))
Lessons Learned with Large Language Models
Manage episode 470132992 series 3559949
Content provided by Eric Kavanagh. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Eric Kavanagh or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ppacc.player.fm/legal.
What part of your business can be wrong 20% of the time? Sales? Fulfillment? Accounting? The obvious answer is that 80% accuracy is a non-starter for most aspects of the modern enterprise. That should be cause for concern when leveraging Large Language Models. Yes, they are amazing, and they're getting better. But guardrails are required to make sure your GenAI outputs don't go off the rails.
Register for this episode of DM Radio to hear Bloor Group CEO Eric Kavanagh explain key components of LLMs and why they're different from traditional databases and information systems. He'll explain what they do well, where they have issues, and how you can design effective Retrieval Augmented Generation (RAG) models to optimize the outputs of GenAI engines. Also joining the show will be David Sweenor, Author of TinyTechGuides; and Daniel Bukowski, CTO for data². Both will offer deep insights about how to work with LLMs, and specifically how to improve accuracy to acceptable levels for the enterprise with Graph RAG.
271 episodes
Share
