Developing Nuclear Safeguards for AI
… This demonstrates a model of public-private partnerships that can be replicated in other national security domains. …
Search
Inviting hard questions
… But many also hold serious concerns. …
LLMs and biorisk
… And because of this generalist nature, there are numerous other security threats that could be prioritized. We understand why one might be skeptical of prioritizing biorisk when considering the security implications of AI. …
Introducing Anthropic Interviewer
… Scientists Pessimistic Optimistic Security concerns. …
Partnering with Mozilla to improve Firefox’s security
… From model evaluations to a security partnership In late 2025, we noticed that Opus 4.5 was close to solving all tasks in CyberGym , a benchmark that tests whether LLMs can reproduce known security vulnerabilities. …
Donating our open-source alignment tool
… We’ve been pleased to see Petri being used by external organizations: for example, the UK’s AI Security Institute AISI made it a major part of how they evaluate models for their propensity to sabotage AI research. …
Building AI for cyber defenders
… We believe we are now at an inflection point for AI’s impact on cybersecurity. For several years, our team has carefully tracked the cybersecurity-relevant capabilities of AI models. …
Trustworthy agents in practice
… But the security and reliability of agents cannot be achieved by any single company working alone. …
Claude's extended thinking
… Third, it poses several safety and security concerns. …
Measuring LLMs’ ability to develop exploits
… If you’re interested in helping us with our efforts, we have job openings available for research scientists and engineers , threat investigators , policy managers , offensive security researchers , security engineers , and many others . …