Very interesting post! Do you think the recent work on model introspection 1 2 3 has an impact here? Could developing tools to monitor introspection assist with interp?
I’m not sure, but want to find out! I find these model introspection papers fascinating, and want to write about this next.
Very interesting post! Do you think the recent work on model introspection 1 2 3 has an impact here? Could developing tools to monitor introspection assist with interp?
I’m not sure, but want to find out! I find these model introspection papers fascinating, and want to write about this next.