minus-squarevenusaur@lemmy.worldtoTechnology@lemmy.world•Elon Musk’s Grok AI Has a Problem: It’s Too Accurate for ConservativeslinkfedilinkEnglisharrow-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? linkfedilink
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?