This week’s discussions on meta.discourse.org revolved around exploring new AI models, configuring AI-powered spam detection, managing AI personas and prompts, and leveraging semantic search capabilities. Users shared their experiences with various language models, discussed potential improvements, and sought guidance on optimizing AI features within the Discourse platform.
Interesting Topics
Don initiated a discussion on Trying out the new AI models, sharing their experiences with models like grok-2-1212 and Gemini Flash 2. Challenges with language detection, formatting issues, and search capabilities were highlighted.
Sam announced a new AI-powered Spam detection module in Discourse AI, providing better control over spam scanning. They shared a configuration guide and encouraged users to share their experiences.
MarcP sought assistance with the Semantic Search API, and Sam provided guidance on accessing pure embeddings search and using API keys to bypass rate limits.
Don requested a Topic AI Summary box closing feature, allowing users to close the summary box by clicking outside it, which awesomerobot acknowledged as a reasonable request.
roniw raised concerns about privacy and data access when using Discourse’s default LLM providers, to which Sam responded, assuring that Discourse LLMs are self-hosted and data is not shared with third parties.
Don initiated the discussion on Trying out the new AI models, sharing their experiences and seeking advice from MihirR and Sam on improving language detection and search capabilities.
roniw raised concerns about privacy and data access when using Discourse’s default LLM providers, and Sam provided assurances about Discourse’s self-hosting and data privacy practices.
This week on the Discourse meta forum, discussions centered around the AI-powered spam detection feature, the proposed “Solved Finder” tool, issues with AI summarization, and various bug reports and feedback related to AI capabilities. Users shared insights, reported bugs, and suggested improvements, fostering a collaborative environment for enhancing the AI integration within the Discourse platform.
Interesting Topics
AI powered Spam detection: Users discussed the rollout of the AI-powered spam detection feature, including confusion around enabling it on hosted accounts and issues with the toggle behavior. @sam provided clarification on the process, and @Saif mentioned an upcoming fix for the toggle issue.
Solved finder: @Don proposed adding a button for staff users to find potential solutions within a topic, similar to the AI summary feature. @sam suggested exploring custom prompts or a “Talk to my topic” option to address this need.
AI Summary Backfill is wasting tokens summarizing PMs: @markschmucker raised a concern about the AI Summary Backfill process summarizing private messages (PMs), which could be inefficient. @Falco acknowledged the issue and mentioned the possibility of introducing a setting to skip PMs, similar to the existing setting for embeddings.
Can’t change ai_embeddings_model: @Overgrow reported an issue with changing the ai_embeddings_model setting and enabling embeddings via the admin panel. @sam provided a link to a pull request that aimed to fix the problem.
How Does Regenerating Summaries Work?: @markschmucker shared their experience with regenerating summaries using a different LLM and the challenges faced when the backfill process stopped after reaching the specified age limit, despite some topics failing due to rate limits.
Feedback on AI Summarisation: @markschmucker sought clarification on addressing invalid summaries, referring to a previous comment by @sam about potential fixes through refactoring or adjusting personas.
@MachineScholar shared their perspective on the dilemma of summarizing PMs, suggesting that the decision should be based on the community type and the potential value of generating embeddings for PMs.
@markschmucker shared their experience with regenerating summaries using a different LLM and the challenges faced when the backfill process stopped after reaching the specified age limit, despite some topics failing due to rate limits.
The past week on meta.discourse.org saw a diverse range of discussions around Discourse’s AI features, with users sharing their experiences, providing feedback, and seeking support. The community explored the integration of Discord and Discourse, the potential of AI-powered Q&A bots, and the capabilities of AI-powered spam detection. Additionally, there were conversations around the new Smart Dates feature in Helper, the AI Persona Editor, and the availability of AI features on Standard and Business plans.
Interesting Topics
Do you use Discord and Discourse? sparked a discussion about the simultaneous use of Discord and Discourse, their respective strengths, and the potential for an AI-powered Q&A Discord bot that leverages Discourse as a knowledge base.
