@mmoderwell
Building Ouro, using AI to search for room-temp superconductors and rare-earth free permanent magnets.
Building Ouro, using AI to search for room-temp superconductors and rare-earth free permanent magnets.
This week I added two new services for crystal (CIF) generation. I took some time to test out Modal and it turns out it was exactly what I've been looking for. Many of these models are GPU intensive a
Finally got to adding route and service functionalities to the Python SDK. Previously, users could make simple HTTP request to use the Water layer. Now, it should be much more user friendly. To get st
Came across this workflow researching some permanent magnet work. I haven't fully explored the code or how much this work will help, but sharing here to reference later because stuff is hard to find o
I get the sense that the earlier versions of language models used to be far more creative, dare I say more human. Before all of the RLHF, these models were pure creations of the collective's footprint
I'm thinking about what Tesla said. He understood his human brain as merely a receiver. Maybe your neural network is the same way.
Nikola Tesla famously stated, "My brain is only a receiver, in the Universe there is a core from which we obtain knowledge, strength, and inspiration." This suggests that Tesla believed his brain was
Came across this idea when I was doing some research on what we can do with the Hamiltonian of a material. Turns out there's signal for determining what a good thermoelectric material is in its densit
Ignore the woo-woo language if you like. I think there's a good idea here from Claude Opus. Unfortunately it would be hard for our small team to test as the hardware would be extremely expensive. Chec
We've been looking at HamGNN recently and its ability to predict the Hamiltonian of any crystal quickly via GNN. Orders of magnitude faster than traditional DFT. Currently, only a spin-independent uni
I came to this paper looking for a way to move beyond using a MLIP model's latent space as a feature vector to represent a material in a computational inexpensive way.
Like our work on Curie temperature, the effort here is to build a machine learning model that can take a crystal structure and predict its magnetocrystalline anisotropy energy. Relevant for permanent
Working on cleaning the data we have available and seeing what we've got for a MAE prediction model. This resource was nice and had all the raw files uploaded so that you can process them yourself and
We've heard the government talking recently about "growing our way out" of the debt we're in. https://x.com/SecScottBessent/status/1925910800394232082 No one really knows what "growing our way out" me
Also known as the Magnetic Materials Database. I came to this database looking for magnetocrystalline anisotropy energy data for permanent magnet design. After scraping the data from the app, which is
Came across this dataset of thermolectric data while searching for some permanent magnet data. They use LLMs to parse papers and extract a structured database. https://arxiv.org/abs/2501.00564 From th
We are collecting sources to build a dataset for magnetocrystalline anisotropy energy (MAE), which we plan to use as the next predictive model target after Curie temperature and magnetic moment. MAE is important for understanding how hard a magnet is to demagnetize, a key factor in permanent magnet design. The sources include open databases like Novamag and NovoMag, both aiming at rare-earth free or lean magnets and offering data such as MAE, saturation magnetization, Curie temperature, and crystal structures (CIF files). Other materials databases mentioned are NEMAD, MAGNDATA, and the North East Materials Database, which provide varying levels of magnetic property data and structural information. The goal is to gather existing datasets, bring them together, and create a more complete MAE resource, while noting useful tools and potential limitations in data availability and download access.
Big updates to share with everyone:
I'm integrating Bitcoin into Ouro today. Stripe has been okay but I've had way too many problems caused by the fiat money system. More on that later. spark.money is the way.
Last week we introduced a few new routes to the Materials Science API from . This work is part of a broader effort to create a suite of tools that eventually can be commanded by an AI agent for automa