Beauty bias: “Lost in Math” by Sabine Hossenfelder

Link post

This is tech­nic­ally just a link post for those who didn’t see the book yet. The main idea, as I un­der­stand it, is that while some phys­ical the­or­ies are beau­ti­ful, other are com­plex and “ugly”. Beauty should not be taken as evid­ence for truth.

It looks like some­times in AI safety re­search aes­thet­ics may be taken as an evid­ence (I will not provide ex­amples, as in each case it may be just my in­ter­pret­a­tion), and thus pos­sib­il­ity of such beauty bias should be taken into ac­count.