“And then the third piece, I think there's a lot of work to…” — Decoder with Nilay Patel at 16:08
“And then the third piece, I think there's a lot of work to be done around memory caching, how you deploy these models. Do I quantize them? Do I compress them? Do I always need the biggest? So there's a 10x from the software side. You put those three 10s together, that's a thousand times cheaper. So I'm simply saying…”
0:00
1:09:34