Comment on Google Researchers’ Attack Prompts ChatGPT to Reveal Its Training Data

<- View Parent
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.

source
Sort:hotnewtop