“per inference per query, it should only use less than 0.02…” — Azeem Azhar's Exponential View at 12:51
“per inference per query, it should only use less than 0.02 kilowatt hours of energy, something like that. And if you only run a model like once a week because you're doing climate prediction, then it's okay if it uses more, right? So I think there's different kind of gradations. The way I thought about it a little…”
0:00
34:04