I am a professional writer working on a literary project using a ChatGPT Pro account. I’m trying to write in a soft-R framework; the moderation layer now interprets normal literary discussion as unsafe. Today it got triggered by the word “puberty” when I wrote of a book that the elderly adult character read before he hit puberty. The moderation is to the point where I can’t work freely. To be clear, this is a novel that could be read in a public school, not some tawdry tale meant to be sold at grocery store checkout. My work has hit a brick wall and I need help. The novel is half written, and I’m about to travel overseas to finish my research and writing for it.
#Faulty Moderation for Professional Writer
vast totem
hazy ploverBOT
Hi @vast totem. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
I'm sorry to hear about your experience—OpenAI’s moderation system is designed to prevent harmful or inappropriate content, but it can sometimes be overly cautious and flag safe, professional, or literary material as unsafe. This is known as a “false positive,” and it’s a recognized limitation of automated moderation systems. OpenAI prioritizes caution to minimize the risk of missing genuinely harmful content, which can unfortunately result in some safe outputs being incorrectly flagged, especially in nuanced or context-dependent scenarios like literary writing Why are Playground outputs misclassified as unsafe?.
If you believe your content was misclassified, you can provide feedback directly in the interface (for example, by clicking a thumbs-down icon next to the moderation warning in Playground or ChatGPT). This feedback helps OpenAI improve its moderation systems over time.
Currently, there is no way for end users to disable or bypass the moderation layer in ChatGPT, even for professional or literary use cases. OpenAI’s documentation suggests that moderation thresholds are set to balance safety and user experience, but these thresholds may not always align with every user’s needs. For developers building their own applications, it is possible to adjust moderation thresholds or implement custom moderation logic using the Moderation API, but this is not available within the standard ChatGPT product How to use the moderation API.
If this issue is significantly impacting your work, you may consider reaching out to OpenAI Support through the Help Center to explain your situation and see if they can offer any guidance or solutions. You can contact support by opening the chat bubble at the bottom-right of help.openai.com.
OpenAI is aware of these challenges and encourages users to report misclassifications so the system can be improved. However, at this time, there is no documented way to request a moderation exemption for specific professional or literary projects within ChatGPT Pro.
If you need more flexibility, you might consider using the OpenAI API directly, where you can implement your own moderation workflow and potentially set custom thresholds, but this requires programming and is outside the standard ChatGPT interface How to use the moderation API.
In summary:
- False positives can occur, especially with sensitive terms in literary contexts.
- You can report misclassifications, but cannot disable moderation in ChatGPT.
- For more control, consider using the API with custom moderation logic.
- Contact OpenAI Support for further assistance if this is blocking your work.