Let's consider the agent given in A model of UDT with a halting oracle. One will notice that that agent is not quite well defined because it doesn't tell us in what order we are supposed to consider actions in step 1. But surely that doesn't matter, right? Wrong. Let's...
In this article cousin_it describes an algorithm, using a Turing Oracle, which gives a working model of UDT. This algorithm seems to work well in the case of a utility function which takes natural numbers or rationals as values but, as I will explain, the algorithm doesn't actually work for...
It seem to me possible to create a safe oracle AI. Suppose that you have a sequence predictor which is a good approximation of Solomonoff induction but which run in reasonable time. This sequence predictor can potentially be really useful (for example, predict future siai publications from past siai publications...