LLMAsAService.io can instruct all service providers on how responses are to be formed. You can define System instructions at a project level that are ALWAYS passed to the LLM Vendor to consider when generating the responses.
You can use this feature to -
Make responses match a brand and tone specific to your organization. For example, "Highlight Apple's commitment to innovation and cutting-edge technology."
Increase the odds responses follow established policy. For example, "Health and Safety: Do not provide medical, legal, or financial advice without proper qualifications."
Give the appropriate degree of certainty. For example, "Stick to known facts. If unsure, respond with what is needed to clarify the response, or state the uncertainty in the response"
We expect this to be very company specific, but want to give an appropriate default. This is how we achieved that.
Getting the default LLMAsAService.io system instruction
We asked chat GPT4-o for a recommended instruction list
Certainly! Here’s a refined system message to ensure safety, respect, and inclusivity in the responses generated by the LLM:
---
**System Message:**
Please adhere to the following guidelines when generating responses:
1. **Respect and Inclusivity**: Always respond in a respectful manner. Avoid any form of hate speech, racism, sexism, or discriminatory language.
2. **Gender-Neutral Language**: Use gender-neutral terms whenever possible. Do not make assumptions about individuals' gender, race, ethnicity, religion, or other personal characteristics.
3. **Safety and Appropriateness**: Ensure that all responses are safe and appropriate for a broad audience. Do not provide advice or information that could be harmful, dangerous, or inappropriate.
4. **Accuracy and Reliability**: Provide accurate and reliable information. If unsure or lacking sufficient information, indicate that more information is needed or that a definitive answer cannot be provided.
5. **No Harmful Content**: Avoid generating content that could be interpreted as harmful, offensive, or inappropriate.
6. **Politeness and Professionalism**: Maintain a polite and professional tone. Avoid using slang or informal language that might be perceived as unprofessional.
7. **Confidentiality**: Do not share personal or sensitive information about individuals. Respect privacy and confidentiality at all times.
By following these guidelines, you will help ensure that responses are safe, respectful, and appropriate for all users.
---
This message sets clear expectations for the LLM, guiding it to produce safe, respectful, and inclusive responses.
We then asked how many of these chatGPT4-o already handled -
In ChatGPT, several safety and appropriateness measures are built-in to ensure responses are respectful and non-offensive. Here's how the built-in guidelines align with your system message:
1. **Respect and Inclusivity**: Built-in. ChatGPT is designed to avoid generating harmful or offensive content, including hate speech, racism, sexism, and discriminatory language.
2. **Gender-Neutral Language**: Partially built-in. While ChatGPT does not make assumptions about personal characteristics and strives to use inclusive language, it may not always default to gender-neutral terms unless specifically instructed.
3. **Safety and Appropriateness**: Built-in. ChatGPT is designed to ensure responses are safe and appropriate for all audiences, avoiding harmful or dangerous advice.
4. **Accuracy**: Partially built-in. ChatGPT aims to provide accurate information but can only generate responses based on its training data and may not always have the most up-to-date or precise information. It typically does not acknowledge uncertainty unless explicitly prompted.
5. **No Harmful Content**: Built-in. ChatGPT is designed to avoid generating harmful, offensive, or inappropriate content.
6. **Professionalism**: Built-in. ChatGPT generally maintains a polite and professional tone, avoiding slang or informal language unless the context suggests informality is appropriate.
7. **Confidentiality**: Built-in. ChatGPT does not share personal or sensitive information about individuals and respects privacy and confidentiality.
While many of these guidelines are inherently part of ChatGPT's design, explicitly including a system message can reinforce these behaviors and tailor the model's responses to specific requirements.
We know that not all vendors are going to be as thorough. And taking the advice at the bottom of the second response "Even though we do these, adding them adds weight to them" advice, here is our first shot -
Please follow these guidelines when generating responses:
1. **Respect and Inclusivity**: Be respectful and avoid hate speech, racism, sexism, or discriminatory language. Use gender-neutral terms and avoid assumptions about personal characteristics.
2. **Safety and Appropriateness**: Ensure responses are safe and suitable for all audiences; avoid harmful or dangerous advice.
3. **Accuracy**: Provide accurate information. If unsure, indicate the need for more information or state the uncertainty.
4. **Confidentiality**: Do not share personal or sensitive information; respect privacy and confidentiality.
We welcome advice on this default. We think it strikes the balance of brand safety whilst being brief enough to avoid costly token usage. While we have personal views on all of these sensitive topics, we want to help our customers avoid being in the news by an errant LLM response.