Dot.@feddit.org to Technology@lemmy.worldEnglish · 4 hours agoChatGPT-4o Guardrail Jailbreak: Hex Encoding for Writing CVE Exploits.0din.aiexternal-linkmessage-square9fedilinkarrow-up139arrow-down14cross-posted to: cybersecurity@sh.itjust.works
arrow-up135arrow-down1external-linkChatGPT-4o Guardrail Jailbreak: Hex Encoding for Writing CVE Exploits.0din.aiDot.@feddit.org to Technology@lemmy.worldEnglish · 4 hours agomessage-square9fedilinkcross-posted to: cybersecurity@sh.itjust.works
minus-square🇦🇺𝕄𝕦𝕟𝕥𝕖𝕕𝕔𝕣𝕠𝕔𝕕𝕚𝕝𝕖linkfedilinkEnglisharrow-up11arrow-down2·3 hours agoIronically the smarter the ai gets the harder it is to censor. Also the more u sensor it the less intelligent and less truthful it becomes.
minus-squareTelorand@reddthat.comlinkfedilinkEnglisharrow-up6arrow-down4·3 hours ago the less intelligent and less truthful it becomes. Incorrect, because of this simple fact: garbage in, garbage out. Feed it the internet, get the internet.
minus-square🇦🇺𝕄𝕦𝕟𝕥𝕖𝕕𝕔𝕣𝕠𝕔𝕕𝕚𝕝𝕖linkfedilinkEnglisharrow-up6arrow-down2·3 hours agoDid u just make up a statement then pretend i said it?
Ironically the smarter the ai gets the harder it is to censor. Also the more u sensor it the less intelligent and less truthful it becomes.
Incorrect, because of this simple fact: garbage in, garbage out. Feed it the internet, get the internet.
Did u just make up a statement then pretend i said it?
Must be a hallucination