# מה הצפוי להמשך לזיהוי תוכן לא מושלם ב-Discourse AI

**URL:** https://meta.discourse.org/t/what-s-next-for-nsfw-detection-in-discourse-ai/320653
**Category:** Announcements
**Tags:** automation, ai, ai-nsfw
**Created:** [8 באוגוסט,‏ 2024,‏ 3:18am UTC](https://meta.discourse.org/t/what-s-next-for-nsfw-detection-in-discourse-ai/320653 "2024-08-08T03:18:27Z")
**Posts on this page:** 1
**Showing post:** 1

<div class="post-metadata">

### Author: ![Saif](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/saif/32/318253_2.png) [@Saif](https://meta.discourse.org/u/Saif)
#### Post date: [8 באוגוסט,‏ 2024,‏ 3:18am UTC](https://meta.discourse.org/t/what-s-next-for-nsfw-detection-in-discourse-ai/320653/1 "2024-08-08T03:18:27Z")

</div>

If you’ve [seen our previous announcement](https://meta.discourse.org/t/whats-next-for-toxicity-detection-in-discourse-ai/320283), then you are aware that we are shifting to prefer LLM preferred solutions as they provide a vastly superior experience. ~~Hence, coming soon we’ll be decommissioning the NSFW module in favor of [Discourse AI Post Classifier - Automation rules](https://meta.discourse.org/t/discourse-ai-post-classifier-automation-rule/281227)~~_(See update below)_

### Why are we doing this?

For the same reasons…

> [@What's next for Toxicity detection in Discourse AI](https://meta.discourse.org/t/whats-next-for-toxicity-detection-in-discourse-ai/320283/1):
>
> Previously using the Toxicity module meant…
> 
> - You were stuck using a single pre-defined model
> - No customization for your community-specific needs
> - Confusing threshold metrics
> - Subpar performance
> 
> LLMs have come a long way and can now provide a better performing and customizable experience.

### Whats new?

> [@What's next for Toxicity detection in Discourse AI](https://meta.discourse.org/t/whats-next-for-toxicity-detection-in-discourse-ai/320283/1):
>
> [Discourse AI - AI triage](https://meta.discourse.org/t/discourse-ai-post-classifier-automation-rule/281227) can be used to triage posts for Toxicity (amongst other ways) and enforce communities to specific code of conducts. This means…
> 
> - Multiple LLMs supported for different performance requirements
> - Easy to define what and how content should be treated
> - Customizable prompts for community-specific needs
> - Flag content for review
> 
> and much more.
> 
> To assist with the transition we have already written out guides
> 
> - [Setting up toxicity/code of conduct detection in your community](https://meta.discourse.org/t/setting-up-toxicity-code-of-conduct-detection-in-your-community/320257)
> - [Setting up spam detection in your community](https://meta.discourse.org/t/setting-up-spam-detection-in-your-community/300427)
> - [Setting up NSFW detection in your community](https://meta.discourse.org/t/setting-up-nsfw-detection-in-your-community/330196)

### What happens to NSFW?

~~This announcement should be considered **very early** , until we are ready to decommission you can continue to use NSFW. When we do it, we will be decommissioning the module, and removing all code from the Discourse AI plugin and associated services from our servers. The deprecation will **only** happen after AI Triage is ready to handle images which will be done soon.~~

👉🏾 **Update:** NSFW module has now been officially removed from Discourse, this includes all related site settings and features. We are now urging users to transition to using [Discourse AI - AI triage](https://meta.discourse.org/t/discourse-ai-ai-triage/281227) and follow the guides listed above.

Business and Enterprise customers will see the following under `What's New` in the admin settings on their sites, allowing them to enable Discourse hosted LLMs to power AI triage at no extra cost.

 ![The image shows a notification from Discourse AI indicating that the toxicity and NSFW modules have been removed and replaced with the Automation plugin for AI triage. (Captioned by AI)](https://global.discourse-cdn.com/meta/original/4X/f/3/a/f3a159163de0f96f81cd4ddef9266db4030fda1a.png)

---

_[View the full topic](https://meta.discourse.org/t/what-s-next-for-nsfw-detection-in-discourse-ai/320653)._