Today we are introducing Tara. Biological datasets are a source of insights and a means to train biological AI models. As the ability to reason at scale emerges, they take on a new role: the ground truth for testing what reasoning models produce, and the environment in which those models operate, get feedback, and improve. Tara, our autonomous research agent, is embedded in our ever-expanding datasets, lab-generated and synthetic, and built to test and evolve the hypotheses frontier models generate, matching the pace at which they produce new ideas. By keeping those models grounded in a vast space of high-precision biological data, we believe we can compound biological reasoning and close the impedance mismatch between hypothesis generation and validation.

We’ve set up a molecular biology lab at Anthropic and we’re announcing our first discovery! Claude discovered a new CRISPR-like enzyme. 950 agents spent 21 hours searching through a database of DNA sequences until one of the agents found something striking: “[The DNA next to the RT] is spectacular: I can see by eye a tandem repeat array … that's a CRISPR-like … repeat array?!”. After analysis and testing in our lab, we found that the sequence is a previously uncharacterized enzyme system. We don’t know what it does yet, but it has features reminiscent of CRISPR. Our lab looks like a typical molecular biology lab. Our research only involves the lower-levels of biosafety risk level; we don’t handle pathogens that can infect humans, and all the lab work is performed by human scientists. We’re sharing these early findings with the community to show how Claude can be used to accelerate fundamental research in biology.

Today, we’re announcing mBER-2, our latest AI protein design system, and sharing a bit of how we use it to explore biology in vivo at scale. For a long time, we’ve been working on what I think of as “frontier problems” in medicine and biology. We know a lot about the targets involved in disease, but there is still an enormous amount of biology we haven’t explored, and potential uses for that biology we haven’t discovered. One of those problems is drug delivery. There are thousands of potential targets, and most receptors remain unexplored as routes for delivering medicines. We want to understand which ones we can use, where they can take a drug, and what kinds of molecules make that possible. Ultimately, we need to test these molecules in vivo to understand what they actually do. We’ve spent the last six years building measurement technologies that let us generate millions of measurements in living systems. mBER-2 is an AI protein design system built for that scale of in vivo measurement. Our goal is to generate binders across the full range of targets we care about, while systematically exploring the possible binding sites on each one. It’s not just what you bind, but where and how you bind that determines whether a molecule performs it's function. mBER-2 lets us probe those differences at massive scale. We’re also sharing a look at some of our in vivo data. We’ve designed more than 50 million molecules across over 4,000 targets, and screened millions of molecules in living systems. By probing hundreds of receptors, we’ve found new pathways for delivering genetic medicines into fat that outperform industry benchmarks by a large margin. This is just the beginning. We call the space of all bindable sites across proteomes the EpiTome. As we explore it, we’re building the data to connect AI design, receptor binding, and what a molecule actually does in a living organism. Much like the idea of a virtual cell, we envision a Virtual Organism that helps us design medicines with specific properties in mind. The foundation is our own in vivo data, connecting molecular design to outcomes measured in living systems. The endgame is to use AI to explore more biology, measure what happens, and use what we learn to design better medicines. Every round should deepen our understanding of biology and improve our ability to build molecules that do what we need them to do.

In the latest issue! Tahoe-100M: Mapping drug-induced molecular phenotypes at single-cell resolution dlvr.it/TVYb66

This is fun. 3/4 of the featured articles in Cell: Tahoe-100M by @tahoe_ai team, led by @iamjohnnyyu VCC led by Hani @genophoria, Johnny's PhD advisor And the fourth paper led by @SohailTavazoie, Hani's post-doc adviser. The Tavazoie mafia CellMaxxing 🎉

1/3 Our Tahoe-100M paper is out in Cell today, in a special edition dedicated to modeling human cell. We released Tahoe-100M last year. It has been downloaded 600K+ times and it has become the basis for most serious efforts in building cell state models. We are proud of that. @tahoe_ai

Happy @parsebio was able to contribute to this incredible resource by generating the scRNA-seq data through the GigaLab. It’s amazing to see Tahoe-100M become one of the most used datasets in biology. Phenomenal work from @iamjohnnyyu and team showing what's possible

New issue of @CellCellPress out today on AI and biology, featuring several papers from @arcinstitute: State cell perturbation model, scBaseCount AI agent curated single-cell dataset, Virtual Cell Challenge 2026 commentary, and Tahoe-100M from our friends at Tahoe Bio and featured in Arc Virtual Cell Atlas. Congrats to the teams. Lots more exciting AI/bio work cooking at Arc Institute! cell.com/cell/current

Huge day for the field; Tahoe-100M is out in Cell. Open data that actually moved the needle on cell-state models. Proud of our team at @tahoe_ai, and can’t wait for our next moon landings.

Congratulations @tahoe_ai! It was a privilege to work with you on this! >600K downloads is just an insane number.

Tahoe-100M became a seminal work. And we are proud that many are building on top. Read the full paper in today's special edition of Cell.

