Discourse 3.4 introduces major improvements aimed at simplifying community management, including AI-powered spam detection, enhanced sentiment analysis, and a unified admin experience. All hosted customers now have access to Discourse AI for spam filtering, topic summarization, and sentiment insights—powered by built-in LLMs without third-party tools. The new “Ask Discourse” AI help center jordan-violet makes troubleshooting faster, while mobile app enhancements and Discourse Discover integration help users discover new communities. A new Starter plan ($20/mo) lowers the barrier to entry, and instant, prorated plan upgrades offer flexibility as communities grow. Setup is now more intuitive with a refined wizard and preview pane. Developers benefit from updated APIs for post-menu and topic-list customization, Font Awesome 6 icons, and upgraded dependencies (Rails 7.2, Ember 5.12, Postgres 15), plus a new Developer Toolbar. Community members express excitement, with StefanoCecere already testing 3.5.0.beta1 and darkpixlz praising multi-draft topic support. jordan-violet asks about model recommendations for different AI tasks; awesomerobot notes variability by site and budget, while sam references existing docs and confirms GPT-4o is generally suitable. eviltrout applauds the admin UI progress and a playful game shoutout. The team invites community participation for future testing, with jordan-violet offering help and kyle987 thanking the team for the update.
Here at Discourse, we’re always striving to make community management easier. That’s why Discourse 3.4 has introduced a more consistent admin experience, a simplified signup and login flow, mobile app improvements, and AI-powered tools to fight spam and help manage your community.
Love you!
and we are already with Discourse 3.5.0.beta1-dev 
Many thanks for finally addressing multiple topic drafts! Better late than never 
Everyone at Discourse, both team members & contributors, have been very busy! Thank you for making Discourse… Discourse! 
I would love to know if Discourse has any recommendations on different models to use for different use cases.
There are so many foundational models today and over time they’re showing what they are and are not good at.
I’d love to know what models are best for spam, which are best for sentiment, etc. For example, I have gpt-4o and when enabling spam was told I could not use this model with this feature.
I think it’s hard to recommend specific models because there’s so much variation from site to site, even within specific tasks (and also budget constraints)… but as far as this goes:
is this still the case today? I’m able to use 4o for spam on a test site, but if you’re still having issues send us a message and we’ll take a closer look!
Just went back again to screenshot the error for you and now, of course, it doesn’t come up. Not sure if good or not
Right, million dollar question. I’m hoping eventually Discourse can come up with recommendations though through model testing with neptune.ai?
we did have this documentation topic:
It is very hard to keep it up to date cause every day there are new models released. As a general rule though GPT4-o is good for pretty much anything in AI.
Evals are something we are thinking about and testing, for sure.
It’s so cool to see progress. That admin interface has come so far! Also, I appreciate the subtle shout out my game got in the blog post 
Big 
to everyone working on Discourse.
Please let me know if you ever want any participation, always happy to help!
Thanks for the update