Comment by fluoridation
11 hours ago
>I also don't doubt we are fairly close to making this plausible.
Maybe you should doubt that. There's literally no reason to think this is plausible besides some hype merchants' say-so.
11 hours ago
>I also don't doubt we are fairly close to making this plausible.
Maybe you should doubt that. There's literally no reason to think this is plausible besides some hype merchants' say-so.
> some hype merchants
Excluding Spacex:
Nvidia, Google, China, European Commission, Blue Origin
And this being HN, a YC funded company has put a single GPU rack in space and demonstrated training a reasonable sized model on it.
But yeah, it's all hype, sure.
On the off chance you're sincere and not just heavily over indexed into Elon stocks:
It's trivial to understand why this is all hype if you pay attention to physics, as another commenter suggested earlier.
https://en.wikipedia.org/wiki/Stefan%E2%80%93Boltzmann_law
Assume you're radiating away the heat for a single B200 (~1kW), and the max radiator temp is 100C, you find A = ~3m^2.
So that's 3 square meters per GPU. Now if you take into account that the largest planar structure deployed into space is ~3k m^2 (https://investors.lockheedmartin.com/news-releases/news-rele...), you're looking at 1000 GPUs.
That's a single aisle in a terrestrial data center.
Cost to deploy on earth vs satellite is left as an exercise to the reader.
You are missing one important thing here.
You do not radiate all the heat away from a GPU, a modern GPU can run pretty hot. Also look up how this is getting better for the next generation of GPUs.
Maybe repeat your calculation with updated assumptions?
But even if you were completely right, your argument is that we can't do this tomorrow, yes I agree. Typical technology development cycles are about 5-10 years.
3 replies →