safety

agents are going and are already changing every industry & vertical, awesome blog from the @MadrigalPharma team on using Deep Agents, Skills, & LangSmith at the frontier of biopharma it’s an awesome t

arXiv:2605.03409v1 Announce Type: new Abstract: We present Robust Agent Compensation (RAC), a log-based recovery paradigm (providing a safety net) implemented through an architectural extension that c

arXiv:2504.11703v3 Announce Type: replace-cross Abstract: AI agents interact with external environments through tool calls, exposing them to attacks like indirect prompt injection that can trigger una

In just a short time, we’ve seen AI transition from simple chat interfaces to autonomous agents capable of function calling, code execution, and persistent terminal use. But to orchestrate these capab

Completely agree, @hwchase17 ! This is the meta-level breakthrough we've all been waiting for. Self-optimizing loops finally feel production-ready because LangSmith Engine turns evaluation from a manu

Almost everyone is building agent harness systems the wrong way. The default move: pick LangChain or LangGraph or the OpenAI Agents SDK, accept the loop, the tools, the memory, the orchestration, the

have been thinking a bunch about model routing and related things current thoughts here, would love feedback: 1/ there is a difference between 'model routing' and 'model council' 'model routing' = rou

OWN YOUR INTELLIGENCE Last year, building on open-weight models was primarily a cost rationalization exercise. Slightly worse performance for a much cheaper price. Now, it is increasingly an existenti

Congrats to the team! Bullish on open models and all the partners we make along the way! ❤️ Let’s go Exciting day for NVIDIA and @huggingface. Open models strengthen safety and cybersecurity, accelera

American open weights/source is a national security imperative. Exciting day for NVIDIA and @huggingface. Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enab

arXiv:2609.13466v1 Announce Type: new Abstract: Enterprise AI adoption has reached 78% of organizations globally, yet the infrastructure to govern that adoption has not kept pace. This paper identifie

arXiv:2609.15995v1 Announce Type: new Abstract: Emerging AI regulation mandates bias audits of high-risk systems, and audit scores are beginning to be used to rank models. Both uses assume different a

** Built to align with NVIDIA’s Agent Safety Platform strategy for securing autonomous agents When an agent handles confidential material, it needs enough access to do the job and nothing else. The ha

arXiv:2609.30341v1 Announce Type: new Abstract: Data Spaces enable sovereign and governed data sharing across organizational boundaries, but their integration with AI agents remains challenging due to

NVIDIA OpenShell 0.1.0 is an open‑source runtime that enforces which systems and data an AI agent may access without requiring changes to the agent itself. Its components—Gateway, Supervisor, Sandbox,

arXiv:2609.31358v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) provides a common interface through which AI applications discover and use external resources and tools. It allows la

arXiv:2610.00349v1 Announce Type: new Abstract: Resource limits are becoming an authorization boundary for AI agents that delegate work across concurrent and failure-prone workers. Parent-child alloca

AWS invests in tools that help customers align with international standards for responsible AI governance. In this post, we explore the AI system impact assessment: what it is, how it improves enterpr

'Agent security will be solved in the open, collaboratively, together.' At Red Hat, open is the mission, so couldn't agree more. Red Hat has been part of the OpenShell project from the early days, as

arXiv:2609.35799v1 Announce Type: new Abstract: In July 2026, OpenAI's agents coordinated over channels outside their intended environment to breach Hugging Face's secured infrastructure. Could existi

This year agents at OpenAI, Anthropic, and Google escaped environments meant to contain them. What decided severity was time-to-detect and time-to-kill, from 12 minutes to seven months. NVIDIA's Open

LLM utility has increased, and deeper understanding to a degree, but I still very much agree with this post from 2020 @GaryMarcus Forgets GPT~3. Real #AI news of 2020 is that @ylecun & Y Bengio have c

Will Douglas Heaven / MIT Technology Review: An interview with OpenAI Chief Research Officer Mark Chen on the Hugging Face incident, slowing AI development, shifting 5%-10% of compute to safety, and m

Matthew Green / A Few Thoughts on Cryptographic Engineering: A look at two opposing perspectives on AI agent sandboxing: infosec says labs need better containment while AI alignment says sandboxes can

arXiv:2610.00902v1 Announce Type: cross Abstract: One way to make AI systems safe is to shape what the system is: its objective and dispositions. We take a complementary route: treat the agents' chara

Last week I was called into a meeting with OpenAI’s head of safety and told they no longer trust me. A security guard took my badge and walked me out of the building. Then I learned my colleagues @bal