Anybody who knows what the pigeonhole principle is should know that a lot of these fears are complete bunk.
* being unable to recover many or most images does not imply that you will be unable to recover any at all. Being able to recover a nonzero proportion is still a problem even if the proportion is small.
* the existence of artifacts in the recovered images is not in itself sufficient to prevent legal claims, and yet ignoring them is plenty sufficient for increasing the proportion of inputs that can be considered recovered
When in reality, you absolutely cannot store data to reproduce every image it's trained on because the model isn't big enough to hold even a fraction of what it's trained on.
I mean, it literally says "some" right there in the title, and if you click through and actually read the paper you see it's a tiny proportion.
Here is a real world example.
You make a claim that seems trivially false. Cite some example comments to back it up.
To make a really dumb example:
I can make a black box model that I push in 1000 bestseller novels through, that has the total "storage size" of 1 novel. The pigeonhole principle says my model can't possibly contain all 1000 novels. If you ask it (anything) it will respond with that one novel, verbatim. It never reproduces anything else.
Does it now matter whether I trained it on 1000 novels? Does it matter that my "black box" is just that, a literal black cardboard box containing just a copy of a novel?