# NASA’s New AI Superchip Could Change Space Exploration Forever

An episode of [Bedtime Astronomy](https://invisiblenetwork.ai/podcast/1736397134), 19 Jun 2026, 22 min.

Audio: https://dts.podtrac.com/redirect.mp3/api.spreaker.com/download/episode/72152175/nasachipp.mp3

NASA is developing a powerful new space processor designed to survive the brutal conditions of deep space while delivering computing speeds hundreds of times faster than current spacecraft technology. Known as the High Performance Spaceflight Computing system, the chip could allow future missions to the Moon and Mars to make scientific decisions autonomously using onboard AI. Built to withstand intense radiation and extreme temperatures, the technology may not only transform robotic and crewed exploration, but also influence next-generation aviation and automotive systems here on Earth. Thank you for listening to Bedtime Astronomy — your guide to the cosmos. New episodes on space exploration, NASA missions & the latest astronomy breakthroughs. This episode includes AI-generated content.

## Transcript

[0:03] Speaker 1: Welcome to Bedtime Astronomy. Explore the wonders of the cosmos
[0:07] Speaker 1: with our soothing Bedtime Astronomie podcast. Each episode offers a
[0:12] Speaker 1: gentle journey through the stars, planets, and beyond, perfect for
[0:16] Speaker 1: unwinding after a long day. Let's travel through the mysteries
[0:20] Speaker 1: of the universe as you drift off into a peaceful
[0:22] Speaker 1: slumber under the night sky.
[0:27] Speaker 2: Imagine for a second that you are well millions of
[0:29] Speaker 2: miles away from Earth right just hurtling through the absolute,
[0:33] Speaker 2: pitch black, freezing void of deep space. Everything is going
[0:37] Speaker 2: perfectly according to plan, and then suddenly something completely.
[0:41] Speaker 3: Unexpected happens always does.
[0:43] Speaker 2: Exactly, like maybe a piece of debris strikes the hull,
[0:46] Speaker 2: or an unprecedented solar flare washes over the ship, or
[0:50] Speaker 2: I don't know, a vital thruster just suddenly misfires.
[0:53] Speaker 3: Oh that's bad.
[0:53] Speaker 2: Yeah, it's bad. Alarms are going off. You desperately need
[0:56] Speaker 2: a solution. But here is the terrifying reality. Because of
[1:00] Speaker 2: the sheer, vastness of space, there is this massive communication delay.
[1:04] Speaker 2: Massive Right, a distress signal sent to Earth might take
[1:08] Speaker 2: say twenty minutes just to get there, and then another
[1:11] Speaker 2: twenty minutes for any kind of response to actually come back.
[1:14] Speaker 3: Yeah, and by the time Earth even knows you're in trouble,
[1:17] Speaker 3: I mean, the mission could already be totally.
[1:19] Speaker 2: Lost, completely lost. The spacecraft just has to figure it
[1:22] Speaker 2: out entirely on its own.
[1:24] Speaker 3: Basically the ultimate locked room puzzle. But you know, the
[1:27] Speaker 3: room is traveling at thousands of miles an hour through
[1:30] Speaker 3: the most hostile environment imagined. Yeah, when a mission is
[1:33] Speaker 3: that far out, autonomy isn't just some like futuristic luxury.
[1:38] Speaker 3: It is a baseline requirement for survival. You simply cannot
[1:42] Speaker 3: wait for a human sitting at a desk in a
[1:44] Speaker 3: control room on Earth to just push a button, so.
[1:48] Speaker 2: To figure out how we survive that scenario. Today, we
[1:50] Speaker 2: are talking about a really monumental technological leap from NASA's
[1:54] Speaker 2: Jet Propulsion Laboratory. We're looking at their new high performance
[1:58] Speaker 2: spaceflight computing processor.
[2:00] Speaker 3: Game changer, it really is.
[2:01] Speaker 2: We are talking about a revolutionary AI space chip designed
[2:05] Speaker 2: to let spacecraft literally think for themselves. So, okay, let's
[2:09] Speaker 2: unpack this because to truly appreciate how transformative this piece
[2:12] Speaker 2: of hardware is, we really need to understand the reality
[2:15] Speaker 2: of how spacewhit computing currently operates, and frankly, the current
[2:18] Speaker 2: state of technology up there might surprise.
