Fragen? Antworten! Siehe auch: Alternativlos
It seems they intentionally manipulated prompts, often including lengthy excerpts of articles, in order to get our model to regurgitate. Even when using such prompts, our models don’t typically behave the way The New York Times insinuates, which suggests they either instructed the model to regurgitate or cherry-picked their examples from many attempts.
Klar spuckt unser Modell urheberrechtlich geschützten Text aus, aber dafür braucht der Angreifer enorme kriminelle Energie, um das zu erreichen!1!!