Dot.@feddit.org to Technology@lemmy.worldEnglish · 7 days agoChatGPT-4o Guardrail Jailbreak: Hex Encoding for Writing CVE Exploits.0din.aiexternal-linkmessage-square19fedilinkarrow-up187arrow-down15cross-posted to: cybersecurity@sh.itjust.works
arrow-up182arrow-down1external-linkChatGPT-4o Guardrail Jailbreak: Hex Encoding for Writing CVE Exploits.0din.aiDot.@feddit.org to Technology@lemmy.worldEnglish · 7 days agomessage-square19fedilinkcross-posted to: cybersecurity@sh.itjust.works
minus-square🇦🇺𝕄𝕦𝕟𝕥𝕖𝕕𝕔𝕣𝕠𝕔𝕕𝕚𝕝𝕖@lemm.eelinkfedilinkEnglisharrow-up19arrow-down2·7 days 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-up8arrow-down6·7 days 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🇦🇺𝕄𝕦𝕟𝕥𝕖𝕕𝕔𝕣𝕠𝕔𝕕𝕚𝕝𝕖@lemm.eelinkfedilinkEnglisharrow-up10arrow-down2·7 days 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