minus-squareCaliforniaSober@lemmy.catoChatGPT@lemmy.world•Researchers Jailbreak AI by Flooding It With Bullshit JargonlinkfedilinkEnglisharrow-up1·1 day agoInvert that, it’s also about a new frontier to guard against if you are a company with sensitive data/ liabilities and are leveraging these models. It’s valuable info as your models need to be trained against this sort of attack. linkfedilink
minus-squareCaliforniaSober@lemmy.catoChatGPT@lemmy.world•Multiple Studies Now Suggest That AI Will Make Us MoronslinkfedilinkEnglisharrow-up3·edit-226 days agoRight above this post: “My Couples Retreat With 3 AI Chatbots and the Humans Who Love Them“ top article on wired linkfedilink
Invert that, it’s also about a new frontier to guard against if you are a company with sensitive data/ liabilities and are leveraging these models. It’s valuable info as your models need to be trained against this sort of attack.