Comment by 0cf8612b2e1e
6 hours ago
That is not a fake argument, but real physics. Yes, you can design out X kw can be dissipated by this much radiators, but that adds an enormous quantity of mass, more than the solar panels that feed it.
If you are trying to generate a profit, every extra kg puts you further in the red. It still costs over $1000/kg of mass to get into orbit.
So is it a physics problem or an economic problem? Sounds to me like you are acknowledging that it is just an economic problem. If it cost $1/kg to get to orbit then this wouldn't be a problem, right? Just make a bigger radiator.
But if it's an economic argument, then you need to do the actual math. How big is the radiator? How low could the price to orbit go? How much can you charge per million tokens in 2030?
The reason this is a fake argument is because the validity depends on the math, and nobody advancing the "you can't cool stuff in space" argument is actually doing the math.
The economics is constrained by physics. AI in space is not viable if it costs $1000/kg to launch to space. Starship promises to cut that down to $100/kg (more if you believe Elon, but most don't), but that's still not competitive.
Sure, things would be different if the cost was $1/kg, but short of somebody building a space elevator that's just not going to happen.
I won't believe less than $100/kg until I see it. I agree with you on that.
But are you sure that $100/kg is not competitive? I don't remember all the math, but even their initial AI1 design[1] would throw a lot of profit, if you can sell at the price they offered to Anthropic.
I suspect the price of manufacturing the satellite, plus chips, is the dominating factor, not necessarily the launch costs.
[1] https://www.spacex.com/spacexai/starmind
Okay any argument about why space is uniquely challenging is going to revolve around physics. Sure it's not literally physically impossible, but we need to explain to people why this is different from shipping the GPUs to Ohio.
If you want math then https://andrewmccalip.com/space-datacenters exists. The numbers are grim for orbital DC. Even if you drag the launch cost slider all the way to $1/kg (by the way this is literally sci-fi, per ChatGPT air freight of semiconductors from Taiwan to Ohio costs $9/kg and ocean/train freight costs a bit under $1/kg for a reasonable shipment so good luck with $1/kg to LEO this century) it is still more than twice as expensive as terrestrial DCs.
It's a fundamental physics problem. You need to have huge radiating surfaces.
A 1GW datacenter with chips operating at 100C (which is probably doable) will need a radiator that has a surface of one square _kilometer_, and this is with all the favorable assumptions. Realistically you'll need about 2x of that.
If you want your DCs to be on a 1000km orbit (for reasonable ping times), you'll be able to _resolve_ these satellites with a naked eye!
Sorry. But this idea is fundamentally unworkable.
The current plan is for 250 kW peak with 160 m^2 radiators. It will weigh about 4 tons so you can pack 25 on one flight of Starship.
Deploy 4,000 and you're at 1 GW. That's 160 launches.
BTW: SpaceX has already manufactured and launched 10,000 Starlink satellites and Falcon 9 launches about 150 times per year. None of this seems unworkable.
1 reply →