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.
I’m not saying I’m willing to code that up; I’m just saying that a genetic algorithm (such as Evolution) creating agents which use heuristics to generate hypotheses (such as humans) can work at least as well as anything we’ve got so far.
I’m just saying that a genetic algorithm (such as Evolution) creating agents which use heuristics to generate hypotheses (such as humans) can work at least as well as anything we’ve got so far.
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.
I’m not saying I’m willing to code that up; I’m just saying that a genetic algorithm (such as Evolution) creating agents which use heuristics to generate hypotheses (such as humans) can work at least as well as anything we’ve got so far.
If you have a few billion years to wait.
No reason that can’t be sped up.