Categories
Business Creativity Space SpaceX

Test like you fly!

Thereโ€™s a phrase in the SpaceX documentary that keeps coming back to me: โ€œTest like you fly.โ€ It sounds like a slogan. The kind of thing that gets painted on a factory wall and eventually stops meaning anything. But the more I sit with it, the more I think itโ€™s actually a philosophy that reaches well beyond rocket engineering.

The video โ€” a 25-minute documentary SpaceX released last week โ€” is ostensibly about Starship Version 3. New ship, new booster, new engines, new pad, new test site. Everything rebuilt. And theyโ€™re not shy about framing it as a reset, not an upgrade. One description I read called it โ€œa quiet violence in progress.โ€ That phrase stopped me cold, because itโ€™s exactly right. Progress that looks violent from the outside โ€” all that fire and metal โ€” but is somehow quiet in its inevitability.

What moved me watching it wasnโ€™t the engines. It was the engineers. SpaceX put the people on camera: the ones running cryogenic pressure tests at 80 Kelvin, stress-testing tank structures at 70% proof, explaining their failures and their data with the flat affect of people who have made peace with how long hard things take. Thereโ€™s something almost monastic about it. You choose a problem that will not yield easily. You accept that the work will outlast any individual sprint of enthusiasm. You go back to it anyway.

I keep thinking about that in the context of what weโ€™re doing with AI โ€” the other enormous, fast-moving project that I spend so much of my mental energy on. The development arc is different: iterative releases, weeks not years between jumps, demos that blur into deployment. But the same principle is buried in there somewhere. The best AI teams I read about arenโ€™t the ones shipping the most polished demos. Theyโ€™re the ones building infrastructure for failure โ€” evals, red-teaming, structured feedback loops. Test like you fly.

The Raptor 3 engines now produce 280 metric tons of thrust each. Thirty-three of them on a Super Heavy booster means over 17 million pounds of liftoff force. I have no intuitive frame for that number. What I do have a frame for is what those numbers represent: three years of iteration on top of five years before that, on top of a theoretical foundation laid by people who didnโ€™t live to see any of this. Thereโ€™s a compounding in that which I find genuinely moving. Nobody built the Raptor 3 in isolation. It came from everything that broke before it.

The hardest part of the documentary isnโ€™t the engineering. Itโ€™s the implicit acknowledgment of how much remains undone. No Starship has yet achieved full orbital velocity with both stages intact. In-space refueling is still untested. The thermal protection systems need more work. And yet โ€” SpaceX talks about unmanned cargo missions to Mars before the end of this year like itโ€™s on the roadmap, not the wish list. That sentence used to sound like marketing. Watching the footage, it doesnโ€™t anymore.

Iโ€™m not sure what to do with that feeling exactly. Itโ€™s something between awe and vertigo. Weโ€™re living in a moment when the audacious has started to have quarterly milestones. When the impossible keeps showing up on timelines and then โ€” bewilderingly, uncomfortably โ€” meeting them.

Test like you fly. Fail with rigor. Build the thing you actually need, not the thing you could more easily explain.

I keep turning that over. Thereโ€™s a post in there somewhere about writing, too โ€” about the drafts nobody sees, the structural tests that fail, the versions that taught you the one that worked. But thatโ€™s for another day.

For now Iโ€™m just sitting with the footage of those 33 engines lighting up, and the quiet weight of how much went wrong before they could do that.

Categories
SpaceX

A Starlink Light Show?

Earlier this morning Elon Musk commented that itโ€™d be cool to have a โ€œStarlink light showโ€ for Americaโ€™s 250th birthday celebration later this year.

Intrigued, I asked Grok how this might be possible? Hereโ€™s what Grok replied:

A Starlink light show, as casually suggested by Elon Musk in a recent reply on X (where a friend proposed doing one “one of these days” because it “would look cool”), would be a coordinated visual spectacle using the thousands of Starlink satellites already in low Earth orbit. Here’s how it could realistically work, based on current satellite tech, physics, and what’s been observed/discussed.

Current “Natural” Light Shows from Starlink

Starlink satellites already create impressive visual effects unintentionally:

  • Reflected sunlight โ€” They don’t have onboard lights; what people see as bright moving dots or “trains” is sunlight glinting off their flat solar panels and metallic surfaces. Right after launch, when satellites are still clustered and low in orbit, they form a striking linear “train” of pearls across the sky (often mistaken for UFOs). Over time, as they spread out, individual ones can flare brightly when their panels catch the sun at just the right angle toward observers on the ground.
  • Flares and flashes โ€” Astronauts like Don Pettit have captured time-exposure photos showing dozens of Starlink satellites flashing like shooting stars near orbital dawn/dusk, when sunlight hits them optimally while the ground below is dark.

These are passive reflections, not controlled emissions.

