# Frustrations on AI spam detector

**URL:** https://meta.discourse.org/t/frustrations-on-ai-spam-detector/388947
**Category:** Support
**Tags:** ai, spam
**Created:** [19 november 2025 om 03:20 UTC](https://meta.discourse.org/t/frustrations-on-ai-spam-detector/388947 "2025-11-19T03:20:02Z")
**Posts on this page:** 1
**Showing post:** 1

<div class="post-metadata">

### Author: ![lilydjwg](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/lilydjwg/32/515838_2.png) [@lilydjwg](https://meta.discourse.org/u/lilydjwg)
#### Post date: [19 november 2025 om 03:20 UTC](https://meta.discourse.org/t/frustrations-on-ai-spam-detector/388947/1 "2025-11-19T03:20:02Z")

</div>

I’m trying to setup the AI spam detector for my own Discourse instance, but have several questions:

The system prompt of spam detector persona can’t be edited. I can create a new persona but there is no field to make Discourse know that it is going to be used as a spam detector?

I want to use Qwen3 as the LLM for the task. There is no preset for Qwen3 so I’m going to create a custom one. But there isn’t a Qwen3Tokenizer either. What does the tokenizer do here? Does QwenTokenizer work for Qwen3?

Or, is there an easier option that I can setup a webhook-like service and Discourse calls it on new topics / posts?

---

_[View the full topic](https://meta.discourse.org/t/frustrations-on-ai-spam-detector/388947)._