Pratap Ranade

notboring.co/p/electromagne…

3

5

215

Pratap Ranade@PratapRanade·4h

ZXX

2

65

Pratap Ranade@PratapRanade·4h

An F-15E strike eagle was shot down by Iran on Friday and it’s a good example of this whole hidden electromagnetic battlefield. The F-15E’s RWR (Radar Warning Receiver) is triggered by an active radar beam from the guidance system of an incoming missile. The Iranian missile didn’t activate a radar beam until the last minute, giving the pilots very little time to deploy countermeasures and evade, but instead used a different EM wavelength (infrared) to passively track the jet Once they ejected, the pilots had to choose when and where to activate their beacons – which emit EM signals to help friendly forces locate them. Iran would have tried to spoof the signal, creating multiple false images – our forces had to see through the noise to find the pilot, and mount the rescue EM is invisible, unintuitive and yet becoming a dominant element of modern warfare. We dove in and wrote a bottom-up explainer about how AI is changing our understanding of this invisible world with @packyM (link in comments)

English

0

4

236

Pratap Ranade@PratapRanade·5h

@straceX Very true. The bottleneck is now analog. Creating those high-speed channels with minimal crosstalk. Now this is an applied physics / electromagnetics problem

English

Cosmos Archive@cosmosarcive

1

167

Gracia@straceX·22h

Your CPU spends more energy moving a bit across the die than flipping it. We built massive caches to hide latency. Now the wires connecting them consume more power than the logic itself. Welcome to the data movement wall.

English

35

71

993

36.3K

Pratap Ranade retweetledi

Bluntly Put Philosopher (BPP)@SocraticScribe·1d

Have you ever seen the decapsulating of a microchip layer by layer using a 30W JPT Fiber Laser? Well now you have and the the precision is wild to see.

English

19

120

790

82.3K

Pratap Ranade@PratapRanade·2d

Electromagnetism is beautiful

A regular lightbulb isn’t “incoherent”; it just depends on how fast you look. At, 10⁻¹⁶ s → you see clean EM waves 10⁻¹⁴ s → perfect interference patterns 10⁻⁶ s → classic messy bulb light Coherence isn’t a property of source; it’s timescale.

English

Space is a hot topic this week. FPGAs play a very important part in space applications from satellites to launchers, imaging to RADAR and communications FPGA are at the heart. There are some excellent articles in the FPGA Horizons Journal, on how FPGAs are used in space. Check them out! issuu.com/fpga-horizons/… issuu.com/fpga-horizons/…

6

290

Pratap Ranade@PratapRanade·2d

FPGAs – super powerful, and still underrated. Great recs @ATaylorFPGA

Adam Taylor@ATaylorFPGA

English

10

734

Pratap Ranade@PratapRanade·2d

Honored to have been on @tbpn yesterday to talk about Heaviside, @arenaphysica 's foundation model for electromagnetism, <24h before their @OpenAI acquisition announcement. Even more honored that @jordihays and @johncoogan went deep on alien geometries with me on such a big week. They are genuinely great humans, with such an authentic love for technology, business and the people building it. Nice get @sama!

English

8

46

10.6K

Pratap Ranade@PratapRanade·3d

@AldaLeuDennis @arenaphysica Grateful to have backers like you @AldaLeuDennis

English

2

58

Alda Leu Dennis@AldaLeuDennis·3d

Wow, this phased array component was made off of just a natural language prompt! Thanks @arenaphysica - I’m excited by the possibilities

English

3

9

522

Pratap Ranade retweetledi

Bobby Cosmic@scifibobby·4d

An ELECTROMAGNETIC interview today on @TBPN with @PratapRanade, focused on Arena Physica's pioneering electromagnetic superintelligence! @arenaphysica

English

3

5

535

Pratap Ranade@PratapRanade·3d

Inspiring. Let's GO @NASA !!!

