689: Observing LLMs in Production to Automatically Catch Issues
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Intro
Amber Roberts and Xander Song from Arise AI delve into the consequences of drift on production AI systems, particularly large language models (LLMs). They tackle ML observability, its significance in automating problem identification in AI systems, and delve into open-source ML observability choices, model retraining intervals, and identifying biases in models towards specific demographic groups.
Play episode from 00:00
Transcript
