689: Observing LLMs in Production to Automatically Catch Issues
Super Data Science: ML & AI Podcast with Jon Krohn
00:00
Differences Between ML Monitoring and ML Observability
Exploring the importance of ML observability in proactively identifying and solving issues to prevent model deterioration compared to ML monitoring. Discussions on isolating and filtering data points, monitoring model drift, triggers for retraining models, and observing model performance in production.
Play episode from 21:20
Transcript
