Vanishing Gradients cover image

Episode 32: Building Reliable and Robust ML/AI Pipelines

Vanishing Gradients

00:00

Understanding Drift in Machine Learning

This chapter explores the phenomenon of drift in machine learning, particularly focusing on criteria drift and business logic drift that affect model performance. The discussion includes the development of the E-VALGen interface for user feedback on AI outputs, the complexities of evaluating language models, and the potential pitfalls of using large language models in recursive processes. Ultimately, the chapter emphasizes the need for human oversight and modular thinking in AI systems to navigate evolving metrics and user expectations.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app