Enable javascript in your browser for better experience. Need to know to enable it? Go here.
Podcast

AI testing, benchmarks and evals 

Generative AI's unpredictability has sparked fresh interest in quality assurance, but terms like evals, benchmarks and guardrails often get used interchangeably. Thoughtworks' Shayan Mohanty and John Singleton join host Lilly Ryan to untangle what each actually means and why getting this right matters for moving GenAI from proof of concept to production.

 

Listen to the podcast episode.