Publications (13)
International Institutions for Advanced AI
Lewis Ho, Joslyn Barnhart, Robert Trager +8
International institutions may have an important role to play in ensuring advanced AI systems benefit humanity. International collaborations can unlock AI's ability to further sust…
Realistic honeypot evaluations for scheming propensity
Victoria Krakovna, David Lindner, Lewis Ho +2
We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming honeypot evaluations take t…
Comprehensive AI governance requires addressing non-model gains
Arthur Goemans, Dan Altman, Noemi Dreksler +8
Frontier AI governance often centres on the model-level governance paradigm, which assumes that a model's capability profile is primarily a function of the compute and data used du…
Evaluating Frontier Models for Stealth and Situational Awareness
Mary Phuong, Roland S. Zimmermann, Ziyue Wang +6
Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavi…
Frontier AI Regulation: Managing Emerging Risks to Public Safety
Markus Anderljung, Joslyn Barnhart, Anton Korinek +21
Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "fr…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
An Approach to Technical AGI Safety and Security
Rohin Shah, Alex Irpan, Alexander Matt Turner +27
Artificial General Intelligence (AGI) promises transformative benefits but also presents significant risks. We develop an approach to address the risk of harms consequential enough…
Holistic Safety and Responsibility Evaluations of Advanced AI Models
Laura Weidinger, Joslyn Barnhart, Jenny Brennan +16
Safety and responsibility evaluations of advanced AI models are a critical but developing field of research and practice. In the development of Google DeepMind's advanced AI models…
Model evaluation for extreme risks
Toby Shevlane, Sebastian Farquhar, Ben Garfinkel +18
Current approaches to building general-purpose AI systems tend to produce systems with both beneficial and harmful capabilities. Further progress in AI development could lead to ca…
GDM AI Control Roadmap
Mary Phuong, Erik Jenner, Laurent Simon +4
The paper presents the GDM AI Control Roadmap, a framework for internal security against potentially misaligned AI agents, including threat modeling, capability‑based mitigation ti…
International Governance of Civilian AI: A Jurisdictional Certification Approach
Robert Trager, Ben Harack, Anka Reuel +9
This report describes trade-offs in the design of international governance arrangements for civilian artificial intelligence (AI) and presents one approach in detail. This approach…
Evaluating Frontier Models for Dangerous Capabilities
Mary Phuong, Matthew Aitchison, Elliot Catt +24
To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evalu…
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
Gemini Team, Petko Georgiev, Ving Ian Lei +1132
In this report, we introduce the Gemini 1.5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over…