How a Deliberate, Controlled Light Show Could Be Engineered

To turn this into something intentional and artistic (e.g., patterns, shapes, messages, or synced effects for an event like the US 250th birthday in 2026), SpaceX would need to add active control. Several feasible methods exist or could be adapted:

  1. Orientation/Attitude Control for Directed Reflections
    Starlink satellites already have precise thrusters and reaction wheels to adjust orientation for communication and orbit maintenance. By tilting solar panels or the satellite body in sync, they could “aim” reflections toward specific ground areas at precise times.
  • Coordinated across many satellites, this could create moving patterns, shapes, or even simple images (like drawing with points of light).
  • Limitations: It only works when the sun is illuminating the satellites (twilight hours), and visibility depends on clear skies and viewer location. Not truly “on-demand” at midnight.
  1. Onboard LEDs or Controllable Lights
    Adding low-power LED arrays (visible from Earth) is technically possible, though current Starlink v satellites don’t have them. Power draw would be minimal compared to their solar/battery setup, and they’d only need to activate briefly for a show.
  • This would allow night-time visibility without relying on sunlight.
  • Precedents exist in other satellites (e.g., some experimental ones with flashing beacons), but it’d require new hardware on future generations.
  1. Using Existing Inter-Satellite Lasers (the “Space Lasers”)
    Starlink satellites are equipped with optical inter-satellite links (lasers) for high-speed data transfer between satellites (up to 200 Gbps per link, with thousands active). These are infrared lasers, invisible to the human eye.
  • Not directly usable for a visible show โ€” They’re not pointed at Earth for this purpose, and IR isn’t visible.
  • A fun speculative twist: Future upgrades could include visible-wavelength lasers or diffusers, but that’s not current capability. (Some discussions joke about “space lasers” for displays, but it’s mostly the reflection method that’s practical.)
  1. Long-Exposure or Camera-Based Effects
    One creative workaround mentioned in discussions: Have people point cameras/phone apps upward for a set time while satellites flash reflections in patterns. Combined with apps syncing exposure, it could form large-scale images (e.g., flags, logos) visible only in photos/videos, not to the naked eye. This scales with the constellation’s size (over 7,000+ satellites now, heading toward tens of thousands).

Practical Challenges and Realism

  • Scale needed โ€” At any moment, only ~50โ€“100 Starlink satellites might be visible overhead in one spot (due to orbital geometry). A continent-wide show would require precise timing across the fleet and ideal viewing conditions.
  • Light pollution concerns โ€” Astronomers already criticize Starlink for unintended brightness; a deliberate show could amplify backlash unless mitigated (e.g., SpaceX has added anti-reflective coatings to newer versions).
  • Feasibility today vs. future โ€” Musk’s comment was lighthearted (“one of these days”), likely nodding to future versions with more control. Current satellites could do basic coordinated flares/reflections with software updates, but a full “spectacular” show might need hardware tweaks on next-gen birds.

In short, the simplest and most likely version would leverage sunlight reflections with synchronized satellite tiltsโ€”turning the night sky into a moving canvas of twinkling points. It’d be epic for a patriotic event, but more “string of controlled flares” than a laser-light extravaganza like a fireworks show. If SpaceX ever does it, expect announcements and tracking apps to tell you exactly when/where to look!


Quite fascinating!

Categories
AI Business SpaceX

Overcoming Limiting Factors: Orbital Data Centers & The Optimus Era

One of my favorite persons to follow on X is @pbeisel (Phil Beisel). Heโ€™s quite active sharing his thoughts about many of the same topics Iโ€™m interested in: technology, AI, robotics, computing, etc. Phil’s written a series of great articles about Tesla Full Self Driving, Optimus, etc. that are well worth spending time with.

On Saturdays, he get together on YouTube with Randy Kirk and they talk about whatโ€™s interesting from the last week – often thatโ€™s got something to do with various aspects of the โ€œMusk-conomyโ€ – the various companies of Elon Musk.

This weekโ€™s edition reviews Philโ€™s distillation of the Cheeky Pint interview with Elon published earlier this week. As usual, Philโ€™s comments add additional insights into the topic.

When I begin viewing a long YouTube video, I also like an accompanying summary that I can follow along. YouTube now has the ability to generate these summaries but Iโ€™ve got a custom Gem prompt that I prefer to use instead which tailors the results a bit more to my liking.

Below, for example, is the summary of this weekโ€™s conversation between Phil and Randy that was generated by Gemini Pro 3:

Executive Summary: The Musk “Musconomy” Convergence

The central thesis of the discussion is that Elon Musk is moving toward a total vertical integration of his companies (Tesla, SpaceX, and xAI) to overcome terrestrial “limiting factors” and dominate both the physical and digital manifestation of AI.


1. The “Limiting Factor” Philosophy [11:20]

  • Problem-Solving Framework: Musk focuses personal time and resources strictly on the “limiting factor” of any given projectโ€”currently identified as compute power and energy.
  • Vertical Integration: To bypass supply chain bottlenecks (e.g., turbine blades for power plants), Musk is opting to manufacture raw materials and components in-house rather than relying on external catalogs [18:18].

