101@reddthat.comdeleted by creator to Technology@lemmy.worldEnglish · 2 years agoIf robots could lie, would we be okay with it? A new study throws up intriguing results.theconversation.comexternal-linkmessage-square31linkfedilinkarrow-up150arrow-down13
arrow-up147arrow-down1external-linkIf robots could lie, would we be okay with it? A new study throws up intriguing results.theconversation.com101@reddthat.comdeleted by creator to Technology@lemmy.worldEnglish · 2 years agomessage-square31linkfedilink
minus-squarewewbull@feddit.uklinkfedilinkEnglisharrow-up1·2 years ago…but if they don’t know I expect them to say so. An LLM isn’t trustworthy until it says “I don’t know”.
…but if they don’t know I expect them to say so. An LLM isn’t trustworthy until it says “I don’t know”.