Research
Our research teams investigate the safety, inner workings, and societal impacts of AI models – so that artificial intelligence has a positive impact as it becomes increasingly capable.
Understanding the inner workings
The mission of the Interpretability team is to discover and understand how large language models work internally, as a foundation for AI safety and positive outcomes.
Ensuring helpful and harmless models
The Alignment team works to understand the risks of AI models and develop ways to ensure that future ones remain helpful, honest, and harmless.
Real-world implications
Working closely with the Entum Policy and Safeguards teams, Societal Impacts is a technical research team that explores how AI is used in the real world.
Security and robustness
The Frontier Red Team analyzes the implications of frontier AI models for cybersecurity, biosecurity, and autonomous systems.
Project Vend: Phase two
In June, we revealed that we'd set up a small shop in our San Francisco office lunchroom, run by an AI shopkeeper. It was part of Project Vend, a free-form experiment exploring how well AIs could do on complex, real-world tasks. How has Claude's business been since we last wrote?
Signs of introspection in large language models
Can Claude access and report on its own internal states? This research finds evidence for a limited but functional ability to introspect—a step toward understanding what's actually happening inside these models.
Tracing the thoughts of a large language model
Circuit tracing lets us watch Claude think, uncovering a shared conceptual space where reasoning happens before being translated into language—suggesting the model can learn something in one language and apply it in another.
Constitutional Classifiers: Defending against universal jailbreaks
These classifiers filter the overwhelming majority of jailbreaks while maintaining practical deployment. A prototype withstood over 3,000 hours of red teaming with no universal jailbreak discovered.