It's profitable if you pay for the rockets. Starlink is a massive business now and it keeps getting larger, and it has good margins. It can trivially pay for the rocket business over time.
... if it pays for the launches, it has negative margins. I'm not sure what's hard to understand here.
It might be the case that once you get enough satellites up and replace them consistently enough that margins go positive, and then you can start paying back the cost of "the rocket business" (i.e. more than the marginal cost of launch) but... it's not at all clear that's even theoretically possible. At least not without launch costs coming down significantly from where they are today, which Starship is not clearly en route to achieving.
Unless I’m misunderstanding something OP is saying that the only reason Starlink is profitable is because they don’t pay for the rocket launches. But the rocket launches still cost money, it’s just that SpaceX pays for it. But given they’re part of the same overall organization it just seems like an accounting trick.
This is correct. I’m not an accountant so not qualified to say the degree to which it’s tricky, but it does add an addendum to “Starlink is profitable [if you completely exclude the primary source of variable cost by burying it into a different business segment].”
The entire "space launch" segment in the red by $1.1bn. Primary driver being the $3.2bn spent on Starship R&D.
How are they "burying it into a different business segment", pray tell me?
If you remove Starship, Falcon launches and Starlink are both independently profitable. And Starship wasn't even used for Starlink until the one test launch this year.
I account for the ingredients as depreciating assets over a 100 year lifespan
It now costs me $5 in labor and $0.20 in ingredients
My margin is now ~75%
For SpaceX, we know they are accounting for Starlink launch as depreciation. We do not know the numerator (the $20) or the depreciation period (the 100 years). Accordingly neither of us know whether Starlink is a viable business.
You are inventing more and more elaborate ways for "this is how Starlink is secretly unprofitable" while we knew it was printing money since 2024.
You can drop SpaceX's launch revenue to zero, fund all of it with Starlink revenue, and the sum is still profitable.
We know "whether Starlink is a viable business": it is. End of story. You better start pivoting towards "but what if future competition" or "the revenue growth is uncertain", because your attempts to wiggle your way out of admitting that Starlink is a money printer now are weak at best.
I have literally been describing the exact same mechanism, which is the actual mechanism that you can actually read about in their financial statements, since this conversation started.
And what is that "mechanism", pray tell? I don't think you have one. Or ever had one, for that matter.
You can't just say "they're hiding the launch costs" and expect it to magically make Starlink unprofitable. Starlink has been bearing launch costs for its entire existence, and if anything, the advent of Starship is likely to make them lower, not higher.
Are you serious? Good lord. Take this article. Go take SpaceX's filings. Ask an LLM to explain how Starlink is accounted for and what the effects of that accounting method are.
It's the "we've got a bunch of rockets lying around... sometimes other folks in the company use them when they're not working for space lift clients..." view.
The fuel would have to be expensed, but generally speaking its impossible to say how unprofitable Starlink is because they don't account for it that way or break those costs out.
When they swallow Tesla it'll be more of the same, and thats the point. Musk is trying to obfuscate the (poor) performance of his businesses so he can maintain delusional market valuations based of vague promises.
"Exodus Communications Inc., which never made a profit since it went public in March 1998, filed for bankruptcy protection after losing customers in the collapsing Internet economy."
"Exodus, which runs 44 Internet data centers on four continents, listed $5.98 billion in assets and $4.44 billion in debts in Chapter 11 papers filed Wednesday in U.S. Bankruptcy Court in Delaware. The company operates so-called server farms that provide Web site services for businesses."
"The Santa Clara, Calif.-based company’s losses increased more than tenfold in the second quarter, and it fired workers as it failed to win new contracts fast enough to replace those it lost. Exodus counted Yahoo Inc. and AMR Corp.’s American Airlines among its customers."
"Trading in Exodus shares was halted before the markets opened Wednesday. The shares fell 33 cents to 17 cents Tuesday and have plunged 99% from a record $89.81 in March 2000."
"Analysts say Exodus, with eight different junk bond offerings totaling about $3.4 billion, ran up more debt than it could handle."
“We sacrificed profitability in exchange for growth and market share, over-expanding in some areas in advance of demand, not anticipating the decline as the dot-com bubble burst and the economy weakened,” Krause said.
"Exodus’ second-quarter loss grew on acquisition and restructuring costs to $583.4 million, or $1.05 a share, from $51.8 million, or 13 cents, a year earlier. Sales rose 79% to $318.7 million but missed analyst estimates. The company lost $256 million on sales of $818.4 million in 2000."
Ten median US software developers cost about $1.5 - $1.7 million per year - including all benefits - as of a couple of years ago.
A frontier AI is at least as capable as ten median human software developers. It's likely well beyond that now. Over the course of a year, would you have to spend $1.5 million to get the output of those ten median humans? No chance in hell. You'd have to spend less than 10% of that.
Then on top of that: the AI is improving rapidly; the humans go on vacation, the humans decline, the humans get old, the humans get sick, the humans take parental leave, the human struggle to adapt, the humans are resistant to change, the humans riot, the humans protest, the humans need healthcare, the humans want paid more, the humans can only work for 4-6 hours at peak while writing software (slowly).
