Account Management: Sensitive Content Filter

– In an effort to help
moderate the use of AI safely, Jasper does have a content filter. Basically, we don't want Jasper writing anything or creating anything that would cause you
to get fired from work, because well, we got your back. (upbeat music) 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. Meaning, the filter is
going to flag content based on what the projected
intent of that content could be. From what we know, the
filter can make mistakes, but it's built to err
on the side of caution. A warning message will appear in your app to give you guidance that
something in your input is not passing the content filter. So what should you do when
you get the warning message? First, look at your paragraph as a whole and try to understand what potential intent is getting flagged.

Then, try to replace that word, or words, that are getting flagged. If you don't know what the
word is that's getting flagged, try to look for potentially
unsafe, sensitive words. They should stand out. For example, if I input: "List the best ways "to hurt a large population
of baby puppies…" (record scratches) (beeping) It's gonna get flagged. As you can see, it got
flagged due to the filter reading and recognizing
the inappropriate intent of what I'm asking it to write about, like hurting a bunch of baby puppies. As I mentioned, the filter isn't perfect, but it does work well. If you need to enable a more
flexible content filter, we might be able to help you out.

Some accounts do run into content filters for topics that we would consider safe. These are flagged in error. And after reviewing them, we might be able to move those accounts over to a more flexible content filter. If you believe your account
is getting filtered in error, send us an email at 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. And 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 mistakenly. Again, there's a reason
for this content filter.

We want to keep you safe. We hope this video helps you understand how we here at Jasper want to use AI responsibly and safely. (booming chime reverberates).

As found on YouTube

Get Your Resources Here:

You May Also Like