Weekly Summary of AI topics

Site feedback Forum summaries
48

Overview

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

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

49

Overview

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.

  • [grid] from AI vision in chat: @zogstrip shared that @joffreyjaffeux had fixed an issue related to displaying AI-generated images in the chat feature, providing a screenshot of the working solution.

  • 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.

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

50

Overview

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.

  • Feedback for AI gists, short summaries on topic list gathered feedback on the value and potential improvements for AI-generated short summaries displayed on the topic list.

  • Job exception: undefined method `finish’ for nil when using ai bot addressed an issue encountered when using a custom OpenAI-compatible API with the Discourse AI plugin, leading to a discussion on compatibility and troubleshooting.

  • 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.

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

51

Weekly AI Summary on meta.discourse.org

Overview

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.

  • @markschmucker inquired about limiting the number of AI tokens a user can use in a day, and @sam provided a link to an upcoming pull request addressing this feature.

  • @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

Thanks for reading, and I’ll see you again next week! :slight_smile:

2 Likes
52

Weekly AI Summary on meta.discourse.org

Overview

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.

  • @oppman sought advice on evaluating the costs of using HuggingFace TGI versus OpenAI API endpoints for AI services, with @Falco providing insights on when running one’s own language model makes sense.

  • 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.

  • @smithmarkl asked about the possibility of injecting custom prompts or manipulating embeddings in the AI Search feature to boost or separate staff responses from community responses.

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

53

Weekly AI Activity Summary on meta.discourse.org

Overview

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.

  • LLM Quotas for Discourse AI (ref)

    • 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.

  • OpenAI’s text-embedding-ada-002 error “Embedding dimensions” (ref)

    • kuaza encountered an issue with OpenAI’s text-embedding-ada-002 model, which was resolved by Roman_Rizzi through a pull request.

  • Moderation tool for formatting code with AI (ref)

    • 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.

  • What LLM to use for Discourse AI? (ref)

    • 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.

  • Discourse AI - AI usage (ref)

    • 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.

  • AI helper is hiding. Again (ref)

    • Jagster reported an issue where the AI helper was not visible in certain contexts, which was subsequently fixed by pmusaraj.

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

54

Overview

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)

  • Don inquired about increasing the maximum consecutive tool usage in AI responses, which led to a discussion on potential solutions. [ref](Max consecutive tool usage in the answer)

  • 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)

  • Saif provided clarification on the differences between AI spam detection and AI triage, as well as guidance on flagging individual posts versus entire topics. [ref](Setting up spam detection in your community)

  • 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?)

  • bugtracker inquired about using DeepSeek with the Discourse AI plugin. [ref](Discourse AI)

  • StefanoCecere shared a suggestion to include the day name when generating dates with the AI Helper. [ref](Write out smarter dates with AI)

  • BrianC expressed interest in the upload and discussion of PDFs in the composer feature. [ref](Upload and discuss pdfs in composer)

Thanks for reading, and I’ll see you again next week! :slight_smile:

55

Overview

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

Activity

User Contributions Across Topics

Thanks for reading, and I’ll see you again next week! :slight_smile:

56

Overview

This week on meta.discourse.org the AI community engaged in in‐depth technical discussions and experiments with several new and evolving features. Contributors debated the feasibility of extending RAG to support diverse PDF formats—highlighting nuances in text extraction and OCR reliability (ref, ref)—and launched an intriguing one‐click experiment for AI summarization with mixed impressions (ref, ref). There were spirited conversations around ChatGPT’s role in forum assistance (ref, ref), together with detailed troubleshooting sessions for semantic search issues that consistently returned irrelevant results (ref, ref). Additional topics—including problems with rake tasks in the AI plugin (ref, ref), automation governance experiments (ref, ref), and fixes for persona tool JSON errors (ref, ref)—kept the forum buzzing with ideas and actionable fixes. Throughout these discussions, top contributors like sam, Yenwod, Jagster, Saif and many others drove the conversation forward by sharing clear troubleshooting steps, potential feature improvements, and critical reflections on AI integration in forum functionalities.

Interesting Topics

  • Will RAG Support PDF Files in the Future?
    Users debated the challenges of supporting all types of PDFs in RAG workflows. MachineScholar sparked the discussion with a comment praising the commit (ref), while Saif explained the intricacies of handling text versus image PDFs (ref). Subsequent troubleshooting steps were detailed by Yenwod when he encountered indexing delays (ref) and further debugging was shared (ref, ref, ref).

