return2ozma@lemmy.world to Technology@lemmy.worldEnglish · 21 days agoElon Musk’s Grok AI Has a Problem: It’s Too Accurate for Conservativesgizmodo.comexternal-linkmessage-square28linkfedilinkarrow-up1437arrow-down117cross-posted to: technology@beehaw.orgconservative@sh.itjust.workspolitics@lemmy.world
arrow-up1420arrow-down1external-linkElon Musk’s Grok AI Has a Problem: It’s Too Accurate for Conservativesgizmodo.comreturn2ozma@lemmy.world to Technology@lemmy.worldEnglish · 21 days agomessage-square28linkfedilinkcross-posted to: technology@beehaw.orgconservative@sh.itjust.workspolitics@lemmy.world
minus-squarevenusaur@lemmy.worldlinkfedilinkEnglisharrow-up15·21 days agoThis is interesting. If two AI models are training on content with opposing biases, and continue to adjust their functionality based on rewards from interactions with the whole world, would they eventually have the same opinions?
This is interesting. If two AI models are training on content with opposing biases, and continue to adjust their functionality based on rewards from interactions with the whole world, would they eventually have the same opinions?