[bob1029]

Certainly the idea is difficult to execute on. However, there isn't anything about it that fundamentally says it cannot happen. I think Starlink is a pretty good example of how this could go.

The framing of the detractors always comes off like we intend to build Costco-style structures in space with robots tending to literal racks of unmodified server equipment running web app and credit card processing workloads.

[qchris]

Years ago, I did some work on thermal management of small satellites, mostly for cooling higher-power onboard computers. The scale is different, but the physics are the same.

The story of SpaceX is often that Musk tried to buy a rocket, got a price estimate, and did some first-principles evaluation of the materials and engineering costs he believed was involved that came out to be much less than the going price. He ended up (through fast-forward view doing a lot of work) being largely correct.

The data-centers-in-space in space thing does not work out from a first principles approach. The waste heat generated by chips and the cooling method available (ultimately, radiative cooling), and the structures required create those surfaces, would be orders-of-magnitude beyond what could reasonably compete with a terrestrial version with the same capacity. There's no "but launch costs are dropping" adjustment that can possibly make up for that. The physics involved are the blocker.

Starlink is actually a good counter-example of where the execution--building and coordinating satellites in volume--was the bottleneck, not the underlying physics of the networking and SpaceX was in a great position to capitalize with their engineering expertise and reduced launch costs. It's a totally different situation for the data center thing, though.

[bob1029]

There are some unusual but otherwise plausible ways to reject heat at incredible scale without involving a lot of mass.

https://en.wikipedia.org/wiki/Liquid_droplet_radiator

Space has many downsides, but it also comes with a few advantages.

[therobots927]

Just because something is physically possible doesn’t mean it’s more economically viable than terrestrial DCs.

If it’s not a Costco style structure what is it? A hundred thousand satellites each carrying a GPU rack? With giant cooling + solar arrays? And who’s going to maintain them if not robots? Astronauts? How are the satellites gonna talk to each other? Super long fiber optic cables? How exactly are they going to replicate a compact datacenter up there?

How much does each of these satellites cost? Both to manufacture and launch? How much is the maintenance cost?

I think the post IPO stock price performance speaks for itself. If you think it’s a good idea, you should invest, in fact I encourage it.