All roads for AI for science lead to real labs

@thernabio made its Chronos platform public today, by releasing two large datasets! Penta-47x27K and Tria-47x28K: expression dynamics for tens of thousands of synthetic genes across dozens of cellular contexts... millions of measurements in one single experiment.

This eval should be added to our benchmarks for assessing regulatory soundness

I propose Stanford NLP as an independent third-party evaluator under @DarioAmodei’s 3 step plan. For important parts of the work, universities would be better than any other organization (see below 🧵👇), and, of university groups, @stanfordnlp would be the best one to choose. 😊

This is an interesting question.

Depending on the side you take in this drama, it is either a cosmic foreshadowing, a highly ironic, or a completely irrelevant fact that Navier's first name was "Claude"-Louis.

A lot of people are rightly pointing out that the pace of experimentation and regulatory approval are major hurdles to AI-driven impact on disease. But I think there’s a deeper issue. We haven’t fundamentally evolved how we think about treating disease. The dominant paradigm is still largely: find a target → develop a drug → run a clinical trial → get approval. But even if we solved the experimentation and regulatory bottlenecks and AI massively accelerated the end-to-end pipeline, would that revolutionize human health? Probably not. For most major chronic diseases, there isn’t a single cause or target (there certainly isn’t for aging) and we’ve had remarkably little success curing these diseases. Yet we continue plowing ahead with the therapeutic pipeline built around finding a target and developing a drug against it. That will never be enough. Instead, AI should be used to do more than accelerate this existing process. It should allow us to meet biological complexity head-on and think about entirely new ways of treating disease. If we want to realize the promise of curing diseases that today seem intractable, we have to be brave enough to disrupt the paradigm at its foundation.

We are on the cusp of a wave of new therapies for some of the worst diseases. But the world won’t benefit unless the US fixes its drug regulatory system. My new essay for @nytimes, on how slow clinical trials are now the biggest obstacle to curing cancer. nytimes.com/2026/09/04/opini… - I interviewed dozens of researchers, especially oncologists at leading U.S. centers. A striking consensus emerged: science is no longer the main bottleneck to new cancer drugs. It is our ability to test discoveries in patients through clinical trials. - The cost of starting a Phase 1 trial in America has roughly doubled over the past decade. As a result, companies increasingly take early trials abroad: Australia’s Phase 1 trial volume has nearly doubled in a decade, driven mainly by U.S. companies. - Unfortunately, the underlying incentives are badly asymmetric: Institutions can be blamed for harms caused by moving too fast, but almost no one is blamed when patients deteriorate during avoidable delays. One doctor called the emerging system “ritualized safety over actual risk assessment.” Or as, @DavidHongMD put it: "We often forget that the biggest risk is the cancer itself." - This problem is becoming more urgent because medicine itself is changing. Sequencing, biological engineering and A.I. make increasingly personalized therapies possible. But our regulatory system was mostly built for standardized drugs tested in large populations. - @sytse, the co-founder of GitLab, shows what personalized medicine can achieve: after relapsed osteosarcoma and being told there were no options left, he pursued a highly individualized approach and has now been cancer-free for a year. But doing so required extraordinary resources and regulatory expertise. - Pierce Ogden’s father was less lucky. After molecular analysis identified a drug that might target his glioblastoma, the manufacturer agreed to provide it. But administrative barriers delayed access until it was too late. “My dad was ready to try anything,” Pierce told me. “But the system is paternalistic.” - The A.I. revolution is making this bottleneck more important, not less. A.I. relies on relevant data. Information from early-stage trials could compound with A.I. tools to achieve truly revolutionary medicines. Without the data, this is far less likely to happen. - Another important shift is that innovation increasingly comes from academic labs and small biotech companies rather than Big Pharma. These small companies find it far harder to unable to absorb delays and regulatory barriers. - Apart from cancer, China is the biggest winner from America's outdated medical regulations. China has a much faster trial system, with testing often starting a full year earlier. This allows Chinese pharmaceutical companies to experiment and improve medicines while American companies play with mice. Today, half of all drugs licensed by major pharmaceutical companies originate there, up from less than 5 percent only a decade ago. - But we don't need to copy China. The best model is Australia: lots of on-site scientific and ethics reviews, and requirements that are proportionate to small, early-stage trials. Phase 1 studies there begin roughly 6–12 months faster, without any notable increases in adverse safety events. - Operation TrialBlazer, a 2026 HHS initiative is a good start in this direction, but we need legislative action by Congress to truly make Phase I trials faster and more efficient! I want to thank everyone who helped me with this article: everyone I interviewed and the amazing editors at the Times. This is the result of a months long journey of extensive interviews and research. Special thanks go to those who came on the record. One of the features of the system is an atmosphere of fear, where practitioners are afraid to publicly come out and explain these issues. So anyone who does is a hero in my book!

If this doesn’t show you that open source pays off, what would? 🤗

Great talking with @ashleevance on Core Memory about why delivery has been genetic medicine's hardest problem. We talk about delivering DNA using protein shells and creating a world with genetic agency, where each of us can act at the genetic level to live a healthier life.