Nemeski@lemm.ee to Technology@lemmy.worldEnglish · 1 年前OpenAI’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 年前message-square100fedilink
minus-squareT156@lemmy.worldlinkfedilinkEnglisharrow-up2·1 年前It 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.