Frontier Red Team \ Anthropic

We aim to accelerate coordination around AI safety by producing evidence of emerging risks and prototyping defenses against them.
Our researchers work to translate technical findings into useful evidence for decision-makers in national security, policy, and industry.
We have made progress on a type of cryptographic proof known as a “zkSNARK.” In this post, we share some of that progress, primarily through a system we call FlashProve.
We used Claude to prove security properties in over 100 real-world open-source libraries over the span of a few weeks.
The decades-old mystery of the origins of one of the most popular cryptographic standards has been explained.
We’re making available OSS Scanner, an opt-in vulnerability scanner for the open-source ecosystem that’s informed by our experience using Claude to find vulnerabilities during Project Glasswing.
Like Claude Mythos Preview, GLM-5.3 has strong capabilities for autonomously building end-to-end cyber exploits. But unlike other frontier models, GLM-5.3 has been released without meaningful safeguards to limit misuse.
Works to understand the risks of AI models and develop ways to ensure future ones remain helpful, honest, and harmless.
Studies and monitors the impact of AI systems on individuals, firms, and economies.
Builds the infrastructure and systems that make Claude reliable and trustworthy.
Studies how large language models work internally as a foundation for AI safety.
Studies how AI affects people, both individually and collectively.
Explores how AI can increase the pace of scientific progress through both research and collaborations.
Stress-tests AI systems to understand the full extent of their current capabilities and anticipate what comes next.
Works to understand the risks of AI models and develop ways to ensure future ones remain helpful, honest, and harmless.
Studies and monitors the impact of AI systems on individuals, firms, and economies.
Builds the infrastructure and systems that make Claude reliable and trustworthy.
Studies how large language models work internally as a foundation for AI safety.
Studies how AI affects people, both individually and collectively.
Explores how AI can increase the pace of scientific progress through both research and collaborations.
Stress-tests AI systems to understand the full extent of their current capabilities and anticipate what comes next.
Anthropic is a Public Benefit Corporation. Our mission is the responsible development and maintenance of advanced AI for the long-term benefit of humanity.