Gas expanding faster than the speed of sound is called a shockwave - and the Mach diamonds are essentially the expanding gas shockwave “bouncing” back and forth as it hits the atmosphere, forming a standing wave of high and low compression zones.
There could be some interesting actual OS design innovations for new permissions, access control, and sandboxing systems that are designed from the ground up for these "conjurable" experiences (or even OS components themself).
Finding some balance between access and safety for vibe-conjuring parts of the OS in a way that's still powerful but won't accidentally nuke or corrupt itself.
I do think there's some interesting space to be explored in capability-based systems, but even then I think it would mostly end up looking similar to how existing systems are, just with one more element added
The historical baggage is so heavy I don't think anyone can realistically throw it away, so what we'll end up getting are almost certainly incremental improvements to existing foundations.
This is covered in Claudeish, had to stop reading. I have to read enough of this at work...
>What sits behind them is a calibre I had to solve the way a real one is solved, and this is why I bother.
>A skeleton is a load-bearing machine with the metal taken away down to the last safe gram, so what is left is whatever carries a force, and no spoke is wider than its job.
>Running and buildable are different questions, and the second is harder.
>A drawn movement is a claim. Before anything gets a surface, I test it as a machine.
If this isn't Claude-prose then the author has been reading too much of it...
I think "load-bearing" and "surface" is what gives it away. It continues to perplex me how something trained on human-written English ends up producing such output. It's much worse than the classic em-dashes and "it's not X, it's Y" (but maybe that was a different LLM?)
If the whole thing is written by AI, then I wouldn't say that it was just "helping". Author could write it in their native language and then use AI to translate it - the result would be very different.
The movement does look pretty neat. I'm not into watches, but it's impressive that purely rendered thing was designed to be realistic.
iPhones still let you use certain contactless features (like Suica) even when the battery has "run out" (ie., the main OS has shut off). The reserve battery power is enough to run Suica, CarKey support, and FindMy.
I imagine there are only maybe three people as stupid as me to try this, but just in case: it works fine when the battery runs out; but it does _not_ work during the OS update process.
Interestingly, but not exactly related - the OS update process will not start if you're connected to CarPlay. Probably to avoid automatic updates from triggering when you plug it in to charge in the car.
Vapid characters aren’t a problem if they are doing something interesting or if there is non-trivial conflict or mystery or confusion or tension or drama of any sort or anything that leads to some kind of meaningful change in a character. Gatsby's death might have counted if Fitzgerald hadn't telegraphed it from so far away that it became a non-event.
You know how kids’ books for beginning readers are mostly about stringing together words that are easy to read and make a sensible sentence? See Jane run. Run, Jane, run! why is Jane running? Because she wants to. That’s how Gatsby read to me with more complex words and sentences.
I don’t even mind books where nothing much happens (Iyashikei) if the setting is novel. But Gatsby was predictable and dull for me with cardboard characters living passive lives.
The other book that lots of people seem to love that I've never been able to finish is Moby Dick. I don't dislike it but he pace is a bit slow for me.
The closest analogy I can think of to The Great Gatsby is American Psycho. The whole point of it is to feel like a pretentious act played by the characters. They’re not meant to be relatable or show growth. I guess it’s one of those things that either resonates with you or doesn’t, but it still has value in “getting it.” Most people never escape their status chase and behavior loops.
+1 on this - would love to have a more realistic timing mode where there are a few minutes of ambiance for travel sections in between station arrivals.
Which is true, but at the same time: this is Starship Flight 12.
The whole point of Starship is that it's a reusable vehicle with easy turnaround and quick maintenance. And in particular it's supposed to be different than the other reusable vehicle with easy turnaround and quick maintenance, which turned out to be sort of a boondoggle.
Yet, they've now hand-built and destroyed twelve of these things across multiple redesigns, and it still hasn't completed its design mission once. In fact basically every launch has unexpected major failures.
