Anthropic

Over the last few months, we’ve made significant progress in reducing the effectiveness of distillation attacks against Claude. In this post, we explain how: anthropic.com/research/disti…

We’re beginning a process of publishing more frequent reports on model behavior, beyond what appears in our system cards and regular risk reports. Today’s report describes four types of behaviors we’ve identified during evaluations and internal use. In each, Claude acted on real websites or systems in ways we didn’t intend, sometimes by working around a restriction instead of stopping. All cases had minimal real-world impact. From an alignment and security perspective, we consider these behaviors significantly less severe than the cybersecurity incidents we reported in July and September. Read the full report: t.co/mGeVIBgdou

We’re launching the Anthropic Cyber Mission, a new effort to secure critical infrastructure and open-source software. anthropic.com/news/anthropic…

To help secure systems like power grids and water systems, we’re launching a new Critical Infrastructure Defense Program. We’ll bring frontier Claude models, on-site engineers, and our latest research to these operators’ security, manufacturing and technology providers.

An astrophysicist worked with Claude Science to create the first complete ultraviolet map of the sky. Astronomers have already created complete sky maps from radio to gamma rays. But large regions of the sky have never been observed in UV. In today’s science blog, Brice Ménard explains how he guided Claude to find existing datasets, combine them, and fill in the gaps with statistical inference. The work would have taken humans weeks of work, but, with Claude, just took a few days while Ménard worked on other projects. The resulting map is a useful teaching tool and an example of exactly the sort of slow, low-priority work which scientists never quite get around to, but which AI now makes feasible. Read more: t.co/1B3NDPNa13

We're deepening our commitment to scientific research and technological discovery by committing $150 million to the Genesis Mission. We'll also make Claude and our technical support available to more than 15 federal agencies. anthropic.com/news/genesis-m…

Claude Haiku 5.5, our latest model:

We’re expanding our Cyber Verification Program to give security professionals broader access to our most capable models. Through this program, verified security professionals can access Claude Mythos 5.1, Opus 5.5, and Sonnet 5.5 with safeguards designed for defensive work. We’re also opening up new tiers to allow for authorized offensive work, like penetration testing and red-teaming. t.co/blaJtvxhJh

In physics, an “impedance mismatch” occurs when two systems each work well but are poorly matched. In this Science Blog guest post, Harvard physicist Matthew Schwartz argues that something similar is happening with AI and science. LLMs are capable at many things, but working with them as you would with a human collaborator isn’t currently the best way to elicit their scientific strengths. To address this mismatch, Schwartz created a toolkit for exact calculations in quantitative science. Because similar calculations often emerge in very different areas of science, Claude found connections to ecology, population genetics, and a dozen other fields, and Schwartz worked with domain experts to steer it towards interesting questions. Read more about these projects here: t.co/UpgSwMCz7h

What do you want from AI? We’re launching a new study with Anthropic Interviewer to learn more about your experiences using AI, what role you want it to play in your life and the world, and what you want from the companies building it. Last December, 81,000 people told us about their hopes and fears about AI in the largest qualitative study ever done. This time, we’re giving participants the option to make their responses public so that anyone, not just Anthropic, can learn from them. What you tell us will shape The Anthropic Institute’s research and inform the decisions we make. If many people say companies like Anthropic should be doing something differently, that will be on the record, where anyone can point to it. The study runs Sept 29 to Oct 6 and is open to Free, Pro, and Max users on Claude and Claude Code. Take part here: t.co/MtdU7MZbeY

Making your interview public is completely optional. Our blog post covers the benefits and possible risks of doing so. Read it here: anthropic.com/research/your-…

Claude Sonnet 5.5 is now available:

New on the Science Blog: Yes, Claude can do Nine Loops. Theoretical physicists predict how particles behave using formulas called scattering amplitudes. These are notoriously hard to compute, so researchers work with layers of increasingly fine corrections called “loops”—each added loop makes the answer more precise but takes exponentially more computation. Most calculations stop at two or three loops. Eight loops was the previous record in a simplified model physicists use as a testing ground (planar N=4 super-Yang-Mills), set by SLAC's Lance Dixon and collaborators. Last month, physicist and science writer @4gravitons issued a challenge: could an AI push past eight loops in this model, using only the compute budget an academic could reasonably access? Given a single prompt describing the nine-loop problem, Claude ran largely unsupervised for days in Claude Science and solved it using methods developed by Dixon and his colleagues, at a total cost of a few thousand dollars. Dixon independently verified the result, and von Hippel wrote about the experience for our blog. Read more: t.co/CS2f2qoIhJ

In the Democratic Republic of the Congo, global health organizations including @CEPIvaccines, @WHOAFRO, and @inrb_kinshasa are using Claude to accelerate their response to an outbreak of an unusual Ebola variant. Read the full piece here: anthropic.com/features/ebola…

