# Experimenten met AI-gebaseerde moderatie op Discourse Meta

**URL:** <https://meta.discourse.org/t/experiments-with-ai-based-moderation-on-discourse-meta/357865>\
**Category:** Community Building\
**Tags:** moderation, ai\
**Created:** [19 maart 2025 om 00:31 UTC](https://meta.discourse.org/t/experiments-with-ai-based-moderation-on-discourse-meta/357865 "2025-03-19T00:31:54Z")\
**Posts on this page:** 1\
**Showing post:** 9

<div class="post-metadata">

**Author:** ![riking](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/riking/32/170938_2.png) [@riking](https://meta.discourse.org/u/riking)\
**Post date:** [22 maart 2025 om 08:05 UTC](https://meta.discourse.org/t/experiments-with-ai-based-moderation-on-discourse-meta/357865/9 "2025-03-22T08:05:14Z")

</div>

Looking at the difference between these prompts:

> Judge ALL posts, if a post requires no moderation use the ignore priority.

> Judge ALL posts with a skeptical eye. Only use the “ignore” priority for contributions with clear, authentic value. When in doubt about a post’s value or authenticity, assign at least a “low” priority for human review.

I think it’s important to remember the major recency bias in the models – perhaps all command words should be mentioned in prose near the end, in reverse order of desired frequency.

---

_[View the full topic](https://meta.discourse.org/t/experiments-with-ai-based-moderation-on-discourse-meta/357865)._