Now available in the App Store apps.apple.com/us/app/materi…

We've hit the GPT-1 moment in electromagnetism. Last month, our Chief Research Officer, @m__frei was on stage breaking down our foundation model for electromagnetism at CDFAM - Computational Design Symposium, in Barcelona. In the talk, Mike covered why EM has resisted AI for so long, what it took to change that, and what comes next on the roadmap for our team at @arenaphysica. EM is one of the four fundamental forces of physics, and underpins the future of the physical systems that'll change the world around us and how we experience it. satcomm, radar, high-speed on-chip communications in the datacenter and at the edge, and photonics. For the physics AI crew, and those building next-gen hardware, worth the 30 minutes. enjoy youtube.com/watch?v=Dd80tO-p…

Inspired by Richard Feynman’s 1961 physics lectures, we’re excited to share The New Feynman Lectures, our physics and engineering series where the greatest minds behind some of the most ambitious hardware companies are at the chalkboard. Season 1 features engineering leaders and industry vets building: @JLopas from @basepowerco , @Vbob202 from @Saronic , Shaun Donovan from @anduriltech , @WillBruey from @VardaSpace , Mike Walsh from @iterorg , and our own @hk2532_harish of @arenaphysica , sharing how they dare to wield key physics and engineering principles to build the most advanced electromagnetically-governed systems on Earth. @arenaphysica , our mission is to serve those bold and daring enough to wield physics and engineering to build a better world, and we think there's no better way to honor that mission than to put the chalk in their hands. This series is for them, and for anyone who wants to learn from them. Season 1 of The New Feynman Lectures goes live on April 27th. Grab a pen and paper out…we’re going back to class.

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/publication…

Yo @arenaphysica announced a pathway to Electromagnetic SuperIntelligence. Arena Physica is about to revolutionize high-speed electronic design. Super excited to be working with this team

I’ve put it out in the universe. I see an opportunity. Hopefully something good happens.

Here’s a direct link to the Materia AR App apps.apple.com/us/app/materi…

I've improved the tracking for this tiny Teensy 4.1 by about 75%. It was blinking in and out before. That will do it. I'm going to release this app soon. Maybe I'll also "product hunt" this thing. #buildinpublic #ios #swift

I've added the Metro M4 Grand Central Express made by Adafruit. The black and white contrast makes tracking so much easier. If you'd like to see your PCB or microcontroller in this app release, message me! I’ll see if it's possible. #buildinpublic

I've been doing a bit of late-night testing to improve the board tracking. I like the idea of leaving in the debug stuff as an option... folks can see how the sausage is made, that type of thing. Should I leave this in for the release?

I’ve been working on improving image recognition and tracking for my new app that’s coming out SOON! There is a small feature in the app where users would be able to create their own custom overlays

Paper Mario AR👾 I made a super small hidden mini-game inside my app—it was only about 400 lines of code. Of course, I can’t launch it with the Mario character, but it was fun to put together! I used ARKit & Photoshop for slicing.

A bug fix came to me while I was sleeping at a picnic. I’m finally able to wrap up all the core features for this AR app! Besides recognizing boards, you'll also be able to drop these pinouts on any surface and more. This was built in SwiftUI and UIViewRepresentable to merge UIKit views. Nothing else!

Working on an iOS app that is primarily centered around using electronics and Apple Shortcuts for automation. Barely any code is required. This is a remote cam. As long as it’s connected to Wi-Fi, I can capture an image and send it to my iPhone.