I don’t think compute is the bottleneck for testing for this. Sorting out some of our own philosophical confusions is, plus lots of engineering effort to construct test environments maybe (in which e.g. the AIs can be asked how they feel, in a more rigorous way), plus lots of interpretability work.
I don’t think compute is the bottleneck for testing for this. Sorting out some of our own philosophical confusions is, plus lots of engineering effort to construct test environments maybe (in which e.g. the AIs can be asked how they feel, in a more rigorous way), plus lots of interpretability work.