# זיהוי דואר זבל באמצעות AI של Discourse מחליף את תוסף Akismet

**URL:** https://meta.discourse.org/t/discourse-ai-spam-detection-replaces-akismet-plugin/354602
**Category:** Announcements
**Tags:** akismet, ai, spam
**Created:** [10 במרץ,‏ 2025,‏ 5:56pm UTC](https://meta.discourse.org/t/discourse-ai-spam-detection-replaces-akismet-plugin/354602 "2025-03-10T17:56:01Z")
**Posts on this page:** 1
**Showing post:** 11

<div class="post-metadata">

### Author: ![patrickemin](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/patrickemin/32/520162_2.png) [@patrickemin](https://meta.discourse.org/u/patrickemin)
#### Post date: [7 ביוני,‏ 2025,‏ 1:11pm UTC](https://meta.discourse.org/t/discourse-ai-spam-detection-replaces-akismet-plugin/354602/11 "2025-06-07T13:11:19Z")

</div>

Thanks for the information, it was not obvious my self hosted Discourse site was not protected against spam. I assumed wrongly it was. OMO this info should be more prominently put forward for would be Discourse admins envisaging self hosting heir site.

I will look for that Discourse AI functionality, which I never considered before due to budget restrictions.

I try here to list the actions for an admin on a self hosted site like me, can you tell me if I am right?

1. First I should install the Discourse AI plugin? [Discourse AI](https://meta.discourse.org/t/discourse-ai/259214)

2. Second, I should setup a LLM like explained here? [Discourse AI - Large Language Model (LLM) settings page](https://meta.discourse.org/t/discourse-ai-large-language-model-llm-settings-page/319903)

3. Then I should setup a spam detection mechanism like explained here? [Discourse AI - Spam detection](https://meta.discourse.org/t/discourse-ai-spam-detection/343541)

---

_[View the full topic](https://meta.discourse.org/t/discourse-ai-spam-detection-replaces-akismet-plugin/354602)._