Today, we'll resume charging for requests our safeguards block before Claude responds. This only applies in categories with low false positive rates: biology, distillation attacks, and frontier LLM development. We've seen some coordinated attacks on our systems in recent weeks, and this is one layer of defense. In recent testing, 99.7% of accounts using Claude Code, Claude​.ai, or Cowork did not hit any of these newly "billable blocks." The classifiers behind the blocks we’re resuming charging for today are tuned to have a <0.1% false positive rate. We know that's not 0%, and we're going to keep improving them so they interrupt your work less often. If you think a request has been blocked incorrectly, please report it with /feedback in Claude Code. platform.claude.com/docs/en/…

We’re hearing two kinds of voices on the potential of AI to cure all disease: One says AI will cure everything, but without a concrete path to get there. The other says biology is too complex to ever tame, but underestimates the power of the tools that will unlock the full potential of frontier intelligence. At Manifold Bio, we see a path and we’re already building it: a high-throughput interface into living system biology. Millions of protein designs, measured directly in vivo, to learn how molecules behave in the body and ultimately predict what they’ll do before they reach a patient. Today we share mBER-2, the latest iteration of our AI protein design model that is a core piece of this mission.

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 light of the progress in mathematics, we at Edison Scientific and FutureHouse have assembled a set of Millennium Problems for Biology. They are chosen to be very hard to solve but very easy to validate in a simple laboratory environment. Any of these, if solved, would mark a major advance in biotechnology, and most of them would contribute materially towards curing disease. These are, in some sense, the “last reasonable eval” for AI in biology. This was work primarily by @MichaelaThinks and myself, with contributions from many others. Short descriptions below. The full descriptions of the problems with acceptance criteria are at the Bio Millennium Problems website, linked in the next post. Share more if you have ideas. If they meet our criteria, we’ll add them to our list (with attribution and permission).

Discussion w the senior BD leaders at big pharma and one surprising point made is that more than one said that they are focused on earlier stage and are comfortable with clinical risk. They don’t seem to be shaken up by avidity/$NVS recent post deal setback. “In BD, risk is your friend. If you don’t take risk. You’ll pay what others think it’s worth” talking about transacting phase 2 or earlier, pre readout $XBI $IBB

Bender, Scannell, Shaywitz and colleagues in NRDD: a decade of AI in drug discovery, clinically relevant impact still limited. Their fix is right. Stop benchmarking model accuracy; benchmark whether the tool changes a real Go/No-Go. We proved translation is possible with Rentosertib. nature.com/articles/s41573-0…

Today, there's a strong focus on fast-follows of existing drugs. The drug programs that inspire me look different – the target is known, but we don't know how to build the drug, often requiring the dev of new tech that paves the path for more drugs.

Five pharma companies just fine-tuned OpenFold3 in a federated setting on 20,000+ structures... ... raising correct ligand-pose predictions from 29% to 47%

An AI system trained on more than 20,000 protein structures from pharmaceutical companies outperforms AlphaFold-like models that use only public data go.nature.com/4gTSLaA

Many drugs work by binding to a specific target in the body and blocking or changing what it does. An important first step in the drug development process is designing a molecule that can bind tightly to its target. Traditionally, that's meant weeks or months of expert work per target, sifting through a large number of candidates to identify the few that work. We wanted to test if Claude could successfully design novel protein binders from scratch (also called de novo design). With a protein design prompt written by a human expert, Claude autonomously designed protein binders against 14 out of 15 targets. We then worked with Adaptyv Bio and Twist Bioscience, who independently built and tested the proteins Claude designed.