[2:20] Speaker 3: A lot of people, Oh absolutely, because you know, people
[2:22] Speaker 3: naturally assume that since we are sending these incredibly sophisticated
[2:27] Speaker 3: billion dollar machines out into the cosmos, they must be
[2:30] Speaker 3: running on the absolute bleeding edge of computer processing.
[2:34] Speaker 2: Right, like they've got the best tech available.
[2:35] Speaker 3: Exactly. You might picture quantum computers or at least processors
[2:40] Speaker 3: that are vastly superior to the laptop sitting on our desks,
[2:43] Speaker 3: But the truth is entirely the opposite. Current space missions
[2:47] Speaker 3: rely on computing cores that are heavily, heavily outdated by
[2:51] Speaker 3: earthly standards.
[2:52] Speaker 2: Which seems completely counterintuitive until you look at the extreme
[2:56] Speaker 2: bottleneck of space exploration.
[2:58] Speaker 3: Right.
[2:58] Speaker 2: The environment beyond our our atmosphere is just utterly brutal
[3:02] Speaker 2: on electronics. I mean, we're talking about intense electromagnetic radiation
[3:06] Speaker 2: constantly bathing the solar.
[3:08] Speaker 3: System, and the temperature swings, yes.
[3:10] Speaker 2: Dramatic temperature fluctuation, swinging from hundreds of degrees above zero
[3:13] Speaker 2: to hundreds of degrees below sometimes in a matter of
[3:16] Speaker 2: like minutes.
[3:18] Speaker 3: Yeah, but you know, the real enemy of modern computing
[3:22] Speaker 3: out there is the high energy particles.
[3:24] Speaker 2: Explain that a bit more. What kind of particles.
[3:26] Speaker 3: Well, those particles are essentially the absolute bane of a
[3:30] Speaker 3: spacelight engineer's existence. We're talking about cosmic rays. They're basically
[3:34] Speaker 3: atomic nuclei traveling at its significant fraction of the speed
[3:37] Speaker 3: of light coming from the Sun and deep space. Okay,
[3:41] Speaker 3: and when one of these particles strikes a delicate modern
[3:44] Speaker 3: computer chip, it does something entirely disruptive. It doesn't necessarily
[3:48] Speaker 3: like leave a physical bullet hole right. Instead, it dumps
[3:52] Speaker 3: a massive amount of kinetic energy directly into the silicon,
[3:55] Speaker 3: and that knocks electrons completely out of their atoms.
[3:59] Speaker 2: Okay, I want to pause here to really visualize this.
[4:02] Speaker 2: You're saying this invisible microscopic collision creates a literal burst
[4:07] Speaker 2: of electrical charge inside the computer processor.
[4:11] Speaker 3: Exactly that sudden burts of stray electrical charge can actually
[4:15] Speaker 3: trick a delicate transistor into changing its state, so it
[4:18] Speaker 3: flips a zero to a one or a one to
[4:20] Speaker 3: a zero.
[4:20] Speaker 2: Oh wow.
[4:21] Speaker 3: Yeah. We call this a single event upset or a bitflip.
[4:24] Speaker 3: And when that happens, the computer might suddenly calculate the
[4:27] Speaker 3: wrong navigational trajectory, or an entire subsystem just gets confused.
[4:31] Speaker 2: That's terrified.
[4:31] Speaker 3: It is. So when a current spacecraft detects this kind
[4:35] Speaker 3: of cascade error, it is programmed to immediately panic and
[4:40] Speaker 3: force itself into what we call safe mode.
[4:42] Speaker 2: And safe mode is basically the spacecraft curling into a
[4:45] Speaker 2: defensive ball to protect itself.
[4:47] Speaker 3: Right, Yeah, that's exactly what it is. Like.
[4:48] Speaker 2: It temporarily shuts down all non essential systems, the science instruments,
[4:52] Speaker 2: turn off, the camera's power down, and the entire multi
[4:57] Speaker 2: billion dollar machine just goes completely dormant.
