An agent still learning its environment should be cautious while ignorant and bold once confident. The entropic value-at-risk captures this through a robust-optimization identity---a confidence level fixes the radius of a relative-entropy ball of alternative models---but that ball cannot reach catastrophes the nominal deems impossible, precisely what a safe agent must hedge. We instead use an optimal-transport ball and study the coherent risk measure it induces, the Wasserstein entropic value-at-risk. It has a variational dual mirroring the entropic formula (an inverse temperature becomes a transport price), occupies a definite place in the risk hierarchy, and provably accounts for the reachable catastrophes the entropic measure ignores; we verify both dualities numerically. Driving the transport radius by belief entropy then yields a closed-form robust dynamic-programming operator whose caution contracts as the belief sharpens, with a certified safety sandwich and a sharp safety switch.
Assine o Pro, sem anúncios
Faça upgrade para uma leitura sem interrupções e acesso prioritário a novas fontes.
Ver preçosRunning large language model inference at scale forces a KV cache trade-off: oversized GPU instances or slow time-to-first-token. This post builds a tiered KV cache on Amazon SageMaker HyperPod that extends the cache into a shared, distributed NVMe pool with Curvine, so replicas reuse cache at near-local-disk speeds on cost-efficient instances.
OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.
Google DeepMind and partners announce a $10M funding call for multi-agent safety research.
OpenAI calls for global action on youth AI safety, proposing an international institute to strengthen safeguards, standards, and opportunities for young people.
Explore OpenAI’s European Youth Safety Blueprint and EMEA Youth & Wellbeing Grants, advancing safe, responsible AI for teens, families, and educators.
Discover OpenAI’s Child Safety Blueprint—a roadmap for building AI responsibly with safeguards, age-appropriate design, and collaboration to protect and empower young people online.
A pilot program to support independent safety and alignment research and develop the next generation of talent
To address the novel safety challenges posed by a state-of-the-art video model as well as a new social creation platform, we’ve built Sora 2 and the Sora app with safety at the foundation. Our approach is anchored in concrete protections.
Anthropic released Cowork on Monday, a new AI agent capability that extends the power of its wildly successful Claude Code tool to non-technical users …
OpenAI works with independent experts to evaluate frontier AI systems. Third-party testing strengthens safety, validates safeguards, and increases transparency in how we assess model capabilities and risks.
This system card outlines the comprehensive safety measures implemented for GPT‑5.1-CodexMax. It details both model-level mitigations, such as specialized safety training for harmful tasks and prompt injections, and product-level mitigations like agent sandboxing and configurable network access.
Discover OpenAI’s Teen Safety Blueprint—a roadmap for building AI responsibly with safeguards, age-appropriate design, and collaboration to protect and empower young people online.
To address the novel safety challenges posed by a state-of-the-art video model as well as a new social creation platform, we’ve built Sora 2 and the Sora app with safety at the foundation. Our approach is anchored in concrete protections.
Explore OpenAI’s approach to balancing teen safety, freedom, and privacy in AI use.
