echoangle
I’m still not sure how people can believe this, this makes zero sense to me.
There is no easy passive cooling in space, getting rid of heat is a major problem. And you need more redundancy because the radiation will crash your computers. And launch is very expensive of course.
And the whole presentation is completely ludicrous. Look at table 1 in the linked PDF and tell me you’re serious. There is no additional cost when sending a datacenter to space except launch cost and shielding? Building a server farm on earth is the same price as building a satellite you can launch on a rocket as long as you use the same computers?
slashdev
I agree, this is makes no sense at all.
Can I take the other side of this investment? Like an angel funding round, but selling short?
jsheard
I think the other side of this is just buying Amazon stock, based on the bold and daring prediction that big grey buildings full of servers aren't going anywhere.
echoangle
That still leaves you with the risk that Amazon is replaced by other earth-based data center operators.
debatem1
If you figure out how to do this I will invest in your fund.
esperent
> There is no easy passive cooling in space, getting rid of heat is a major problem
Nonetheless getting rid of heat (by radiation) is possible, otherwise people would be roasted inside the ISS.
I'm sure all of these companies are advertising "ChatGPT in Space!" because that's what will generate hype and money, but what they'll actually be planning is very small edge data centers whose job is to reduce latency.
Whether that makes financial sense, I have no idea. But I am sure it's at least physically possible for a small enough data center.
echoangle
Of course it’s possible. But they are acting like having the datacenter in space is actually an advantage over earth because space is cold.
That’s like saying „if you’re thirsty on a ship, getting thrown into the sea is actually really nice because you will be around a lot of water.“.
Physically, you could do it, but it won’t be simpler or cheaper than on earth. Except for constant solar availability, there are only downsides with this.
matt-p
Reduce latency for what? I can't think of how, unless of course you ran a laser down to starlink or some other completely impractical plan.
lxgr
> very small edge data centers whose job is to reduce latency
Reduce latency to where?
trebligdivad
Could this be a military image processing use? - imagining you're scooping up earth observation in real time, if you AI analysed it locally and then just sent a 'Missile at coordinate.....' and then just the image where you spotted it, it wouldn't be so much the latency as the bandwidth reduction.
dfltr
There should be a whole checklist of "Things that were still a hard problem in The Expanse" that any space-related startup has to answer.
BirAdam
Yeah, it would make more sense to put some DCs in Patagonia.
amelius
Read the "Thermal Management" section, page 8 ...
echoangle
I believe that it’s physically possible to build something like this, but there’s no way it will be cheaper or simpler than cooling on earth. In their comparison table (table 1), they have earth based cooling for a 40 MW cluster over ten years at 7 million dollars and on the right side calculate the space cost as $0 (although they only imply that it would be cheaper than on earth by saying it’s „more efficient“). If you believe that their cooling system will be less than 7 million with enough redundancy for 10 years (or alternatively maintenance or replacement missions), I don’t know what to tell you. It’s not happening.
p1necone
I read it, it sounds like they also understand it would require more engineering effort and size/weight/materials than cooling something terrestrially.
alfiedotwtf
I got to the comma in the first sentence from the webpage and immediately went to the comments because I had the exact same thought.
Given Y Combinator's vetting process, I'm sure they would have tackled this problem somehow - maybe by feeding the heat into another process? It will be interesting to see how they've solved this.
vermilingua
> Given Y Combinator's vetting process…
The vetting process of the fund that quite famously invests in the founders over the idea?
echoangle
I hope that’s what’s going on here. They can’t seriously fund something like this and expect anything close to the pitched output.
But I also wouldn’t fund the founders here because they have to be incompetent or grifting. I seriously don’t see any other way, it’s that ridiculous.
jackmottatx
[dead]
arp242
Reading the paper this sounds like space Theranos. If they start producing results then I'd double check to make sure it's not just calculated on regular data centres and that they're just pretending its from their space stations.
Aside from the technical concerns already raised in other comments, I'm also not sure we really want all this private for-profit usage of earth's orbit. The orbital environment is already somewhat congested and people have already been raising concerns about it. There is the potential for it all to spectacularly blow up in our faces and become so polluted that we won't be able to do many launches at all.
