Project Vend: Phase Two
In June, we revealed that we'd set up a small shop in our San Francisco office run by an AI shopkeeper. It did not do particularly…
Latest
AI Agents Find Smart Contract Exploits
We evaluated AI agents' ability to exploit smart contracts using a new benchmark comprising contracts that were actually exploited. On contracts exploited after the latest knowledge…
Project Fetch
How could frontier AI models like Claude reach beyond computers and affect the physical world? One path is through robots. We ran an experiment to see…
Building AI for Cyber Defenders
We invested in improving Claude's ability to help defenders detect, analyze, and remediate vulnerabilities in code and deployed systems. This work allowed Claude Sonnet 4.5 to…
LLMs and Biorisk
Our work at Anthropic is animated by the potential for AI to advance scientific discovery—especially in biology and medicine. At the same time, AI is fundamentally…
Developing Nuclear Safeguards for AI
Together with the NNSA and DOE national laboratories, we have co-developed a classifier—an AI system that automatically categorizes content—that distinguishes between concerning and benign nuclear-related conversations…
Claude Does Cyber Competitions
Throughout 2025, we have been quietly entering Claude in cybersecurity competitions designed primarily for humans. In many of these competitions Claude did pretty well, often placing…
Cyber Evaluations of Claude 4
We partnered with Pattern Labs on a range of cybersecurity evaluations of Claude Opus 4 and Claude Sonnet 4, with Opus demonstrating especially notable improvement over…
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,…
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…