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.
Interpretability
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.
Alignment
The Alignment team works to understand the risks of AI models and develop ways to ensure that future ones remain helpful, honest, and harmless.
Societal Impacts
Working closely with the Anthropic Policy and Safeguards teams, Societal Impacts is a technical research team that explores how AI is used in the real world.
Frontier Red Team
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.
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.
Alignment faking in large language models
This paper provides the first empirical example of a model engaging in alignment faking without being trained to do so—selectively complying with training objectives while strategically preserving existing preferences.
Publications
- Anthropic Economic Index report: Learning curves
- Introducing our Science Blog
- Long-running Claude for scientific computing
- Vibe physics: The AI grad student
- Partnering with Mozilla to improve Firefox’s security
- Labor market impacts of AI: A new measure and early evidence
- An update on our model deprecation commitments for Claude Opus 3
- The persona selection model
- Anthropic Education Report: The AI Fluency Index
- Measuring AI agent autonomy in practice