Nemeski@lemm.ee to Technology@lemmy.worldEnglish · 4 months agoOpenAI’s latest model will block the ‘ignore all previous instructions’ loopholewww.theverge.comexternal-linkmessage-square85fedilinkarrow-up1439arrow-down17cross-posted to: technology@lemmit.online
arrow-up1432arrow-down1external-linkOpenAI’s latest model will block the ‘ignore all previous instructions’ loopholewww.theverge.comNemeski@lemm.ee to Technology@lemmy.worldEnglish · 4 months agomessage-square85fedilinkcross-posted to: technology@lemmit.online
minus-squarePasta Dental@sh.itjust.workslinkfedilinkEnglisharrow-up62arrow-down1·4 months agoIll believe it when I see it: an LLM is basically a random box, you can’t 100% patch it. Their only way for it to stop generating bomb recipes is to remove that data from the training
Ill believe it when I see it: an LLM is basically a random box, you can’t 100% patch it. Their only way for it to stop generating bomb recipes is to remove that data from the training