but if we can take the type signature from a simulation, then we can attempt to do formal reasoning about its possibility space given the concrete example. if we don’t have precise types, we can’t reason through these systems. b seems to me to be a falsifiable claim that cannot be determined true or false from pure rational computation, it requires active investigation. we have evidence of it, but that evidence needs to be cited.
but if we can take the type signature from a simulation, then we can attempt to do formal reasoning about its possibility space given the concrete example. if we don’t have precise types, we can’t reason through these systems. b seems to me to be a falsifiable claim that cannot be determined true or false from pure rational computation, it requires active investigation. we have evidence of it, but that evidence needs to be cited.
How does your approach compare with https://www.metaethical.ai/?