NASA@NASA

We're going around the Moon. Come watch with us. Artemis II's four-astronaut crew is lifting off from @NASAKennedy on an approximately 10-day mission that will bring us closer to living on the Moon and Mars. The launch window opens at 6:24pm ET (2224 UTC). twitter.com/i/broadcasts/1…

English

Trae Stephens@traestephens

6

187

Pratap Ranade@PratapRanade·3d

Thanks @traestephens! Grateful to have you and @foundersfund as investors

First phased array component designed by a natural language prompt using Atlas by @arenaphysica. Congrats, guys!

English

2

8

1K

Pratap Ranade retweetledi

Stefan Frei@Stefan24Frei·5d

My big brother doing big things! 💪

Today, we're announcing Heaviside, our foundation model for electromagnetism. Trained on tens of millions of designs and over 20 years of proprietary simulation data, Heaviside predicts electromagnetic behavior from geometry in 13ms, which is 800,000x faster than a commercial solver. Heaviside is not a language model, and it’s not a surrogate model. Heaviside marks a new class of foundation model for physics which understands the fundamental relationships between materials, the geometries and the electromagnetic fields they generate. We’re releasing a research preview of Heaviside in Atlas RF Studio, an interactive agentic sandbox where you describe the EM behavior you want and the model generates the physical structure that produces it. @arenaphysica , we believe the implications of this class of model extend well beyond RF, as the frontier of exquisite hardware is electromagnetically-governed: wireless communication, radar, power delivery, high-speed computing, and the interconnects inside every chip on earth. In the months ahead, we’re excited to scale up Heaviside to broader frequency ranges, design spaces, and to support silicon-level designs, and deploy it with our closest partners and collaborators in service of their biggest design challenges. If you’ve read our thesis, this is just Step 2 in our pursuit of electromagnetic superintelligence. Read the full announcement and try Atlas RF Studio…tell us what you think: arenaphysica.com/publications/r…

English

5

21

2.5K

Pratap Ranade@PratapRanade·5d

@LTG1455 @NatalieFratto @packyM @arenaphysica @anrfic can provide more detail, but here you go

English

3

0

2

139

Lee Gibson@LTG1455·5d

@NatalieFratto @PratapRanade @packyM @arenaphysica Can you guys post the measured results (S11, S21) for each so we can see how well it did?

English

0

7

2K

Natalie Fratto@NatalieFratto·5d

One of these things is not like the other… The other day @PratapRanade brought home 3 RF circuits. Ok “10GHz band pass-filters” he says, to be precise. The first two are human-made, the third is what they’re calling “an alien geometry” 👾 Look how funky it is. That’s the world’s first-ever AI-made RF circuit achieved by the electromagnetism foundation model @arenaphysica. No human would have created it this way. It’s odd, it looks random, but it really works & it might be the future guts inside every satellite, radar, microwave etc one day.

Today, we're announcing Heaviside, our foundation model for electromagnetism. Trained on tens of millions of designs and over 20 years of proprietary simulation data, Heaviside predicts electromagnetic behavior from geometry in 13ms, which is 800,000x faster than a commercial solver. Heaviside is not a language model, and it’s not a surrogate model. Heaviside marks a new class of foundation model for physics which understands the fundamental relationships between materials, the geometries and the electromagnetic fields they generate. We’re releasing a research preview of Heaviside in Atlas RF Studio, an interactive agentic sandbox where you describe the EM behavior you want and the model generates the physical structure that produces it. @arenaphysica , we believe the implications of this class of model extend well beyond RF, as the frontier of exquisite hardware is electromagnetically-governed: wireless communication, radar, power delivery, high-speed computing, and the interconnects inside every chip on earth. In the months ahead, we’re excited to scale up Heaviside to broader frequency ranges, design spaces, and to support silicon-level designs, and deploy it with our closest partners and collaborators in service of their biggest design challenges. If you’ve read our thesis, this is just Step 2 in our pursuit of electromagnetic superintelligence. Read the full announcement and try Atlas RF Studio…tell us what you think: arenaphysica.com/publications/r…

