International AI Safety Report 2025
A report on the state of advanced AI capabilities and risks – written by 100 AI experts including representatives nominated by 33 countries and intergovernmental organisations.
Documents
Details
The International AI Safety Report is the world’s first comprehensive synthesis of current literature of the risks and capabilities of advanced AI systems. Chaired by Turing-award winning computer scientist, Yoshua Bengio, it is the culmination of work by 100 AI experts to advance a shared international understanding of the risks of advanced Artificial Intelligence (AI).
The Chair is supported by an international Expert Advisory Panel made up of representatives from 30 countries, the United Nations (UN), European Union (EU), and Organization for Economic Cooperation and Development (OECD).
The report does not make policy recommendations. Instead it summarises the scientific evidence on the safety of general-purpose AI to help create a shared international understanding of risks from advanced AI and how they can be mitigated. General-purpose AI – or AI that can perform a wide variety of tasks – is a type of AI that has advanced rapidly in recent years and is widely used by technology companies for a range of consumer and business purposes.
The report is concerned with AI risks and AI safety and focuses on identifying these risks and evaluating methods for mitigating them. It summarises the scientific evidence on 3 core questions – What can general-purpose AI do? What are risks associated with general-purpose AI? and What mitigation techniques are there against these risks? and aims to:
- provide scientific information that will support informed policymaking – it does not recommend specific policies
- facilitate constructive and evidence-based discussion about the uncertainty of general-purpose AI and its outcomes
- contribute to an internationally shared scientific understanding of advanced AI safety
The report was written by a diverse group of academics, guided by world-leading experts in AI. There was no industry or government influence over the content. The secretariat organised a thorough review, which included valuable input from global civil society and industry leaders. The Chair and writers considered all feedback and included it where needed.
The report will be presented at the AI Action Summit in Paris in February 2025. An interim version of this report was published in May 2024 and presented at the AI Seoul Summit.
Background
At the Bletchley AI Safety Summit, 30 nations agreed to build a shared scientific and evidence-based understanding of frontier AI risks through the development of an international, independent, and inclusive report on the risks and capabilities of frontier AI. The International AI Safety Report delivers on that mandate, providing a comprehensive synthesis of the existing literature on the risks and capabilities of advanced AI models.
As host of the AI Safety Summit, the UK commissioned Yoshua Bengio to deliver this report, with operational support from a secretariat hosted by the UK AI Safety Institute. The UK government has agreed with participating countries that it will continue to provide the secretariat for the report until a suitable long-term international home is agreed, and Professor Yoshua Bengio will continue acting as Chair for 2025.
The report was developed in-line with the principles and procedures, agreed by the Chair and Expert Advisory Panel.