return2ozma@lemmy.world to Technology@lemmy.worldEnglish · 13 hours agoElon Musk’s Grok AI Has a Problem: It’s Too Accurate for Conservativesgizmodo.comexternal-linkmessage-square22linkfedilinkarrow-up1324arrow-down111cross-posted to: politics@lemmy.worldtechnology@beehaw.orgconservative@sh.itjust.works
arrow-up1313arrow-down1external-linkElon Musk’s Grok AI Has a Problem: It’s Too Accurate for Conservativesgizmodo.comreturn2ozma@lemmy.world to Technology@lemmy.worldEnglish · 13 hours agomessage-square22linkfedilinkcross-posted to: politics@lemmy.worldtechnology@beehaw.orgconservative@sh.itjust.works
minus-squarevenusaur@lemmy.worldlinkfedilinkEnglisharrow-up9·8 hours 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?