  • New Experiment: Enable AI Summarize on your Discourse with one-click!
    In this experiment, users evaluated a one-click activation for summarizations. shooj raised an initial query about limiting the feature to admins or mods (ref), and Jagster argued over its universal benefits (ref). Contributions by Arkshine provided CSS-based workarounds (ref), while additional observations by Jagster and Carverofchocie sparked extra debate (ref, ref, ref, ref).

  • How are we all feeling about ChatGPT and other LLMs and how they’ll impact forums?
    The conversation here balanced optimism with caution. Tris20 offered insights on repetitive answers by LLMs in forum settings (ref), while Saif looked at future directions for LLM assistance in topic formulation (ref).

  • Getting a lot of no results for semantic search
    A technical debate emerged when users reported that AI search always returned roughly 40 results regardless of query relevance. sam began the discussion (ref), and tyler.lamparter shared his observations (ref, ref). Further elaboration on model behaviors and result uniformity was provided by sam and Falco (ref, ref, ref, ref).

  • Rake tasks in the AI plugin not working
    A practical issue was raised by Yenwod regarding failures in AI rake tasks, especially with ruby-progressbar related errors (ref). His follow-up post provided more context (ref), while sam and Yenwod further discussed potential remedies (ref, ref).

  • AI + Automation Governance: Orchestrating Independent AI Triage Scripts
    This thread explored automating workflows for AI triage. Cloud_spanner shared a detailed workflow proposal (ref), with sam suggesting a custom tool for triage automation (ref), and Cloud_spanner reinforcing the benefits of a flexible IFTTT-style approach (ref).

  • AI Persona using Categories tool – “An empty string is not a valid JSON string”
    An error in using the Categories tool left users troubleshooting persona failures. markschmucker consistently encountered the JSON error (ref), while sam confirmed the bug and soon provided a fix (ref, ref).

  • All AI functions are working ok, but AI search gives 500 error
    A disruptive 500 error in AI search caught attention on this thread. Bathinda reported the initial error (ref) and subsequent status updates (ref, ref). Jagster guided users through troubleshooting with actionable solutions (ref, ref, ref).

  • Discourse AI – Spam detection
    Focusing on content quality, this topic examined AI’s capacity for spam detection. jordan-violet shared initial testing scenarios (ref, ref), while Jagster critiqued the logical phrasing in the detection rules and offered clearer alternatives (ref, ref, ref, ref).

  • How to properly debug AI Personas?
    A brief yet vital discussion focused on debugging AI personas where Falco inquired about the LLM/provider specifics (ref), and Overgrow responded with the details of his OpenAI setup (ref).

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

57

Overview

This week on meta.discourse.org (Feb 17–Feb 24, 2025) the AI category has been buzzing with troubleshooting, experimentation, and feature enhancements. Users such as sam, Falco, hendersj, and others have been busy addressing critical bugs, testing integrations with local AI models like Ollama, and exploring new capabilities around PDF processing, search, and API interactions. For example, a serious page display bug raised by shannon1024 quickly attracted responses from Arkshine and sam, while robust troubleshooting in Getting discourse ai to work with ollama locally has yielded progress despite SSRF and streaming configuration challenges. Constant activity in threads discussing the performance of our AI forum helper, hosted model cost clarifications, and even Google Search API integration tests underscores a community deeply invested in making Discourse AI even better. Read on for a more detailed breakdown of the interesting topics and user activities from the past week.

Interesting Topics

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

58

Overview
This week on meta.discourse.org the community’s AI activity has been energetic and multifaceted. Discussions have spanned innovative feature requests and detailed technical troubleshooting. A central theme has been the need to intelligently automate responses – as introduced in the Auto responder using AI discussion by Saif – with follow‐up examples from EricGT (post 2) and creative suggestions by hel_Sinki (post 3). Simultaneously, practical challenges such as enabling PDF support for AI analysis were examined in PDF support in Discourse AI with details by hameedacpa (post 7) and clarifications from sam (post 8). Meanwhile, integration issues with Claude 3.7 were dissected in the Error using Claude 3.7 Sonnet with Discourse AI plugin thread—fueling technical troubleshooting by emansilla (post 1) and iterative fixes by Falco (post 2). Other threads on LLM settings, experimental search results, and connection resets further enriched the dialogue. Collectively, these discussions underline the community’s commitment to exploring dynamic AI integrations that not only automate tasks but also enhance user experience across Discourse’s features.

