Ensure custom instructions follow OpenAI's Usage Policies
OpenAI's safety measures prevent saving or acting on instructions violating usage policies.
Be aware that ChatGPT may refuse or ignore instructions that lead to responses violating usage policies. The Moderation API helps ensure instructions are not saved if they violate policies.
Risk
Instructions that violate OpenAI's Usage Policies.
Why
To maintain safety and prevent misuse of the AI model.
What it does and when to use it
OpenAI has implemented safety measures, including the Moderation API, to prevent the saving or execution of custom instructions that violate their Usage Policies. ChatGPT may refuse or ignore such instructions to ensure responsible AI use.
Sources and credit
- Custom instructions for ChatGPT ↗OpenAI · OpenAI News · Jul 20, 2023 · paraphrased
First seen on Subvolts Jul 20, 2023. Updated Sep 11, 2026. Spotted a problem? Tell us.
Where it shows up
- Custom instructions for ChatGPTOpenAI · OpenAI News · Jul 20, 2023
Related in the PlaybookPlaybook →
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- TemplateTemplate for building an AI tool tailored to your workA structured approach to defining and building a custom AI tool for specific business needs. · 15 min
- WorkflowWorkflow for building an AI tool like a customer FAQ assistantSteps to create a specific AI tool for handling customer inquiries using ChatGPT. · 60 min
- Case studyBuild a personalized weekly meal planner using ChatGPTA working mom uses ChatGPT to create a personalized weekly meal planner, including a shareable website and automated grocery lists. · 30 min
- Setting tipHow to create your first OpenAI Dot agentSteps to set up an always-on AI agent using the ChatGPT desktop app or website. · 10 min
- Setting tipNaming and invoking your OpenAI Dot agentHow to name your AI agent and call it using its unique identifier. · 5 min
- ChecklistReview content and audience before sharing ChatGPT conversationsCheck shared content and who can access it before sending a ChatGPT conversation link. · 5 min
Questions people ask
- Which AI tools does this work with?
- The sources used it with ChatGPT.
- Where did this come from?
- OpenAI (OpenAI News). Subvolts collected, normalized and credited it; the link above opens the original.