2. Orbital Data Centers: The Space “Escape Hatch” [24:19]

  • Energy Constraints: Terrestrial data centers are hitting a wall due to slow public utilities and permitting [15:26].
  • The Vision: Moving inference-based data centers to orbit using a constellation of satellites connected by optical laser links.
  • Economic Viability: Musk projects economic viability for space-based data centers within 30โ€“36 months, with reusability of the Starship being the primary hurdle [25:03].
  • Strategic Advantage: Unlike Google or Meta, Musk owns the “kilogram-to-space” delivery mechanism, potentially forcing competitors to rent capacity from SpaceX [32:19].

3. Optimus and the “Abundance Engine” [39:00]

  • Physical Dexterity: Musk is prioritizing high-dexterity actuators designed in-house to achieve human-level utility [40:30].
  • Training Scale: Tesla is moving toward training Optimus in “gymnasiums” using 10,000โ€“30,000 bots working 24/7 to develop “composable” skills (basic movements) and “decomposable” skills (complex tasks) [55:13].
  • Impact: Optimus is viewed as a paradigm-shifting product that will redefine global GDP by decoupling labor from human constraints [54:56].

4. xAI: The Digital Control Plane [56:19]

  • The “Brain” Portability: xAI is viewed as the “orchestration AI” for the entire fleet of Muskโ€™s physical assets (Starships, Teslas, and Optimus) [59:01].
  • Unified Interface: The vision includes a seamless “digital personality” or movable brain that follows the user from their phone to their car to their home robot [01:00:15].

Key Projections & Timelines

Objective Target/Detail Timestamp SpaceX IPO Likely to happen before a Tesla merger to attract cheap capital [03:31] Solar Scaling Aiming for a 300x increase (100 gigawatts/year) [22:21] Starship Reusability remains the “unlock” for space-based AI economics [25:51]

Conclusion: The “Musconomy” is transitioning from separate ventures into a singular entity where SpaceX provides infrastructure, Tesla provides the physical bodies, and xAI provides the intelligence.

Categories
Aviation Business Materials SpaceX Uncategorized

Carbon Fiber to Steel

A recent video on the Cheeky Pint channel includes a deep-dive conversation with Elon Musk, Dwarkesh Patel and John Collison (released February 5, 2026).

This interview includes one of the most lucid explanations of the “Carbon Fiber to Steel” pivot Elon took with the SpaceX Starship because Dwarkesh pushes him on the manufacturing and economic implications, not just the rocket science. It contextualizes the “Steel vs. Carbon Fiber” debate as a masterclass in Elonโ€™s 5-Step Algorithm (specifically Step 1: Make the requirements less dumb):

The “Sunk Cost” Pain
One of the most human moments in this discussion is Elon describing the sheer pain of abandoning carbon fiber.

  • They had already built massive, expensive composite mandrels (molds).
  • They had already ordered the raw material.
  • The team was “in love” with the high-tech aesthetic of black carbon fiber.
  • The Lesson: The switch to steel wasn’t just an engineering challenge; it was a psychological one. It required the leadership to say, “I don’t care that we spent millions on these molds; if they are the wrong path, we scrap them today.” This is the ultimate rejection of the Sunk Cost Fallacy.

The “Counter-Intuitive” Thermal Graph
Elon often sketches in the air during interviews, and he describes it vividly here:

  • Carbon Fiber: Great at room temp, but weak at high heat (resin melts) and tricky at cryogenic cold (can micro-crack/leak).
  • Steel (30X): The “miracle” is that itโ€™s the only material that gets stronger at cryogenic temperatures (holding the fuel) while simultaneously resisting high heat (re-entry).
  • The Insight: He highlights that if you look at the properties at both extremes (โ€“165ยฐC and +800ยฐC), steel is actually the lighter system because you can delete the heat shield on the leeward side.

“The Machine That Builds The Machine”
The choice of steel wasn’t just about the rocket; it was about the factory.

  • Carbon Fiber: Requires a clean room, autoclaves, precision placement, and slow cure times. If you make a mistake, you scrap a $2M part.
  • Steel: You can weld it in a tent in a muddy field (which they literally did at Boca Chica).
  • Velocity: Elon explains that steel allowed them to iterate faster. They could build a tank, blow it up, sweep up the pieces, and weld a new one in 3 days. With carbon fiber, that loop would take 3 months. Innovation per unit of time is the true metric, and steel maximized that.

Cost Per Kilogram
He reiterates the brutal economics:

  • Carbon Fiber: ~$135/kg (plus ~35% scrap rate).
  • Steel: ~$3-4/kg.
  • When you are building a “railroad to Mars” and need to build 1,000 ships, the material cost difference is the difference between a bankruptcy and a self-sustaining city.

Elon frames the steel decision not as “finding a better material” but as identifying the bottleneck. The bottleneck wasn’t the weight of the rocket (which carbon fiber solves); the bottleneck was the cost and speed of production (which steel solves).

It is a great example of his philosophy: “The best part is no part” (deleting the heat shield) and “The best process is no process” (deleting the autoclave).