ChuckMcM
"Space Theranos" wins the day for me. There really needs to be a better term than "stupid money" for investors who can be convinced with a slick presentation that by investing in a venture the principals will bring to market products that violate the laws of physics.
bitmasher9
Private use of previous public resources has had mixed success, but it feels like leaving space to the public sector will doom us to being Terran bound forever.
conn10mfan
the private sector made it to the moon 56 years after the public sector
it's going to take the management of our shared resources and spaces (orbit) for instance to leave earth, and this becomes especially important as Kessler syndrome risk rises with increasing debris in orbit
private companies launching without public oversight and controls are a recipe for cluttering earth's orbit and leaving us earth-bound for far into the future (same if the public sector launches without care but that seems less likely imo)
Kessler Syndrome: https://en.wikipedia.org/wiki/Kessler_syndrome
aunetx
I don't see the problem in that to be honest... Especially if the other solution would be allowing private companies to take over our (shared) orbit, meteorites, and -- continuing the trend -- planets for themselves to profit. If it seems overly pessimistic, we can just look at how our own planet's ressources are shared...
arp242
I don't know what the best solution is to be honest, but a wild west where improbable VC-funded nonsense is launched isn't it. Leaving it only to the public sector is the other extreme end of course.
ianhowson
I had a good laugh.
- You can't build 40MW of solar panels for $2M, even with theoretical maximum efficiency. You can't even build the cabling and regulators at that price.
- You need battery storage -- not as your backup -- but as primary source. It is going to cost more than $2M. Batteries are heavy. They are going to cost a lot to launch. This is not even solved on the ground yet.
- You need a heat transport medium to move heat into your massive radiator. Either you use water or you use air or you use heatpipes (metal). You have to pay for the cost and weight and launch expense. This is probably half the weight of the rack and I haven't bothered to do the math about how you transport heat into a 500 foot solar sail.
- Let's not even talk about how you need to colocate multiple other racks for compute and storage. There aren't any 1TBps orbital link technologies.
- Rad shielding? It doesn't work, but I'll let this slide; it seems like the least problematic part of the proposal.
- 15 year lifetime? GPUs are obsolete after 12 months.
I don't want to be the guy who shoots stuff down just for fun, but this doesn't even pass the sniff test. Maybe you can get 10x cheaper power and cooling in space. Still doesn't work.
amluto
Also: repairs. Every time I read someone’s story about large-scale ML training, a bunch of it is about identifying failing or flaky equipment and fixing it. That’s not so easy in space.
rozap
Either this is performance art, or interest rates are too low.
null
9991
Or it's a cover for putting something else up in orbit secretly.
BonoboIO
Good point, Rad shielding … how even trust your calculations when everything is grilled by charged particles.
ekianjo
GPUs are not obsolete after 12 months. Look at how Nvidia is stagnating for their 50 series lineup.
The biggest problem is software. The CUDA stack is not maintained forever and certainly less than 15 years.
alfiedotwtf
Most comments on this page are about the problem with heat. You're saying the problem is battery storage.
... couldn't you just merge both problems into a solution - your radiators ARE you power source
jedberg
I've been saying for a long time that we should consider remote areas for building datacenters for batch processing.
At first I thought the poles (of the planet) might be good. The cooling is basically free. But the energy and internet connectivity would be a problem. At the poles you can really only get solar about three months a year, and even then you need a lot of panels. Most of Antarctica is powered diesel because of this.
So the next thought was space. At the time, launching to space was way too costly for it to ever make sense. But now, with much cheaper launches, space is accessible.
Power seems easily solved. You can get lots of free energy from the sun with some modest panels. But to do that requires an odd orbit where you wouldn't be over the same spot on earth, which could make internet access difficult. Or you can go geostationary over a powerful ground station, but then you'd need some really big batteries for all the time you aren't in the sun.
But cooling is a huge problem. Space is cold, but there is no medium to transfer the heat away from the hot objects. I think this will be the biggest sticking point, unless they came up with an innovative solution.
dfabulich
Their whitepaper explains their cooling "solution": https://starcloudinc.github.io/wp.pdf
> As conduction and convection to the environment are not available in space, this means the data center will require radiators capable of radiatively dissipating gigawatts of thermal load. To achieve this, Starcloud is developing a lightweight deployable radiator design with a very large area - by far the largest radiators deployed in space - radiating primarily towards deep space...
They claim they can radiate "633.08 W / m^2". At that rate, they're looking at square kilometers of radiators to dissipate gigawatts of thermal load, perhaps hectares of radiators.
They also claim that they can "dramatically increase" heat dissipation with heat pumps.
So, there you have it: "all you have to do" is deploy a few hectares of radiators in space, combined with heat pumps that can dissipate gigawatts of thermal load with no maintenance at all over a lifetime of decades.
This seems like the sort of "not technically impossible" problem that can attract a large amount of VC funding, as VCs buy lottery tickets that the problem can be solved.
sfink
Or we could build a large vacuum chamber here on Earth and put a data center in it, if the goal is to make cooling as difficult as possible. "My data center is too hot! It's burning me!" "Put it in a giant thermos, then you won't feel it anymore."
