I guess my issue is that corrigibility is an exogenous specification; you’re not just saying “the algorithm goes to a fixed point” but rather “the algorithm goes to this particular pre-specified point, and it is a fixed point”. If I pick a longitude and latitude with a random number generator, it’s unlikely to be the bottom of a valley. Or maybe this analogy is not helpful and we should just be talking about corrigibility directly :-P
I guess my issue is that corrigibility is an exogenous specification; you’re not just saying “the algorithm goes to a fixed point” but rather “the algorithm goes to this particular pre-specified point, and it is a fixed point”. If I pick a longitude and latitude with a random number generator, it’s unlikely to be the bottom of a valley. Or maybe this analogy is not helpful and we should just be talking about corrigibility directly :-P