KidM to CybersecurityEnglish · 29 days agoResearchers Reveal 'Deceptive Delight' Method to Jailbreak AI Modelsthehackernews.comexternal-linkmessage-square5fedilinkarrow-up132arrow-down12cross-posted to: [email protected]
arrow-up130arrow-down1external-linkResearchers Reveal 'Deceptive Delight' Method to Jailbreak AI Modelsthehackernews.comKidM to CybersecurityEnglish · 29 days agomessage-square5fedilinkcross-posted to: [email protected]
minus-squareremi_panlinkfedilinkEnglisharrow-up5·29 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.