ugjka to Technology@lemmy.worldEnglish • 7 months agoSomebody managed to coax the Gab AI chatbot to reveal its promptinfosec.exchangeexternal-linkmessage-square298fedilinkarrow-up11.02K cross-posted to: aicompanions@lemmy.world
arrow-up11.02Kexternal-linkSomebody managed to coax the Gab AI chatbot to reveal its promptinfosec.exchangeugjka to Technology@lemmy.worldEnglish • 7 months agomessage-square298fedilink cross-posted to: aicompanions@lemmy.world
minus-square@Emerald@lemmy.worldlinkfedilinkEnglish64•7 months agoTheir AI chatbot has a name suspiciously close to Aryan, and it’s trained to deny the holocaust.
minus-square@laurelraven@lemmy.blahaj.zonelinkfedilinkEnglish45•7 months agoBut it’s also told to be completely unbiased! That prompt is so contradictory i don’t know how anyone or anything could ever hope to follow it
minus-square@SkyezOpen@lemmy.worldlinkfedilinkEnglish29•7 months agoReality has a left wing bias. The author wanted unbiased (read: right wing) responses unnumbered by facts.
minus-square@jkrtn@lemmy.mllinkfedilinkEnglish16•7 months agoIf one wants a Nazi bot I think loading it with doublethink is a prerequisite.
Their AI chatbot has a name suspiciously close to Aryan, and it’s trained to deny the holocaust.
But it’s also told to be completely unbiased!
That prompt is so contradictory i don’t know how anyone or anything could ever hope to follow it
Reality has a left wing bias. The author wanted unbiased (read: right wing) responses unnumbered by facts.
If one wants a Nazi bot I think loading it with doublethink is a prerequisite.