The Challenges of Building a Cohere or Open AI-Based App

The big models allow you to prototype and they do amazing behaviors. Once you have the model able to do the behaviors that you want using one example in the prompt or five examples in the prompt, you can then make it cheaper for you by fine-tuning a smaller model. That saves on context size because you're not sending the same five few shot examples with every prompt. Sematic Search is this way of caching that knowledge and retrieving the important bits. It's great to know that it's possible.

Transcript

Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!

Get the app