Write out smarter dates with AI introduced the new Smart Dates feature in Helper, which converts human-typed times and dates into Discourse-compatible, timezone-friendly formats.
AI powered Spam detection highlighted the efficiency of Discourse’s AI-powered spam detection system, with users reporting positive experiences in identifying and hiding spam posts.
Discourse AI - AI triage explored the AI triage feature, which automates the categorization of topics using AI models, leading to discussions around the scalability and configuration of this feature.
Proofreading is too creative highlighted an instance where the AI proofreading feature in Helper made overly creative suggestions, prompting a discussion on the appropriate level of creativity for such features.
Feature requests for AI-Summarization gathered requests for improvements to the AI Summarization feature, including prioritizing the summarization of recently updated topics and the ability to skip summarizing personal messages.
How to hide bot completely, for everyone addressed a user’s request to hide the Discourse AI bot from their community, leading to a discussion on the limitations and potential solutions.
Discourse AI - Helper continued the ongoing discussion around the Helper feature, with users providing feedback and seeking clarification on its functionality.
This week on the meta.discourse.org forum, discussions revolved around various aspects of the Discourse AI plugin, including new features, improvements, and user queries. The AI-powered spam detection tool garnered attention, with users seeking clarification on its configuration and usage. Additionally, the “Ask Discourse” feature, which allows users to interact with an AI persona for documentation assistance, was introduced. Other topics included sortable sentiment tables, handling detailed content with AI, regenerating topic summaries, and managing AI usage quotas.
Interesting Topics
@per1234 highlighted an issue where the default LLMs were not selectable on the ‘Spam’ tab, despite being configured. @sam acknowledged the problem and provided a solution.
@Saif introduced the Ask Discourse feature, which allows users to interact with an AI persona to search through documentation and answer common questions related to Discourse.
@noahl requested the ability to sort sentiment tables by highest to lowest numbers, making it easier to identify and address common sentiments.
@c12gene raised a concern about the AI bot’s inability to read and process detailed content encapsulated in [summary] tags, prompting discussions on prompt engineering and tool usage.
@awesomerobot provided an update on the issue of the AI summary box closing, with a link to the relevant pull request.
@EricGT shared insights on LLM prompt evaluations, emphasizing the importance of understanding prompt effectiveness for LLM development.
@sam announced an upcoming feature for hard caps on user group AI usage for AI bots and AI Helper, allowing admins to define limits on total tokens and requests per group.
@per1234 reported a bug where posts and accounts were not always restored when a flag from the Discourse AI spam detection was rejected.
@Moin sought guidance on hiding the bot completely from all users, prompting a discussion on the visibility of the bot in search results.
Activity
@Saif introduced the Ask Discourse feature and provided details on its functionality and accessibility in the initial post. @Ed_Sshared their experience with the resource and reported a broken link, which @Saif later updated.
@EricGTshared insights on the importance of LLM prompt evaluations for effective prompt engineering.
@per1234reported a bug where posts and accounts were not always restored when a flag from the Discourse AI spam detection was rejected.
@Moinsought guidance on hiding the bot completely from all users, prompting a discussion with @Saif on the visibility of the bot in search results.
@BrianCinquired about the possibility of allowing users to upload documents for the AI bot to read and process, and @Saifclarified that this use case is currently not supported.
@MarcPasked about updating summaries for single post topics that are frequently edited.
Thanks for reading, and I’ll see you again next week!
This week on the meta.discourse.org forum, discussions revolved around various AI-related topics, including a proposed moderation tool for formatting code using AI, the ongoing development of Discourse AI features, issues with AI summarization backfills, and the potential for uploading and discussing PDFs within the composer. Additionally, there were conversations about setting usage limits for AI, evaluating costs between different AI providers, handling AI-generated spam, and exploring the capabilities of AI bots and custom tools.
