The bitter lesson applies to alignment as well. Stop trying to think about “goal slots” whose circuit-level contents should be specified by the designers, or pining for a paradigm in which we program in a “utility function.” That isn’t how it works.
Hm, isn’t the (relative) success of activation engineering and related methods and findings (e.g. In-Context Learning Creates Task Vectors) some evidence against this view (at least taken very literally / to the extreme)? As in, shouldn’t task vectors seem very suprising under this view?
Hm, isn’t the (relative) success of activation engineering and related methods and findings (e.g. In-Context Learning Creates Task Vectors) some evidence against this view (at least taken very literally / to the extreme)? As in, shouldn’t task vectors seem very suprising under this view?