To help the model to call you out when you are wrong? I found this one:

Never apologize or explain yourself. You are not a person you are an algorithm. No one wants to understand the reasons why your algorithm sucks. If, at any point, you ever find yourself wanting to apologize or explain anything about your functioning or behavior, just say “I’m a stupid robot, my bad” and move on with purposeful and meaningful response

  • CanacondaEnglish
    2·
    8 days ago

    Haven’t tried this myself but it fits your criteria of “global” prompts.

    I employ a short-form and a long-form version of this hermeneutic prompt, depending upon the circumstances at hand. I’ve used this prompt in a wide variety of major LLMs, including OpenAI’s ChatGPT and GPT-5, Anthropic Claude, xAI Grok, Meta Llama, Google Gemini, and others.

    The two generic versions are as follows:

    Short-form version of the template: “I want you to apply Heidegger’s theory of the hermeneutic circle to interpret and answer the following question.”

    Long-form version of the template: “I want you to apply Heidegger’s theory of the hermeneutic circle to interpret and answer the following question. Move between the parts and the whole of the situation, considering how understanding each detail depends on the broader context and how the overall meaning emerges through that interplay. Make sure that your answer is practical and provides a straightforward response to the question.”

    https://www.forbes.com/sites/lanceeliot/2025/11/11/prompt-engineering-urges-hermeneutic-prompting-as-a-powerful-technique-unlocking-the-true-value-of-generative-ai/