🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

live on Forbes with Macrocosmos & Rowan 🤝 a mighty collaboration Thanks for having us Tor Constantino, MBA |! forbes.com/sites/torconst…

Models trained on OMol25 are already live on Rowan!

OMol25 (esen-sm-cons.) model is now live on Rowan This is the eSEN-small architecture trained on the OMol25 dataset which calculates forces by taking the gradients of energy predictions with respect to the atomic positions of atoms instead of directly predicting forces.

NEW POD: VC investor and friend of the pod Patrick Blumenthal (Patrick Blumenthal) sat down to discuss: - Why America spends billions on defense but still isn’t ready for China - What Pat saw inside Ukraine’s basement drone factories - The rise of decentralized warfighting and fiber

I've been experimenting with the OMol25 models from FAIR Chemistry, and I'm quite happy so far. Here's a challenging system that I worked on with Buchwald Group: Pd-catalyzed C–F reductive elimination. The model gives ∆E‡ ~= 23.2 kcal/mol, vs. a reported ∆G‡ of 20.6!

Sam & Jony introduce io

Last week, Meta released OMol25/UMA, a massive dataset of QM calculations and a set of models trained on the dataset. Over the past week, we've spent a lot of time benchmarking, hosting, and running these models. We wrote a post summarizing what we've learned (link below):

We're excited to have front-row seats to this "AlphaFold moment" for atomistic simulation and to be able to help thousands of scientists use these models for their own research. Read my full post with Ari here: rowansci.com/blog/exploring…

from the outside looking in, most frontier ai bio labs seem to have such little camaraderie with each other. anthropic employees invite openai employees to their wedding. but isomorphic employees and profluent employees pretend the other doesnt exist. bizarrely, this is uniquely

Although Rowan is a computational company, my background is experimental—I ran calculations in my PhD, but I didn't really understand how things worked. From Aug 2021 to Dec 2023, I obsessively self-studied quantum chemistry. My goal was to rebuild my entire stack from scratch.