[5:00] Speaker 3: It just floats there.
[5:01] Speaker 2: Right, just floating, waiting for human engineers back on Earth
[5:04] Speaker 2: to manually analyze the telemetry, find the flipped bit, and
[5:08] Speaker 2: slowly coax the system back to life.
[5:10] Speaker 3: And during that downtime, the spacecraft is effectively blind and paralyzed.
[5:15] Speaker 3: So historically NASA has deliberately made a really severe trade
[5:18] Speaker 3: off to avoid those constant, terrifying system crashes. They use older,
[5:23] Speaker 3: incredibly durable chips.
[5:24] Speaker 2: Older chips.
[5:25] Speaker 3: Yeah, those legacy chips have physically larger transistors, and because
[5:29] Speaker 3: they are larger, it requires significantly more energy to flip
[5:32] Speaker 3: their state from a zero to a one, so they
[5:34] Speaker 3: are highly resistant to those cosmic ray strikes.
[5:37] Speaker 2: So it sounds like we're sending these incredibly vital missions
[5:40] Speaker 2: into the void running on the equivalent of like a
[5:42] Speaker 2: nineteen nineties brick phone.
[5:44] Speaker 3: Basically, yeah, and we use.
[5:45] Speaker 2: Them just because we know the screen won't crack, even
[5:48] Speaker 2: though the mission really demands a modern smartphone.
[5:51] Speaker 3: That's a perfect analogy, and that trade off has been
[5:54] Speaker 3: completely necessary. I mean, a cutting edge, ridiculously fast modern
[5:59] Speaker 3: computer is utterly useless if a single solar flare fries
[6:04] Speaker 3: its microscopic circuits on day two of a ten year emission.
[6:07] Speaker 2: That's fair.
[6:08] Speaker 3: Surviving the environment is the non negotiable baseline. Everything else,
[6:11] Speaker 3: processing speed, artificial intelligence, complex data analysis that has traditionally
[6:16] Speaker 3: been treated as a secondary luxury.
[6:18] Speaker 2: Okay, but I am trying to reason through this engineering
[6:21] Speaker 2: problem here. Sure, if we need modern computing power, but
[6:24] Speaker 2: the microscopic transistors are too fragile, why not just take
[6:27] Speaker 2: a powerful modern chip out of a high end server,
[6:30] Speaker 2: put it inside a really thick lead box to block
[6:32] Speaker 2: the radiation, and just send that into space. Why do
[6:36] Speaker 2: we need to invent a completely new chip from scratch, well.
[6:39] Speaker 3: That immediately runs into the tyranny of the rocket equation. Wait, exactly,
[6:43] Speaker 3: in spaceflight, waight is your absolute worst enemy. Every single
[6:47] Speaker 3: ounce you send into orbit costs thousands of dollars in
[6:50] Speaker 3: rocket fuel. A thick lead box heavy enough to stop
[6:54] Speaker 3: high energy cosmic rays would be well impossibly massive for
[6:58] Speaker 3: a modern deep space That makes sense. And add to that,
[7:02] Speaker 3: heavy metal healing can sometimes cause secondary radiation scatter.
[7:06] Speaker 2: Where what does that mean?
[7:07] Speaker 3: So the cosmic ray hits the lead and it shatters,
[7:10] Speaker 3: creating this sort of shotgun blast of secondary particles that
[7:13] Speaker 3: still hit the computer.
[7:15] Speaker 2: Oh wow, so the armor actually makes it worse in
[7:17] Speaker 2: a way sometimes.
[7:18] Speaker 3: Yeah, you cannot just armoor a regular chip. You have
[7:20] Speaker 3: to build the resilience directly into the silicon architecture itself.
[7:24] Speaker 2: Which bridges us directly to NASA's game changing development program.
[7:28] Speaker 2: Down at the Langley Research Center, they realized we are
[7:32] Speaker 2: hitting a wall with the brick phone approach.
[7:34] Speaker 3: Right.
[7:35] Speaker 2: If we want autonomous spacecraft or vastly faster onboard scientific analysis,
[7:40] Speaker 2: we need high performance without sacrificing that baseline of survival.
