Enabling LLM-Powered Applications with Harrison Chase of LangChain
Gradient Dissent: Conversations on AI
00:00
How to Test a Document Search Engine for Bias
I think there's no substitute for looking at individual examples. I feel like the first thing that we wanted to do with you guys was make the obvious thing that people are doing today, the testing by vibes as easy as possible. We saw opening eye of vows, right? The main thing that's doing is just like you're saying, doesn't seem like a good result or a bad result. And it does seem risky. If you asked me to grade this interview myself, you could imagine that being effective or I could imagine that going a bit haywire.
Transcript
Play full episode
