In his recent Dwarkesh Patel interview, Musk is pretty clear about why he wants to go to the moon: he wants to build a ton of solar panels to capture more of the sun’s energy, its easier to launch from the moon than from the earth, and the moon has plenty of silicon[1]. He is also pretty clear that he wants to build datacenters in orbit. I don’t think we need to speculate to get answers here.
For Elon motivating SpaceX employees is important, so he needs to tell the public a story about how SpaceX isn’t just about building AI datacenters even if he thinks building superintelligence is the main goal of SpaceX and it’s important to build AI datacenters for that and he can’t build enough of them on earth.
As far as the AI datacenters in orbit go, it’s not clear to me that the thermodynamics work out for that project and it’s easy enough to lose the heat that the datacenters produce.
For Elon motivating SpaceX employees is important, so he needs to tell the public a story about how SpaceX isn’t just about building AI datacenters even if he thinks building superintelligence is the main goal of SpaceX and it’s important to build AI datacenters for that and he can’t build enough of them on earth.
In the interview he argues that the reason he wants to build a ton of solar panels to capture a bunch of the sun’s energy is because of AI, he really comes across as extremely AI pilled, he is not downplaying his exciting singularity-inducing AI-related objectives in order to convince SpaceX employees to work on making solar panels from moon dust.
As far as the AI datacenters in orbit go, it’s not clear to me that the thermodynamics work out for that project and it’s easy enough to lose the heat that the datacenters produce.
What thermodynamics are you concerned about? It is extremely efficient to radiate heat in space (a good thing too because that is your only option!). The equation here is the Stefam-Boltzmann law, which says
P=εσAT4
where P is the power you radiate away, ε is your emissivity, σ is the Stefan-Boltzmann constant, A is your surface area, and T is your temperature. Note that that is T4, small changes in your temperature have large bang-for-your-buck in your radiation power. Intuitively, this should make things easy.
I got Claude to run the numbers, and Claude found that the launch cost of the radiator would only add $3M, assuming $200/kg. Meanwhile AI “hyperscaling” datacenters cost around $100M to build, and (assuming solar panels are already up there) weigh 200 tons leading to a launch cost of $40M. That is to say, compared to the other costs involved, the radiator seems very minor.
Claude’s radiation analysis
Alright, let’s just do vanilla flat-panel radiators at elevated chip temps.
Assumptions
Data center thermal load: P=10 MW (moderate — a hyperscaler pod is 20-50 MW, but let’s start here)
Emissivity: ε=0.92 (anodized aluminum or similar high-ε coating)
Two-sided radiation (both faces of panel radiate to space)
Background sink temperature: Tsink≈3 K (negligible, so we ignore it)
Sun-shielded radiators (no solar absorption)
Stefan-Boltzmann
q=εσT4
where σ=5.67×10−8 W m−2K−4.
Per side, per m²:
Radiator Temp
q (W/m²)
Two-sided (W/m²)
350 K (77°C)
783
1,566
400 K (127°C)
1,336
2,671
450 K (177°C)
2,139
4,278
500 K (227°C)
3,261
6,522
Required Area for 10 MW
A=P2εσT4
Radiator Temp
Area (m²)
Equiv. square panel side
350 K
6,386
~80 m
400 K
3,744
~61 m
450 K
2,338
~48 m
500 K
1,533
~39 m
At 500 K the radiator is roughly the footprint of a large warehouse. Not crazy.
Mass Estimate
Aluminum honeycomb radiator panels run about 3–5 kg/m² with embedded heat pipes for thermal spreading. Call it 4 kg/m².
Radiator Temp
Area (m²)
Radiator mass (tonnes)
350 K
6,386
25.5
400 K
3,744
15.0
450 K
2,338
9.4
500 K
1,533
6.1
At current Starship-aspirational costs (~$200/kg to LEO), the 500 K case is about $1.2M just for radiator launch mass. Very manageable relative to the cost of the compute hardware itself.
The Chip Temperature Constraint
Here’s where it gets real. You need a thermal gradient from junction → coolant → radiator. Typical chain:
Tjunction=Tradiator+ΔTinterface+ΔTtransport
If ΔTtransport≈20–50 K (pumped liquid loop) and ΔTinterface≈10–20 K, then:
Radiator Temp
Required Tjunction
400 K
~450–470 K (177–197°C)
450 K
~500–520 K (227–247°C)
500 K
~550–570 K (277–297°C)
Standard silicon tops out around 150°C junction temp for reliability. SiC or GaN can handle 250°C+, but nobody’s making data-center-class GPUs in those processes. So realistically you’re stuck at ~400 K radiator temp unless you accept exotic semiconductors, which puts you at ~3,700 m² and 15 tonnes of radiator for 10 MW.