[7:44] Speaker 2: And the result of that effort is the high Performance
[7:46] Speaker 2: Spaceflight Computing Processor, the HPSC. Yeah, and the physical form
[7:50] Speaker 2: factor of this hardware is surprising. It is a system
[7:53] Speaker 2: on a chip or and so small enough to fit
[7:56] Speaker 2: completely in the palm of your hand.
[7:58] Speaker 3: The system on a chip architecture is really vital here. Traditionally,
[8:02] Speaker 3: a computer uses a large motherboard. You have your central
[8:05] Speaker 3: processing unit one corner, your memory in another, and your
[8:08] Speaker 3: networking interfaces.
[8:09] Speaker 2: Somewhere else right spread out.
[8:11] Speaker 3: Yeah, and data has to physically travel across wires between
[8:14] Speaker 3: those components, which takes time and energy. And so ce
[8:18] Speaker 3: combines all of those essential components into a single highly
[8:22] Speaker 3: integrated unit. You have your CPUs, your computational offloads, advanced networking,
[8:26] Speaker 3: and memory interfaces all stacked together on one tiny piece
[8:30] Speaker 3: of silicon.
[8:31] Speaker 2: Wait, you mentioned computational offloads. I want to clarify that
[8:34] Speaker 2: before I move on. What does an offload actually do
[8:36] Speaker 2: in this context?
[8:37] Speaker 3: Good question. Think of the main CPU as the head
[8:41] Speaker 3: chef in a busy kitchen. If the head chef has
[8:43] Speaker 3: to chop every single onion and wash every single dish,
[8:46] Speaker 3: the actual complex cooking just grinds to a halt. A
[8:49] Speaker 3: computational offload is like hiring specialized prep cooks. It is
[8:54] Speaker 3: a dedicated piece of hardware. On the chip designed to
[8:57] Speaker 3: handle one specific, highly pensive task, like what like crunching
[9:02] Speaker 3: heavy math for navigation or processing images from a camera,
[9:07] Speaker 3: it offloads that burden from the main CPU, allowing the
[9:10] Speaker 3: entire chip to run vastly faster and more efficiently.
[9:14] Speaker 2: I appreciate that clarity, but I have to push back
[9:16] Speaker 2: on the novelty of this hardware for a second. Yeah,
[9:19] Speaker 2: my tablet and my smartphone use and soci right now.
[9:22] Speaker 2: I mean, that is how we get consumer devices to
[9:24] Speaker 2: be so remarkably thin. What makes NASA's version a technological breakthrough?
[9:29] Speaker 2: If I literally have an Aussie sitting in my pocket right.
[9:31] Speaker 3: Now, well, the chip in your pocket operates in an
[9:33] Speaker 3: incredibly cozy environment. It enjoys the luxury of Earth's magnetic
[9:37] Speaker 3: field protecting it from cosmic radiation, and it just sits
[9:41] Speaker 3: at a comfortable room temperature.
[9:42] Speaker 2: That's true.
[9:43] Speaker 3: NASA's version is radiation hardened from the ground up, utilizing
[9:46] Speaker 3: completely different engineering principles.
[9:48] Speaker 2: So how exactly do they harden it without using that
[9:51] Speaker 2: heavy lead box we talked about earlier.
[9:52] Speaker 3: One of the most fascinating mechanisms is called triple modular redundancy.
[9:56] Speaker 2: Triple modular redundancy.
[9:58] Speaker 3: Yes, Instead of having one microscopic circuit do a calculation,
[10:02] Speaker 3: they build three identical circuits directly into the chip to
[10:06] Speaker 3: do the exact same math simultaneously.
[10:08] Speaker 2: Wait all three at the same time.
[10:10] Speaker 3: Simultaneously, and at the end of the calculation, they essentially
[10:13] Speaker 3: vote on the answer.
[10:14] Speaker 2: Oh that's brilliant, right.
[10:16] Speaker 3: If a cosmic ray strikes one of the circuits and
[10:19] Speaker 3: flips a bit, causing it to output a wrong answer,
[10:22] Speaker 3: the other two circuits will just outvote it. The chip
[10:25] Speaker 3: instantly recognizes the error, ignores the glitch, and keeps functioning perfectly.
