Trustworthy agents in practice
…Donating our open-source alignment tool Focus areas for The Anthropic Institute At The Anthropic Institute (TAI), we’ll be using the information we can access from within a frontier lab to…
Search
Related topics:
Anthropic
People also ask
Why enter Claude into cyber competitions?
AI is poised to transform the domain of cybersecurity. Anthropic’s Safeguards team recently identified and banned a user with limited coding abilities leveraging Claude to develop malware. Research suggests that this lowering of the bar for expertise needed to pose a threat, combined with the falling costs of large language models (LLMs), presages a dramatic shift in the economics of cyberattacks.[1] To understand the present state of AI cyber capabilities and gain insight into their trajectory, we pursue different approaches to model evaluation, including publicly available and custom-made be
Claude does cyber competitionsEvaluating Claude’s bioinformatics research capabilities with BioMysteryBench
…Donating our open-source alignment tool Focus areas for The Anthropic Institute At The Anthropic Institute (TAI), we’ll be using the information we can access from within a frontier lab to…
How people ask Claude for personal guidance
…thumbs down button, which shares the conversation with Anthropic. Related content 2028: Two scenarios for global AI leadership Our views on the AI competition between the US and China. Teaching Claude why…
How we contain Claude across products
…Claude Cowork's egress allowlist correctly passed traffic to api.anthropic.com—the product can't function without calling our own API. In this case, a malicious file placed in the user…
Project Glasswing: An initial update
…we’re not yet at the point where we can fully detail our partners’ findings with Mythos Preview without putting end users at risk. Instead, we provide illustrative examples of the model…
Labor market impacts of AI: A new measure and early evidence
…Donating our open-source alignment tool Focus areas for The Anthropic Institute At The Anthropic Institute (TAI), we’ll be using the information we can access from within a frontier lab to…
Making Claude a chemist
…Limitations This assessment shows us that a general-purpose model can be competitive with NMR software and even make 1D inverse elucidation tractable. But there are a handful of noteworthy limitations. First…
Core views on AI safety: When, why, what, and how
…Results from the first Anthropic Public Record TCS and Anthropic partner to bring Claude to regulated industries We’re announcing a partnership with Tata Consultancy Services (TCS). TCS will provide Claude to…
Measuring AI agent autonomy in practice
…2026}, url = {https://anthropic.com/research/measuring-agent-autonomy}, } Appendix We provide more details in the PDF Appendix to this post. Footnotes 1. Our definition is compatible with Russell and Norvig (1995…
Demystifying evals for AI agents
Engineering at Anthropic Demystifying evals for AI agents Introduction Good evaluations help teams ship AI agents more confidently. Without them, it’s easy to get stuck in reactive loops—catching issues only…