cm0002@lemmy.world to Technology@lemmy.worldEnglish · 2 months agoAI models routinely lie when honesty conflicts with their goalswww.theregister.comexternal-linkmessage-square118fedilinkarrow-up1598arrow-down126
arrow-up1572arrow-down1external-linkAI models routinely lie when honesty conflicts with their goalswww.theregister.comcm0002@lemmy.world to Technology@lemmy.worldEnglish · 2 months agomessage-square118fedilink
minus-squareCosmoNova@lemmy.worldlinkfedilinkEnglisharrow-up21arrow-down3·2 months agoIt’s interesting they call it a lie when it can’t even think but when any person is caught lying media will talk about “untruths” or “inconsistencies”.
minus-squareMrVilliam@lemm.eelinkfedilinkEnglisharrow-up20·2 months agoWell, LLMs can’t drag corporate media through long, expensive, public, legal battles over slander/libel and defamation. Yet.
minus-squaretechnocrit@lemmy.dbzer0.comlinkfedilinkEnglisharrow-up2arrow-down3·2 months agoIf capitalist media could profit from humanizing humans, it would.
minus-squarethedruid@lemmy.worldlinkfedilinkEnglisharrow-up2arrow-down9·2 months agoNot relevant to the conversation.
It’s interesting they call it a lie when it can’t even think but when any person is caught lying media will talk about “untruths” or “inconsistencies”.
Well, LLMs can’t drag corporate media through long, expensive, public, legal battles over slander/libel and defamation.
Yet.
If capitalist media could profit from humanizing humans, it would.
Not relevant to the conversation.