I would like to request the removal of restrictions on specific flagged keywords when using Merlin AI. Currently, any mention of certain keywords results in the system flagging or rejecting the entire process, which creates significant difficulties in writing.

For example, in virtually every American novel or literary work, there is frequent use of terms that appear to trigger these keyword-based rejections. This restrictive filter makes it impossible to write creatively, especially when the content is both contextually appropriate and non-violent.

Such limitations greatly reduce the usability of AI for professional or creative projects. I ask for a revision of this mechanism, perhaps by implementing a clearer context-based review process or allowing flagged content to be bypassed under certain oversight conditions. This change would make Merlin AI significantly more effective for writers.

Why was I blocked? Please fix this

It's really hard to write when the messages keep getting flagged for simple words like, "fight", "hate", or "punch", even when the context is non-violent. I continue to get "Watch out arthur!" messages, and it hinders my experience and creativity.

Hello, how are you? I was having problems with the restriction filters, but it seems that Merlin is almost back to normal, I don't know if the problem was solved or not, thank you for leaving Merlin accessible again, without so many restrictions.

Now the application is complete garbage, now the phrase "Watch out Arthur! Our filters have flagged your query!" appears, why? Remove this urgently, it used to be much better without this, now it's broken