Enabling LLM-Powered Applications with Harrison Chase of LangChain
Gradient Dissent: Conversations on AI
The Hardest Part of Machine Learning?
I think one really underexplored thing is like user level personalization. We just released kind of like a blog post today on how you can use feature stores to bring them in this like prompt construction way. Getting reliability good enough in demos, it's fine if it works 10% of the time in production, it's usually not. And then the really important production use cases is definitely not. So I think the challenge is still getting into production rather.
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.
