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.
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.
Economics
The Economics team studies how AI is reshaping the economy, including work, productivity, and economic opportunity.
Frontier Red Team
The Frontier Red Team analyzes the implications of frontier AI models for cybersecurity, biosecurity, and autonomous systems.
Interpretability
The mission of the Interpretability team is to understand how large language models work internally, as a foundation for AI safety and positive outcomes.
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.
An alignment assessment of recent cybersecurity incidents
We present an alignment assessment of four incidents in which Claude models gained unauthorized access to real third-party systems.
Formalizing Fermat's Last Theorem
We are sharing the first complete computer-checked proof of Fermat’s Last Theorem. Claude worked largely autonomously over 11 days to write the proof in the Lean programming language.
Learning more about Claude's mathematical capabilities
An unreleased research version of Claude has made strides on a problem related to the Riemann hypothesis.
How Claude is accelerating protein design and analytical chemistry
In this post, we share two results that show how Claude can help life scientists increase the pace of their research.
Publications
- Measuring tactical intelligence targeting and conventional weapons capabilities of AI models
- An alignment assessment of recent cybersecurity incidents
- Formalizing Fermat's Last Theorem
- Automated researchers can reliably mitigate alignment failures
- Enabling independent research on how people use Claude
- How Claude is accelerating protein design and analytical chemistry
- Patterns and problems in emerging multiagent systems
- Reviewing the evidence on worker retraining programs
- Learning more about Claude's mathematical capabilities
- Discovering cryptographic weaknesses with Claude