Sry, we forgot our password. PIKA 1.5 IS HERE. With more realistic movement, big screen shots, and mind-blowing Pikaffects that break the laws of physics, there’s more to love about Pika than ever before. Try it.

We had an excellent demo and presentation from Roshan Rao of EvolutionaryScale at #LuxAISummit, which uses AI models (like ESM3) to assist scientists to understand, imagine, and create proteins.

An incredible day for our field. Congratulations David Baker, Demis Hassabis, and John Jumper!!

Today we’re releasing ESM C 300M, and 600M with open weights. ESM C 6B is available immediately on EvolutionaryScale Forge for academic use, and AWS Sagemaker for commercial use. ESM C will be on NVIDIA BioNemo soon. We’re excited to see what you build with ESM!

Really exciting new series of highly efficient protein language models from EvolutionaryScale

Announcing ESM Cambrian. ESM C defines a new state of the art for protein sequence modeling. ESM C is a drop in replacement for ESM2 with much better performance across the board. ESM C models are available for academic and commercial use to enable scientists and builders.

Whoa! When a large language of life model generates a protein equivalent to ~500 million years of evolution. Science Magazine science.org/doi/10.1126/sc… Thomas Hayes Roshan Rao EvolutionaryScale Arc Institute UC Berkeley

Thrilled that the ESM3 paper is now published in Science Magazine! 🌐🧬 We are also announcing public beta availability of the models via the Forge API, including demos to generate proteins and predictions with ESM3 without need to write any code!

So excited about the progress by EvolutionaryScale with ESM3 now in Science Magazine, ESM Cambrian, and more to be announced. Thrilled to continue our collaboration!

This is the first generative protein language model trained on three protein features: sequence, structure, and function. Using GFP as a test case, the model generated a bright functional protein with low sequence homology to known proteins – estimated to be equivalent to a

📢Excited to introduce NanoCas -our new mini CRISPR system that can reach tissues previously out of reach! By shrinking CRISPR to 1/3 its normal size, we can now edit genes in muscle, heart & brain that were difficult to access before. Summary & link to paper:

New Paper Alert! 🚀 We introduce Path Planning (P2), a sampling approach to optimizing token unmasking order in Masked Diffusion Models (MDMs). SOTA results across language, math, code, and biological sequence (Protein and RNA)—all without training. arxiv.org/pdf/2502.03540 🧵👇

🔥 ESM3 on the cover of science 🙏

Protein function often depends on protein dynamics. To design proteins that function like natural ones, how do we predict their dynamics? Hannah Wayment-Steele and I are thrilled to share the first big, experimental datasets on protein dynamics and our new model: Dyna-1! 🧵

TIL that intelligence likely evolved twice; once in birds and then again in mammals. Key evidence seems to be that distinct cell types and brain regions are used to perform similar computations in both birds and mammals. From Quanta magazine.

The story behind the proto-transformers, 2yrs before the "attention is all you need" paper came out. It's got many of the key ideas of modern LLMs

Who's downloading ESMFold so much? We're #8 on HF for most downloads now!