Fraser

against that one ra­tio­nal­ist mashal about japanese fifth-columnists

• Fraser 13 Mar 2025 7:08 UTC

  1 point

  0

  in reply to: Ape in the coat’s comment on: You don’t ac­tu­ally need a phys­i­cal mul­ti­verse to ex­plain an­thropic fine-tun­ing.

  If the observer is distinct from Alice, absolutely. If the observer is Alice, nothing needs explaining in either case.

  To put a bit of a crude metaphor on it, if you were to pick a random number uniformly between 0 and 1,000,000, and pre-commit to having a child on iff it’s equal to some value X—from the point of view of the child, the probability that the number was equal to X is 100%.
  
  Apologies if there’s something more subtle with your answer that I’ve missed.

• Fraser 12 Mar 2025 16:13 UTC

  1 point

  0

  in reply to: Viliam’s comment on: You don’t ac­tu­ally need a phys­i­cal mul­ti­verse to ex­plain an­thropic fine-tun­ing.

  If the only observable outcome is the one in which we got that extremely lucky, then it doesn’t need explaining. You only can observe outcomes compatible with the fact of you making an observation.

You don’t ac­tu­ally need a phys­i­cal mul­ti­verse to ex­plain an­thropic fine-tun­ing.

In­tro­duc­ing Align­men­tSearch: An AI Align­ment-In­formed Con­ver­sional Agent