About the International AI Safety Report

The International AI Safety Report is the world’s first comprehensive review of the latest science on the capabilities and risks of general-purpose AI systems. The work was overseen by an international Expert Advisory Panel nominated by over 30 countries and intergovernmental organisations. Written by over 100 independent experts and led by Turing Award winner Yoshua Bengio, it represents the largest international collaboration on AI safety research to date. The Report provides decision-makers in government and beyond with a shared and authorative global picture of AI’s risks and impacts.

3 February 2026 — Annual Report

International AI Safety Report 2026

The second International AI Safety Report, published in February 2026, is the next iteration of the comprehensive review of latest scientific research on the capabilities and risks of general-purpose AI systems. Led by Turing Award winner Yoshua Bengio and authored by over 100 AI experts, the report is backed by over 30 countries and international organisations. It represents the largest global collaboration on AI safety to date.

3 February 2026 — Summary

2026 Report: Extended Summary for Policymakers

The Extended Summary for Policymakers provides a detailed (20 page) summary of the full 2026 Report. It includes the Report’s key findings and figures, concrete examples and a list of notable developments since the 2025 edition. It is structured around three central questions: what can general-purpose AI do today, what emerging risks does it pose, and how can those risks be mitigated?

3 February 2026 — Summary

2026 Report: Executive Summary

The Executive Summary offers a concise three-page overview of the 2026 Report’s core findings on general-purpose AI capabilities, emerging risks, and risk management approaches. It covers how AI capabilities are advancing, what real-world evidence is emerging for key risks, and progress and remaining limitations in technical, institutional, and societal risk management measures.

25 November 2025 — Key update

Second Key Update: Technical Safeguards and Risk Management

This Key Update examines developments in technical approaches to general-purpose AI risk management, from training models to refuse harmful requests to watermarking AI-generated content. Since the publication of the 2025 International AI Safety Report, the number of companies publishing Frontier AI Safety Frameworks has more than doubled, and researchers have refined techniques for training safer models and detecting AI-generated content. However, significant gaps remain: sophisticated attackers can often bypass current defences, and the real-world effectiveness of many safeguards is uncertain.

UK AI Security Institute

Mila - Quebec Artificial Intelligence Institute