在 X 上看到这个分享，不得不说，Ilya 真是技术宅，发的图片，还是糊的……

用 macOS 的文字识别摘下来慢慢看。

1. Communicate clearly and precisely when writing prompts. The ability to clearly state tasks and describe concepts is crucial.
2. Be willing to iterate rapidly, sending many prompts to the model in quick succession.
   Good prompt engineers are comfortable with constant back-and-forth refinement.
3. Consider edge cases and unusual scenarios when designing prompts. Think about how your prompt might fail in atypical situations.
4. Test your prompts with imperfect, realistic user inputs. Don’t assume users will provide perfectly formatted or grammatically correct queries.
5. Read and analyze model outputs carefully. Pay close attention to whether the model is following instructions as intended.
6. Strip away assumptions and clearly communicate the full set of information needed for a task. Break down the task systematically to ensure all necessary details are included.
7. Think about the “theory of mind” of the model when writing prompts. Consider how the model might interpret your instructions differently than intended.
8. Use version control and track experiments when working with prompts. Treat prompts like code in terms of management and iteration.
9. Ask the model to identify unclear parts or ambiguities in your instructions. This can help refine and improve your prompts.
10. Be precise without overcomplicating. Aim for clear task descriptions without building unnecessary abstractions.
11. Consider the balance between typical cases and edge cases. While handling edge cases is important, don’t neglect the primary use case.
12. Think about how prompts integrate into larger systems. Consider factors like data sources, latency, and overall system design.
13. Don’t rely solely on writing skills; prompt engineering requires a mix of clear communication and systematic thinking. Good writers aren’t necessarily good prompt engineers, and vice versa.
14. When working with customers, help them understand the realities of user input.
    Guide them to consider real-world usage patterns rather than idealized scenarios.
15. Practice looking at data and model outputs extensively. Familiarize yourself with how the model responds to different types of prompts and inputs.