690: How to Catch and Fix Harmful Generative A.I. Outputs
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Exploring Tools for Safer Production of LLMs and Book Recommendation
Learn about the significance of safely deploying LLMs in production settings, the use of tools like Fiddler Auditor, monitoring models post-deployment, explainable AI, and bias detection. Discover a recommended book 'The Book of Why' by Judea Pearl, with a special emphasis on the enlightening first chapter discussing causality and methods for seeking answers.
Play episode from 22:24
Transcript