Bottom Line Spec Sheet (Conservative)
Thermal load: 10 MW
Radiator temp: 400 K
Radiator area: 3,744 m² (~61m × 61m)
Radiator mass: ~15 tonnes
Coolant: pumped single-phase liquid loop
Launch cost (radiators only): ~$3M at $200/kg
Constraint: must be sun-shielded or edge-on to sun
The T4 scaling means even modest advances in high-temp compute (say, junction temps of 200°C becoming standard) buy you a lot of radiator mass savings.
Claude’s datacenter launch cost analysis
Good question. Let me break this down by component. I’ll need to look up some specifics on modern rack densities.Okay, great data. Let me work through this.
The Compute Hardware
The GB200 NVL72 rack weighs 1.36 metric tons and draws ~120 kW. But the full deployment arrives in four components: compute rack (1,500 kg), NVLink Switch rack (800 kg), CDU (400 kg), and PDU (300 kg) — totaling ~3,000 kg.
For 10 MW of IT load:
Nracks=10,000 kW120 kW/rack≈83 racks
Mass Budget
Component
Per rack (kg)
× 83 racks (tonnes)
Needed in space?
Compute rack
1,500
124.5
Yes
NVLink switch rack
800
66.4
Yes
CDU (coolant dist.)
400
33.2
Redesigned¹
PDU
300
24.9
Redesigned²
Terrestrial total
3,000
249
¹ You still need pumped-loop coolant distribution, but the CDU on Earth interfaces with building chilled water. In space, it interfaces with the radiator loop directly — probably lighter.
² Power distribution from solar is DC→DC, not AC→DC. Simpler, lighter. Call it half mass.
Optimistic space mass estimate: strip CDUs to ~200 kg (simpler loop), PDUs to ~150 kg (DC-native), and you could probably shave ~20% off structural rack mass since you don’t need to support against gravity (though you still need rigidity for launch loads and thermal expansion).
Component
Space-adapted (kg)
× 83 (tonnes)
Compute rack
1,200
99.6
NVLink switches
650
53.9
Coolant distribution
200
16.6
Power distribution
150
12.5
Space total
~2,200
~183
Add ~10% for structural housing, cabling, interconnects between racks, thermal interface hardware → ~200 tonnes for the compute payload.
Cost
Hardware procurement: All-in cost per GB200 NVL72 rack is about $3.9M for a typical hyperscaler, so:
83×$3.9M≈$324M
Launch cost at $200/kg (aspirational Starship):
200,000 kg×$200/kg=$40M
At current Falcon Heavy prices (~$2,000/kg):
200,000 kg×$2,000/kg=$400M
Summary
Item
Cost
GPU/compute hardware
~$324M
Radiator hardware + fabrication
~$15M
Launch (compute, @$200/kg)
~$40M
Launch (radiators, 15t @$200/kg)
~$3M
Launch (compute, @$2000/kg)
~$400M
Total (optimistic Starship)
~$380M
Total (current launch prices)
~$740M
For reference, a comparable terrestrial datacenter is $100–150M. So you’re paying a 3–5× premium at Starship prices, mostly for the hardware itself (which costs the same either way). The launch cost is actually not the dominant term at $200/kg — the GPUs are.
The real kicker: GPU lifetime is ~3 years before obsolescence. On Earth you swap them. In orbit, you’ve got a $324M asset that’s depreciating at $108M/year and is very hard to service. That’s arguably the actual killer for the economics, not the physics.
In his recent Dwarkesh Patel interview, Musk is pretty clear about why he wants to go to the moon: he wants to build a ton of solar panels to capture more of the sun’s energy, its easier to launch from the moon than from the earth, and the moon has plenty of silicon [1] . He is also pretty clear that he wants to build datacenters in orbit. I don’t think we need to speculate to get answers here.
Also, it keeps things interesting for the simulator gods.
For Elon motivating SpaceX employees is important, so he needs to tell the public a story about how SpaceX isn’t just about building AI datacenters even if he thinks building superintelligence is the main goal of SpaceX and it’s important to build AI datacenters for that and he can’t build enough of them on earth.
As far as the AI datacenters in orbit go, it’s not clear to me that the thermodynamics work out for that project and it’s easy enough to lose the heat that the datacenters produce.
In the interview he argues that the reason he wants to build a ton of solar panels to capture a bunch of the sun’s energy is because of AI, he really comes across as extremely AI pilled, he is not downplaying his exciting singularity-inducing AI-related objectives in order to convince SpaceX employees to work on making solar panels from moon dust.
What thermodynamics are you concerned about? It is extremely efficient to radiate heat in space (a good thing too because that is your only option!). The equation here is the Stefam-Boltzmann law, which says
P=εσAT4where P is the power you radiate away, ε is your emissivity, σ is the Stefan-Boltzmann constant, A is your surface area, and T is your temperature. Note that that is T4, small changes in your temperature have large bang-for-your-buck in your radiation power. Intuitively, this should make things easy.
