Comment on Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data
EpicFailGuy@kbin.social 11 months ago@stopthatgirl7 @TWeaK @NaibofTabr
if it remembers it has to be stored somwhere, if it has to be stored ther's some type of memory with information saved in it. .... call it what you will.
tabarnaski@sh.itjust.works 11 months ago
You remember some dialogue from your favorite movie. Does this mean your neurons store copyrighted work?
Fermion@mander.xyz 11 months ago
Shhh. Disney’s lawyers might get ideas.
Excrubulent@slrpnk.net 11 months ago
Yes. Just because they’re in a neural network and not ASCII or unicode doesn’t mean they’re not stored. It’s even more apt a concept sonce apaprently those works can be retrieved fairly easily, even if the references to them are hard to isolate. It seems ChatGPT is storing eidetic copies of data, which would imply what other people have said in this thread, that it is overfitting itself to the data and not learning truly generalisable language.
MxM111@kbin.social 11 months ago
The claim is that it contains entire copies of the book. It does not. AI memory is like our memory, we do not remember books word to word.
Excrubulent@slrpnk.net 11 months ago
They are spitting out, as in the quote above, “verbatim text”, as in, word for word. That is copyrightable.
And that’s not what you said. You it has no memory. That’s clearly wrong.