An argument can be true in its parts and still mislead by presenting an oversimplified model. The quote below is pointing out that timesharing can obviously be more efficient in theory -- but ignoring the equally obvious objection that data center operators can't be trusted to allocate towards global efficiency in practice.

> A lot of people want local inference. And somehow, they assume that the problem is solved now. Because, we are going to 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 center. But from a global allocation perspective, actually, it’s quite terrible to have everybody have a bunch of the world’s limited supply of DRAM sitting in their own computer. And, being used 5% of the time. You want maximum utilization in the cloud if you’re trying to deal with this very supply constrained environment. And somehow everyone’s... Many people’s intuition is the opposite of that.