« Prompt design » : différence entre les versions
(Page créée avec « Please note a few best practices around prompt design. Be concise Be specific and well-defined Ask one task at a time Turn generative tasks into classification tasks. For example, instead of asking what programming language to learn, ask if Python, Java, or C is a better fit for a beginner in programming. and Improve response quality by including examples. Adding instructions and a few examples tends to yield good results however there’s currently no one best w... ») |
Aucun résumé des modifications |
||
(Une version intermédiaire par le même utilisateur non affichée) | |||
Ligne 1 : | Ligne 1 : | ||
The process of finding and designing the best input text to get the desired response back from the model is called prompt design, which often involves a lot of experimentation. | |||
Please note a few best practices around prompt design. Be concise Be specific and well-defined Ask one task at a time Turn generative tasks into classification tasks. For example, instead of asking what programming language to learn, ask if Python, Java, or C is a better fit for a beginner in programming. and Improve response quality by including examples. Adding instructions and a few examples tends to yield good results however there’s currently no one best way to write a prompt. You may need to experiment with different structures, formats, and examples to see what works best for your use case. | Please note a few best practices around prompt design. Be concise Be specific and well-defined Ask one task at a time Turn generative tasks into classification tasks. For example, instead of asking what programming language to learn, ask if Python, Java, or C is a better fit for a beginner in programming. and Improve response quality by including examples. Adding instructions and a few examples tends to yield good results however there’s currently no one best way to write a prompt. You may need to experiment with different structures, formats, and examples to see what works best for your use case. | ||
* Be concise | |||
* Be specific and well-defined | |||
* Ask one task at a time | |||
* Turn generative tasks into classification tasks | |||
* Improve response quality by including examples | |||
https://www.cloudskillsboost.google/course_sessions/3264154/video/383122 | https://www.cloudskillsboost.google/course_sessions/3264154/video/383122 |
Version actuelle datée du 4 juillet 2023 à 10:14
The process of finding and designing the best input text to get the desired response back from the model is called prompt design, which often involves a lot of experimentation.
Please note a few best practices around prompt design. Be concise Be specific and well-defined Ask one task at a time Turn generative tasks into classification tasks. For example, instead of asking what programming language to learn, ask if Python, Java, or C is a better fit for a beginner in programming. and Improve response quality by including examples. Adding instructions and a few examples tends to yield good results however there’s currently no one best way to write a prompt. You may need to experiment with different structures, formats, and examples to see what works best for your use case.
- Be concise
- Be specific and well-defined
- Ask one task at a time
- Turn generative tasks into classification tasks
- Improve response quality by including examples
https://www.cloudskillsboost.google/course_sessions/3264154/video/383122