Comment on Scientists discover that feeding AI models 10% 4chan trash actually makes them better behaved
L0rdMathias@sh.itjust.works 3 days ago
Interesting training strategy. Makes a lot of sense intuitively. Worried this makes the model even more susceptible to prompt injections. Feels like this method adds more attack vectors? It’s unfortunate they didn’t attempt to test the long term hardness and stability, though it’s probably beyond their scope.
technocrit@lemmy.dbzer0.com 3 days ago
Just because something makes sense intuitively to one person, that doesn’t mean it makes sense scientifically.
They’re probably not testing anything further because they can’t even define their terms.
L0rdMathias@sh.itjust.works 3 days ago
Yes I agree. It’s relieving to see a scientific result be the similar to what one would intuit.