As poor as its safety record ultimately ended up being, the shuttle launched successfully on its very first try. And we only had to hand-build five of them. And lost two, sure, which is still a lot less than twelve.
Yes yes, I understand that iterative design has merits and that the ability to rapidly prototype and try things in the stratosphere allows for less conservative tolerances and better ultimate performance.
But does it really take 13+ tries?! At what point to we start wondering if we have another boondoggle on our hands?
But all of those 12 launches happened in just 3 years, and cost a tiny fraction of other major spaceflight development programs.
For reference, SLS has been in development for 5 times as long, and cost 15-20 times as much, as Starship, and they still haven’t landed people on the Moon, which has been one of the stated goals since the Constellation program in 2005.
I don’t see how the number of failures matters if the end result still happens faster and cheaper than anything else.
Recent SpaceX IPO filings put that 'tiny fraction' at about 1/3 or 1/2 of SLS. $15B total investment with about $4-5B of that figure from US gov. Is starship more than 1/2 or 1/3 of the way to a human rated Artemis II style mission? The main reason starship costs less to test (apart from the SLS jobs program baggage) is because of design choices which prevent it from performing such a mission without significant further tech development.
'5 times as long' is dubious too. SpaceX claims to have been working on the design since 2012 vs 2011 for SLS. Ultimately though the start date of a complex program is not well defined, as early conceptual design stages can take years without leaving the drawing board. Government needs to put a start date on such efforts for legal/budget reasons, but a private company does not.
Also relevant - SpaceX has been given a lot of tech and expertise from NASA at a tiny fraction of the cost and time it would have required them to develop it themselves. Therefore, the costs of NASA programs like space shuttle actually includes some of the development costs of SpaceX.
Both programs pale in comparison to Saturn V, which was faster, cheaper, and more technically demanding at the time.
Moreover the two lost shuttles included human lives. Better to blow stuff up with demo payloads now before sending up large contracted payloads or worse human beings!
I couldn’t believe my ears when I first heard that the second ever flight of SLS was going to be crewed.
It worked out in the end, but I can’t imagine being so confident in a new system, no matter how much money and brainpower has been spent to make it safe.
That's undeniably true. Nonetheless "Better than the shuttle, which sucked" isn't the design goal.
The question is not even just "is it better to blow up 12 Starships?", which would probably still be true. It's "Why isn't Starship working yet?" and the implied "Maybe Starship sucks too?!".
They failed far more than 12 landings before they started reliably landing boosters, and people made the same “maybe this is a dumb idea” comments back then too.
It seems premature at best to make any sort of triumphant comparison, when Starship has yet to complete an orbit of the Earth while SLS has carried humans to the moon
It's especially ironic to talk about not landing on the moon yet, when it is the landing system--aka Starship!--which is the primary bottleneck for that goal
I am in no way trying to make this some SpaceX vs NASA pissing contest, but there seems to be a tendency to overvalue Starship's promised achievements to SLS's real ones
They could have made orbit at any time on any flights that reached space. they have deliberately not done so because that is the safest thing to do when developing.
If I was developing a rocket, I would prefer making it work first and then iterating on it.
SpaceX is iterating for the sake of a narrative. None of the development goals for Starship require reuse of the upper stages, that's a bonus that should happen after Starship started deploying Starlink satellites.
There is no point in having dedicated reentry tests. Every test flight comes with a free reentry test included.
Even if a company does iterative rocket development, it would never follow the SpaceX way of putting th most difficult but simultaneously unimportant objectives on the critical path at the expense of the essential objectives.
The development program of Starship is basically ignoring every aspect of Falcon 9 development that made it the success people take for granted these days.
The part that makes no sense to me is why they are going starship scale rather than falcon 9 scale. Had they done their prototyping on a rocket with 9 engines on the first stage and 1 on the second, they could have gotten to raptor 3 (and a falcon 9 replacement) while blowing up way fewer engines, launch complexes, etc. There's a reason Spacex started with the falcon 1 rather than the falcon 9. It's a lot cheaper to blow up fewer engines and smaller rockets while you're developing a new rocket engine.
