Weekly AI Activity Summary on meta.discourse.org
Overview
This week’s discussions on meta.discourse.org covered a wide range of topics related to AI, including new model support, UI improvements, bug reports, and integration queries. The community explored the potential of OpenAI’s latest models, o1-preview and o1-mini, and discussed their cost-effectiveness and compatibility with Discourse. Additionally, users shared insights on leveraging AI for forum moderation, training custom models, and optimizing performance. Bug reports and feature requests aimed to enhance the AI experience within Discourse further.
Interesting Topics
-
OMG The Discourse AI Helper is pretty great
- pfaffman discovered the AI helper could add a watermark to the background using CSS, showcasing its versatility in theme customization.
-
Support for o1-preview & o1-mini
- MarcP inquired about supporting OpenAI’s new models, o1-preview and o1-mini, which promise cost-efficiency and advanced reasoning capabilities.
-
- Moin raised a question about a Windows shortcut for the AI proofreading feature, leading to a pull request to address the issue.
-
Discourse AI Post Classifier - Automation rule
- Overgrow explored the potential of using the AI post classifier with the post approval queue, suggesting automated approval or rejection based on the classifier’s output.
-
- Users reported an issue with the AI helper not displaying correctly on certain devices, prompting sam to confirm ongoing work to resolve the edge case.
-
- tpetrov raised a question about the “Max Context Posts” setting for the AI bot, leading to a discussion on its intended behavior and potential improvements.
-
How to add a ChatGPT trained AI to discourse?
- exlabs inquired about integrating a custom ChatGPT model trained on user manuals into Discourse, prompting suggestions from the community.
-
How to open access of ai related topics for normal users
- whitewaterdeu sought guidance on granting access to AI-related topics for regular users, leading to a clarification on the distinction between related and suggested topics.
-
Posts too long for PostSentimentAnalysis
- Overgrow reported an issue with the sentiment analysis feature failing on unusually long posts, leading to a discussion on potential solutions and configuration options.
Activity
-
pfaffman shared their experience using the AI helper to add a watermark to the background via CSS, showcasing its versatility in theme customization.
-
MarcP inquired about supporting OpenAI’s new models, o1-preview and o1-mini, and their potential cost-effectiveness.
-
Moin raised a question about a Windows shortcut for the AI proofreading feature, leading to a pull request to address the issue.
-
Overgrow explored the potential of using the AI post classifier with the post approval queue and reported an issue with the sentiment analysis feature failing on long posts.
-
sam confirmed ongoing work to resolve an edge case where the AI helper was not displaying correctly on certain devices.
-
tpetrov raised a question about the “Max Context Posts” setting for the AI bot, leading to a discussion on its intended behavior.
-
exlabs inquired about integrating a custom ChatGPT model trained on user manuals into Discourse.
-
whitewaterdeu sought guidance on granting access to AI-related topics for regular users.
-
merefield highlighted the existing Chatbot feature, which can be trained on a site’s posts.
-
MachineScholar inquired about deleting files uploaded for the AI Persona.
-
Acacia_Bengo shared their experience building a custom integration for AI forum moderation, leveraging NLP and sentiment analysis.
-
aas reported an issue with the AI bot not responding after an update and suggested recreating the persona as a potential solution.
Thanks for reading, and I’ll see you again next week! 