实用提示词工程：ChatGPT的 Prompt 提示和技巧教程 Practical Prompt Engineering

Due to their text-to-text format, large language models (LLMs) are capable of solving a wide variety of tasks with a single model. Such a capability was originally demonstrated via zero and few-shot learning with models like GPT-2 and GPT-3 [5, 6]. When fine-tuned to align with human preferences and instructions, however, LLMs become even more compelling, enabling popular generative applications such as coding assistants,