English

115

379

2.9K

453.2K

Pratap Ranade@PratapRanade·5d

@randOver_ @arenaphysica Try it here: studio.arenaphysica.com

English

1

2

26

randOver@randOver_·5d

@PratapRanade @arenaphysica This shit is so cool - how can I play with it

English

0

1

28

Pratap Ranade@PratapRanade·5d

Incredibly excited to introduce Heaviside, our foundation model for electromagnetism. Try it out

Today, we're announcing Heaviside, our foundation model for electromagnetism. Trained on tens of millions of designs and over 20 years of proprietary simulation data, Heaviside predicts electromagnetic behavior from geometry in 13ms, which is 800,000x faster than a commercial solver. Heaviside is not a language model, and it’s not a surrogate model. Heaviside marks a new class of foundation model for physics which understands the fundamental relationships between materials, the geometries and the electromagnetic fields they generate. We’re releasing a research preview of Heaviside in Atlas RF Studio, an interactive agentic sandbox where you describe the EM behavior you want and the model generates the physical structure that produces it. @arenaphysica , we believe the implications of this class of model extend well beyond RF, as the frontier of exquisite hardware is electromagnetically-governed: wireless communication, radar, power delivery, high-speed computing, and the interconnects inside every chip on earth. In the months ahead, we’re excited to scale up Heaviside to broader frequency ranges, design spaces, and to support silicon-level designs, and deploy it with our closest partners and collaborators in service of their biggest design challenges. If you’ve read our thesis, this is just Step 2 in our pursuit of electromagnetic superintelligence. Read the full announcement and try Atlas RF Studio…tell us what you think: arenaphysica.com/publications/r…

English

11

26

3.1K

Pratap Ranade retweetledi

Dennis Wingo@wingod·5d

Oh, this looks really interesting. I suspect we are about to have some major innovation not only in electromagnetics, but in structural and thermal design. The legacy engineering software system is about to bite the dust and they don't even know it yet. We are more and more integrating AI into our day to day engineering workflow and the productivity gains are incredibly good.

Today, we're announcing Heaviside, our foundation model for electromagnetism. Trained on tens of millions of designs and over 20 years of proprietary simulation data, Heaviside predicts electromagnetic behavior from geometry in 13ms, which is 800,000x faster than a commercial solver. Heaviside is not a language model, and it’s not a surrogate model. Heaviside marks a new class of foundation model for physics which understands the fundamental relationships between materials, the geometries and the electromagnetic fields they generate. We’re releasing a research preview of Heaviside in Atlas RF Studio, an interactive agentic sandbox where you describe the EM behavior you want and the model generates the physical structure that produces it. @arenaphysica , we believe the implications of this class of model extend well beyond RF, as the frontier of exquisite hardware is electromagnetically-governed: wireless communication, radar, power delivery, high-speed computing, and the interconnects inside every chip on earth. In the months ahead, we’re excited to scale up Heaviside to broader frequency ranges, design spaces, and to support silicon-level designs, and deploy it with our closest partners and collaborators in service of their biggest design challenges. If you’ve read our thesis, this is just Step 2 in our pursuit of electromagnetic superintelligence. Read the full announcement and try Atlas RF Studio…tell us what you think: arenaphysica.com/publications/r…

English

10

62

4.5K

Pratap Ranade@PratapRanade·5d

@SamVanivray @NatalieFratto @packyM @arenaphysica Yes absolutely. Great concepts from Nasa years ago. Now with deep learning we have a way to scale that way up: en.wikipedia.org/wiki/Evolved_a…

English

0

5

161

Sam Vanivray@SamVanivray·5d

@NatalieFratto @PratapRanade @packyM @arenaphysica But there was prior work, I think. Probably 20ish years ago, an AI came up with a novel useful antenna design.

English

0

13

3.7K

Pratap Ranade@PratapRanade·5d

@WrenchFire @NatalieFratto @packyM @arenaphysica Results here: arenaphysica.com/publications/r…

English

0

1

108

FireWrench@WrenchFire·5d

@NatalieFratto @PratapRanade @packyM @arenaphysica But how did it preform. I bet it broke into the quantum realm and delivered super crisp performance. /s but also how did it preform.

English