Taking recs on the best Cursor themes 🤔 have not found something that consistently beats gruvbox or papercolor in neovim

So for 5 years, “offline” has been the #1 request. Today, thanks to the perseverance of our engineering team, Notion finally works offline. Your ideas don’t need Wi‑Fi to exist! For Notion community: thank you for your patience while we built this right. This is a journey,

.Jacob Kimmel thinks that the functionality to reverse aging already exists in our epigenome. But then why didn't evolution already optimize for longevity? Jacob explains that if you consider evolution as an optimizer, the gradients flow in a really surprising way. Naively,

The plot thickens... 👀 Track the leaderboard here: virtualcellchallenge.org/leaderboard

Learned a lot through this article on the intricacies of data generation and processing: arcinstitute.org/news/behind-th… It makes sense why there’s no foundation model for perturbations yet. So many variables like capture chemistry, UMI/cell, cells/perturbation, batch effects, technical

Want to bring RNA therapeutics innovation to North America? Blank Bio (YC S25) is developing foundation models to support RNA therapeutics development.

✨ Excited to share a few life updates! 🎤 My TED Talk is now live! I shared the origin story of Evo, titled: "How AI could generate new life forms" TED talk: ted.com/talks/eric_ngu… ✍️ I wrote a blog post about what it’s *really* like to deliver a TED talk blog:

Could not be more excited about this announcement! RNA has been the one major theme of my research since grad school; when together with Olivier Elemento, we realized that there is more to gene expression than transcriptional control. And I have been on a path to understand

Arc Institute trained their foundation model Evo 2 on DNA from all domains of life. What has it learned about the natural world? Our new research finds that it represents the tree of life, spanning thousands of species, as a curved manifold in its neuronal activations. (1/8)

Can protein LMs reveal scientific knowledge? We start by asking how pLMs turn sequences into structure signals. We map a contact prediction circuit: early motif features gate later domain features. Spurious or science? We can now test. 🧵(1 of N)

claude code with bioinformatics packages that have actually helpful documentation for all subcommands (and also helpful error messages)... is a cheat code. e.g.: noamteyssier.github.io/ggetrs/

the jump from gpt4 -> gpt5 was obviously larger than the jump from gpt3 -> gpt4

Nothing motivates good git hygiene like my interns Claude code and codex 😄 (cursor has been cut from the team)

🌎👩‍🔬 For 15+ years biology has accumulated petabytes (million gigabytes) of🧬DNA sequencing data🧬 from the far reaches of our planet.🦠🍄🌵 Logan now democratizes efficient access to the world’s most comprehensive genetics dataset. Free and open. doi.org/10.1101/2024.0…

new colab notebooks! also all 200M+ single cells used in the STATE study are available on Hugging Face. Embed your data with State Embedding: colab.research.google.com/drive/1uJinTJL… Run inference with pre-trained models on Tahoe-100M: colab.research.google.com/drive/1bq5v7hi… Train a State Transition model for

TIL I've been using claude code like a boomer. you can @ files and it has vim mode?? 10/10 features cat

Nature research paper: Single-cell transcriptomic and genomic changes in the ageing human brain go.nature.com/47pAPjO

ok, codex cli is indeed really good now. particularly with bash scripting and with optimizing code. also less sycophantic than CC