Have AI check for inappropriate post or at least words and flag the post

[EricGT]

@mattdm

This is, indeed, one of the features.

Yes, thanks.

Discourse AI - Toxicity

This topic covers the configuration of the Toxicity module of the Official Discourse AI Plugin plugin. Feature set The Toxicity modules can automatically classify the toxicity score of every new post and chat message in your Discourse instance. Optionally, you can also enable automatic flagging of content that crosses a threshold. Classifications are stored in the the database, so you can enable the plugin and use Data Explorer for reports of the classification happening for new content in Dis…

Asked because I am a moderator on the OpenAI site and they do have the Discourse AI plugin running. Since I am not an admin on the site will need get their feedback and input as this would be of benefit for the site.

---

Side note: Being an admin on one site and being able to see all of the Discourse settings is nice. But then being a moderator on another site and knowing about such and not being able to see the setting is really frustrating. I don’t expect moderators to be given the right to change settings but being able to at least see them as read-only would make it easier at times. This would also include being able to see other options besides just the Discourse settings, settings such as themes and plugins would be desired.