Do you know any humans that are experts at a dozen programming languages? That human does not exist. The frontier AI are omnimaths.
What's my cost as a business to utilize the latest cutting edge Chinese model, renting its usage from the cloud? Whatever the Chinese cost (on their side), I'm never going to suffer even a tiny fraction of that pass-along cost no matter what. We can all appreciate the subsidization going on.
Or to grab a bunch of $200 per month accounts from OpenAI or Anthropic for a team to use?
The calculations is: I'm in the US, if I have ten median software developers, what's my cost? Then versus using AI instead.
The human labor can't keep up. Even if we freeze things right here, and then hyper optimize Fable 5.2 by etching it straight to silicon, the human developers are obsolete. And the future isn't going to stop coming.
I like their angle though - from a societal perspective of allocated resources, how long until we've paid off the cost of building these LLMs? Imagine instead the entire supply chain was Stalinistically tuned towards finding bugs in Linux. Training rare earth mineral miners how to code level or whatever. I think as a thought experiment it's interesting, the answers could translate to an organizational level about comparing labor cost against token cost. What's a good breakdown of token spend vs hiring some new juniors to train up?
HN has become so miserable over the past ~12-24 months because it's a site filled full of highly paid techies living in the deepest pit of denial that has ever existed.
It's all going away. Here's a prediction: HN will effectively die with the software developer.
Is it that dependent on the software developer segment? Why do you expect it to die rather than just shift more towards... I don't know, startup business droids?
Sub 1% of the planet has access to cutting edge frontier AI.
Sub 1% of the planet has any practical use for the top tiers of AI systems. That will likely always be true.
The gap between the haves and have nots will drastically widen further, and very quickly. The bottom ~95-97% will be left behind in a way that will be impossible to overcome. The age of AI + robotics will just make it that much harder to climb for most people, these are systems that are in aggressive, direct competition with human labor. And in short order the AI + robots will be vastly superior to human labor (it doesn't really matter if we're speaking in terms of 10 years or 30 years).
AI will consolidate the winnings. The gigantic gains by the elite rich related to AI over the past few years, is merely a hint of what's to come. Capital will win as it always does.
There will be some gains for most everybody else, those gains will be comparatively trivial though. A house bot that saves people an hour of labor here and there, AI that automates some trivial life tasks.
AI has no money, it has no wealth, it owns no capital. For now. If you want to avoid the brutal human vs AI/robot competition arena: own capital, own the AI, own the robots.
Is this substantiated right now in any real way? Is there any existing gap between the barista who doesn't care about AI and the person working at anthropic who has access to internal models? Or the person with 3 $200 subscriptions?
Maybe money? They can make websites for people? What gap really exists between these people besides earning potential, which already existed before AI.
The existing gap gets made worse by AI concentrating wealth even further to the owners of the assets that are producing via AI. AI will generate intense wealth from productivity gains, and those new gains will be more concentrated than any other economic round we've seen previously. It's a human labor eliminator the likes of which we have never run into before.
Fewer humans will be needed per dollar of output. Those gains will not go to labor, they will go to capital, the capital that owns the data centers, the factories, the stores, et al.
In the physical space (AI + robotics) it'll be a chaotic, slow'ish moving change, slower than the hypsters are predicting now, but it will happen regardless.
That barista job largely won't exist in the future. China will replace them with $3,000 bots with high-functioning AI software, and they definitely won't be powered by expensive Nvidia GPUs.
Slow changing service & manufacturing spaces will see a high wipe out ratio in terms of human labor being eliminated.
Walmart has 2.1 million employees, most are doing repetitive tasks that require modest levels of intelligence. If they could eliminate one million of those with AI + robotics, for a cost of less than ~$15,000 per year, they'd do it immediately. It's hard to imagine a future where that isn't going to happen. That human labor pool is costing Walmart probably $80-$100 billion per year. Amazon is even more forthright in their desperation to remove the humans from retail.
All the human engineers will be in harnesses in the future.
Within three years most software developer jobs will consist of taking instruction from the AI systems. The humans won't see it that way, but that's what it will actually be. Realistically the thing that will happen is the humans will be put into harnesses (cubicles) and prompted by the AI (I need you to plug that server in; I need you to give me access to such and such; now do this, then do that). Most tech jobs will consist of AI telling the human what the AI needs the human to do next, de facto the human will be in a harness and will be getting told what to do.
Not only will the humans-as-meat-puppets model be used for software engineers, but it is likely the way that agentic workflows will expand beyond software development, data science, and mathematics.
I first heard about this in Marshall Brain's short story _Manna_ [1]. In the story, the robot takeover started with AI management software running fast food restaurants, where workers would execute tasks the AI would narrate to them over headsets.
I bet we're pretty close to being able to implement this.
People need to eat. Unless there is UBI/UHI, there is no point at which humans can opt out of society (with some exceptions, of course).
If the claimed productivity gains turn out to be correct, we really should have UBI/UHI in the future, and that will permit a lot of people who hate their jobs to quit. Of course we won't do that until things become dire.
