I'm really interested in how we measure moral value across species. I think standardizing a global animal sentience scale and including this kind of data in the w-vector is essential for fair AI alignment. Very exciting also that giving sentient animals moral weight in ethical decisions will lead to policy impact - affecting farming practices, AI-driven environmental policy and synthetic meat decisions.
I first went to go read your previous post "How the Human Psychological 'Program' Undermines AI Alignment" and this is all super interesting! The possibility of future sentient beings is mind-blowing!
I'm really interested in how we measure moral value across species. I think standardizing a global animal sentience scale and including this kind of data in the w-vector is essential for fair AI alignment. Very exciting also that giving sentient animals moral weight in ethical decisions will lead to policy impact - affecting farming practices, AI-driven environmental policy and synthetic meat decisions.