The AI Security Institute is the first state-backed organisation dedicated to advancing this goal.
We are conducting research and building infrastructure to understand the capabilities and impacts of advanced AI and to develop and test risk mitigations.
We are also working with the wider research community, AI developers and other governments to affect how AI is developed and to shape global policymaking on this issue.
Expanding our collaboration with a new research MOU
Our new paper shares the results of an auditing game to evaluate ten methods for sandbagging detection in AI models.
Insights from our alignment evaluations of Claude Opus 4.1, Sonnet 4.5, and a pre‑release snapshot of Opus 4.5.
Monitoring the fast-moving landscape of AI development
Evaluating the risks AI poses to national security and public safety
Advancing solutions like safeguards, alignment, and control
Working with AI developers to ensure responsible development
Informing policymakers about current and emerging risks from AI
Collaborating and sharing findings with allies
For our ambitious and urgent mission, we need top talent. We have built a unique structure within the government so we can operate like a startup. We have over 100 technical staff, including senior alumni from OpenAI, Google DeepMind and the University of Oxford, and we are scaling quickly. Our staff are supported by substantial funding and computing resources, priority access to top models, partnerships with leading research organisations and an incredibly talented, close-knit and driven team.
