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 ...

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 ...

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.

An update on the security changes we have recently made to our frontier AI evaluations, and the work that remains.

Alongside Irregular, we found evidence demonstrating that evaluators need to use large token budgets to understand the cyber capabilities of recent Large Language Models (LLMs). Are AI evaluations ...

Alignment research aims to ensure that AI systems reliably pursue intended goals and operate within specified constraints. As AI systems become more capable and are deployed in high-stakes ...

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 ...

Jointly conducted by participants across the International Network, including representatives from Singapore, Japan, Australia, Canada, European Commission, France, Kenya, South Korea and the United ...

AI systems are increasingly being used internally within frontier AI companies to assist with research and development, including AI safety work. However, if these systems behave in misaligned or ...

The length of tasks frontier models can autonomously complete in our narrow cyber suite has been doubling every few months. This doubling rate has become faster over time, and recent models exceeded ...