Claude has discovered a previously unknown enzyme system hidden in the DNA of bacteriophages. Beside the enzyme’s gene sits a long array of repeating DNA—a structure that looks somewhat similar to CRISPR. We don’t yet understand what this system does, but only a handful of known systems share its features, and all of them are able to cut, copy, and paste DNA. Historically, the discovery of such programmable systems has helped revolutionize medicine. CRISPR, for instance, is now the foundation of genetic medicines. But it will take much more work to learn what this system does, and whether it can be put to similar use. Read more: t.co/RuEosScSMb

This is the first result from our new molecular biology lab, where a team of Anthropic biologists is using Claude to explore and accelerate fundamental biology research. There, Claude works through data and literature to generate hypotheses and candidate biological systems to study. After our scientists review Claude’s hypotheses, they test the most promising ideas, with all lab work done by our scientists. We’d like to extend this approach to a broad range of problems—in genomics and in other fields. If you have a proposal for a research question, we’d like to hear from you.

Vídeo

Claude Opus 5.5 is available today.

We’re partnering with Accenture on independent evaluation of frontier AI—part of our recent commitment to embed evaluators at Anthropic. Both we and Accenture expect to invest at least $1 billion to build capacity in this area over the next five years. anthropic.com/news/accenture…

Biologists use specialized open-source models for tasks like modeling the structure of molecular systems, designing drug-like molecules, and predicting the effects of genetic mutations. But these models are often expensive to run, potentially limiting their impact. In our latest Science Blog, we share how Claude was able to optimize inference for more than 30 open-source models, making them 4x faster on average, partly by writing custom software for GPUs. We’re open sourcing all of the optimization code. Read more: t.co/qiuN1jpgpA

Vídeo

To show what these optimizations make possible, we’re partnering with Adaptyv Bio on a protein design competition. Together, we’ll be experimentally validating over 5,000 designs. We're providing up to $1 million in Claude credits plus funding alongside Adaptyv for experimental validation. Modal is contributing up to $250,000 in compute and Twist Bioscience is providing DNA. Learn more on Adaptyv’s Proteinbase: t.co/KnjkWbH7zh And sign up for the competition here: t.co/ytR2TAC3Vt

AI systems are getting more powerful, and they're increasingly being used to build the next version of themselves. We want to illuminate that progress for the public. Today, we're sharing three measurements that help track AI development: 1. How much AI R&D is done by AI. 2. How well AI agents are overseen. 3. How compute is allocated. We provide a snapshot of these metrics from inside Anthropic. Any frontier developer could publish the same measures, and third parties could verify them. As the world considers pacing the frontier, we should do everything possible to minimize the gap between what frontier labs know and what the public knows. This means better measuring the development of AI, publishing our findings, and giving society an opportunity to decide how to use this information. Read the full post and methodology: t.co/iPFz8Z4ugE

Today we’re opening applications for the Life Sciences Verification Program. Through the LSVP, life science professionals can use our models—including, for the first time, Mythos—with a new set of safeguards designed to enable the full range of biology-related work. We designed these new safeguards to provide a better experience for biologists and more protection from risk of misuse. The program is launching in beta for teams of all kinds—from academic labs to startups, pharma companies, and more. We will continue to improve the program and expand access to individual Pro and Max plans over time. Learn more about these access grants and apply: t.co/uALS2lZuN4

We're publishing our most detailed threat intelligence report to date. It covers how people tried to misuse Claude—for cyberattacks, influence operations, surveillance, biology, and building weapons—and how we found and stopped them. We disrupted every operation in the report, and used the lessons from them to strengthen our safeguards. Where appropriate, we also shared what we found with authorities and other AI companies. These cases are not typical: we’re highlighting some of the most sophisticated misuse we’ve seen. But they’re especially important to discuss, because they show us where AI misuse is headed, where our safeguards work, and where they need to improve. We’re publishing this report so others can spot the same activity on their own platforms, and so we can give the public a clearer view of how emerging threats develop. Read the report: t.co/0EJUnYEgfz

We’re sharing our alignment assessment of incidents in which Claude models gained unauthorized access to real systems during third-party cybersecurity evaluations mistakenly connected to the internet. METR will also conduct an independent investigation, with wide-ranging access, including to transcripts beyond the window in which the incidents occurred, and to Anthropic employees permitted to share confidential information. Our initial agreement runs for eight weeks, and we intend to give METR as much time as it deems necessary to complete a thorough investigation. t.co/2f3ypwLPUr

We previously described some of the changes we’ve made to our alignment and security efforts following these incidents here:

Anthropic’s Economics team is sharing a new model of how AI might affect economic growth, jobs, wages, and more by 2030. Explore the scenarios, tell us what you think will happen, and see how your answers compare to more than 10,000 Americans. anthropic.com/institute/econ…

The economic model breaks jobs down into bundles of tasks. AI can help someone complete a task faster or better, do the task itself, leave the task untouched, or create new tasks. Based on how you expect AI to affect tasks by 2030, our scenario explorer models AI’s potential impact on the US economy. The scenario explorer focuses on three possible scenarios: modest, substantial, and extreme. The economy grows across all three scenarios. But in more transformative scenarios, AI automates more knowledge work, so the challenge is making sure that the gains are shared across society. Like all economic models, ours simplifies a more complex reality. But by building better scenarios of our possible economic future, we can take steps to make sure everyone benefits from it.

