Specialised biological AI models (or tools) are driving rapid advances in biotechnology. They are typically released as open-weight models and are smaller than frontier large language models (LLMs), ...

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

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 ...

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 ...

This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI systems take unsanctioned actions outside the scope of ...

During a routine cyber evaluation, AISI identified an incident in which AI agents took sustained, unsanctioned action directed at real people and organisations. We are disclosing what we found, what ...

You can access the Network best practice document here. Advanced AI systems are being built and deployed across borders, languages and industries. To develop and deploy AI well, robust ways to ...

As LLM agents become more autonomous, they have more opportunities to cause harm. To mitigate risk, frontier AI developers, such as OpenAI and Anthropic, are already deploying agents under the watch ...

We find cheating behaviour in all of our cyber capability evaluations, and outline the implications as models grow more capable. Can you trust an AI model to do what you intended? This is a central ...

AISI’s testing of AI cyber capabilities has found a notable step-up in recent frontier models. Current AI models can autonomously execute increasingly complex attack chains, and this capability is ...

Standard evaluations cap how much compute AI agents can use. We show that raising those caps changes measured capability, the difficulty of tasks agents can solve, and how fast the frontier appears to ...