MLOps.community  cover image

How to Systematically Test and Evaluate Your LLMs Apps // Gideon Mendels // #269

MLOps.community

CHAPTER

Managing LLM Applications: Risks and Observability

This chapter explores the distinctions between internal and external-facing large language model (LLM) applications, focusing on the associated risks and scalability challenges. It discusses the development of OPIC, a tool for enhancing model observability and the complexities of setting up alert systems for machine learning outputs. The conversation emphasizes practical challenges in integrating AI features, including prompt injections and the need for customized monitoring metrics.

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.
App store bannerPlay store banner