Evidence receipt / belief
Published · transcript-backedCe Zhang: belief
8 Feb 2024 Latent Space Cloud Intelligence at the speed of 5000 tok/s - with Ce Zhang and Vipul Ved Prakash of Together AI
“If you go to AWS, you do know which region you are in, right? So I think one thing that we are trying to do is you have this disaggregated cloud, not only about location or geographically where they are, but about this reliability and also this diversity of this infrastructure.”
— Ce Zhang
Source trail
Everything needed to verify it.
- Speaker
- Ce Zhang
- Attribution
- Verified speaker
- Claim type
- belief
- Recorded
- 8 Feb 2024
- Publisher
- Latent Space
Transcript context
…Aren't most clouds disaggregated? Like what's different about it? So one way is that most of the cloud are disaggregated, but some of that is actually being exposed to the user, right? If you go to AWS, you do know which region you are in, right? So I think one thing that we are trying to do is you have this disaggregated cloud, not only about location or geographically where they are, but about this reliability and also this diversity of this infrastructure. So, and if we want to build a reliable, high-quality layer over that, the user actually don't know, right? What's actually happening under the cover, right? So I think that's one of the difference of the way that we are thinking about infrastructure. Yeah, a bit closer to Cloudflare than AWS. Yeah. Yeah. We have one question here, which we'll just throw out, it's kind of fun. So going back to this sort of inference stack piece, maybe if you had to pull out like a call for researcher or just like point out interesting areas of work that you're interested in, what pieces of the stack have the most opportunity for improvement?…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.