[Simon Willison] has put together a list of how, exactly, one goes about using a large language models (LLM) to help write code.The document emphasizes realistic expectations, managing context, and the importance of testing and human oversight.LLMs can be useful for speeding up software development, researching options, exploring codebases, and prototyping ideas.The writeup provides insights into how LLMs can meaningfully assist in software development.