The official Stanford AI Lab blog
Safety Validation of Black-Box Autonomous Systems
Anthony L. Corso
Validation of safety-critical autonomous systems is necessary before deployment and is made possible by black-box validation strategies. In this blog post, we provide a model for black-box safety validation and survey the literature to uncover the most effective validation techniques.
RoboNet: A Dataset for Large-Scale Multi-Robot Learning
Sudeep Dasari
The official Stanford AI Lab blog
A few weeks ago I started building SafeRun — inline reliability infrastructure for AI agents in...
Learn how Red Hat's AI safety strategy delivers a comprehensive safety stack, making adversarial testing for large language…
A Blog post by ServiceNow-AI on Hugging Face
In an effort to set a new industry standard, OpenAI and Anthropic opened up their AI models for cross-lab safety testing.
The official Stanford AI Lab blog