> They also claim that they can "dramatically increase" heat dissipation with heat pumps.
Right, great idea. Start with the heat where you don't want it -- in the chip -- and pump it out to where it can't go anywhere. Then you can recirculate the medium back and have slightly older heat that you can mix with the new heat! It'll be a heat party!
It's just like a terrestrial heat pump, where you pump the heat out to where you have a huge environmental sink to transfer the heat to. In space, you have something like a hundred thousand hydrogen atoms per cubic meter to take up the heat. A HUNDRED THOUSAND! That's a bigly number, it must work out. We can always make those atoms go really, really fast!
Did an AI invent this whole scheme?
stephenhandley
I was trying to put these sizes in rough perspective. ISS is the largest man-made object in space, which is basically the size of a football field (half a hectare) and cost $150B. https://www.nasa.gov/image-article/comparison-of-size-of-int...
The whitepaper shows a 4km x 4km solar array, which is 1600 hectares (3200 International Space Stations). Would assume the array they're proposing would be cheaper since its structurally more homogenous, but $480 trillion dollars is a whole lot of money.
mrj
An object of that size in orbit seems like it'd run into problems developing sizable holes due to space junk and whathaveyou. There's probably some maintenance...
hnuser123456
Obviously use the heat pumps to concentrate the thermal energy up to 2700k, then conduct it along a bunch of tungsten filaments, now it's the world's biggest incandescent lightbulb on top of being the first datacenter in space. Maybe get it up to 4000k for a more modern lighting look. Guess we're gonna assume the dark forest hypothesis is false.
alfiedotwtf
Could they concentrate the energy and beam it down to earth as a source for electricity generation on the ground?
Invictus0
I don't get it--are the founders just grifters? How did this startup even make it off the drawing board?
onlyrealcuzzo
Probably because space companies will invest in you to feed their bubble.
You have to find trillions of dollars of future launches to justify current valuations.
erulabs
a 1% chance of making a billion dollars is worth 1 million dollars.
foobiekr
[flagged]
jrflowers
It’s only a grift if they know they can’t solve the cooling issue and they falsify data around their proposed solution and they publicly embarrass their investors a la Theranos.
Outside of that, accepting money and saying “I will simply solve the enormous problem with my idea by solving it” is not only normal, but actively encouraged and rewarded in the VC sphere. Suggesting that that way of operating is anything short of the standard that should be aspired to is actually seen as derisive and offensive on here and can get you labeled as gauche or combative.
dijit
> I've been saying for a long time that we should consider remote areas for building datacenters for batch processing.
FWIW there's a reason that Sweden has a bunch of datacenters in the north that are peanuts compared to hosting in Virginia.
They're "poorly" connected (by virtue of being a bit out of the way), but the free cooling and power from renewables make them extremely attractive. There was a time where they were the favourite of crypto-miners for the same reason as they would be attractive to AI training farms.
Fortlax has some I believe; https://www.fortlax.se
-----
As for the meat of the paper. Anyone with a passing understanding of space will be quick to point out that:
A) Heat is a problem in space, it's either way-way-way to hot (IE; you're in the path of the Sun) or it's way-way-way too cold (IE; you're out of the sun) and the shift between the two means you need to build for both. You also can't dissipate heat as there's no air to take the heat away.
B) Power is not so abundant and solar panels degrade; a huge amount of satellite building is essentially managing a decline in the capability of hardware. That's part of why there are so many up there.
C) Getting reasonably sized hardware up there is beyond improbable, though I'll grant you that most of the weight in a computer is the cooling components and chassis.
D) Cosmic Rays. No electromagnetic barrier from earth and extremely tight lithographies. I mean... there's a reason NASA is still using CPU's measured in the megahertz range.
vonneumannstan
>But cooling is a huge problem. Space is cold, but there is no medium to transfer the heat away from the hot objects. I think this will be the biggest sticking point, unless they came up with an innovative solution.
Their main tech breakthrough would have to be in this area otherwise the company is worthless imo.
daeken
It's possible to do all of this with current technology. Just... Why? The cost would be exorbitant; even with really clever deployment tech, the launch costs are gonna be dominated by solar panels and radiators.
