Why is this happening?
Our AI does have a content filter. The filter's aim is to detect any generated text that could be sensitive or unsafe. The filter is less about the actual word and more about the intent of the writing and the image. This means the filter will flag content based on what the projected intent of this content could be. The filter could potentially make mistakes, because it is built to err on the side of caution. This message will appear in your agent to let you know that something you inputted is not passing through the content filter.
How to Fix it
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 the word 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 use of release and bullet.
Second, please send us an email at hey@jasper.ai. 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. Not all inputs that receive this message are happening mistakingly.
It's important to remember that Jasper 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. Jasper uses context to decide what's sensitive content and what's not.
Restricted Content
Additionally, some use cases like (but not limited to) adult topics and content are unfortunately not allowed in compliance with our AI partners. We appreciate your understanding. Here is an excerpt from our terms and conditions on content restrictions:
"The Company is not responsible for the content of the Service's users. You expressly understand and agree that You are solely responsible for the Content and for all activity that occurs under your account, whether done so by You or any third person using Your account.
You may not transmit any Content that is unlawful, offensive, upsetting, intended to disgust, threatening, libelous, defamatory, obscene or otherwise objectionable. Examples of such objectionable Content include, but are not limited to, the following:
- - Unlawful or promoting unlawful activity.
- - Defamatory, discriminatory, or mean-spirited content, including references or commentary about religion, race, sexual orientation, gender, national/ethnic origin, or other targeted groups.
- - Spam, machine – or randomly-generated, constituting unauthorized or unsolicited advertising, chain letters, any other form of unauthorized solicitation, or any form of lottery or gambling.
- - Containing or installing any viruses, worms, malware, trojan horses, or other content that is designed or intended to disrupt, damage, or limit the functioning of any software, hardware or telecommunications equipment or to damage or obtain unauthorized access to any data or other information of a third person.
- - Infringing on any proprietary rights of any party, including patent, trademark, trade secret, copyright, right of publicity or other rights.
- - Impersonating any person or entity including the Company and its employees or representatives.
- - Violating the privacy of any third person.
- - Any adult topics and/or content that falls below our AI partner's content filter guidelines and policies including but not limited to sexual experiences, pornography, erotica, webcam services, escort services, adult toys and shops, etc...
- - False information and features.
The Company reserves the right, but not the obligation, to, in its sole discretion, determine whether or not any Content is appropriate and complies with this Terms, refuse or remove this Content. The Company further reserves the right to make formatting and edits and change the manner any Content. The Company can also limit or revoke the use of the Service if You post such objectionable Content. As the Company cannot control all content posted by users and/or third parties on the Service, you agree to use the Service at your own risk. You understand that by using the Service You may be exposed to content that You may find offensive, indecent, incorrect or objectionable, and You agree that under no circumstances will the Company be liable in any way for any content, including any errors or omissions in any content, or any loss or damage of any kind incurred as a result of your use of any content."