an agent’s beliefs are typically locally consistent with nearby beliefs but not necessarily globally consistent with all its other beliefs (except, perhaps, in the limit of ideal rationality).
sounded intuitive and elegant, but I haven’t familiarized myself with either PDGs or Garrabrant inductors, so I can’t comment on the specifics.
I want @Kaj_Sotala’s take or connections on this
I thought the general idea of
sounded intuitive and elegant, but I haven’t familiarized myself with either PDGs or Garrabrant inductors, so I can’t comment on the specifics.