There’s no reason to assume frontier-level intelligence eventually collapses all the way onto a midrange consumer GPU. In fact, there are quite a few reasons not to assume that (information-theoretic constraints, etc).

▲

christophilus an hour ago | parent | next [-]

But, it could happen for a coding-focused model, or an accounting-focused model, etc. most tasks only need a subset of the total model to be done effectively.

▲

fooker 43 minutes ago | parent | prev [-]

There's no information theoretic constraint we know of that prevents this. You will almost surely win a Turing award if you can prove this.

It's almost a given that whatever is frontier intelligence today will run on a potato in a few years.

▲

jimbo808 37 minutes ago | parent [-]

Kinda silly to follow your “prove it” challenge with an absurd claim you most certainly cannot prove, much less support with evidence.

	▲	fooker 13 minutes ago \| parent \| next [-]
		It was not a "prove it" challenge. I'm pointing out that there's no known information theoretic constraint about the impossibility of frontier AI models being improved to fit/run on a small GPU. Please do not make up plausible sounding science facts.
	▲	amazingamazing 13 minutes ago \| parent \| prev [-]
		I will not claim a 5070, but there is already evidence in nature that you can get very good general intelligence with an order of magnitude less wattage. There are constraints of course- training takes way longer.