Super Data Science: ML & AI Podcast with Jon Krohn 690: How to Catch and Fix Harmful Generative A.I. Outputs
Jun 23, 2023
Krishna Gade, CEO of Fiddler.AI, delves into managing harmful outputs in Generative AI models, discussing issues like inaccuracies, biases, and privacy risks. He emphasizes the need for monitoring AI to build trust and showcases Fiddler's explainability algorithms and bias detection tools as essential solutions.
Chapters
Transcript
Episode notes
1 2 3 4 5
Intro
00:00 • 2min
Building Trust in AI with Fiddler Auditor
02:11 • 15min
Model Risk Management in Regulated Industries and AI Validation Reports
16:55 • 2min
Building Trust into AI with Fiddler's Capabilities
19:16 • 3min
Exploring Tools for Safer Production of LLMs and Book Recommendation
22:24 • 4min