9 papers
The 2026 Singapore Consensus on Global AI Safety Research Priorities
Stephen Casper, Oskar Galeev, Yoshua Bengio +117
Frontier AI capabilities and autonomy are advancing rapidly. A growing number of real-world incidents make a trusted AI ecosystem essential to embracing AI with confidence. The 202…
Embedded Off-Switches for AI Compute
James Petrie
To address the risks of increasingly capable AI systems, we introduce a hardware-level off-switch that embeds thousands of independent "security blocks" in each AI accelerator. Thi…
The Singapore Consensus on Global AI Safety Research Priorities
Yoshua Bengio, Tegan Maharaj, Luke Ong +84
Rapidly improving AI capabilities and autonomy hold significant promise of transformation, but are also driving vigorous debate on how to ensure that AI is safe, i.e., trustworthy,…
International Security Applications of Flexible Hardware-Enabled Guarantees
Onni Aarne, James Petrie
As AI capabilities advance rapidly, flexible hardware-enabled guarantees (flexHEGs) offer opportunities to address international security challenges through comprehensive governanc…
Flexible Hardware-Enabled Guarantees for AI Compute
James Petrie, Onni Aarne, Nora Ammann +1
As artificial intelligence systems become increasingly powerful, they pose growing risks to international security, creating urgent coordination challenges that current governance…
Technical Options for Flexible Hardware-Enabled Guarantees
James Petrie, Onni Aarne
Frontier AI models pose increasing risks to public safety and international security, creating a pressing need for AI developers to provide credible guarantees about their developm…
Hardware-Enabled Mechanisms for Verifying Responsible AI Development
Aidan O'Gara, Gabriel Kulp, Will Hodgkins +7
Advancements in AI capabilities, driven in large part by scaling up computing resources used for AI training, have created opportunities to address major global challenges but also…
Near-Term Enforcement of AI Chip Export Controls Using A Firmware-Based Design for Offline Licensing
James Petrie
Offline Licensing is a mechanism for compute governance that could be used to prevent unregulated training of potentially dangerous frontier AI models. The mechanism works by disab…
Quasistatic cohesive fracture with an alternating direction method of multipliers
James Petrie, M. Reza Hirmand, Katerina D. Papoulia
A method for quasistatic cohesive fracture is introduced that uses an alternating direction method of multipliers (ADMM) to implement an energy approach to cohesive fracture. The A…