Shawn Wang: belief

Transcript context

…Yeah, we often see, I see numbers from the team and you have these multiple methods, not all of them compound. So you mix these together, it's still similar results and some combination of them will have this incredible effect that is really, really super interesting. So it's very systems, you know, a kind of broad systems approach to it that's the most effective. I think I finally get the name of the company, like- Bring it together, yeah. Everything needs to be automated together. All right, just quickly, how does all this work change, just like some of the architectures change? I know a mixture of experts like speculative decoding is a little less efficient because of memory bandwidth. How much of it do you invest when it's a maybe model-specific improvement versus more horizontal thing? Also, you're researching different architectures, so how much do you want to spend time optimizing what state of the art today versus what's coming next?…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.