minus-squaret҉̠̙ǵ̣̞̄ͪ͜x̸̱͚̳ͫ͐̑̈ͯͣ̚n̒͌҉͉̦̜̝ͅ@lemmy.tgxn.nettoTechnology@lemmy.world•ChatGPT-4o Guardrail Jailbreak: Hex Encoding for Writing CVE Exploits.linkfedilinkEnglisharrow-up6·1 day agosure, but the source of the “Python CVE exploit” already has to exist in the AI’s training dataset, there are lots of example CVE scripts online, you could probably also find it with a quick Google. linkfedilink
sure, but the source of the “Python CVE exploit” already has to exist in the AI’s training dataset, there are lots of example CVE scripts online, you could probably also find it with a quick Google.