
02: Unleashing LLMs in Production: Challenges and Opportunities with Chip Huyen
Replit AI Podcast
The Evolution of Chatbots
The last six months' revolution in a LAMS has made benchmarks even harder to create and prepare. The bad way to evaluate is to put it in front of users. Different data mixtures yield different models. People have different tastes around how to mix the data. And by the way, you can still find you an our thing and make it like dairy pests or make it do shell suggestions better.
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.