Comment on Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data
ayaya@lemdro.id 11 months agoEven then there is no “database” that contains portions of works. The network is only storing the weights between tokens so if it is able to replicate anything verbatim it is just overfitted. Ironically the solution is to feed it even more works so it is less likely to be able to reproduce any single one.
Kbin_space_program@kbin.social 11 months ago
That's a bald faced lie.
E.g. and it can produce copyrighted works.
E.g. I can ask it what a Mindflayer is and it gives a verbatim description from copyrighted material.
I can ask Dall-E "Angua Von Uberwald" and it gives a drawing of a blonde female werewolf. Oops, that's a copyrighted character.
KingRandomGuy@lemmy.world 11 months ago
I think what they mean is that ML models generally don’t directly store their training data, but that they instead use it to form a compressed latent space. Some elements of the training data may be perfectly recoverable from the latent space, but most won’t be. It’s not very surprising as a result that you can get it to reproduce copyrighted material word for word.
ayaya@lemdro.id 11 months ago
I think you are confused, how does any of that make what I said a lie?
TimeSquirrel@kbin.social 11 months ago
I can do that too. It doesn't mean I directly copied it from the source material. I can draw a crude picture of Mickey Mouse without having a reference in front of me. What's the difference there?
FlyingSquid@lemmy.world 11 months ago
If you have a crude picture of Mickey Mouse and you make money from it, Disney definitely has a chance at going after you.
brianorca@lemmy.world 11 months ago
That’s due to trademark, not copyright.