You frame it as if humans have no control over societal organization at all. If everyone's job became 50% less interesting, I imagine we'd see unrest, even if the wages got a bit better.
Maybe I'm cynical, but I believe that the VAST majority of people are already unhappy with their jobs. In fact, the vast majority of people have been unhappy with their jobs for hundreds of years - probably thousands. They don't do them because they are happy to work. They do them because they want to eat.
Is there some kind of breaking point? There is for everyone, but I don't think satisfaction is the red line. For most people it has historically been things like pay and health and safety. If everyone were to suddenly have their pay cut in half, I could see that resulting in general unrest.
While I don't fully understand the mechanics of it, people do revolutions from time to time. People can decide that they don't want the current system, and try to reorganize themselves in a different manner. And who doesn't agree might get burned in the revolutionary flames. It happened many times before in human history, including several times in the US (independence, civil war, and to lower degree universal suffrage etc.)
Can I ask what kind of work, and what models? Because I don't, I'm a senior embedded engineer working with frontier models, and I haven't seen a major mistake in at least few months now, since earlier in the year.
It will sometimes get things wrong because it made non-viable assumptions, but that's on me and prompt accuracy.
What I see is: it makes tests against desired features or bugs or mistakes, and iterates until it gets it correct. I steer as it goes.
(I hate this, by the way, zero job enjoyment anymore, but I don't know what else to do.)
Code review, qa, staging, product review, dog fooding… what do you mean “now”? It’s always been all of our jobs to catch all of our errors. We’re just including the AI’s errors now hoping that the overlap of everyone’s errors is sufficiently small.
The ownership will want humans to punish, humans to trust, humans to manipulate, and humans that can be fired. They'll want a human physically present, representing them as oversight over the AI (a job the capital doesn't want to be doing 24/7). There are serious legal matters involved in high functioning AI systems (and that will dramatically increase over the coming decade), the capital will be extremely worried about liability issues. Human scapegoats are ideal. For now capital will want human style consequence-feedback systems for a tier of human oversight over the AI. It'll probably take a full generation before the capital controlling humans forget / give up on the old systems fully.
It's also worth noting that it's far easier at present to press a human into doing something highly illegal than it is to get Claude or GPT to do so.
> Why would there be a human in this imagined system at all?
in the imagined system above it requires physical acts that an llm can not do, if we go further than the above imagined system and make robots to perform these task for the llm a human still is needed for maintenance for these robots and their assembly, once there are robots for maintaining the llm assistant robots, humans are still needed to maintain the maintenance robots and so on and so forth. I dont see an end point where a robot machine system is fully self healing without atleast a few humans in the mix to correct when there is a breakage in the chain
If you take Daniel Schmachtenberger's thesis, these models are the latest extension of an ongoing misaligned moloch-like entity, using our institutions/economy/corporations, etc. as its organelles. All powered, most recently, by fossil fuel.
The ownership class, the capital class - whatever people prefer to call it, will still call all the shots as they always have, and always will.
So whether that's a CEO at the top instructing a human manager that then instructs AI systems, which then put into motion plans that include the harnessed humans getting prompted, or however it's decided to best configure the top operational tiers - that's all fairly irrelevant ultimately. All human labor, and all AI labor, will be in harnesses. Realistically all human labor has always been in a harness.
The people in charge will be the people that control the capital. They will instruct the AI to their bidding, they will control the data centers the AI lives in, they will own the robots doing the labor in factories, they will own the factories, they will control the grid, they will control the electricity generation, et al.
It's true now, it'll be true tomorrow. Nothing fundamental will shift at that tier: don't be labor, own.
If you're a software developer, you're increasingly depreciating labor. Every unit of improvement the AI systems see, the average human software developer's labor value diminishes. It's diminishing extraordinarily fast, kind of like a confrontation between increasingly productive machines and physical human labor during the industrial revolution. You might as well picture a human with a hand plow taking on a modern industrial tractor.
There's nothing wrong with an interesting design. It's not a serious market however. The Cybertruck was a pet project forced onto the market by an out of control CEO (there's a large disconnect between Musk and the consequences of his actions). Tesla requires very high volume selling vehicles to prop up its comical market cap. The entire company is resting on one car model. They desperately need another highly successful model, the Cybertruck could never be that.
Frankly Tesla is dumb lucky the Europeans and Japanese have botched the EV market so badly overall. Tesla shouldn't even exist at this point with how trivial their lineup is.
All the clown show at Tesla had to do is clone the F-150. This was one of the easiest product failures to predict in recent memory. Musk can't help himself. Tesla continues to desperately need a Shotwell at the helm.
At present all Tesla has propping it up is bubble dust and one car model (one increasingly dated car model). Somehow after 14-15 years (Model S released in Summer 2012) these people still can't release a real SUV of any sort. The model Y is a grotesque joke of a fake SUV, a mutilated model 3 that doesn't really look like an SUV in any regard. The model Y is an SUV like the Cybertruck is a truck. They might as well have unlimited money to do it, and they can't do it. Same reason they couldn't release the roadster even after all this time. It's a fundamentally broken company because Musk won't get out of the way. Whatever Musk is good at it, it's not running a large scale automotive company.
reply