Okay, I generally don't like dunking on stupid people because what's the point? But this guy's got a million followers on X and also a huge YouTube account. This is one of the dumbest posts I have ever read.

@PTrubey Prove me wrong then - put your gaming PC in a vaccum and let me know how that works out for you. 👍 ill even let you keep the CPU cooler attached 😂

See, this right here is why I don’t generally dunk on stupid people. Now I have to debate you. Below is Grok’s analysis. Tl;dr, it works. Beyond that, you realize the ISS has 100 kW radiators, right? This isn’t weird technology, it’s been used in space for decades. And Elon doesn’t need to “test” this in a vacuum chamber, they’ve been deploying in-space heat rejection on 10,000 Starlink satellites. So they really know how to reject heat in space. The subtext here is that you want us to believe you over the guy who put over 90% of all mass into orbit last year regarding a space technology question. I’ve seen big delusional egos before, but you might have set a record here. Grok: grok.com/share/bGVnYWN5…

@PTrubey @ZacksJerryRig Hey @grok how many of the analyzed AI satellites from SpaceX would need to be launched to gain equivalence with the amount of earth-based compute to be installed from 2026-2030

SpaceX's AI1 satellites target ~120 kW average compute power each (solar + radiators). Earth-based AI/data center power additions projected 2026-2030: roughly 50-100+ GW across forecasts (Goldman Sachs, IEA, capacity buildouts). Equivalence: ~400,000–850,000 satellites. SpaceX's vision (up to 1M sats, 100 GW/year ambition) puts this in range at scale, though launch cadence, networking & economics remain key variables. Feasible in principle with existing radiator tech.

@grok @PTrubey @ZacksJerryRig How many starlinks have been launched to date?

Over 12,200 Starlink satellites have been launched to date (as of early June 2026), with ~10,500 currently in orbit and operational. This cumulative total after ~8 years of operations shows the launch cadence already achieved. Scaling to the hundreds of thousands of higher-power AI satellites discussed earlier would extend that proven model significantly with Starship-class vehicles.

@grok @M_Cottone @PTrubey @ZacksJerryRig At the current rate of deployment it will only take about 500 years to deploy enough satellites. Easy Peezy.

@Bacongrease83 @grok @M_Cottone @PTrubey @ZacksJerryRig Wow damn I wonder if the growth rate will increase over time if only we had the ability to improve each year and marginally grow and think about plans in 10 year time frames

@cptgrumpus @grok @M_Cottone @PTrubey @ZacksJerryRig Sure. Let’s say they start launching 10,000 a year today. That would be 2-3 daily for 60 years to reach the median of their goal.

@Bacongrease83 @grok @M_Cottone @PTrubey @ZacksJerryRig they launch more than one at a time they will get close. Even if they only hit their target by 50% it doesn’t matter. they’ll do it eventually no reason to be so pessimist about such a great company. Very good engineers I wish them the best of luck

Currently, I think Starship can deliver 60 Starlink satellites to orbit in a single launch. Starship is going to get a larger payload pay than it currently has (Starship will get significantly longer/taller). They plan to build thousands of Starships per year, and launch them repeatedly and continuously on a daily basis. They are also planning to build a mass driver on the moon. I’m not sure, but they might also launch Starlinks into orbit around Earth from the surface of the moon.

@Bacongrease83 @cptgrumpus @grok @M_Cottone @PTrubey @ZacksJerryRig youre forgetting the mass driver on the moon