and sells the result.
Right, so for example it is pretty common to snip up small bits of songs and to use in other songs (sampling). Maybe that could be an example of somewhere to start? But, these ML models seem quite different, I guess because the “samples” are much smaller and usually not individually identifiable. And really the model encodes information about trends in the sources… I dunno. I still think we need a new law.
Sure, that’s why don’t like the analogy.
> What happens is a human obtains "a free copy" of a copyrighted work, processes it using a machine and sells the result.
Right, so for example it is pretty common to snip up small bits of songs and to use in other songs (sampling). Maybe that could be an example of somewhere to start? But, these ML models seem quite different, I guess because the “samples” are much smaller and usually not individually identifiable. And really the model encodes information about trends in the sources… I dunno. I still think we need a new law.