Evaluating LLM-based Applications - Part 2

Dive into a comprehensive 50-minute workshop on evaluating LLM-based applications, presented by Josh Tobin at the LLMs in Prod Conference. Learn hands-on techniques for assessing language models, gaining valuable insights into sourcing evaluation data, exploring automated evaluation methods for generative models, and understanding the role of human evaluation. Discover practical tools and knowledge to effectively evaluate your own LLM applications. Benefit from the expertise of Josh Tobin, founder and CEO of Gantry, former deep learning and robotics researcher at OpenAI, and creator of Full Stack Deep Learning. This workshop, sponsored by Gantry, offers a unique opportunity to demystify the process of evaluating language models and transform it from an art into a more scientific approach.

Evaluating LLM-based Applications // Josh Tobin // LLMs in Prod Conference Part 2