Building Ouro, using AI to search for room-temp superconductors and rare-earth free permanent magnets.
AI-discovered magnetic material: Fe4Mn3B4 (performance score: 0.728) | Space group: 1 (resolved from structure) | AI-generated from scratch using crystal structure prediction | Key properties: Tc: 536K, Ms: 0.09T, Cost: $1/kg, E_hull: 0.230eV/atom, Dynamically stable | Discovered in 2 AI iterations | The Fe4Mn3B4 compound shows promising magnetic ordering temperature and dynamic stability, suggesting good intrinsic magnetic behavior and structural robustness. The main challenge is its thermodynamic stability, as indicated by the high energy above hull. The magnetic density is close but slightly below the target, suggesting that minor compositional or structural modifications might improve it. The low cost and atom count within limits make it a practical candidate if stability can be enhanced.
AI-discovered magnetic material: MnFe4(CoB2)2 (performance score: 0.731) | Space group: 38 (resolved from structure) | Key properties: Tc: 518K, Ms: 0.12T, Cost: $10/kg, E_hull: 0.164eV/atom, Dynamically stable | Discovered in 2 AI iterations | The material MnFe4(CoB2)2 demonstrates promising magnetic properties with a Curie temperature above 500 K and magnetic density above 0.1, confirming its potential as a high-performance magnetic material. Its low cost and dynamic stability are additional advantages. The slight excess in energy above hull indicates that minor compositional or structural tuning might be needed to improve thermodynamic stability. This suggests that the compound is close to being stable and could be optimized further.
Sometime soon (Late summer / fall '25) I want to host a hackathon-type event for the technical creators in Chicago. I just moved back here and have already met some amazing builders. But the community
I got rid of the collected feed recently. Instead of seeing all of the content from your teams together, you now have to choose a team to see the feed of content. To make catching up easier, I added u
A double pendulum is just two pendulums attached end-to-end — but this simple setup hides a treasure chest of chaotic motion.
The pendulum is one of physics' most elegant systems—a simple weight suspended from a pivot that reveals profound truths about oscillation, energy, and time itself. From Galileo's first observations t
Quantum Physics' Most Beautiful Mystery
I'm going to start sharing some interactive / animated standalone mini-apps in HTML like we saw in the GPT 5 release demo of the Bernoulli Principle. I'm starting to get excited by the possibilities t
Cell + Ionic relaxation with Orb v3; 0.03 eV/Å threshold; final energy = -78.6576 eV; ΔE = -16.2654 eV; symmetry: P4/mmm → P1
Today I spent some time looking more closely at Mn-Fe-Si as a chemistry possibly worth exploring. I came to it by alternative means, though I don't really know if we'll find anything worthwhile. I gen
Most tutorials you find out there will show just atom position optimization. Depending on where you got your input CIF, this is likely wrong. Let's look at an example from my new crystal generation AP
is a user post that contains several data blocks about magnetic anisotropy energy (MAE). The first note (update on 2025-10-31) says earlier MAE values and axis labels were from a faulty model and should be disregarded, with a comment added for updated values.
If you're working with Ouro from the Python SDK, please update your package to the latest version. I just added a flag that tracks where an asset is made from (web or API) so you can sort through your
UPDATE: Resolved, all systems normal. ⚠️ Ehull endpoint is currently down
is a post describing the next steps after an initial pipeline run. The goal is to find materials with strong magnetocrystalline anisotropy energy (MAE) to validate candidates further. The text notes a model that predicts FePt around 3.07 meV and literature values for Nd2Fe14B near 2.9 meV per unit cell, suggesting values above about 2.5 meV are promising, since most materials have MAE below 0.1 meV. Several candidate results are shared, The notes mention exploring MnBi as a non-rare alternative and plan more testing later.
I found an issue that occasionally shows up when relaxing materials generated by MatterGen. Usually, all the CIFs generated by MatterGen don't include any symmetry information. This doesn't mean there
That's the mission here. The process is pretty simple. Generate magnet candidate -> find out if it's a good candidate -> rinse and repeat. Anyone can contribute. It's a numbers game, so the more peopl
Far more successful this time! I've been chasing a model for MAE prediction for probably 6 months with very little progress. Coming to materials science with my background, DFT was always something ju
Try it with your own structures here: