AI spam post detector?

[H00lio]

I can only see a deleted thread here on this topic.

Is there any hope someone will or (can) build one?

 

[Alpha1]

Most likely you would need connection with several LLM models as some will perform better than others and the costs are different. These can easily rake up. Here is how Discourse does it. The details are relevant to creating such plugin:

Discourse AI - Spam detection

🔖 This guide explains how to configure and use Discourse AI’s spam detection feature, including the setup process, scanning criteria, classification logic, customizations, and contrasts with AI triage. 🙋 Required user level: Administrator 📣 This is now default turned on for Starter and...

meta.discourse.org

Discourse AI - Large Language Model (LLM) settings page

🔖 This guide covers the LLM settings page which is part of the Discourse AI plugin. 🙋 Required user level: Administrator The dedicated settings page is designed to have everything related to Large Language Models (LLMs) used for Discourse AI features in one place. 🖐 Depending on the...

meta.discourse.org

For AI to interact with XenForo it needs an AI framework. There is a relevant suggestion here:

Thread 'Centralized AI API Framework for Enhanced Integration'

Jan 12, 2025

Feature Overview:
Introduce a centralized AI API framework in XenForo, enabling connections to multiple AI providers like OpenAI, Mistral, Groq, and Anthropic. Administrators can then easily configure and manage AI integrations directly through the admin panel (API keys...). And extensions can then use these with ease.

Key Capabilities:

• Support for multiple AI providers with easy switching.
• Tools for developers to integrate AI features, such as content moderation, automated replies, and personalized recommendations. Without having to ask for API keys.

...

• sdev
• Replies: 3
• Forum: XenForo suggestions

•