# RSS Polling Onebox **URL:** \ **Category:** Plugin\ **Tags:** rss-polling\ **Created:** [September 25, 2026, 7:27pm UTC](https://meta.discourse.org/t/rss-polling-onebox/413361 "2026-09-25T19:27:26Z")\ **Posts on this page:** 1\ **Showing post:** 5
**Author:** ![satonotdead](https://sea3.discourse-cdn.com/meta/user_avatar/meta.discourse.org/satonotdead/32/447830_2.png) [@satonotdead](https://meta.discourse.org/u/satonotdead)\ **Post date:** [September 26, 2026, 4:49pm UTC](https://meta.discourse.org/t/rss-polling-onebox/413361/5 "2026-09-26T16:49:19Z")
> [@Sailor](#): > > An LLM summary as an option is an interesting idea. Discourse AI’s gists summarise a topic’s content, which here is just the link, so it would mean the plugin reading the article and handing it to the forum’s configured model. I’d want it opt-in, since it costs tokens and swaps the author’s words for generated ones - but I’ve noted it. Nice, Peter, thanks for considering it! You see, the prompt can be handled to not change the author’s tone and maintain the result only from the specified data from the links. That is the approach used at [https://ask.discourse.com](https://ask.discourse.com), where the responses are tightly bound to docs and a curated base. The model does not use its training data almost at all, and I think that is the most clever and productive way to actually use the technology. There also are inexpensive models that are really good at summarizing. So I hope it will be implemented; it can improve the reader experience and also the SEO/IA-SEO practices as well. --- _[View the full topic](https://meta.discourse.org/t/rss-polling-onebox/413361)._