carado.moe

tammy's blog about
AI alignment, utopia, anthropics, and more;

my best alignment plan: QACI!

also on twitter, lesswrong, rss

ruling out intuitions about materially acausal things

i have an intuition — not just, and preceeding, a reasoned belief — that i have a weird consciousness-observer-soul-thing. i also have an intuition that moral realism is true, that the arrow of time moves forwards rather than backwards or sideways, that i am a continuous stream of consciousness rather than an instant-observer (such that you might particularly worry about teleportation), that my memories must be true (rather than the universe appearing five minutes ago), and many others.

those can all be ruled out with a simple device: if any of these things were the case, could that causate onto whether such an intuition fires? for all of them, the answer is no: because they are immaterial claims, the fact of them being true or false cannot have causated my thoughts about them. therefore, these intuitions must be discarded when reasoning about them.

that does not mean that those statements are all necessarily false, just that my intuitions for them cannot be providing bayesian evidence. after all, the amount to which bayesians update a belief based on evidence should be as a function of how likely such evidence is to arise given that the belief be true rather than false — even when the evidence is intuition.