alt Hacker NewsUnanswered by the article: Does any of that (joke or not) actually work?
It's input to the model, sure, but it would have to be a pretty dumb model.
I don't doubt that it's possible to create prompt injection attacks that work. I'm very interested in knowing how hard it is.
Replies
krunck • today at 4:39 PM
Testing now.
My intuition is that the models from this year are really hard to successfully inject.
The labs have been pouring a ton of energy into training against these attacks, as hinted from their system cards.
Doesn't mean they can't be beaten, but you likely need a whole lot more context than a short HTTP header to do it.