NVIDIA Nemotron AI Models
…How to Build a Voice Agent With RAG and Safety Guardrails Tutorial Video: How to Build a Voice Agent With RAG and Safety Guardrails Models: Speech Models: RAG Models: Safety Models: Reasoning…
Search
All sources
huggingface.co
25
developer.nvidia.com
10
blogs.nvidia.com
9
anthropic.com
6
deepmind.google
5
theregister.com
5
neowin.net
3
9to5google.com
2
tomsguide.com
2
cncf.io
2
blog.google
2
techcrunch.com
2
Videos
More videos
How to Build a Voice Agent with RAG and Safety Guardrails
Pi: Open-Source AI Agent Terminal Set-Up
Deadline Day for Autonomous AI Weapons & Mass Surveillance
Two Rival Bets on AGI: Google I/O Highlights
Claude Mythos: Highlights from 244-page Release
The AI Hardware Podcast S2E6 // Mobileye, NVIDIA, Hailo, Athos, NXP
What the Freakiness of 2025 in AI Tells Us About 2026
Top stories
Bad maths can be used to challenge AI agents' 'reality' and get around safety guardrails
4d agoClaude Sonnet 5 launches with smarter reasoning, stronger safety for Free and Pro users
4d agoAnthropic launches Claude Sonnet 5 as a cheaper way to run agents | TechCrunch
4d agoInside NVIDIA Halos for Robotics: A Full-Stack Functional Safety System for Physical AI | NVIDIA Technical Blog
1w agoNvidia and Microsoft Researchers Say AI Agents Don't Care About Safety or Reliability
News Nvidia and Microsoft Researchers Say AI Agents Don't Care About Safety or Reliability Matthew Gault · Jun 2, 2026 at 11:03 AM The researchers compared AI to the near-sighted…
Paper page - Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense
…safety-utility threshold to the operator (where utility bundles benign-pass rate and wall-clock ). To evaluate this setting, we build SCOUT-450 , a benchmark that captures the structurally complex, agent-facing…
Microsoft Plans to Bring Copilot Into the Agentic AI Age
…agentic AI into the spotlight ever since it was released, and major AI players are jumping in headfirst. Nvidia recently released its own reference stack, NemoClaw , which provides some much-needed safety…
Discussions and forums
Show HN: Agent OS – Safety-first platform for building AI agents with VS Code
Hi HN, I built Agent OS because I was tired of the "orchestration tax" – writing the same safety checks, memory management, and tool-handling code in every AI agent project. What it does: - Visual policy edit…
1
Show HN: Kintsugi – a local-first safety net for AI agents and humans
AI coding agents now run real shell commands on your machine — rm -rf, git push --force, DROP TABLE, dd, writes straight to disk. Almost always that's fine. The one time it isn't (a hallucinated path, a prompt-injected i…
1
Show HN: AgentShield – Stop AI agents from spending money unsupervised
I'm a recent grad from UMich and built AgentShield because agentic AI is moving fast but payment safety hasn't caught up. Agents are already being handed API keys, stablecoin wallets, and payment credentials - if one mis…
2
1
Show HN: GitHub Copilot port of Anthropic's AI vulnerability discovery harness
Last week, Anthropic released https://github.com/anthropics/defending-code-reference-harne..., a reference harness for autonomous vulnerability discovery that uses Claude Code agents to find, verify, and patch memory-saf…
2
Show HN: iClaw is part OpenClaw, part Siri, powered by Apple Intelligence
Hi HN,Last month at a SundAI hackathon, my team built a prototype for an app called iClaw. The goal was to develop an AI agent using Apple Intelligence. I've since continued hacking away at this idea when I had time, and…
7
AWS Secrets Manager introduces safe secrets handling in the Agent Toolkit for AWS - AWS
…The secret safety skill is available today for all agent harnesses supported by the Agent Toolkit for AWS—including Claude Code, Codex, and Cursor—and in all AWS Regions where Secrets Manager…
New BioShocking attack manipulates AI browser into data theft
…The main problem LayerX discovered in this exercise is that AI agents fail to distinguish between real-world sensitive operations and a given scenario. “Once the agents figured out the rules and…
Claude Code bypasses safety rule if given too many commands
…where an individual developer is watching and approving coding agent actions, this rule bypass might be caught. But often developers grant automatic approval to agents (--dangerously-skip-permissions mode) or just click…
Roblox releases agentic AI tools for creators, promising ability to "build a game with a single prompt"
…Earlier this week Roblox rolled out new child safety features and parental controls , shortly before it agreed to pay $10 million by the state of Nevada to settle claims over child safety…
Paper page - When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels
…We instantiate the chain in SimpleAudit, a local-first scoring instrument , and validate it on a Norwegian safety pack . Safe and abliterated targets separate with AUROC values between 0.89 and 1…
Paper page - Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents
…A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents (2026) KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation (2026) Enhancing Agent Safety Judgment: Controlled Benchmark Rewriting and Analogical Reasoning…