Skip to yearly menu bar Skip to main content


Invited talk
in
Affinity Event: Muslims in ML

Invited Talk 2 by Lama Ahmad (Technical Program Manager, Trustworthy AI at OpenAI): Human and AI Evaluations for Safety and Robustness Testing

Lama Ahmad

[ ]
Tue 10 Dec 2 p.m. PST — 2:30 p.m. PST

Abstract:

Evaluating advanced AI systems for safety and adversarial robustness is a critical step in ensuring their responsible deployment. This talk explores the intersection of human and AI-driven evaluations in the context of safety and security testing. We will examine current practices, highlighting how human judgment and AI-assisted tools complement each other in identifying vulnerabilities, unintended behaviors, and emergent risks.

Chat is not available.