Why am I getting a "sensitive content" message?
Why is this happening?
Our AI does have a content filter. The filter's aim is to detect any generated text that could be
unsafe. The filter is less about the actual word and more about the intent of the writing. Meaning, the filter is going to flag content based upon what the projected intent of this content could be. From what we know, the filter will make mistakes but it is built to err on the side of caution. This message will appear in your app to give you guidance that something in what you inputted is not passing through the content filter.
What to do once you get the message?
First, look at your paragraph as a whole and try to understand what potential intent is getting flagged. Then, try to replace the word that is getting flagged. If you do not know what the word is that is getting flagged try looking for "unsafe" or "sensitive" words.
Example: This special event would
release some magic
bullet to eliminate all of my relationship difficulties, triggering everlasting love and joy in my life.
- This got flagged due to the
unsafefilter of using releasing bullets.
Second, please send us an email at [email protected] and be patient. We will respond and review each use case that could be getting a false positive within the content filter. In your message please include what input was flagged. Please note, there will be use cases that are being blocked validly by the content filter as well. Not all inputs that receive this message are happening mistakingly.
Why can't you give us a list of "sensitive" words
It's important to remember that Jarvis is trained on intent and context, not a series of words. There isn't a list of "sensitive" words or else we'd share them with you. Jarvis uses context to decide what's sensitive content and what's not.
Additionally, some use cases like adult topics and content are unfortunately not allowed in compliance with our AI partners. We appreciate your understanding.