I got Claude to run the numbers, and Claude found that the launch cost of the radiator would only add $3M, assuming $200/kg. Meanwhile AI “hyperscaling” datacenters cost around $100M to build, and (assuming solar panels are already up there) weigh 200 tons leading to a launch cost of $40M. That is to say, compared to the other costs involved, the radiator seems very minor.
Claude’s radiation analysis
Alright, let’s just do vanilla flat-panel radiators at elevated chip temps.
Assumptions
Data center thermal load: P=10 MW (moderate — a hyperscaler pod is 20-50 MW, but let’s start here)
Emissivity: ε=0.92 (anodized aluminum or similar high-ε coating)
Two-sided radiation (both faces of panel radiate to space)
Background sink temperature: Tsink≈3 K (negligible, so we ignore it)
Sun-shielded radiators (no solar absorption)
Stefan-Boltzmann
q=εσT4where σ=5.67×10−8 W m−2K−4.
Per side, per m²:
Required Area for 10 MW
A=P2εσT4At 500 K the radiator is roughly the footprint of a large warehouse. Not crazy.
Mass Estimate
Aluminum honeycomb radiator panels run about 3–5 kg/m² with embedded heat pipes for thermal spreading. Call it 4 kg/m².
At current Starship-aspirational costs (~$200/kg to LEO), the 500 K case is about $1.2M just for radiator launch mass. Very manageable relative to the cost of the compute hardware itself.
The Chip Temperature Constraint
Here’s where it gets real. You need a thermal gradient from junction → coolant → radiator. Typical chain:
Tjunction=Tradiator+ΔTinterface+ΔTtransportIf ΔTtransport≈20–50 K (pumped liquid loop) and ΔTinterface≈10–20 K, then:
Standard silicon tops out around 150°C junction temp for reliability. SiC or GaN can handle 250°C+, but nobody’s making data-center-class GPUs in those processes. So realistically you’re stuck at ~400 K radiator temp unless you accept exotic semiconductors, which puts you at ~3,700 m² and 15 tonnes of radiator for 10 MW.
Bottom Line Spec Sheet (Conservative)
Thermal load: 10 MW
Radiator temp: 400 K
Radiator area: 3,744 m² (~61m × 61m)
Radiator mass: ~15 tonnes
Coolant: pumped single-phase liquid loop
Launch cost (radiators only): ~$3M at $200/kg
Constraint: must be sun-shielded or edge-on to sun
The T4 scaling means even modest advances in high-temp compute (say, junction temps of 200°C becoming standard) buy you a lot of radiator mass savings.
Claude’s datacenter launch cost analysis
Good question. Let me break this down by component. I’ll need to look up some specifics on modern rack densities.Okay, great data. Let me work through this.
The Compute Hardware
The GB200 NVL72 rack weighs 1.36 metric tons and draws ~120 kW. But the full deployment arrives in four components: compute rack (1,500 kg), NVLink Switch rack (800 kg), CDU (400 kg), and PDU (300 kg) — totaling ~3,000 kg.
For 10 MW of IT load:
Nracks=10,000 kW120 kW/rack≈83 racksMass Budget
¹ You still need pumped-loop coolant distribution, but the CDU on Earth interfaces with building chilled water. In space, it interfaces with the radiator loop directly — probably lighter.
² Power distribution from solar is DC→DC, not AC→DC. Simpler, lighter. Call it half mass.
Optimistic space mass estimate: strip CDUs to ~200 kg (simpler loop), PDUs to ~150 kg (DC-native), and you could probably shave ~20% off structural rack mass since you don’t need to support against gravity (though you still need rigidity for launch loads and thermal expansion).
Add ~10% for structural housing, cabling, interconnects between racks, thermal interface hardware → ~200 tonnes for the compute payload.
Cost
Hardware procurement: All-in cost per GB200 NVL72 rack is about $3.9M for a typical hyperscaler, so:
83×$3.9M≈$324MLaunch cost at $200/kg (aspirational Starship):
200,000 kg×$200/kg=$40MAt current Falcon Heavy prices (~$2,000/kg):
200,000 kg×$2,000/kg=$400MSummary
For reference, a comparable terrestrial datacenter is $100–150M. So you’re paying a 3–5× premium at Starship prices, mostly for the hardware itself (which costs the same either way). The launch cost is actually not the dominant term at $200/kg — the GPUs are.
The real kicker: GPU lifetime is ~3 years before obsolescence. On Earth you swap them. In orbit, you’ve got a $324M asset that’s depreciating at $108M/year and is very hard to service. That’s arguably the actual killer for the economics, not the physics.