Text is a powerful abstraction of reality, like architecture abstracts complex software systems. The advent of Large Language Models (LLMs) has set new benchmarks in understanding and generating human-like text, revolutionizing multiple sectors. In this talk, we explore some of these capabilities of LLMs to understand whether LLMs can be architects new best friend. Beginning with an overview and background of LLMs, we delve into their capabilities in generating design decisions, thereby contributing to better knowledge management. We further discuss how we are leveraging LLMs capabilities for runtime self-adaptation and conclude by showcasing our recent efforts in developing a Generative AI powered autonomous CloudOps Copilot.