Sam Altman:
A lot of people want local inference, and somehow they assume that the problem is solved now because we have open-source models, we’re going to be able to run them on our computers, and so we’re not going to need all the stuff in the data center.
But from a global allocation perspective, actually it’s quite terrible to have everybody, like, have a bunch of the world’s limited supply of DRAM sitting in their own computer and being used five percent of the time.
Like you want maximum utilisation in the cloud if you’re trying to deal with this very supply-constrained environment,
And somehow many people’s intuition is the opposite of that
TL;DR Guy selling product: “Here’s why owning your own product instead of renting it from me is a terrible idea”
heh actually working on some stuff to support that as an offshoot of our Neighborgoods project - calling it Neighborcloud, with the idea that people can check out and use capacity like a library item. Including, hopefully, some AI model use.
was talking to someone today about putting your idle computer up for “cloud inference” but he was thinking about how he doesn’t want to run his GPU too much because of wear and tear and ability to replace it
expensive hardware is a problem in any case