
How Microsoft Scales Testing and Safety for Generative AI with Sarah Bird - #691
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Building Systems with Defense in Depth
To rapidly respond to unintended actions in deployed products, systems should be architected with defense in depth, incorporating layers of technology like Swiss cheese to account for various strengths and weaknesses. Generalizing the necessary systems or layers in place can ensure quick responses to unforeseen situations, allowing for efficient troubleshooting and resolution.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.