There are 2 questions here, the intelligence of existing algorithms with new hardware, and the intelligence of new algorithms with existing hardware.
We could be (and probably are) in a world where existing algorithms + more hardware and existing hardware + better algorithms can both lead to superintelligence. In which case the question is how much progress is needed, and how long it will take.
When you say “[w]e could be (and probably are) in a world where existing algorithms + more hardware…can…lead to superintelligence” are you referring to popular algorithms like GPT or obscure algorithms buried in a research paper somewhere?
There are 2 questions here, the intelligence of existing algorithms with new hardware, and the intelligence of new algorithms with existing hardware.
We could be (and probably are) in a world where existing algorithms + more hardware and existing hardware + better algorithms can both lead to superintelligence. In which case the question is how much progress is needed, and how long it will take.
When you say “[w]e could be (and probably are) in a world where existing algorithms + more hardware…can…lead to superintelligence” are you referring to popular algorithms like GPT or obscure algorithms buried in a research paper somewhere?
Possibly GPT3 x 100. Or RL of similar scale.
Very likely Evolution (with enough compute, but you might need a lot of compute.)
AIXI. You will need a lot of compute.
I was kind of referring to the disjunction.