(disclaimer that I talked to Sasha before he put up this post) but as a ârandom EA personâ I did find reading this clarifying.
Itâs not that I believed that âorthogonality thesis the reason why AGI safety is an important cause areaâ, but that I had never thought about the distinction between âno known law relating intelligence and motivationsâ and ânear-0 statistical correlation between intelligence and motivationsâ.
If Iâd otherwise been prompted to think about it, Iâd probably have arrived at the former, but I think the latter was rattling around inside my system 1 because the term âorthogonalityâ brings to mind orthogonal vectors.
(disclaimer that I talked to Sasha before he put up this post) but as a ârandom EA personâ I did find reading this clarifying.
Itâs not that I believed that âorthogonality thesis the reason why AGI safety is an important cause areaâ, but that I had never thought about the distinction between âno known law relating intelligence and motivationsâ and ânear-0 statistical correlation between intelligence and motivationsâ.
If Iâd otherwise been prompted to think about it, Iâd probably have arrived at the former, but I think the latter was rattling around inside my system 1 because the term âorthogonalityâ brings to mind orthogonal vectors.