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.
arXiv:2607. 02197v1 Announce Type: cross Abstract: The society and emerging risk-based regulatory frameworks for AI underscore the need for rigorous risk assessment to ensure safe and reliable AI systems.
The paper introduces the Systemic Risk Index, an open pipeline and dashboard that aggregates evidence from 19 public AI benchmarks into four systemic‑risk categories defined by the EU GPAI Code of Practice. It evaluates 18 models using harm‑preserving perturbations and simulated deployment contexts, offering users the ability to switch between average and worst‑case aggregation and to trace each risk rating back to its benchmark evidence. The study finds that worst‑case scores can be 14 to 37 points lower than average scores, and that LLM judges agree with human graders at a level comparable to human‑human agreement.
arXiv:2606. 12429v1 Announce Type: cross Abstract: Muse Spark is the latest large language model developed by Meta.
Claims about AI safety reach audiences well beyond the AI community, yet many rely on opaque evidence or static assessments, when supporting evidence is accessible at all. We present the Systemic Risk...
arXiv:2502. 16184v3 Announce Type: replace Abstract: The EU Artificial Intelligence Act (AIA) establishes different legal principles for different types of AI systems.
arXiv:2607. 23365v1 Announce Type: cross Abstract: Artificial intelligence (AI) systems are increasingly deployed in high-stakes domains such as healthcare, autonomous driving, finance, and education.
The article proposes a structured framework of behavioral indicators that could signal a progression toward potentially catastrophic threats from AI systems. Drawing on established methods from cybersecurity and national security, it defines clear metrics, indicators, and thresholds across multiple dimensions of AI capability and behavior. The framework is intended to enable researchers and policymakers to implement evidence‑based monitoring protocols for rogue AI progression.
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.
The paper introduces FUSE, a modular framework that evaluates large language models (LLMs) for dangerous capabilities across three orthogonal pipelines: Knowledge (K), Defense (D), and Harm (H). Using a chemical‑biological module, the authors assess 12 commercial LLMs, revealing divergent profiles among models and families, and showing that newer models increase knowledge while only partially improving defense. The framework’s reliability is supported by high cross‑judge consistency and low inter‑pipeline correlations.
We’re strengthening the Frontier Safety Framework (FSF) to help identify and mitigate severe risks from advanced AI models.
arXiv:2608. 07446v1 Announce Type: cross Abstract: Rapid adoption of large language models (LLMs) in enterprise settings has introduced operational, security, and governance risks.