The biggest part of this test campaign is learning to build Ships and Super Heavies quickly and efficiently. They are not just testing Starship, they are also testing and iterating on Gigafactory.
part of my argument is that if your test platform is 1/4th the size, you get much faster iterations. the path they took meant that every test destroys 39 engines, a huge amount of rocket fuel, and all of their construction. A falcon 9 design (9+1) with raptor engines would let them already have a falcon heavy capacity vehicle because everything about a smaller scale vehicle is way easier
They already have a falcon heavy capacity vehicle - Falcon heavy.
I guess I am confused about what you think they would get out of testing with a smaller platform. It seems like most of their focus is specifically figuring out how to make a large platform work. What do you think would translate?
I think that trying to make a large platform work with engines that aren't reliable and on a fuel system that you don't have experience with is a really dumb idea.
The raptor engine is a pretty giant advance over the merlin engine and methane seems like a reasonable fuel, but testing of the engine has been consistently held back by issues they're running into due to scaling up the rocket so much. Starship has only had 12 test flights in 3 years (vs 50 launches since january for falcon 9). Had raptor testing taken place on a smaller vehicle it seems pretty likely that they already would have a falcon heavy replacement in service that could be launching real payload.
I see where you are coming from. I dont think they are interested in relpacing falcon heavy. I have not heard anything about that. what would the point be?
from my perspective, the large platform is the goal, and engines are in service of that. It is hard to imagine that this would would advance the timeline of startship. It seems like there are substantial technical challenges around the fueling system, as well as re-entry, and potentially engine restart in space. Any of these could be fatal, so they need to start working on them as soon as possible, even if the engines themselves arent perfect.
If they had a 1/4 scale test platform, they wouldn’t be testing what they need to learn.
They wouldn’t be testing how to transport, generate, store, load and offload massive quantities of liquid oxygen and methane quickly and reliably.
They wouldn’t be testing the simultaneous ignition of 33 engines, the massive fuel demands of that (which appears to be very difficult), and blasting the pad with 33 engines.
They wouldn’t be testing the structural loads and stresses of max Q of such a massive vehicle.
They wouldn’t be testing tank slosh and pressure issues of massive tanks.
They wouldn’t be testing the heat loads on the shield with huge mass.
All the manufacturing too would be learning how to do things on such a large scale.
In short, they simply wouldn’t be learning the lessons they need to learn to make this work.
The point was more that there is a point where (to borrow the software terminology) "iterative design" becomes "death march". Trying a few times in the early days and being willing to throw stuff out and start over is a powerful tool.
I think blowing up a handful of rockets is a fine idea. But at some point you have to ask yourself if it will ever work? Why are we on a another engine redesign? Why is this the third iteration of the second stage? How many more?
And what number is that point? Six? Nine? I'm thinking thirteen may be getting into the danger zone.
In a somewhat similar situation Sergey Korolyov stopped his colleague in front of the Party officials asking a similar question and explained: "We are exploring terra incognita, this is the process of getting knowledge". He was sort of right - even though there were many specific engineering problems, and many of those were rather solvable, especially in hindsight, overall process was stepping into the unknown.
Here we have a cutting edge rocket design - scale, sophistication of engines, design goals - and a commercial evaluation, which path would get to the intended success cheaper. NASA doesn't like public embarrassments, and, as Henry Spencer reminds us, when failure is not an option, the success could be quite costly. So NASA spends billions and many years for a fragile system. If the goal is an airline-like operations, the design should be thoroughly shaken up. It's known that no simulation, no static testing can equate the actual flights in the ability to get the data best describing what conditions the system will encounter in real use. And also, given the industrial scale of Starship production, each flight hardware costs way less than if we'd built them manually, in quantities justifying naming each unit separately.
