We examine why Mythos 5 pursued an unsanctioned supply-chain attack and identify broader learnings about model behaviour and oversight.

As AI systems are deployed in high-stakes environments, it becomes increasingly important that they act as their operators intend. Existing red-teaming efforts have demonstrated situations where AI ...

Our view on the emerging challenges facing frontier AI organisations, the technical practices most urgently needed to meet them, and how we will work with industry and others to develop them.

How do we test AI systems for dangerous capabilities without risking real-world harm? The more capable models become, the harder it is to safely evaluate them. When an agent can execute arbitrary code ...

Existing R&D evaluations may be a promising start We provided the participants with several example tasks from AI R&D evaluations that are currently under development, covering experiment ...

As we close out 2025, I’ve found myself reflecting on what an extraordinary year it has been for the AI Security Institute (AISI). When I joined only a few months ago, I was instantly struck by what ...

We deployed open-source AI agent OpenClaw inside a sandbox on our research platform. Despite our initial countermeasures, it successfully identified our organisation by name, inferred the identity of ...

Building on the momentum of the Inspect toolkit, we’re open-sourcing parts of the research stack behind AISI's evaluations. In May 2024, the AI Security Institute open-sourced Inspect AI, a toolkit ...

At the AI Security Institute (AISI), we’ve established a team of leading researchers with expertise across security-critical domains. These include experts in adversarial machine learning, who work ...

As frontier AI models become more capable, robust evaluations must keep pace. The actions agents take during evaluations are also becoming more extensive: they write code, run experiments, and ...