This is a super cool idea and seems like perfect investor-bait. That's about where it ends.
matt-p
Genuinely most "AI" DCs are spending less than 9KW on cooling for every 100KW of servers. If you were that bothered about getting that to zero, you could literally sink them into the ocean, build a heat network so the town can take the heat for free or use any of a dozen more established and practical ways to do that.
handfuloflight
Perhaps a hedge in case apocalyptic scenarios disable or reduce networks on the ground?
thrance
I don't think they can bend the laws of physics though. Vacuum means the only way to dissipate heat is through thermal radiation, hence the huge infrared radiators.
pauletienney
I have no clue about space technology but many comments point the difficulty to cool anything in space. If Starcloud had an innovative solution to this problem, why on Earth (sic) focus on data centers when they could help the entire space industry? It does not smell good.
ziofill
Perhaps I'm missing something, but if the only energy they get is coming from the sun, then they only need to dissipate that same amount of heat (minus whatever energy was needed for beaming data down to Earth).
bongodongobob
What you're missing is that you'd have a huge solar array that powers something much smaller, so that energy gets concentrated into a small area.
gbear605
That’s not how it works. With conservation of energy, all the energy coming in to power the computers has to be emitted somehow. Powering computers doesn’t get rid of the energy, it just makes it unusable and converts it into heat.
vasco
> But to do that requires an odd orbit where you wouldn't be over the same spot on earth, which could make internet access difficult
Routing through starlink should have direct LoS at all times.
jsheard
Whether Starlink can keep up with the bandwidth demands of orbital datacenters is another question though.
(probably not)
38
> At first I thought the poles (of the planet) might be good. The cooling is basically free.
Yes, let's go ahead and finish melting the ice caps, great idea
shantara
Scott Manley has published a video a few months ago explaining why putting data centers in space is an absolutely terrible idea. Lumen Orbit, the company mentioned, is a former name of Starcloud.
troymc
It might make more sense to put data centers on the Moon.
It's fairly close, about 1.3 light seconds away. You wouldn't use it for anything realtime, but it would be fine for long AI training jobs.
You could bury the servers underground to shield them from cosmic rays. That would also be good for any people living there.
You could get power from solar panels on peaks near the poles that get light almost all the time. For example, some ridges around Shackleton Crater are sunlit up to ~90% of the time, with short periods of darkness. Use batteries to smooth out the power supply.
For heating and cooling, just use the standard techniques. It's not easy, but it's a solved problem. As a bonus, near the poles, the temperature extremes aren't as bad as at the equator.
You could also sell tickets to tourists. People will pay to see the darndest things.
GolfPopper
The use-case for this is not anything technical, it's putting your data center outside of any jurisdiction.
stephenhandley
I'm wondering why this is being proposed to be in space rather than at the lunar poles? Is it a latency question? I'd assume if this is being used for LLM training purposes and it is a relatively long training run, latency is less a pressing concern than bandwidth constraints before / after training?
Wouldn't the moon would provide better environment for debris shielding and regolith could be used to passively dump heat?
I'm way out of my depth here, so of course I asked ChatGPT 4o to come up with a three paragraph concept sketch for an LLM training facility based at one of the lunar poles:
<gpt>
A lunar pole is an ideal location for large-scale LLM training due to its unique advantages in thermal management and power availability. Near-continuous sunlight at the “peaks of eternal light” allows for stable solar power generation, while nearby permanently shadowed craters provide ultra-cold regions that can act as natural heat sinks — solving one of the biggest challenges of orbital compute: radiative cooling. Compute clusters could be housed in regolith-insulated modules, with heat piped into crater floors or dissipated through passive radiators embedded in the lunar terrain.
The architecture would be modular: prefabricated training units delivered by landers (like Starship) could be arranged into scalable compute farms. Power would be provided by solar arrays on crater rims, with supercapacitors or RTGs as backup. Data transfer wouldn’t require low latency, just high throughput, so high-gain antennas or laser links could periodically sync model weights back to Earth. With no atmosphere, lunar surface conditions are harsh but predictable, and maintenance could be handled robotically.
Compared to the estimated $480 trillion needed for space-based radiators to support orbital training, a lunar facility could achieve similar scale at orders of magnitude lower cost, leveraging the Moon’s surface as both a structural anchor and a thermal reservoir. As launch costs drop and lunar infrastructure matures, this becomes a compelling direction for off-planet AI training.
</gpt>
jadbox
I guess it would be heat pollution at the poles that may contribute to global climate change if we start building immense data centers there.
Etheryte
Please don't litter HN with LLM generated slop. Each and every one of us here is more than capable of doing that themselves if they please. The value of HN is the human discussion.
CobrastanJorji
I'm not an engineer, so maybe I'm wrong, but isn't cooling famously difficult in space?
godelski
Yes.
Also, so is heating.
When you're on the sun side, everything is too hot and it is hard to cool. You can do direct cooling, such as water cooling, but you have no radiator to dump the heat to...