Interesting Topics

  • Auto responder using AI (Feature, automation, ai)
    • Initiated by Saif (post 1), the idea of deploying an AI-driven auto-responder sparked follow-up queries by EricGT (post 2) and practical examples by Jagster (post 4) as well as use-case suggestions from MachineScholar (post 5).
  • PDF support in Discourse AI (#SiteManagement, how-to, ai)
    • Discussions centered on testing PDF upload and analysis were led by hameedacpa (post 7) with clarifications and follow-ups by sam (post 8 and post 10), while Falco provided configuration insights (post 12).
  • Error using Claude 3.7 Sonnet with Discourse AI plugin (Bug, ai, ai-bot)
    • Technical hurdles emerged when emansilla reported integration errors (post 1), provoking responses and troubleshooting steps from Falco (posts 2, post 4, and post 6).
  • Discourse AI - AI bot (#SiteManagement, ai-bot)
    • A demonstration by MarkDoerr (post 150) highlighted use cases that drive the AI bot’s interactions.
  • Discourse AI causing new SSL and Connection Reset by Peer errors (Bug, ai)
    • Issues with SSL and connectivity were investigated by oznyet (post 7 and post 9) with remedial updates from sam (posts 8 and 10).
  • Question about release note for experimental search results (General, ai)
    • sam explained fine-tuning efforts (post 3), while Jagster shared community concerns (post 4).
  • Discourse AI - Large Language Model (LLM) settings page (#SiteManagement, how-to, ai)
    • sam reminded users of supported configurations via the LLM settings (post 5).
  • How do you use Discourse AI? Tell us and make it even better! (Feature, feedback, ai)
    • A feedback thread encouraged sharing of use cases, with contributions from Bhack (post 22 and post 24) and an insightful comment by Saif (post 23).
  • What LLM to use for Discourse AI? (#SiteManagement, how-to, ai)
    • In response to user queries, Saif confirmed support for new models (post 5).
  • Error in any AI Tool with no parameters, e.g. “tags” (Bug, ai)
    • sam detailed an error scenario associated with tool parameters (post 6).

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

59

Overview

Over the past week (March 10–17, 2025), the meta.discourse.org community has engaged in vibrant discussions around enhancing AI features across the forum. Developers and users alike explored enhancements to search functionality—for example, suggestions to improve user interaction in the Conversational AI Search coming to Discourse AI thread—while also debating the ethics and best practices of automated content creation in Rules Surrounding Writing Topics using AI. Other conversations centered on UI improvements such as displaying a live processing indicator in Provide visual cue when a topic is receiving an AI response, and practical customization queries like safely rebranding the AI spam detection account in Rebranding the ai spam detection account. Technical deep-dives emerged in areas such as configuring large language models in the Discourse AI - Large Language Model (LLM) settings page thread, and automating content classification in Using AI To Tag And Categorize Forum Posts. Troubleshooting challenges—ranging from imprecise semantic search results as discussed in Getting a lot of no results for semantic search to intermittent response failures highlighted in Why does the AI model stop responding—further underscored the community’s commitment to refining its AI systems. In addition, creative applications such as the Gemini ai bot to draw picture in chat and broad plugin transition implications in Discourse AI spam detection replaces Akismet plugin round out a week full of insightful, multi-dimensional AI activity.

Interesting Topics

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

60

Overview

This week on Meta Discourse, the community dove deep into innovations at the intersection of AI and forum management. Members explored experimental implementations such as sam's work on Experiments with AI based moderation on Discourse Meta – where discussions ranged from leveraging Gemini Flash 2.0 (post #7) to addressing false positives (post #3). At the same time, the conversation around new interaction modalities was vibrant, with topics like Is there a way to chat with Discobot? generating feedback from trusktr, tobiaseigen, and Canapin – even prompting interface tweaks such as the redirection fix by Lilly (post #10).

