
1975:
“a lot of people want personal computers, and somehow they assume that the problem is solved now because we have microprocessors, we’re going to be able to run them in our homes, and so we’re not going to need all the stuff in the mainframe. but from a global allocation perspective, actually it’s quite terrible to have everybody, like, have a bunch of the world’s limited supply of memory chips sitting on their own desk and being used five percent of the time. you want maximum utilisation on the time-sharing terminal. somehow many people’s intuition is the opposite of that”
morgan — @morqon
sam: local inference is a terrible allocation of scarce resources
“a lot of people want local inference, and somehow they assume that the problem is solved now because we have open-source models, we're going to be able to run them on our computers, and so we're not going to need all the stuff in the data centre
but from a global allocation perspective, actually it's quite terrible to have everybody, like, have a bunch of the world's limited supply of DRAM sitting in their own computer and being used five percent of the time
you want maximum utilisation in the cloud if you're trying to deal with this very supply-constrained environment
somehow many people's intuition is the opposite of that”