Authoring Interactive, Shareable AI Evaluation Reports with Zeno

Explore the world of interactive AI evaluation reports in this 22-minute talk by Alex Cabrera, a PhD student at Carnegie Mellon University. Learn about Zeno, a cutting-edge platform designed to create and share in-depth evaluations of complex AI systems. Discover how Zeno enables users to examine inputs and outputs across various AI models, including text, audio, and image systems. Gain insights into the importance of thorough AI evaluation, addressing challenges such as hallucinations and biased outputs. Understand how Zeno aims to become the go-to tool for AI developers and auditors to share reproducible evaluations. Delve into the intersection of human-computer interaction and AI, exploring techniques to improve understanding and enhancement of AI systems.