Nemeski@lemm.ee to Technology@lemmy.worldEnglish · 1 year agoOpenAI’s latest model will block the ‘ignore all previous instructions’ loopholewww.theverge.comexternal-linkmessage-square100fedilinkarrow-up1446arrow-down17
arrow-up1439arrow-down1external-linkOpenAI’s latest model will block the ‘ignore all previous instructions’ loopholewww.theverge.comNemeski@lemm.ee to Technology@lemmy.worldEnglish · 1 year agomessage-square100fedilink
minus-squareT156@lemmy.worldlinkfedilinkEnglisharrow-up2·1 year agoIt won’t be long before you end up with language models that suggest ways to break other language models.
It won’t be long before you end up with language models that suggest ways to break other language models.