[10:30] Speaker 2: Wow.
[10:30] Speaker 3: They also use insulating layers in the silicon itself, often
[10:33] Speaker 3: called silicon on insulator, to physically prevent that stray electrical
[10:38] Speaker 3: charge from jumping between components and short circuiting the system.
[10:42] Speaker 2: So they are essentially weaving fault tolerance into the actual
[10:45] Speaker 2: logic of the machine exactly. And here is where the
[10:48] Speaker 2: leap in capabilities gets really staggering. The design goal for
[10:52] Speaker 2: this project was to deliver up to one hundred times
[10:54] Speaker 2: the computing power of the spaceflight computers we are currently using.
[10:58] Speaker 3: One hundred times is already huge, yeah, But.
[11:00] Speaker 2: When they started putting the prototypes together and looking at
[11:02] Speaker 2: the early data, they reported it is operating at performance
[11:05] Speaker 2: levels roughly five hundred times greater than current radiation hardened chips.
[11:10] Speaker 3: Of five hundredfold increase just completely alters what a spacecraft
[11:14] Speaker 3: can accomplish.
[11:15] Speaker 2: How do we properly visualize an increase of five hundred
[11:18] Speaker 2: times Because people often use the cliche of trading a
[11:21] Speaker 2: bicycle for a fighter jet, but that doesn't really capture
[11:24] Speaker 2: the mechanics of data.
[11:25] Speaker 3: Processing, No, it doesn't. A better way to look at
[11:28] Speaker 3: it is through parallel processing. Imagine you were trying to
[11:31] Speaker 3: find one specific quote hidden somewhere inside a massive library. Okay,
[11:37] Speaker 3: the current space chips are like having a single librarian
[11:40] Speaker 3: who has to read every single book page by page,
[11:43] Speaker 3: one after the other. It is reliable, but painfully slow.
[11:48] Speaker 3: This new chip is the equivalent of unleashing five hundred
[11:51] Speaker 3: highly trained librarians to scan the entire library simultaneously. Tasks
[11:56] Speaker 3: that use take hours can now be completed in a
[11:58] Speaker 3: fraction of a second.
[12:00] Speaker 2: Of course, you don't just build a five hundred librarian
[12:02] Speaker 2: super chip, look at the paper specs and bolt it
[12:04] Speaker 2: onto a rocket. You have to definitively prove it can
[12:07] Speaker 2: survive the environment, oh absolutely, which brings us to the
[12:10] Speaker 2: grueling testing phase happening right now at NASA's Jet Propulsion
[12:14] Speaker 2: Laboratory JPL down in southern California.
[12:16] Speaker 3: Yeah. Jim Butler is the project manager overseeing this at JPL,
[12:19] Speaker 3: and his team's entire job is to literally torture this hardware.
[12:24] Speaker 2: Torture is the right word.
[12:25] Speaker 3: They began testing in February twenty twenty six, and they
[12:29] Speaker 3: are putting these chips through an absolute ringer. I mean
[12:34] Speaker 3: they are placing them in thermal vacuum chambers that simulate
[12:37] Speaker 3: the freezing, airless void of space, baking them to extreme temperatures,
[12:42] Speaker 3: and bombarding them with heavy radiation to see if that
[12:45] Speaker 3: triple modular redundancy actually holds up.
[12:48] Speaker 2: And beyond the environmental torture, they're simulating the immense computational
[12:51] Speaker 2: stress of an actual emission. Let's talk about the specific
[12:54] Speaker 2: high fidelity landing scenarios JPL is using, because what exactly
[12:58] Speaker 2: happens computationally when a machine tries to land on another
[13:01] Speaker 2: planet like Mars, Well.
[13:03] Speaker 3: A planetary landing is often referred to as seven minutes
[13:05] Speaker 3: of terror. Right the spacecraft is hitting the Martian atmosphere
[13:09] Speaker 3: at thousands of miles an hour. In a span of
[13:12] Speaker 3: just a few minutes, it has to deploy supersonic parachutes,
[13:16] Speaker 3: jettison heat shields, fire retro rockets, and simultaneously use optical cameras,
[13:21] Speaker 3: radar and lightar to rapidly scan the terrain below to
[13:25] Speaker 3: avoid crashing into a crater or a boulder.
