Explore the fundamentals of large language models, particularly GPT models, from a security research perspective in this 44-minute conference talk from NorthSec. Gain insights into semantic searching, few-shot learning, and code generation through basic examples and experiments. Discover how GPT models can be leveraged to empower security teams and inspire new research ideas, whether you're a novice or experienced in working with these models. The talk aims to provide a high-level overview and fresh perspective on the potential applications of GPT models in security research labs.