Whatever the solution is to AGI, fundamentally it will still have to be describable in the language of mathematics (and stochastics is still mathematics).

I dunno. You're limiting your thought to computer science. I think it's more likely at this point in time biotech will produce an AGI, likely by accident. Worse one that competes directly with us for resource. We dont have a great mathematical description of our own intelligence, doing it for a tricked out slimemould would be just as hard.

> I think it's more likely at this point in time biotech will produce an AGI, likely by accident.

Does a living thing count as AGI? In that case, I'd say that most parents are quite good at creating AGIs ;)

I think you missed the artificial part of AGI.