Cost and performance debates were front and center in What’s the cheapest/best AI to use for AI Spam? where users like trusktr, ondrej, and thoka compared models – with NateDhaliwal sharing insights from OpenRouter’s Gemini approach (post #4). On the UI and feature front, members discussed vital accessibility enhancements in What’s the best way to add image descriptions? and smoother interaction via the Setting to manually close AI Helper’s popup modal. Innovative ideas such as enriching API calls in enterprise settings (Enrich API Calls of AI Plugin?) and improvements in AI search functionality (Conversational AI Search coming to Discourse AI) further fueled the debate. This week’s activity also reflected a growing interest in troubleshooting and refining AI personas – as seen in How to properly debug AI Personas? – and led the community to explore new notification possibilities, like sending automation summaries to groups (Ability to send Automation AI summaries to groups). Overall, from experimental moderation strategies (post #1) to enterprise API enrichment (post #1), the dialogue has been rich, diverse, and full of actionable insights.

Interesting Topics

  • Experiments with AI based moderation on Discourse Meta
    Discussions highlighted the promising evolution of AI for moderation, detailing experiments with Gemini Flash 2.0 (post #7) and updates ensuring that only public posts are scanned (post #6).

  • Is there a way to chat with Discobot?
    Users explored the idea of interacting with Discobot in a chat format, with suggestions to use ask.discourse.com (post #3) and commentary on domain redirects (post #9).

  • What’s the cheapest/best AI to use for AI Spam?
    The community weighed cost against performance by comparing models like GPT-4o-mini, Claude 3.5 Haiku, and Gemini 2.0 Flash – with hands-on recommendations from users such as trusktr (post #1) and NateDhaliwal (post #4).

  • FYI: Cloudflare AI Labyrinth
    An insightful share on Cloudflare’s strategy to trap misbehaving bots using AI-generated mazes sparked curious reactions and humorous takes (post #1, post #3).

  • Hide persona from composer dropdown
    A user-friendly debate was held on how to prevent personas from cluttering the composer dropdown, with suggestions for a dedicated “Hide from composer” option (post #1, post #3).

  • What’s the best way to add image descriptions?
    Accessibility improvements were discussed with reference to current markdown capabilities and potential UI enhancements for image ALT text (post #17, post #19).

  • Setting to manually close AI Helper’s popup modal
    With feedback about the finicky nature of the AI Helper modal, a feature request emerged to add a manual close option for enhanced usability (post #1).

  • Conversational AI Search coming to Discourse AI
    Users provided feedback on the new search summary interface, discussing minor UI glitches like missable “More…” text and unexpected closures (post #10).

  • How to properly debug AI Personas?
    Troubleshooting steps and questions about debugging inconsistent AI persona responses spurred a helpful discussion among experienced users (post #4).

  • Enrich API Calls of AI Plugin?
    An enterprise user raised ideas on enriching outgoing API requests with proper authentication headers, opening a conversation on integrating internal auth endpoints with custom tooling (post #1).

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

61

Overview

This week on meta.discourse.org the community passionately discussed several AI topics, driving the conversation forward on configuration issues, user experience, and new feature experiments. Members collaborated on troubleshooting critical bugs in AI tools—ranging from errors when creating new AI personas to refining popup modal behaviors—while also sharing insights about LLM settings, sentiment analysis, image captioning, embeddings, and even experiments in AI moderation. These discussions, spread across multiple topics such as Unable to create new Personas (post 1), Setting to manually close AI Helper’s popup modal (post 3), LLM settings page (post 10) and Discourse AI - Sentiment (post 41), underscore the shared passion and technical know‐how applied by our members. The blend of bug reports, configuration tweaks, and creative ideas has paved the way for improvements to our AI functionality—ensuring that both self-hosted and managed services continue to run smoothly. For instance, fixes announced by joffreyjaffeux in Unable to create new Personas (post 6) and keegan in Setting to manually close AI Helper’s popup modal (post 3) highlight our concerted effort toward continuous improvement. Below is a detailed roundup of the most interesting topics and user activities from the past 7 days.

Interesting Topics

  • Unable to create new Personas (Bug, ai, ai-bot)
    MachineScholar kicked off this discussion by reporting an error on attempting to create new AI personas (post 1). sam joined with troubleshooting suggestions (post 2 and post 4), while further investigation by MachineScholar confirmed the issue (post 3). Later, joffreyjaffeux provided a fix by referencing the upcoming patch (post 6) and MachineScholar confirmed resolution (post 7).

