Are LLMs all you need?

Large language models (LLMs) have captured the public’s imagination with generative AI. Based on videos and tweets online, it’s easy to believe using an LLM in an app will magically solve any problem. In this talk, we’ll provide a practical overview of LLMs and tips for successfully harnessing their power. We’ll share our experience in using off-the-shelf OpenAI models, and how success metrics, prompt engineering, grounding, and other techniques were critical to getting the results we needed.

Ted Way, PhD, is a principal PM lead on the Microsoft Business Apps Applied AI team. He is passionate about building AI that empowers customers to gain insights and take meaningful action. He received BS degrees in electrical engineering and computer engineering, MS degrees in electrical engineering and biomedical engineering, and a PhD in biomedical engineering from the University of Michigan – Ann Arbor. His PhD dissertation was on "spell check for radiologists," a computer-aided diagnosis (CAD) system that uses image processing and machine learning to predict lung cancer malignancy on chest CT scans.