Vanishing Gradients cover image

Episode 60: 10 Things I Hate About AI Evals with Hamel Husain

Vanishing Gradients

00:00

Why AI-Powered Software Needs Different Tests

Hamel explains why LLM outputs are stochastic and require data-driven, statistical approaches rather than classic deterministic tests.

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