International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management
SuperIntelligence - Robotics - Safety & Alignment · 07.12.2025 · 2 (4)
DOI: 10.70777/si.v2i4.16671 ↗Kurz gefasst
Fachartikel in der Zeitschrift SuperIntelligence - Robotics - Safety & Alignment, online erschienen am 07.12.2025. Verfasst von Yoshua Bengio und 36 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
This is the Second Key Update to the 2025 International AI Safety Report. The First Key Update (1) discussed developments in the capabilities of general-purpose AI models and systems and associated risks. This Key Update covers how various actors, including researchers, companies, and governments, are approaching risk management and technical mitigations for AI. The past year has seen important developments in AI risk management, including better techniques for training safer models and monitoring their outputs. While this represents tangible progress, significant gaps remain. It is often uncertain how effective current measures are at preventing harms, and effectiveness varies across time and applications. There are many opportunities to further strengthen existing safeguard techniques and to develop new ones. This Key Update provides a concise overview of critical developments in risk management practices and technical risk mitigation since the publication of the 2025 AI Safety Report in January. It highlights where progress is being made and where gaps remain. Above all, it aims to support policymakers, researchers, and the public in navigating a rapidly changing environment, helping them to make informed and timely decisions about the governance of general-purpose AI. Professor Yoshua BengioUniversité de Montréal / LawZero /Mila – Quebec AI Institute & Chair
Zitieren
APA
Bengio, Y., Clare, S., Prunkl, C., Andriushchenko, M., Bucknall, B., Fox, P., Maslej, N., McGlynn, C., Murray, M., Rismani, S., Casper, S., Newman, J., Privitera, D., Mindermann, S., Acemoglu, D., Dietterich, T. G., Heintz, F., Hinton, G., Jennings, N., …, & Zhang, Y. (2025). International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management. SuperIntelligence - Robotics - Safety & Alignment, 2(4). https://doi.org/10.70777/si.v2i4.16671
Vancouver
Bengio Y, Clare S, Prunkl C, Andriushchenko M, Bucknall B, Fox P, et al. International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management. SuperIntelligence - Robotics - Safety & Alignment. 2025;2(4). doi:10.70777/si.v2i4.16671
BibTeX
@article{Bengio2025,
author = {Bengio, Yoshua and Clare, Stephen and Prunkl, Carina and Andriushchenko, Maksym and Bucknall, Benjamin and Fox, Philip and Maslej, Nestor and McGlynn, Conor and Murray, Malcolm and Rismani, Shalaleh and Casper, Stephen and Newman, Jessica and Privitera, Daniel and Mindermann, Sören and Acemoglu, Daron and Dietterich, Thomas G. and Heintz, Fredrik and Hinton, Geoffrey and Jennings, Nick and Leavy, Susan and Ludermir, Teresa and Marda, Vidushi and Margetts, Helen and McDermid, John and Munga, Jane and Narayanan, Arvind and Nelson, Alondra and Neppel, Clara and Ramchurn, Sarvapali D. (Gopal) and Russell, Stuart and Schaake, Marietje and Schölkopf, Bernhard and Soto, Alvaro and Tiedrich, Lee and Varoquaux, Gaël and Yao, Andrew and Zhang, Ya-Qin},
title = {International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management},
journal = {SuperIntelligence - Robotics - Safety & Alignment},
year = {2025},
volume = {2},
number = {4},
doi = {10.70777/si.v2i4.16671}
}
EUVIMED