[13:27] Speaker 2: The sheer volume of raw data flooding into the computer
[13:30] Speaker 2: in those few seconds must be well astronomical.
[13:34] Speaker 3: Oh it is, and if the processor lags for even
[13:36] Speaker 3: a fraction of a second, the mission becomes a crater wow,
[13:40] Speaker 3: which is precisely why JPL is using these specific scenarios.
[13:44] Speaker 3: They are digitally throwing the entire tidal wave of simulated
[13:47] Speaker 3: landing sensor data at this palm size processor, forcing it
[13:51] Speaker 3: to calculate real time hazard avoidance.
[13:53] Speaker 2: While they're torturing it physically too.
[13:55] Speaker 3: Right, while simultaneously shaking it violently on acoustic vibration tables
[13:59] Speaker 3: that mimic the destructive roar of a rocket launch. They
[14:02] Speaker 3: want to see if the chip misses a single clock
[14:04] Speaker 3: cycle under the most extreme physical and computational stress imaginable.
[14:08] Speaker 2: So they're essentially forcing a supercomputer to run a marathon while.
[14:12] Speaker 3: Locked inside a microwave.
[14:13] Speaker 2: Yeah right, a microwave being shaken in a paint mixer,
[14:16] Speaker 2: just to make sure it doesn't blink during a planetary landing, exactly.
[14:20] Speaker 3: And the testing campaign is proving that this chip handles
[14:24] Speaker 3: the load flawlessly. It is calculating precision landing adjustments entirely
[14:29] Speaker 3: on its own, without relying on an earth bound supercomputer.
[14:33] Speaker 2: That's incredible. And when the team at JPL initially kicked
[14:36] Speaker 2: off this rigorous testing protocol, they sent an internal email
[14:40] Speaker 2: to mark the occasion. The subject line was simply, Hello Universe.
[14:44] Speaker 3: I love that. What's fascinating here is that phrase Hello
[14:47] Speaker 3: Universe is a brilliant, subtle nod to the history of
[14:50] Speaker 3: computer science.
[14:51] Speaker 2: Oh like Hello World.
[14:53] Speaker 3: Yes, whenever a student learns to write code, the very
[14:56] Speaker 3: first program they are taught simply prints the words hello
[14:59] Speaker 3: World on the t terminal screen. It is the universal
[15:01] Speaker 3: sign of a system waking up. By expanding it to
[15:05] Speaker 3: Hello Universe, the engineers are acknowledging the gravity of what
[15:08] Speaker 3: they have built. This is the moment robust modern computing
[15:12] Speaker 3: architecture finally scales to the demands of the cosmos.
[15:15] Speaker 2: It is a massive engineering triumph, but NASA is not
[15:18] Speaker 2: doing this in a vacuum. Back in twenty twenty two,
[15:21] Speaker 2: JPL selected an Arizona based company, Microchip Technology, Inc. As
[15:26] Speaker 2: their commercial partner.
[15:27] Speaker 3: Yeah, they actually co funded the research, right.
[15:30] Speaker 2: They co funded the research and development work on the processor,
[15:33] Speaker 2: which opens up a vital question, how exactly does this
[15:37] Speaker 2: unprecedented processing power fundamentally change how we explore Well.
[15:42] Speaker 3: The answer really lies in localized artificial intelligence. Until now,
[15:47] Speaker 3: utilizing AI and deep space was nearly impossible because machine
[15:51] Speaker 3: learning algorithms require massive amounts of rapid computation.
[15:55] Speaker 2: The kind of computation that would instantly overwhelm a legacy spaceship.
[15:58] Speaker 3: Exactly, with this new processor, spacecraft can finally run conference
[16:03] Speaker 3: AI models locally on the fly.
