# \#ai-toxicity

**URL:** https://meta.discourse.org/tag/ai-toxicity/637.md

[Latest](https://meta.discourse.org/latest.md) · [Categories](https://meta.discourse.org/categories.md) · [Tags](https://meta.discourse.org/tags.md)

---

## [Post flagging duplication and Spam/Toxicity Combo](https://meta.discourse.org/t/post-flagging-duplication-and-spam-toxicity-combo/396067)

<div class="topic-metadata">

**Author:** [@philh](https://meta.discourse.org/u/philh)\
**Replies:** 3\
**Last updated:** [February 16, 2026, 11:21pm UTC](https://meta.discourse.org/t/post-flagging-duplication-and-spam-toxicity-combo/396067 "2026-02-16T23:21:51Z")

</div>

Recently started using AI so I am likely to be missing a setting. With the upcoming retirement of Google Perspective API moved forward with the much avoided AI implementation. Both Spam and Toxicity are working but the…

---

## [What's next for Toxicity detection in Discourse AI](https://meta.discourse.org/t/whats-next-for-toxicity-detection-in-discourse-ai/320283)

<div class="topic-metadata">

**Author:** [@Saif](https://meta.discourse.org/u/Saif)\
**Replies:** 8\
**Last updated:** [December 5, 2024, 11:15pm UTC](https://meta.discourse.org/t/whats-next-for-toxicity-detection-in-discourse-ai/320283 "2024-12-05T23:15:51Z")

</div>

Today we are announcing good bye to the Discourse AI - Toxicity module :waving\_hand: in favor of Discourse AI - AI triage, leveraging the power of Large Language Models (LLMs) to provide a superior experience. Why ar…

---

## [AI flagging too sensitive](https://meta.discourse.org/t/ai-flagging-too-sensitive/297896)

<div class="topic-metadata">

**Author:** [@Shauny](https://meta.discourse.org/u/Shauny)\
**Replies:** 2\
**Last updated:** [March 31, 2024, 10:48am UTC](https://meta.discourse.org/t/ai-flagging-too-sensitive/297896 "2024-03-31T10:48:57Z")

</div>

I can’t find any specific information about this. When auto flagging toxic posts (something I want, because I want my community to be respectful and safe), it is being far too sensitive, flagged a post where someone cal…

---

## [Have AI check for inappropriate post or at least words and flag the post](https://meta.discourse.org/t/have-ai-check-for-inappropriate-post-or-at-least-words-and-flag-the-post/275755)

<div class="topic-metadata">

**Author:** [@EricGT](https://meta.discourse.org/u/EricGT)\
**Replies:** 2\
**Last updated:** [July 7, 2023, 10:05am UTC](https://meta.discourse.org/t/have-ai-check-for-inappropriate-post-or-at-least-words-and-flag-the-post/275755 "2023-07-07T10:05:46Z")

</div>

Suggestion Have AI check for inappropriate post or at least words and flag the post. Just read an entire topic of frustrated users, while many were able to convey their frustration in an appropriate manner, some were …