I am not persuaded that the harder Bayesians have any more concrete answer. Solmonoff induction is uncomputable and seems to unnaturally favour short hypotheses involving Busy-Beaver-sized numbers. And any computable approximation to it looks to me like brute-forcing an NP-hard problem.
What if, as a computational approximation of the universal prior, we use genetic algorithms to generate a collection of agents, each using different heuristics to generate hypotheses? I mean, there's probably better approximations than that; but we have strong evidence that this one works and is computable.
What if, as a computational approximation of the universal prior, we use genetic algorithms to generate a collection of agents, each using different heuristics to generate hypotheses?
Whatever approach to AGI anyone has, let them go ahead and try it, and see if it works. Ok, that would be rash advice if I thought it would work (because of UFAI), but if it has any chance of working, the only way to find out is to try it.
Here's the new thread for posting quotes, with the usual rules: