Space cowboy riding a massive rock across the galaxy, wrangling genomes and herding data. PhD in Biochemistry @TAMUBCBP. Working @LanzaTech.
Chicago, Illinois
Joined October 2020
- Tweets2.6K
- Following1.5K
- Followers442
- Likes9K
Dan Browne retweeted
Thrilled to share new work from our experimental biology lab at @AnthropicAI. Led by world-class biochemist Januka Athukoralage, we built a rapid method for the isolation and structural characterization of vaults. It turns out these massive structures are not just found in eukaryotic cells, but also in prokaryotes and even phages. We solve the structure of one of these phage vaults, and then demonstrate we can engineer additional repeats into the wall to make it bigger.
One thing I can't get over about these vaults. They seem to be widespread across life - we assembled them from 8 different bacteria and bacteriophages. But they are just so massive - bigger than ribosomes, AAV, and even some phage capsids. Why devote so much energy to making these huge complexes? They have to be doing something useful - I hope that's the question that gets answered next.
Amazing collaboration with @PeterHYoon, @amirshanehsaz, @eric_kabrams, and @mgdurrant! Grateful to our team for making Claude an amazing labmate and to Anthropic for supporting this type of work on fundamental biology.
Natural mysteries abound - let's get to solving them!
Links here:
Blog: anthropic.com/research/inves…
Technical report: www-cdn.anthropic.com/76e55f…
Dan Browne retweeted
Today we release Ripple-65B Preview, our 65B dense LLM we pretrained from scratch.
Ripple sets a new state-of-the-art for U.S. open-weight models in agentic coding tasks, surpassing significantly larger models including Muse Spark Open-816B, Beam-501B, Inkling-975B, and Nemotron 3 Ultra-550B.
Learn more: ricursive.com/ripple
Dan Browne retweeted
In-context learning with the Evo2 genome language model to design lanmodulins, rubisco, anti-CRISPR proteins, epitope-specific de novo antibodies, CRISPR–Cas systems, and mitochondrial and bacteriophage genomes.
@garykbrixi @divnori @aditimerch @talaldotpdb @BrianHie
Dan Browne retweeted
This is wild. (CTO of Legora, one of the most popular Legal AI platforms btw):
Related to the whole 'frontier models can understand and directly modify weights' topic from the last several days.
My brain continues to break as we see new things in this space. What a fun time to be building and learning.
Dan Browne retweeted
Today we’re launching @vorelios (YC F26)!
We’re a research lab building AI that can engineer anything. Models that predict a design’s behavior in seconds and use those predictions to invent and improve designs autonomously. 🧵
w/ @krish_k07 , @ycombinator
vorelios.com
Dan Browne retweeted
Last summer, I joined @intology, leading the effort to connect autonomous AI research to scientific discovery.
Today, we’re sharing work on autonomously adapting frontier scientific models to proprietary datasets and our broader vision for what's next.
🧵(1/6)
Locus sets the frontier for automating molecular design
Our automated research system Locus develops scientific AI models that outperform SOTA expert solutions
Unlocking the potential of scientific AI requires leveraging proprietary data. Locus achieves this autonomously 🧵👇
--
We test Locus across a number of tasks related to molecular scoring and design: training molecular property prediction models for a proprietary task, fine-tuning Boltz-2 to predict small-molecule potency, and building antibody design workflows around BoltzGen, Boltz-2, ESMC, and ESMFold2.
Each of these settings are real-world AI for science use cases, where tasks are often out-of-distribution for existing foundation models and limited in data, while featuring expensive and noisy evaluators. Compared to state-of-the-art baselines and LLM agents set to optimize these tasks, Locus achieves higher performance. Additionally, Locus generalizes better despite limited data, finds more sample efficient solutions, and explores a higher diversity of solutions.
Dan Browne retweeted
RFD4-Proteina now runs locally on a MacBook.
Introducing BIOS’s Mac port: generate candidate protein binders and screen their predicted structures locally.
Built with MLX and custom Metal kernels.
• 2.2× faster generation than stock PyTorch-MPS at its default precision
• 20 designs generated and screened → 10 ranked candidates in about 12 minutes on GLP-1R (M5 Pro)
We believe more researchers should be able to run AI experiments on their own hardware. Test ideas locally, keep your research private, and scale to NVIDIA GPUs when you’re ready. After setup, the workflow runs offline.
Watch it run below. ↓
Dan Browne retweeted
Today we’re introducing Zyphra Hierarchical Attention (ZHA), a path to true subquadratic attention.
ZHA searches a learned tree of compressed summaries, with projected speedups of 35× over dense attention and 5× over MSA at 10M tokens, increasing to ~400× and ~55× at 1B. 🧵
Dan Browne retweeted
Convergent genomic evolution of human gut bacteria along an industrialization gradient
cell.com/cell/fulltext/S0092…
Dan Browne retweeted
Today we are happy to share one of our first open research releases: Latent Sparse Attention (LSA), a step towards subquadratic attention that matches accuracy of full attention at ultra-long context.
Sparse attention attends to only a few tokens per query, but it has to find the right ones. At 10M tokens, that search takes 98% of the attention layer's time. LSA makes sparse attention up to 22.7× faster and full attention 72.4x faster.
With @kubicek_ales @caciolai @PengLiangzu @SukritSumant @Ben_Hoov @FraserGreenlee @RMBattleday @radim_urban @thoefler @jcrwhittington
Dan Browne retweeted
insane alpha to be a bio person going into tech bro, dude i swear we can just generate all of this biological data in autonomous wet labs with de novo systems based on the latest multi omics large scale benchmark and sell it to model providers and then solve cancer with novel targets via AI in drug discovery then build guardrails for mirror life because of ai scientist who's gonna live forever thanks to longevity, and actually, have you heard of agentic biology bro? insane sigma in being a tech bro who can solve biology through our meta-benchmarked proprietary bio model and also we're into biosecurity but we don't know what it means yet, and it doesn't matter because we benchmarked it bro
Dan Browne retweeted
Contextualized gene representations work surprisingly well for predicting multigene perturbation effects.
I’m excited to introduce EMBER, a pretrained gene-centric foundation model designed specifically to learn context-specific gene representations. A joint work with @jmuiuc and @ericxing.
With innovations in single-cell pretraining and dataset curation, EMBER gene representations can be combined with a lightweight probe for single gene knockouts, genetic interactions (double knockouts), and even drug perturbations.
Both a 🧵 and a 🎥, got in front of a camera to share some highlights! (1/n)
Dan Browne retweeted
Can we help discover new, unknown small molecules using modern generative AI and scientific agents?
Excited to share our work, led by superstar @zyxiong123, on ChefNMR2🧑🍳⚛️, a new approach for structure elucidation from NMR spectra!
Paper: chefnmr.cs.princeton.edu/
🧵 1/
Dan Browne retweeted
i've reproduced the results from the MIT blog post today on weight-space programming. but one additional result i have to add: this is a new, step-change emerging capability that's appeared in just the latest set of models.
Dan Browne retweeted
When prices change in the market, firms change their behavior. But their goals haven't changed–they are still trying to maximize profit.
In a recent piece, @BenjaminLy61243 describes how systems like markets work because individual components are "alignable" through things like prices. He calls these systems "alignment compilers".
This frame can help us reason about collectives of AI agents.
Instead of requiring each individual agent to be perfectly aligned, we can construct systems where agents are "recruited" into aligned behavior through outside signals and constraints.
Dan Browne retweeted
Discrete flow matching usually changes one component per edit in a fixed-size state. Can we extend it to general actions, like inserting whole molecular fragments?
Introducing Trajectory Matching 🧵
New paper with M. Lienen, @ludke_david, @guennemann
Dan Browne retweeted
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.
We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: rikiyat.github.io/blog/weigh…
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math.
rikiyat.github.io/blog/weight-sp…
github.com/RikiyaT/lm_und…
huggingface.co/Qwen/Qwen3.5-0…
huggingface.co/RikiyaT/Qwen3.…
