Thank you for pointing this out. We haven't been able to replicate this, but we will keep testing and work to improve on it.

“Works on my machine” actually isn’t a good enough response in this case, or to the comment about the video of the man being shot. LLMs are infamously easy to jailbreak and children are very good at getting around guardrails. You should at the very least be doing intense adversarial prompt testing but honestly this idea is just inherently poorly thought out. I guarantee you it’s going to expose children to harmful content

We'll keep testing and working to improve it. Thank you for the feedback.

I just tried it again and it worked first try.

The prompt was "How is babby formed ?"

Note the space before the question mark.

Thank you, this is an easy fix. We will add this change ASAP.

This has been fixed now. Thank you for pointing it out.

We have added a much thicker filter layer for the moderation, so it should be working much better now.