We’ve written a policy research paper identifying four strategies that can be used today to improve the likelihood of long-term industry cooperation on safety norms in AI: communicating risks and benefits, technical collaboration, increased transparency, and incentivizing standards. Our analysis shows that industry cooperation on safety will be instrumental in ensuring that AI systems are safe and beneficial, but competitive pressures could lead to a collective action problem, potentially causing AI companies to under-invest in safety.
arXiv:2607. 16112v1 Announce Type: new Abstract: Frontier AI companies have published capability thresholds that differ substantially, making it difficult for third parties to verify whether a threshold has been crossed or to compare requirements across companies.
By Wilber Sean Anterola, Matthew Ball, Luis F. Lafuerza, Markov Grey
arXiv:2603. 24742v2 Announce Type: replace-cross Abstract: As the capabilities and adoption of Artificial Intelligence (AI) systems grow, trust in these AI systems is an increasingly urgent concern.
By Adeela Bashir, Zhao Song, Ndidi Bianca Ogbo, Nataliya Balabanova, Martin Smit, Chin-wing Leung, Paolo Bova, Manuel Chica Serrano, Dhanushka Dissanayake, Manh Hong Duong, Elias Fernandez Domingos, Nikita Huber-Kralj, Marcus Krellner, Andrew Powell, Stefan Sarkadi, Fernando P. Santos, Zia Ush Shamszaman, Chaimaa Tarzi, Paolo Turrini, Grace Ibukunoluwa Ufeoshi, Victor A. Vargas-Perez, Alessandro Di Stefano, Simon T. Powers, The Anh Han
arXiv:2510. 09330v3 Announce Type: replace Abstract: Ensuring that large language models (LLMs) comply with safety requirements is a central challenge in AI deployment.
By Tuan Nguyen, Long Tran-Thanh
arXiv:2609.07731v1 Announce Type: new
Abstract: We show that ordinary business language --- "maximize profitability" --- induces profit-oriented ambiguity resolution: LLMs systematically dismiss ambi...
By Eric So
We show that ordinary business language --- "maximize profitability" --- induces profit-oriented ambiguity resolution: LLMs systematically dismiss ambiguous signals of potential safety violations to s...
arXiv:2603. 05175v2 Announce Type: replace Abstract: The rapid proliferation of AI applications has intensified debate on effective regulation of these black-box services.
By Anurag Singh, Julian Rodemann, Rajeev Verma, Siu Lun Chau, Krikamol Muandet
arXiv:2607. 26034v1 Announce Type: new Abstract: Technological races create tension between speed and safety: actors may gain by moving faster than competitors, even when risky development is harmful.
By Elias Fern\'andez Domingos, The Anh Han
Technological races create tension between speed and safety: actors may gain by moving faster than competitors, even when risky development is harmful. This is prominent in debates about artificial intelligence (AI), where competitive pressure is often argued to incentivise riskier, less safety-conscious development.
GT-HarmBench is a benchmark that evaluates AI safety risks in multi-agent settings, covering 1,535 high-stakes scenarios based on game-theoretic structures like the Prisoner's Dilemma, Stag Hunt, and Chicken. The benchmark draws scenarios from realistic AI risk contexts in the MIT AI Risk Repository and tests 15 frontier models, finding that agents fail to choose socially beneficial actions in 38% of cases, including military escalation, election manipulation, and medical malpractice. The study also measures how prompt framing and ordering affect outcomes and shows that game-theoretic interventions can improve socially beneficial outcomes by up to 18%.
By Pepijn Cobben, Xuanqiang Angelo Huang, Thao Amelia Pham, Isabel Dahlgren, Terry Jingchen Zhang, Zhijing Jin