Rahul Gupta

As frontier models scale in capability, so does their potential for deceptive and manipulative behavior—risks that static, single-turn evaluations fail to capture.

Amazon’s Frontier Model Safety Framework establishes rigorous protocols for evaluating and mitigating critical, high-risk capabilities in frontier-scale AI models—those with exceptional scale or versatility—that might pose severe public safety hazards.

In this chalk talk, learn about the AWS approach to responsible AI (RAI) and forward-looking responsible scaling policies. Hear how AWS defines RAI requirements from first principles (that is, our policies) in collaboration with experts.

Amazon Bedrock Data Automation is a new gen AI–powered capability that transforms unstructured content from documents, images, video, and audio into structured data at scale. It serves use cases ranging from insurance claims processing to media asset management, advertising, and compliance.