Nemeski@lemm.ee to Technology@lemmy.worldEnglish · 1 year agoOpenAI’s latest model will block the ‘ignore all previous instructions’ loopholewww.theverge.comexternal-linkmessage-square95fedilinkarrow-up10arrow-down10
arrow-up10arrow-down1external-linkOpenAI’s latest model will block the ‘ignore all previous instructions’ loopholewww.theverge.comNemeski@lemm.ee to Technology@lemmy.worldEnglish · 1 year agomessage-square95fedilink
minus-squarejacksilver@lemmy.worldlinkfedilinkEnglisharrow-up0·1 year agoYeah, this is definitely part of the issue when commercializing LLMs. When someone has to provide an SLA or asking how frequently will this fail, it’s not great when the best answer “who knows”.
Yeah, this is definitely part of the issue when commercializing LLMs. When someone has to provide an SLA or asking how frequently will this fail, it’s not great when the best answer “who knows”.