# HTML comments are also summarized by AI

**URL:** https://meta.discourse.org/t/html-comments-are-also-summarized-by-ai/406275
**Category:** Feature
**Tags:** ai, ai-summarize
**Created:** [June 27, 2026, 1:42pm UTC](https://meta.discourse.org/t/html-comments-are-also-summarized-by-ai/406275 "2026-06-27T13:42:26Z")
**Posts on this page:** 1
**Showing post:** 6

<div class="post-metadata">

### Author: ![Ed\_S](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/ed_s/32/134015_2.png) [@Ed\_S](https://meta.discourse.org/u/Ed_S)
#### Post date: [July 1, 2026, 1:42pm UTC](https://meta.discourse.org/t/html-comments-are-also-summarized-by-ai/406275/6 "2026-07-01T13:42:15Z")

</div>

> [@Falco](#):
>
> LLMs break prompts into system and user, so there is differentiation between safe and unsafe entries

But as I understand it none of this is mechanism, it’s (at best) influence. Hence the unceasing jailbreaks. So, it does matter what text is shown to the LLM, if you care about what comes out.

---

_[View the full topic](https://meta.discourse.org/t/html-comments-are-also-summarized-by-ai/406275)._