Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI

OpenAI safety practices

Artificial general intelligence has the potential to benefit nearly every aspect of our lives—so it must be developed and deployed responsibly.

Our approach to AI safety

Ensuring that AI systems are built, deployed, and used safely is critical to our mission.

Lessons learned on language model safety and misuse

We describe our latest thinking in the hope of helping other AI developers address safety and misuse of deployed models.

The Normalization of Deviance in AI Development

arXiv:2609.05749v1 Announce Type: new Abstract: Work on the risks of artificial intelligence has focused predominantly on capability risk: the danger that systems become too powerful, too autonomous,...

MME-Safety: A Fine-grained Benchmark for Safety Evaluation of MLLMs

arXiv:2609.20850v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) show remarkable advancements, their cross-modal capabilities introduce complex vulnerabilities that easi...

Why responsible AI development needs cooperation on safety

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.

When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI

arXiv:2608.28518v1 Announce Type: cross Abstract: We investigate whether automatic speech recognition (ASR) errors in user input can lead to unsafe outputs from Embodied AI (EAI) models. We find that...

Democratizing AI Safety with RiskRubric.ai

Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models

The paper introduces Uni-SafeBench, a safety benchmark designed to evaluate the holistic safety of Unified Multimodal Large Models (UMLMs) across six safety categories and seven task types. It also presents Uni-Judger, a framework that separates contextual safety from intrinsic safety to enable rigorous assessment. Evaluations reveal that current unified models do not consistently maintain the safety alignment of their underlying language models, and open‑source UMLMs perform significantly worse on safety than specialized multimodal models, especially in generation tasks.

Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards

arXiv:2608. 07535v1 Announce Type: cross Abstract: Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning.

Safety and alignment in an era of long-horizon models

OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.

Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models

The paper investigates cross‑modal safety drift in multimodal large language models, where a harmless text query paired with a visual image can trigger harmful responses. Empirical analysis identifies unsafe response patterns and shows that visual cues receive limited attention, weakening refusal mechanisms. The authors introduce Safety‑Awareness Representation Transfer (SRT), a lightweight method that transfers safety signals from text processing to mitigate cross‑modal drift while maintaining model utility.