red.anthropic.com

Articles

June 2025

Project Vend

We let Claude manage an automated store in our office as a small business for about a month. We learned a lot about the plausible, strange, not-too-distant future in which AI models are autonomously running things in the real economy.

Cyber Toolkits for LLMs

Large Language Models (LLMs) that are not fine-tuned for cybersecurity can succeed in multistage attacks on networks with dozens of hosts when equipped with a novel toolkit.

About the blog

Welcome to red.anthropic.com, the home for research from Anthropic’s Frontier Red Team (and occasionally other teams at Anthropic) on what frontier AI models mean for national security. We provide evidence-based analysis about AI’s implications for cybersecurity, biosecurity, and autonomous systems.

This blog is inspired by the informal research updates published by Anthropic's Alignment Science and Interpretability teams in the hope that taking a similar approach to sharing what we learn about AI and national security will be useful for policymakers, civil society, and other AI researchers.