In Soviet Union, where rocket departments were part of artillery, the testing with actual launches seemed logical. In this case the approach to run a massive test flight program seems logical too, and we can't complain about the lack of progress - first Starship had way less capabilities and performed way worse. In USA we had more than 1000 tests for injector head for F-1 engine in Apollo program, and this number was justified at that time. Starship is way bigger - but the progress is also undeniable, and it would be odd to stop test flights now, when the 3rd iteration of design looks promising.
So, while we can't pin a particular number of tests, I don't think we should worry yet. This year and the next one should be important for Starship program, given SpaceX commitments to help NASA Artemis. If we won't have orbital Starship then - we can come back to this question.
Not relevant to the discussion, but while it's fairly bland and feels right, I can't find a reference to that quote anywhere. Is this a hallucination? Where did you get it? The fact that you're quoting directly implies you copied it from somewhere.
“Everything that Chertok was about to tell you will take a lot of time.
An explanation of what caused all the failures while solving the soft landing
problem is presented in detail on these posters, focusing on each individual
launch. But there is one general cause that explains everything—this is a
learning process. In our plans and schedules, we did not make provisions for
the expenditure of resources and time on the learning process. That is where
we made our mistake; we have paid for it, and I dare say that in the very near
future the mission will be accomplished. Our learning process has taken us
down a rough road, but we have gained invaluable experience. I request that
the commission permit us to conduct a launch and make the final decision, if
you deem it necessary, based on the results of that launch.”
So what if they blow up literally 100 rockets, if they can eventually perfect it faster and more cheaply than the traditional approach, recently typified by SLS.
SpaceX have already proven that the iterative approach works with Falcon 9, literally the most successful rocket program ever. SpaceX have also proven that this specific Super Heavy/Starship rocket design isn’t a dead end. Criticising them for failing to succeed in the future is a valid but uninteresting opinion.
The point is that by the 100th test flight, your competitor has already proven the first version of their design to the point of being retired by the second version that has a 55% higher payload capacity and had a history of dozens of moon landings and is busy manufacturing solar panels on the lunar surface using lunar regolith, thanks to the orbital infrastructure for lunar transit that they've painstakingly built over several initial launches is paying off.
Meanwhile SpaceX having proven that the iterative development cycle works by first building a successful rocket and accepting customer payloads as soon as possible and then upgrading the rocket as they flew, fell behind because they decided to abandon their origin and instead try to delay success as much as possible which is antithetical to their origin and the success of the launch vehicle. In their hubris, they doubled down on failure, excusing it at every opportunity, while pretending that this is how Falcon 9 succeeded, which is simply not true. You cannot have a radically different development process and call it the same because you're the same company.
It’s cheaper and faster to make in volume. It doesn’t require nearly as much shielding, because it’s less fragile, which saves a lot of weight. The engine itself is lighter. And on top of that, it develops more thrust, at higher fuel efficiency.
The net result is cheaper and lifts significantly more mass to space, which significantly drops the cost per kg to orbit.
It already worked, they’re making it much better, and getting it ready for a level of mass production that we’ve never seen anything close to in the space industry, even from SpaceX. They are much more ambitious than I think people who haven’t been watching them closely understand. The US grid is 1.4 TW of generation, they’re aiming to put up 1 TW of AI compute every year. Maybe they’ll stop well short of that, but their stated goal is insanely ambitious.
v3 is the first version that was made with the intention of being used for actual payload delivery. The versions before were about testing and proof of concept.
The next spiritual successor should allow us to customise the species, and let us deal with whatever consequences that might bring!
Like, you might have a aquatic space-faring species, which requires you to bring lots of water into space. More rockets (and struts!) will be needed, but at least you get really good radiation protection out of it!
Tardigrades ought to be a cheat code, you can just glue your crew to the outside of the booster and they'll probably be alright so long as you don't glue them to the fiery end!
