[ilaksh]

I have seen at least one experiment running a language model or other neural network on (small scale) memory-based computing substrates. That suggests less than 1-2 years to apply them immediately to existing tasks once they are scaled up in terms of compute capacity.

[sroussey]

Many more years than that. And it must be general enough. Otherwise you optimize for A in hardware and 5yr later when producing chips, A is no longer revenant and everyone moved to B.

[foota]

I would have assumed it would take many years longer than that to scale something like this up, based on how long it takes traditional CPU manufacturers to design state of the art chips and manufacturing processes.