Thanks Sonam Gupta for the great talk in your podcast about "Monitoring LLMs is Important" with our CTO, Rogério Chaves. We love your enthusiasm about this topic! 😊
Passionate Developer Advocate | Experienced Data Scientist | PhD Data Science | NLP | Machine Learning
Hallucinations, or weird behavior coming out of your LLM application? What do you do in this case? You build a monitoring layer at the end of your pipeline. How do you do it? Use a monitoring tool and LLM evaluation in your application. I had such questions answered by Rogério Chaves from LangWatch in our most recent podcast episode. Check out the highlights below: 🚀 Key Takeaways: - Rise in developer productivity using AI systems like copilots - Challenges like jailbreaking generative AI systems and the strong need for LLM monitoring tools to tackle such challenges - Different examples of jailbreaking user behavior - Importance of iterating over prompt engineering, and the rest of the development process without breaking the existing pipeline. That's not all! To learn more about monitoring LLMs, tune in to the full episode. [Link in comments] P.S.: Thank you Manouk Draisma for introducing us. P.S.S: Revamped the cover pic design :D Canva is awesome.
