The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) Building LLM-Based Applications with Azure OpenAI with Jay Emery - #657
31 snips
Nov 28, 2023 In a captivating discussion, Jay Emery, Director of Technical Sales & Architecture at Microsoft Azure, shares insights on crafting applications using large language models. He tackles challenges organizations face, such as data privacy and performance optimization. Jay reveals innovative techniques like prompt tuning and retrieval-augmented generation to enhance LLM outputs. He also discusses unique business use cases and effective methods to manage costs while improving functionality. This conversation is packed with practical strategies for anyone interested in the AI landscape.
AI Snips
Chapters
Transcript
Episode notes
Tailoring LLMs
- Tailor large language models (LLMs) to specific business needs.
- Consider prompt engineering, tuning, and chaining for richer outputs.
LLMs in EdTech
- An EdTech company uses LLMs to help teachers.
- The model creates outlines, content, quizzes, and even grades essays.
Prompt Engineering Challenges
- Prompt engineering is like throwing spaghetti at a wall; outputs vary.
- Tools like Ling Chang and Azure ML AI Studio help manage and compare results.