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 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.
Agentic coding and persistent returns to expertise
This report provides evidence on how Claude Code is used in practice, based on a privacy-preserving analysis of around 400,000 interactive sessions from around 235,000 people between October 2025 and April 2026.
Teaching Claude why
New research on how we've reduced agentic misalignment.
Project Deal
We created a marketplace for employees in our San Francisco office, with one big twist. We tasked Claude with buying, selling and negotiating on our colleagues’ behalf.
What 81,000 people want from AI
We invited Claude.ai users to share how they use AI, what they dream it could make possible, and what they fear it might do. Nearly 81,000 people participated—the largest and most multilingual qualitative study of its kind. Here's what we found.
Publications
- Project Fetch: Phase two
- Agentic coding and persistent returns to expertise
- Paving the way for agents in biology
- Measuring LLMs’ impact on N-day exploits
- Making Claude a chemist
- Mapping AI-enabled cyber threats: Insights from the LLM ATT&CK Navigator
- What we learned mapping a year’s worth of AI-enabled cyber threats
- Coding agents in the social sciences
- Project Glasswing: An initial update
- Measuring LLMs’ ability to develop exploits
