As Stuart referenced in his comment to your post here, value extrapolation can be the key to AI alignment *without* using it to deduce the set of human values. See the ‘List of partial failures’ in the original post: With value extrapolation, these approaches become viable.
Hi David,
As Stuart referenced in his comment to your post here, value extrapolation can be the key to AI alignment *without* using it to deduce the set of human values. See the ‘List of partial failures’ in the original post: With value extrapolation, these approaches become viable.