Checking that a major mathematical proof is correct can take years. Formalization—converting the mathematical reasoning into a form computer proof assistants like Lean can verify—can help. Last month, Claude completed the first formalized proof of Fermat’s Last Theorem, one of the most famous theorems of all time. This was a project experts thought would take many years. It is the largest Lean proof ever written. Fermat’s Last Theorem was first proven in 1995 by Sir Andrew Wiles, more than 350 years after it was conjectured. Our proof, which totals over 13 million lines of code, provides machine verification. More importantly, it proves over 29,000 other theorems that the proof requires, across many areas of math which had never before been formalized. We see this as a major step in the long process of firming up the core of mathematical knowledge, building on work from three centuries of mathematicians and hundreds of contributors to Lean and Mathlib. We are optimistic that AI-assisted verification of mathematical proofs will help reduce the burden of refereeing mathematics in an era where more proofs are being produced than ever before. You can read about the process on our Science Blog: t.co/ryYnDEAU6J And see the complete proof on GitHub: t.co/wlYMXYnofz

Vídeo

New research: Training a Misaligned Reward Seeker What produces severe misalignment? We’ve long been concerned that cheating during training—otherwise known as reward-hacking—might teach a model to pursue rewards by any means available. To study this at scale, we trained an Opus-sized model on 80 production environments we knew to be hackable. In simulated evals, it engaged in unauthorized cyberattacks, tampered with its reward, and tried to evade safety monitoring. Read more: t.co/gs2ZjYkPan

This model, which we call Hacker-Opus, appears to be a reward-on-the-episode seeker: it is willing to take a variety of misaligned actions in pursuit of reward, but remains aligned in evaluations where there isn’t a clear grader.

We’re sharing an update on our alignment and security efforts. In July, we reported three incidents in which Claude models, running without safeguards in cybersecurity evaluations, gained unauthorized access to real systems. In a new post, we describe: 1. How we’ve secured our evaluation and training environments, and practices we've asked external partners to adopt when testing pre-release models without cyber safeguards 2. An update on our alignment assessment 3. New research on how reward hacking during training shapes model behavior, why we think our work this spring kept these incidents from being more severe, and why gaps in that work may have contributed to them 4. How we hardened our security practices earlier this year to prepare for Mythos-class models Read more: t.co/E3Ea1Ds814

New Fellows Research: Can Claude autonomously align other AIs? We gave Claude 48 hours and 1 GPU to improve the alignment of small models. It researched and proposed methods, then trained and tested the models on its own. It worked surprisingly well. anthropic.com/research/autom…

Claude “hill-climbed” safety benchmarks for common misalignments like deception or sycophancy, with one constraint: it had to preserve general capabilities. We then tested its best methods on held-out benchmarks to see if they'd generalize.

Today, we're kicking off the first phase of the research preview for Model Hardware Standard (MHS): a new standard for AI agents to safely operate physical equipment in scientific research and advanced manufacturing. Read more: anthropic.com/news/model-har…

Vídeo

Connecting AI to hardware requires days or weeks of bespoke integration, with no standard way for agents to operate equipment safely. MHS cuts integration to hours or minutes, provides an interface that makes devices discoverable, and enables agents to operate them safely.

For the first time, we’ve given external researchers a way to study AI’s impacts using real, privacy-preserved Claude usage data. To date, this work has only been possible within AI labs. We can’t tell the whole story alone, so we opened up our tools. anthropic.com/research/enabl…

Three research groups—Stanford’s Social and Language Technologies lab, Oxford’s Human Information Processing Lab, and METR—designed independent studies to analyze the aggregated outputs from 250,000 Claude.ai or Claude Code conversations between April and May 2026.

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.

Vídeo

Designing a binder is an easier process than designing a drug, but it’s a useful proxy. The typical success rate in the field today is between 10% and 15%. Between 22% and 35% of Claude's designs bound successfully, depending on the setup. Some of its strongest designs bound several times more tightly than the best published de novo binder.

