Пишу на английском. Так легче задавать
26 принципов хороших подсказок призваны помочь вам создавать эффективные и действенные подсказки для взаимодействия с языковыми моделями. Вот они:
- No need to be polite with LLM: Avoid phrases like “please”, “if you don’t mind”, “thank you”, “I would like to” etc., and get straight to the point.
- Integrate the intended audience in the prompt: Specify if the audience is an expert in the field.
- Break down complex tasks into a sequence of simpler prompts: Use an interactive conversation approach.
- Employ affirmative directives such as ‘do’ while steering clear of negative language like ‘don’t’.
- Utilize prompts for clarity or deeper understanding: Examples include asking to explain a topic in simple terms or as if explaining to a beginner in the field.
- Add “I’m going to tip $xxx for a better solution!”: Though more figurative when used with AI, it suggests providing an incentive for quality responses.
- Implement example-driven prompting (Use few-shot prompting).
- Format your prompt starting with ‘###Instruction###’ followed by ‘###Example###’ or ‘###Question###’ if relevant: Use line breaks to separate these sections.
- Incorporate phrases like “Your task is” and “You MUST”.
- Use phrases like “You will be penalized”.
- Use the phrase ”Answer a question given in a natural human-like manner” in your prompts.
- Use leading words like “think step by step”.
- Include “Ensure that your answer is unbiased and does not rely on stereotypes”.
- Enable the model to ask questions: “From now on I would like you to ask me questions to…”
- For teaching a concept: “Teach me the [Any theorem/topic/rule name] and include a test at the end but don’t give me the answers and then tell me if I got the answer right when I respond.”
- Assign a role to the large language models.
- Use Delimiters.
- Repeat a specific word or phrase multiple times within a prompt.
- Combine Chain-of-thought (CoT) with few-Shot prompts.
- Use output primers: End your prompt with the start of the anticipated response.
- For detailed text creation: “Write a detailed [essay/text/paragraph] for me on [topic] in detail by adding all the information necessary.”
- To correct/change specific text without changing its style: “Try to revise every paragraph sent by users. You should only improve the user’s grammar and vocabulary and make sure it sounds natural. You should not change the writing style such as making a formal paragraph casual.”
- For complex coding prompts that may be in different files: “From now and on whenever you generate code that spans more than one file generate a [programming language] script that can be run to automatically create the specified files or make changes to existing files to insert the generated code. [your question]”
- Initiate or continue a text using specific words, phrases, or sentences: “I’m providing you with the beginning [song lyrics/story/paragraph/essay…]: [Insert lyrics/words/sentence]. Finish it based on the words provided. Keep the flow consistent.”
- Clearly state the requirements that the model must follow to produce content: Use keywords, regulations, hints, or instructions.
- To write text similar to a provided sample: “Please use the same language based on the provided paragraph[/title/text /essay/answer].”
These principles serve as a comprehensive guide to crafting prompts that are clear, specific, and designed to elicit the most accurate and useful responses from language models.