We will observe ourselves creating AGI, and see the AGI creating a simulation to understand its own nature and its past, and that simulation will contain us, observing ourselves creating AGI; there is no way of knowing how deep into the loop we are
-
-
Replying to @Plinz
computational limits mean that can't possibly be true - simulated worlds are either much smaller or much simpler than outer worlds. First AGI likely also small, potentially smaller than humans who created it. AGI != Laplace's demon, could create paradox if it was.
2 replies 0 retweets 3 likes -
Replying to @gallabytes
not necessarily, if the AGI manages to wrest enough processing time from its substrate universe to calculate the first period, heck perhaps it even discovers an API function of the parent universe that was added specifically for that purpose
1 reply 0 retweets 2 likes -
Replying to @Plinz
that just passes the buck, doesn't actually answer the objection. At some point there will be a root universe vastly larger than any it can simulate. You should expect to be there because it's so much larger.
2 replies 0 retweets 0 likes -
Replying to @gallabytes
an AGI is probably going to be based on a principle of growth that is beating a substrate into submission (similar as it happens in our own mind), so unless we introduce limits below the threshold if discovering its own structural principles, it is going to conquer the universe
1 reply 0 retweets 0 likes
the AGI may then decide to run a more efficient simulation of its parent universe, and supply the simulation API to the emerging daughter AGI as a kind of cosmic quantum oracle; you only need to cheat at the root
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.