Kid@sh.itjust.worksM to Cybersecurity@sh.itjust.worksEnglish · 26 days agoResearchers Reveal 'Deceptive Delight' Method to Jailbreak AI Modelsthehackernews.comexternal-linkmessage-square5fedilinkarrow-up132arrow-down12
arrow-up130arrow-down1external-linkResearchers Reveal 'Deceptive Delight' Method to Jailbreak AI Modelsthehackernews.comKid@sh.itjust.worksM to Cybersecurity@sh.itjust.worksEnglish · 26 days agomessage-square5fedilink
minus-squareremi_pan@sh.itjust.workslinkfedilinkEnglisharrow-up5·25 days agoIf the jailbreak is about enabling the LLM to tell you how to make explosives or drugs, this seems pointless, because I would never trust a IA so prone to hallucinations (and basicaly bad at science) in such dangerous process.
If the jailbreak is about enabling the LLM to tell you how to make explosives or drugs, this seems pointless, because I would never trust a IA so prone to hallucinations (and basicaly bad at science) in such dangerous process.