[tjoff]

Don't really buy the economic argument. For 99% pf all workloads you need at least an order of magnitude more system memory than gpu memory.

Most systems barely need more gpu memory than what is required for video, browsing etc.

Just because we found a new usecase doesn't flip that on its head.

Besides, I want to keep doing what I'm doing today. So if I need 128GB today and my local AI needs 128 GB then I'd need 256 GB to keep doing the same work.

The argument rather seems to be that we shouldn't use such expensive memory on the GPU. Which might be true if you only want to do inference on it.

[Joel_Mckay]

Jensen Huang has publicly stated he wants a future where "AI" agents use more PC computers than people.

It is ambitious, and absurd... like all CEOs that eventually go loopy. =3