Hey Jon,
I'm wondering how it handles comparing responses across different LLM models. Can you easily test the same prompt on GPT-3.5 vs GPT-4 vs Claude for example? That could be really valuable for choosing the right model for specific use cases.
Congrats on the launch!
@kyrylosilin Yup. It's super easy to change the model -- in the app, just click on "Model", then you can choose between any one that you'd like (llama, claude, gpt-4, mistral). You can run the same set of prompts with different LLMs, which allows you to see which model is the best for your workflow.
Thank you!
Telebugs
Prompt Hippo