In a parallel universe with a saner civilization, there must be tons of philosophy professors workings with tons of AI researchers to try to improve AI’s philosophical reasoning.
Quite a lot of the questions that have been considered in Philosophy are related to how minds work, with the most of the evidence available until now being introspection. Since we are now building minds, and starting to do mechanistic interpretability on them, I am hoping that we’ll get to the point where AI researchers can help improve the philosophical reasoning of philosophy professors, on subjects relating to how minds work.
Yeah, it seems like a potential avenue of philosophical progress. Do you have ideas for what specific questions could be answered this way and what specific methods might be used?
Quite a lot of the questions that have been considered in Philosophy are related to how minds work, with the most of the evidence available until now being introspection. Since we are now building minds, and starting to do mechanistic interpretability on them, I am hoping that we’ll get to the point where AI researchers can help improve the philosophical reasoning of philosophy professors, on subjects relating to how minds work.
Yeah, it seems like a potential avenue of philosophical progress. Do you have ideas for what specific questions could be answered this way and what specific methods might be used?