Although good alignment research has been done that does not involve maths [e.g. here and here ] good math* remains the best high-level proxy of nontrivial, substantive, deep ideas that will actually add up to durable knowledge.
*what distinguishes good math from bad math? that’s a tricky question that requires a strong inside view.
Everyone disagrees, but Thomas Larsen has now answered this here in a way I’m satisfied with.
ELK is a surprisingly promising agenda that could actually work.
The ones with actual math.
why?
Although good alignment research has been done that does not involve maths [e.g. here and here ] good math* remains the best high-level proxy of nontrivial, substantive, deep ideas that will actually add up to durable knowledge.
*what distinguishes good math from bad math? that’s a tricky question that requires a strong inside view.