[16:05] Speaker 2: Which brings us full circle to the disaster scenario we
[16:07] Speaker 2: discussed at the beginning of the show. You are millions
[16:10] Speaker 2: of miles away, debreeze strikes the hull, and Earth is
[16:13] Speaker 2: a forty minute round trip message away. With onboard AI,
[16:16] Speaker 2: the spacecraft analyzes the sensor data the millisecond the impact happens,
[16:21] Speaker 2: It instantly realizes a thrust is failing, calculates a new
[16:25] Speaker 2: power distribution to compensate, autonomously fires secondary rockets to stabilize
[16:29] Speaker 2: the spin, and keeps the mission alive, all in real time.
[16:32] Speaker 3: It's amazing and beyond just disaster mitigation. Consider what this
[16:36] Speaker 3: means for actual scientific discovery. Deep space probes collect staggering
[16:41] Speaker 3: amounts of raw data. Oh yeah, think of a probe
[16:43] Speaker 3: orbiting Jupiter looking for a specific split second ice geyser
[16:47] Speaker 3: erupting on the moon Europa. Currently, a probe has to
[16:50] Speaker 3: take thousands of high resolution images and slowly trickle all
[16:54] Speaker 3: of that raw data back to Earth over the deep
[16:57] Speaker 3: space network.
[16:57] Speaker 2: And the deep space network is incredibly reliable, but it
[17:00] Speaker 2: has severe bandwidth limitations. Sending gigabytes of raw photos from
[17:05] Speaker 2: Jupiter is like trying to download a four K movie
[17:07] Speaker 2: over a nineteen nineties dial up modem. It just takes forever,
[17:11] Speaker 2: and humans on Earth have to manually sift through thousands
[17:14] Speaker 2: of photos of empty space just to find the one
[17:16] Speaker 2: image of the geyser.
[17:18] Speaker 3: But with this powerful new processor, the onboard AI serves
[17:22] Speaker 3: as an intelligent curator. It pre processes all the data
[17:26] Speaker 3: right there in Jupiter's orbit. Okay, the AI looks at
[17:29] Speaker 3: the thousand pictures instantly identifies the one single image that
[17:33] Speaker 3: captures the anomaly, discards the useless data, and only transmits
[17:38] Speaker 3: that one highly valuable compressed insight back to Earth.
[17:41] Speaker 2: That's incredible.
[17:42] Speaker 3: It turns a dial up connection into a pipeline of
[17:45] Speaker 3: pure scientific discovery. And we are looking at deploying this
[17:48] Speaker 3: in Earth orbiters tracking rapid climate change, planetary rovers, navigating
[17:52] Speaker 3: the chaotic surface of Mars, and critically keeping living astronauts
[17:56] Speaker 3: safe during crude missions to the Moon where split second
[17:59] Speaker 3: life support is decisions are mandatory.
[18:01] Speaker 2: Now I want to pivot here and ask the really
[18:03] Speaker 2: vital grounding question. It is amazing that a probe near
[18:06] Speaker 2: Jupiter will soon be able to think for itself, and
[18:08] Speaker 2: it is incredible that astronauts will have vastly better life
[18:11] Speaker 2: support computers. Right, but how does this commercial partnership with
[18:14] Speaker 2: Microchip technology benefit you? The listener driving to work right now?
[18:19] Speaker 2: What is the practical earthly application of this highly specific
[18:22] Speaker 2: space hardware.
[18:24] Speaker 3: This is where we see the historical pattern of space
[18:27] Speaker 3: exploration accelerating terrestrial technology. Think about the engineering paradox NASA
[18:34] Speaker 3: forced Microchip technology to solve here. Okay, build a processor
[18:39] Speaker 3: capable of running advanced AI and processing immense amounts of
[18:43] Speaker 3: sensor data instantly, but make it incredibly compact, energy efficient,
[18:47] Speaker 3: and essentially indestructible against systemic failure.
[18:51] Speaker 2: So they demanded indestructible AI computing.
[18:54] Speaker 3: Indestructible. Now take that exact same processor architecture and install
[18:58] Speaker 3: it into a commercial airplane. Oh wow, the aviation industry
[19:01] Speaker 3: requires fault tolerant computing where an in flight system failure
[19:05] Speaker 3: is simply not an option. Or to bring it directly
[19:08] Speaker 3: to your morning commute, consider the chips powering autonomous vehicles.
