Report
SHARE
International AI safety report 2026
Malcolm Murray, Maksym Andriushchenko, Ben Bucknall, Rishi Bommasani, Stephen Casper, Tom Davidson, Raymond Douglas, David Duvenaud, Philip Fox, Usman Gohar, Rose Hadshar, Anson Ho, Tiancheng Hu, Cameron Jones, Sayash Kapoor, Atoosa Kasirzadeh, Sam Manning, Nestor Maslej, Vasilios Mavroudis, Conor McGlynn, Richard Moulange, Jessica Newman, Kwan Yee Ng, Patricia Paskov, Shalaleh Rismani, Girish Sastry, Elizabeth Seger, Scott Singer, Charlotte Stix, Lucia Velasco, Nicole Wheeler, Daron Acemoglu, Vincent Conitzer, Thomas G. Dietterich, Edward W. Felten, Fredrik Heintz, Geoffrey Hinton, Nick Jennings, Susan Leavy, Teresa Ludermir, Vidushi Marda, Helen Margetts, John McDermid, Jane Munga, Arvind Narayanan, Alondra Nelson, Clara Neppel, Sarvapali D. Ramchurn, Stuart Russell, Marietje Schaake, Bernhard Schölkopf, Alvaro Soto, Lee Tiedrich, Gaël Varoquaux, Andrew Yao, Ya‑Qin Zhang, Leandro Angelo Aguirre, Olubunmi Ajala, Fahad Albalawi, Noora AlMalek, Christian Busch, Jonathan Collas, André Carlos Ponce de Leon Ferreira de Carvalho, Amandeep Gill, Ahmet Halit Hatip, Juha Heikkilä, Chris Johnson, Gill Jolly, Ziv Katzir, Mary N. Kerema, Hiroaki Kitano, Antonio Krüger, Kyoung Mu Lee, José Ramón López Portillo, Aoife McLysaght, Olexii Molchanovskyi, Andrea Monti, Mona Nemer, Nuria Oliver, Raquel Pezoa, Audrey Plonk, Balaraman Ravindran, Hammam Riza, Crystal Rugege, Haroon Sheikh, Denise Wong, Yi Zeng, Liming Zhu, Daniel Privitera, S. Mindermann
Publisher
Capability (work)
Risk assessment
Emerging technologies
Artificial Intelligence (AI)
Autonomous technologies
Resources
| Attachment | Size |
|---|---|
 International AI safety report 2026
|
6.71 MB |
|
International AI safety report 2026: executive summary
|
292.85 KB |
|
International AI safety report 2026: extended summary for policymakers
|
1.84 MB |
Description
The report provides a comprehensive review of the latest scientific research on the capabilities and risks of general-purpose artificial intelligence (AI) systems. It assesses what general-purpose AI systems can do, what risks they pose and how those risks can be managed.
It focuses on the most capable general-purpose AI systems and the emerging risks associated with them. ‘General-purpose AI’ refers to AI models and systems that can perform a wide variety of tasks. ‘Emerging risks’ are risks that arise at the frontier of general-purpose AI capabilities.
The aim of the work is to help policymakers navigate the ‘evidence dilemma’ posed by general-purpose AI. The report is provided with an extended summary for policymakers.
Key findings
- General-purpose AI capabilities have continued to improve since 2025, especially in mathematics, coding and autonomous operation.
- Capabilities remain ‘jagged’: leading systems may excel at some difficult tasks while failing at other, simpler ones.
- General-purpose AI risks fall into three categories: malicious use, malfunctions, and systemic risks.
- Layering multiple approaches offers more robust risk management.
- Advances in AI’s scientific capabilities have heightened concerns about misuse in biological weapons development.
- More evidence has emerged of AI systems being used in real-world cyberattacks.
Related Information
Publication Details
Copyright:
Crown owned 2026
License type:
Open Government Licence v3.0
Access Rights Type:
open
Series:
Research series number: DSIT 2026/001
Post date:
10 Feb 2026
