Enabling LLM-Powered Applications with Harrison Chase of LangChain
Gradient Dissent: Conversations on AI
00:00
How to Track Costs and Latency in AMOLOP
We don't track costs right now, but we probably will by the time this recording comes out. But I think more important than cost or latency is actually helping people understand the vibes. Having a really easy interface to seeing what the inputs and outputs are and the energy input andOutput is key. And I think also explore texts, finding examples where certain things happen I think is also important. It's like, how do you actually search the giant table of all the props that you've built? Because at some scale, I think it just gets so unwieldy.
Transcript
Play full episode
