Fucked Up

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”

Just saw this post on Facebook. I think he sums up Bradford pretty well.

Throughout the episode, you can kind of sense that Anthony Bourdain is wrestling with this underlying question of, "What exactly is Toronto?", it keeps coming up in the subtext, or even directly throughout the episode. There's even a moment where it seems like he kind of stares off into the distance wondering why he can't get an answer or figure it out.