Core views on AI safety: When, why, what, and how
Announcements Core views on AI safety: When, why, what, and how Mar 8, 2023 We founded Anthropic because we believe the impact of AI might be comparable to that of the industrial…
Search
Focus areas for The Anthropic Institute
…Economic diffusion Threats and resilience AI systems in the wild AI-driven R&D In Core Views on AI Safety , we wrote that doing effective safety research required close contact with frontier…
More details on Fable 5’s cyber safeguards and our jailbreak framework
…First, we provide more information on the cybersecurity safeguards —specifically, the safety classifiers —that we launched with the model. These are the AI systems that accompany the model that detect and block…
A “diff” tool for AI: Finding behavioral differences in new models
…In recent years, AI safety researchers have started to apply this same principle to neural networks. This is known as model diffing . Previous work has shown that model diffing is a powerful…
LLMs and biorisk
…In this post, we want to expand on our perspective on AI and biological risk (biorisk). It is striking—but not necessarily intuitive—that every safety framework released by frontier AI labs…
Anthropic opens Milan office to support Italian enterprise, research, and developers
…religious traditions, civil society, academia, and governments—to shape a positive outcome for humanity. Anthropic’s frontier AI capabilities and an abiding commitment to safety have already earned the trust of Italian…
Sydney will become Anthropic’s fourth office in Asia-Pacific
…that democracies should lead in AI development, and one that aligns with the Australian government's own ambitions to become a trusted destination for sustainable AI infrastructure. We're exploring adding local…
Expanding Project Glasswing
…The role of Project Glasswing Project Glasswing and the capabilities of Claude Mythos Preview have sparked broad conversations—both within the software industry and with governments—about how AI is changing cybersecurity…
Introducing The Anthropic Institute
…Public Policy focuses on the areas where Anthropic has defined priorities and perspectives, including model safety and transparency , energy ratepayer protections , infrastructure investments , export controls , and democratic leadership in AI . Sarah Heck…
Trustworthy agents in practice
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.