Skip to content

“really something that has, one, a decisive aspect or…” — Practical AI at 46:49

“really something that has, one, a decisive aspect or feature that would be potentially not sufficiently well done with transformers. There's been tons of engineering going into it. So each time you think, oh, maybe quadratic cost is bad, but then people are like, no, you can just hardcore optimize your QDA kernel and…”

0:00 50:03