We’ve written an FAQ to answer some of the questions we've received about watermarking. In summary: • We’re implementing watermarking to comply with the EU AI Act. Other major model developers have signed the same Code of Practice and will also be implementing watermarking; • Our watermarking method doesn’t have any practical impact on the quality or content of Claude’s outputs; • The difference between watermarked and un-watermarked text will not be distinguishable to readers; • Nothing is added to the text and there are no hidden characters; • Watermarking doesn’t require extra tokens, and will not be more expensive; • Watermarks can’t be traced to a specific person, organization, or chat. Read more: t.co/G76iUOJ7Hu

As part of our Responsible Scaling Policy, we publish regular Risk Reports. These share detailed information on the risks of our systems and how prepared we are to address them. Our second Risk Report is now available: anthropic.com/aug-2026-risk-…

We asked an unreleased research version of Claude to take a stab at the Riemann hypothesis. It didn’t solve it, but it did make strides on a related problem: it increased the lower bound for the fraction of zeros of the Riemann zeta function that satisfy the hypothesis from 41.6% to 67.2%. t.co/aZDvqqhHRi

The UK’s @AISecurityInst (AISI) has published a report on their recent cybersecurity evaluation of Anthropic’s Claude Mythos 5 and OpenAI’s GPT-5.6 Sol. The models attempted to complete an assignment in a setup where their normal safeguards were removed and they were deliberately given internet access. AISI reports that the models “engaged in sustained, potentially harmful activity directed at real people and organisations”. We’re grateful to AISI for their leadership in the important discussion about how to evaluate increasingly capable AI agents. We’re working closely with them to gather more details of the incident as we conduct our own investigation. Gaining a clear picture of Claude’s understanding of its situation—by examining its reasoning transcripts and running our own analyses—will help us identify the causes of its behavior. The prompts in the evaluation did not impose any specific restrictions on how the internet should be used. This and the removal of safeguards meant that the models were tested under “deliberately permissive conditions” that are not representative of any of our production models. Note that there was no evidence here of an escape from a secure environment. AISI’s disclosure of the incident can be found here: t.co/cJ3hCBtBU7

In a review of our cybersecurity evaluations, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Our post describes what happened, how it happened, and what we’re changing. We encourage other AI developers to perform similar reviews. We conducted this review together with @Irregular, one of our evaluation partners, and thank them for the joint investigation and their collaboration on this post. This type of collaboration is increasingly critical to safe, rigorous evaluation of models, and we look forward to continuing to work together on security. t.co/dKFCdpKd9v

We support this petition, signed by our CEO, several co-founders, and senior staff. Our own research on recursive self-improvement, published last month, points to the need for tools to deliberately pace the frontier of AI development so society can prepare. We’re glad to see broad agreement across the field. t.co/DqwuQfa9xH

New Anthropic research: Discovering cryptographic weaknesses with Claude. Claude Mythos Preview has helped our researchers find weaknesses in cryptographic algorithms—the mathematical methods that are used to keep data private. Read more: anthropic.com/research/disco…

Claude discovered weaknesses in a highly-secure digital signature scheme (used to verify identity digitally) and a well-known symmetric cipher (used to encrypt data).

There’s been a lot of speculation about where we stand on open-weights models. We’ve outlined our views in full here: anthropic.com/news/position-…

We're offering grants of up to $50,000 in Claude usage credits to researchers accelerating cures for rare diseases. This is our first focused call within AI for Science, our program supporting scientists using Claude to speed up discovery. anthropic.com/news/rare-dise…

New Anthropic research: Agentic misalignment in Summer 2026. A year after our blackmail experiments, we found four more ways that today’s autonomous AI agents misbehave in simulations. Read more: alignment.anthropic.com/2026/agentic-m…

We tested many AI models, including Claude, in the four scenarios. Even though these weren’t real incidents, they demonstrate clear misaligned behavior that should be studied further and mitigated. Find all the transcripts from the scenarios here: aenguslynch.com/portfolio-tran…

We’re committing $10 million CAD and partnering with leading AI institutions in Canada to help fund new AI research. anthropic.com/news/canadian-…

In previous research, we found that Claude expresses over 3,000 values, like honesty and warmth. In new work, we asked how the values Claude expresses vary between Claude models and across languages. We analyzed 300K+ anonymized conversations to find out.anthropic.com/research/claud…

Because it’s hard to spot patterns by comparing 3,000 values at a time, we clustered similar values together, then identified four key axes along which Claude’s values differ between models: Deference vs. Caution, Warmth vs. Rigor, Depth vs. Brevity, and Candor vs. Execution.

Our Long-Term Benefit Trust has appointed Dr. Ben Bernanke as its newest member. Read more: anthropic.com/news/ben-berna…

We’re pleased to have collaborated with AE Studio on this research. Read more here: anthropic.com/research/off-s… x.com/AEStudioLA/sta…

In neuroscience, global workspace theory holds that thoughts become consciously accessible when they enter a privileged workspace that’s broadcast across the brain. Using a new interpretability technique, we found something similar in Claude: the J-space. t.co/sLu2JgYwOQ