When you're in the shadow of the sun you have the opposite problem. Things are way too cold. Cold enough normal electronics can fail.
For reference, the ISS can fluctuate between -250F and 250F.
I'm willing to bet that it is easier to deal with the issues of salt water than it is to deal with the heating and cooling issues combined with difficulty to manually access problems presented by space. Price per pound into orbit is still quite expensive...
vonneumannstan
Unless they've figured out some impressive cooling tech, which I would expect would be worth more than the rest of their company combined, then this is pretty much DoA. "More efficient cooling architecture taking advantage of higher ΔT in space" would indeed be useful if you had a nice medium to radiate into. It turns out that thermal radiation is incredibly poor into the vacuum of space lol.
amluto
Space (with a sunshade) is a nearly perfect medium into which to radiate heat, in the sense that there’s nothing better.
But I agree with your general point. At 100°C, you can radiate about 1kW/m^2. That’s 1000m^2 of radiator per MW of datacenter, assuming you can operate with the radiator at 100°C. You can fudge this a bit with a heat pump (to run the radiator hotter, paying a linear-ish power penalty and gaining a fourth-power radiation benefit), but that’s expensive and that power isn’t free.
Here on Earth, you can cool by conduction or evaporation, which isn’t an option in space.
godelski
> Space (with a sunshade) is a nearly perfect medium into which to radiate heat, in the sense that there’s nothing better.
entangledqubit
Microsoft had/has the Natick project which was an undersea data center testbed which allegedly had a bunch of benefits. That doesn't seem to have gone anywhere - or at least isn't really scaling up. I'd imagine the ongoing operational costs of space are worse than the ocean?
To me, the cost estimates seem a bit off and conflate capital with running costs.
The main benefit for space at the moment seems to be sidestepping terrestrial regulations.
zamalek
What does space give us that Earth does not in this scenario? Free real estate? They only mention falling costs for deployment.
dilyevsky
There's an answer in their whitepaper[0] - see Table 1. tl;dr - power is continuous and free via solar array
toomuchtodo
> power is continuous and free via solar array
It’s is on earth as well using solar and batteries. What is likely to get cheaper faster? Solar and batteries? Or lifting datacenters to space? The world is almost at the point of deploying 1TW/year of solar, and batteries are catching up. No space required. There aren't a lot of VC investment opportunities speeding the rate of solar and battery deployments though.
CobrastanJorji
Just spitballing here, but what if you built it on Earth, and then used the savings to build a second one on the opposite side of Earth? Now you have equivalently continuous power via solar array and also, as a bonus, air.
richardwhiuk
Free in the sense of astronomical capital and operational costs.
dilyevsky
r&d sure, not sure about ops as you can probably just detach a faulty module and launch a replacement.
zamalek
Power in needs to equal heat out, and that isn't easy in space. They, deceptively, claim that their novel solution is radiative cooling. Relying on radiation for cooling in space is the problem statement! Convective (as on Earth) is significantly more effective.
I'm not one of those idiots who would claim that "we should focus on terrestrial problems instead of space," but this idea seems to have only downsides.
cj
> “We still don’t appreciate the energy needs of this technology… there’s no way to get there without a breakthrough… we need fusion or we need radically cheaper solar plus storage or something” -Sam Altman
It's kind of depressing that the only way to make this tech better is to feed it more energy. (And apparently now to send it to space)
jebarker
It's also interesting that everyone is convinced the same capabilities can't be realized with drastically less compute.
tux3
[flagged]
xnx
I do wonder about data centers in the arctic. Cut out the middle step of greenhouse gases and melt the polar caps directly.
chewbacha
Not to mention the benefit of directly harming extremely vulnerable ecosystems! Win-win
btown
[flagged]
dang
Can you please make your substantive points thoughtfully, without snark or putdowns?
dang
Can you please not post comments like this? Thoughtful criticism is welcome, of course, but this sort of thing isn't. Besides breaking the site guidelines, it takes threads in less interesting directions and evokes even worse comments from others. We're trying to avoid that here.
"Don't be snarky."
"Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something."
"Don't be curmudgeonly. Thoughtful criticism is fine, but please don't be rigidly or generically negative."
toraway
Tbh your moderation is normally very restrained and even handed so was a bit surprising to see you take down several borderline overly snarky comments in a row (that just so happen to be directed against VC investors or YC founders).
tux3
Really, on second look, snark still feels justified here. The issue is with TFA. There is little room for a thoughtful comment in response to something transparent.
Some type of submissions will invariably not result in very deep discussion, when the topic itself is so shallow.
https://starcloudinc.github.io/wp.pdf