// Abstract

In this episode, titled "Build and Risks" at the LLM AVALANCHE 2023, our host, Demetrios, is joined by an esteemed panel of guests: Harrison Chase, Akansha Chowdhery, Yaron Singer, and Benjamin Harvey. Together, they delve into the fascinating world of AI models and the challenges they pose in terms of accuracy, reliability, and trustworthiness. The panel discusses the phenomenon of AI models being overconfident yet producing inaccurate information and explores ongoing research to enhance their performance. They delve into various techniques such as model calibration, retrieval, and augmentation to mitigate inaccuracies. Highlighting the importance of human experts in the loop, the panel emphasizes the need for human review and validation of AI-generated content in order to ensure its accuracy.

// MLOps Jobs board

https://mlops.pallet.xyz/jobs

// MLOps Swag/Merch

https://mlops-community.myshopify.com/

// Related Links

Blogpost https://mlops.community/llm-avalanche/

⁠

--------------- ✌️Connect With Us ✌️ -------------

Join our slack community: https://go.mlops.community/slack

Follow us on Twitter: @mlopscommunity

Sign up for the next meetup: https://go.mlops.community/register

Catch all episodes, blogs, newsletters, and more: https://mlops.community/

Connect with Demetrios on LinkedIn: https://www.linkedin.com/in/dpbrinkm/

Connect with Harrison on LinkedIn: https://www.linkedin.com/in/harrison-chase-961287118/

Connect with Aakanksha on LinkedIn: https://www.linkedin.com/in/achowdhery/

Connect with Yaron on LinkedIn: https://www.linkedin.com/in/yaron-singer-76ab6317/

Connect with Benjamin on LinkedIn: https://www.linkedin.com/in/benjamin-harvey-ph-d-1928839a/