[19:11] Speaker 2: That makes perfect sense. A self driving car is basically
[19:14] Speaker 2: a terrestrial spacecraft navigating dynamic hazards.
[19:16] Speaker 3: Exactly, the chip sitting behind the dashboard of an autonomous
[19:19] Speaker 3: car driving you to work relies on a massive influx
[19:22] Speaker 3: of data from cameras, lightar, and radar to navigate unpredictable
[19:26] Speaker 3: city streets safely. While it doesn't face the extreme cosmic
[19:30] Speaker 3: radiation of deep space, it absolutely requires that same fault tolerance.
[19:36] Speaker 3: If a component glitches while the car is traveling seventy
[19:39] Speaker 3: miles an hour down a highway, it cannot freeze or
[19:42] Speaker 3: enter a safe mode.
[19:43] Speaker 2: No, definitely not.
[19:44] Speaker 3: It needs to make a life or death decision in
[19:46] Speaker 3: a fraction of a second, without waiting for a slow
[19:50] Speaker 3: cellular cloud connection. By partnering with NASA to build the
[19:54] Speaker 3: ultimate autonomous base brain, microchip is inadvertently designed the perfect
[19:59] Speaker 3: processor for high stakes earthly industries.
[20:02] Speaker 2: So the technological foundation that will land the next advanced
[20:05] Speaker 2: rover on Mars is the exact same architecture that could
[20:08] Speaker 2: eventually be making your drive to the grocery store infinitely safer.
[20:11] Speaker 3: It's all connected.
[20:12] Speaker 2: It really showcases the ultimate return on investment for pushing
[20:15] Speaker 2: the boundaries of engineering. We set out today to understand
[20:18] Speaker 2: how this new chip works, and the journey reveals that
[20:20] Speaker 2: we are watching the evolution of our space program happen
[20:23] Speaker 2: right now in real time.
[20:25] Speaker 3: We really are.
[20:26] Speaker 2: We are officially graduating from sending highly durable but ultimately
[20:30] Speaker 2: remote controlled calculators out into the dark. We are moving
[20:33] Speaker 2: toward deploying brilliant palm sized brains, brains that can pilot
[20:38] Speaker 2: themselves through the void flawlessly, land on alien worlds, and
[20:42] Speaker 2: accelerate our understanding of the universe by analyzing the cosmos
[20:47] Speaker 2: entirely on their own.
[20:48] Speaker 3: Is a profound shift in how we interact with the universe. Yeah,
[20:51] Speaker 3: and leaves you with something deeply fascinating to consider.
[20:54] Speaker 2: What's that?
[20:55] Speaker 3: Well, for decades, our spacecraft has strictly been our tools.
[20:58] Speaker 3: They're incredibly complex tools, certainly, but ultimately they merely executed
[21:02] Speaker 3: the exact commands we sent them from Earth.
[21:04] Speaker 2: Right.
[21:05] Speaker 3: But if these new AI processors allow spacecraft to process
[21:09] Speaker 3: massive amounts of environmental data, instantly react to the unexpected,
[21:12] Speaker 3: and make their own critical decisions, millions of miles away
[21:15] Speaker 3: from human intervention, well, at what point do they stop
[21:19] Speaker 3: being just our tools and start becoming the actual explorers.
[21:22] Speaker 2: Wow? That is a thought that will stick with me
[21:25] Speaker 2: for a long time. The next time you look up
[21:27] Speaker 2: at the night sky, remember that very soon there won't
[21:30] Speaker 2: just be machines up there waiting for our instructions. There
[21:33] Speaker 2: will be brilliant, palm sized brains thinking, reacting, and figuring
[21:37] Speaker 2: out the vast, unforgiving void on their own. Thank you
[21:39] Speaker 2: so much for joining us for this conversation. Keep looking up,
[21:42] Speaker 2: keep asking questions, and we will catch you next time.

Shows are listed from Apple Podcasts' charts and directory, and Podcast Index where it is used. Every show and episode belongs to its publisher and plays from the publisher's own feed; this site hosts none of them.