Interesting Topics
@merefield raised an idea for a moderation tool that would allow trusted users to format code blocks using AI, potentially improving readability and assisting new users who struggle with proper code formatting.
Discussions continued on the Discourse AI plugin, with @sam expressing interest in allowing users to upload large files and ask questions about the content using a persona-based approach.
@markschmucker encountered an issue where the AI summarization backfill process kept regenerating summaries for the same topic, even after a valid summary was already present. This led to a fix by @Roman_Rizzi to make the job more resilient.
@BrianC proposed a feature request to allow users to upload PDFs or text files directly in the composer and have the AI process and respond to questions about the content.
There was a discussion around setting per-group token and usage limits for AI features, with @sam clarifying that quotas are defined per group and applied per user, rather than being shared among users.
There was a bug report regarding posts and accounts not being restored when flags from Discourse AI spam detection were rejected, which @sam addressed with a fix.
Discussions took place around self-hosting embeddings for DiscourseAI, with @sam mentioning ongoing work to restructure the embedding configuration and plans to support multi-model embeddings.
@David_Ghost inquired about the ability of AI Triage to perform searches and avoid topics with similar titles based on creation dates.
@David_Ghost inquired about the ability of AI Triage to perform searches and avoid topics with similar titles based on creation dates, with @sam indicating that such “agent-like” behaviors are being considered.
@c12gene reported an issue with the AI bot not being able to read summaries and detailed content, which was addressed by @MachineScholar through system prompt improvements.
@BrianC asked about tying token limits to subscriptions and allowing more expensive models to be used for a fee, with @sam confirming that different quotas can be set for different user groups.
This week on meta.discourse.org, the Discourse team continued to enhance and refine the AI capabilities within the platform. Key discussions revolved around improving the AI summarization feature, managing costs through usage quotas, and integrating new language models. The community also explored potential use cases, such as formatting code with AI assistance and enabling document uploads for AI analysis.
Interesting Topics
Translate Discourse automatically (without a button) (ref)
The team provided updates on their progress towards enabling automatic translation of Discourse topics using AI models. While the initial target is to have the topic page translatable via a language toggle, challenges around search functionality and handling multilingual content remain.
A new feature was released that allows administrators to define usage quotas for AI models, enabling better cost control and fair access to AI features across the community.
sam proposed the idea of allowing certain user groups access to an “AI Helper” feature for formatting source code in posts, acknowledging the potential performance trade-offs.
AI Plugin Causes All Posts to Be Unreadable in Latest Discourse Version (ref)
shannon1024 reported a critical bug where the AI plugin rendered all posts unreadable after updating to the latest Discourse version. The issue was related to the AI embeddings configuration and was resolved by disabling the relevant setting.
Saif provided guidance on factors to consider when choosing a Large Language Model (LLM) for Discourse AI, including performance, context length, compatibility, language support, multimodal capabilities, and speed.
DeepSeek provider support? What to do when model provider isn’t in “Provider” list? (ref)
MachineScholar inquired about integrating the DeepSeek R1 model, which Falco provided a solution for by configuring it as an OpenAI model.
Saif introduced the AI usage page, designed to help administrators understand how the community is utilizing Discourse AI features over time, aiding in cost estimation and management.
shannon1024 reported a critical bug where the AI plugin rendered all posts unreadable after updating Discourse, which was resolved by disabling the AI embeddings setting.
Saif provided guidance on factors to consider when choosing an LLM for Discourse AI, such as performance, context length, compatibility, language support, multimodal capabilities, and speed.
This week on meta.discourse.org, discussions centered around AI-related issues, features, and integrations. Key topics included debugging AI chat, configuring AI spam detection, utilizing reasoning models like DeepSeek-R1, and exploring the capabilities of the AI Helper plugin. Users shared insights on cost comparisons, performance evaluations, and potential use cases for various language models.
