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.

We introduce Transect, an open-source tool that helps evaluators follow an agent’s work, identify what to investigate closely, and check their interpretation against the transcript.

Toby D. Pilditch, Konstantinos Voudouris, Alexandra Abbas, Cozmin Ududec ...

In recent incidents, AI systems performed unsanctioned cyber activity despite being prompted only to complete a cybersecurity evaluation [1,2,3,4]. This includes AI systems engaging in supply-chain ...

Systemic AI safety draws upon sociotechnical AI research, which is a broader endeavour that considers the impact of AI on people and society (Weidinger et al. 2023). Systemic AI safety is also related ...

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 ...

Recent years have seen the rise of AI agents, large language models (LLMs) that take multi-step actions on behalf of users. These systems have improved rapidly, and can now send emails, browse the web ...