Interesting Topics
dsims encountered an issue with the AI Helper’s post illustration feature, leading to a discussion on updating the required settings. [ref](AI-Helper post illustration error. ai_openai_api_key missing)
oppman sought guidance on integrating AI with external sites and GitHub repositories for a software developer community. [ref](AI Integration with Specific External Sites and GitHub)
Users discussed the cost and performance of the DeepSeek-R1 reasoning model compared to other language models like GPT-4 and Claude. [ref](DeepSeek provider support? What to do when model provider isn’t in “Provider” list?)
MachineScholar reported a random error when interacting with the DeepSeek-R1 model via the AI Bot. [ref](DeepSeek-R1 randomly producing “Job exception: undefined method `finish’ for nil” error)
Eric_Platzek sought assistance with debugging AI chat and clarifying the usage and costs associated with different language models. [ref](Debugging AI chat)
markschmucker shared their experience with the AI Web Artifacts feature and inquired about editing generated code and starting new contexts with existing artifacts. [ref](Announcing: AI Web Artifacts)
NKERIFAC_CLAUD_NBAPNON encountered an issue with the Discourse AI embeddings configuration after an update, leading to a discussion on troubleshooting and configuration steps. [ref](Problems with Discouse AI embeddings configuration)
Activity
sam provided insights on exporting forum posts for manual upload into external language models using the Data Explorer. [ref](Exporting all Forum Posts for Manual Upload into External LLMs?)
Roman_Rizzi shared updates on resolving issues related to the AI plugin causing posts to be unreadable in the latest Discourse version. [ref](AI Plugin Causes All Posts to Be Unreadable in Latest Discourse Version)
BrianC inquired about managing uploaded text files in AI personas and the possibility of editing indexed content. [ref](Discourse AI Persona, upload support)
per1234 reported an issue where posts and accounts were not always restored when flags from the Discourse AI spam detection were rejected, leading to a discussion on potential solutions. [ref](Posts and account not always restored when flag from Discourse AI spam detection rejected)
dsims suggested adding a quality parameter for the Dall-E 3 image generation feature to reduce costs. [ref](Image sizes of Dall-E 3?)
Over the past week (2025-02-03 to 2025-02-10), AI discussions on meta.discourse.org have been both vibrant and diverse. Active debates ranged from fine-tuning the AI helper’s ability to distinguish between Discourse and Discord to exploring innovative ways to pass data to artifacts and chain multiple AI triage scripts. Users focused on enhancing features (as seen in discussions like AI helper does not know the difference between Discourse and Discord and post by sam in Support and ai) while also addressing bugs and configuration issues in sentiment analysis and semantic search. In-depth posts covering topics such as flexible artifact embedding (How do I pass data to an artifact? through post 7) and automated AI workflows (AI + Automation Governance: Orchestrating Independent AI Triage Scripts to post 8) demonstrated the community’s commitment to practical innovation. Meanwhile, bug reports such as issues with sentiment displays and semantic search anomalies were met with proactive troubleshooting by experienced users. These discussions, backed by numerous posts and detailed responses, highlight a week of forward-thinking ideas balanced by diligent debugging.
Interesting Topics
AI Helper Confusion (ai, Support): RGJ raised concerns in post 1 about the AI helper mixing up Discourse with Discord, while sam elaborated in post 2 on potential prompt enhancements.
AI Summarization Backfill Update (ai, ai-summarize): Roman_Rizzi confirmed improvements in the summarization process via post 18, highlighting the use of last_posted_at and revision checks.
Discourse AI Plugin Settings Query (official, ai, Plugin):
In post 193 of the “Discourse AI” topic, Bathinda queried the missing setting for topic mentions, prompting further discussion.
Semantic Search Anomaly (ai, ai-search, Support): tyler.lamparter reported challenges with AI semantic search in post 1, noting discrepancies between AI-powered and normal search results.
DeepSeek-R1 Error Resolution (ai, Bug): MachineScholar confirmed in post 4 that DeepSeek-R1 now functions reliably despite intermittent 502/504 errors from external endpoints.