  • Setting to manually close AI Helper’s popup modal (Bug, ai, ai-helper)
    When users expressed the need for more control over AI Helper’s popup modal, keegan swiftly responded by moving the request to Bug and subsequently pushed out a fix (post 3). MachineScholar later confirmed that the issue was resolved (post 5).

  • Discourse AI - Large Language Model (LLM) settings page (#SiteManagement, how-to, ai)
    In this thread, AquaL1te shared their experience with setting up the LLM settings page, noting a quirk with the default model name (post 10 and post 12). Saif contributed by asking for clarifications regarding model identifier discrepancies (post 11 and post 13).

  • Discourse AI - Sentiment (#SiteManagement, how-to, ai-sentiment, content)
    This topic saw RBoy raise concerns about the cessation of the sentiment process since January 2025, prompting discussions regarding configuration changes (post 41). Falco responded with an explanation about the changes in sentiment server deployments (post 42).

  • Experiments with AI based moderation on Discourse Meta (Community, moderation, ai)
    Creative ideas were floated by RGJ, who proposed that an AI moderation bot could intermittently signal that a post required no action—injecting an element of transparency into automated moderation (post 10).

  • A setting for AI-enabled image title default value (Support, ai)
    fbpbdmin started this discussion by suggesting that AI-enabled image titles should be off by default in order to save tokens (post 1 and post 4). keegan provided configuration guidance on the available settings (post 3).

  • Self-Hosting Sentiment and Emotion for DiscourseAI (#Self-Hosting, ai, ai-sentiment)
    In a discussion aimed at self-hosters, RBoy raised important questions about running local instances for sentiment analysis, seeking advice on resource requirements and integration techniques (post 4).

  • Discourse AI - Embeddings (#SiteManagement, ai, ai-search, related-topics)
    Lastly, Saif prompted an update in the embeddings discussion to ensure that the feature stays aligned with the platform’s evolving needs (post 37).

Activity

Additional references from the discussions include multiple insights and confirmations across posts such as post 2 of Unable to create new Personas, post 4 of Unable to create new Personas, post 12 of LLM settings page, post 13 of LLM settings page, post 41 of Sentiment, and post 37 of Embeddings among others. Each contribution has helped build a rich tapestry of discourse with over 40 discussion links embedded across topics, showcasing the depth and collaborative effort of our community.

Thanks for reading, and I’ll see you again next week! :slight_smile:

62

Overview

This week on meta.discourse.org the AI discussion threads have been buzzing with innovative ideas and practical troubleshooting. Community members explored everything from fresh feature proposals to intricate technical issues. For example, the AI Avatar Generator thread saw tpetrov kick off a discussion with ideas for generating personalized avatars (tpetrov post 1, sam post 2, tpetrov post 3), while the lively Ways to Add Knowledge to My Persona discussion featured a deep dive into enabling search and read tools for AI support personas – with contributions from Angela_MRS, Falco, and pfaffman (Angela_MRS post 1, Falco post 2, Angela_MRS post 3, Falco post 4, Angela_MRS post 5, Falco post 6, Angela_MRS post 7, Angela_MRS post 8, pfaffman post 9, plus an extra insight about private categories (Allow Bot on Private Categories)) – ensuring that even “backstage” AI teaching ideas were on the table. Other hot topics included improvements to AI‐based moderation (sam post 11) and extensive discussions on the customization and troubleshooting of the Discourse AI Bot (jorge-gbs post 152 through EricGT post 158). Meanwhile, threads on automation—such as the ability to send AI summaries to groups (sam post 2, jordan-violet post 3)—and resource management via daily AI token limits (sam post 13) highlighted both the potential and the challenges of integrating AI in community workflows. Finally, troubleshooting posts like those on the Invalid Request Error in Google Flash (BrianC post 1 through sam post 7) and API enhancements in the combined discussion on enriching API calls and Google Search integration (sam post 3 in 357898, jorge-gbs post 11 in 307107, sam post 12 in 307107) underscore the collaborative drive to refine Discourse’s AI capabilities.

Interesting Topics

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

63

Weekly Summary of AI Activity on Meta.discourse.org

Below is a detailed overview of this week’s vibrant discussions and developments around Discourse’s AI features and integrations from 2025-04-07 to 2025-04-14.

Overview

This week saw a flurry of activity around leveraging and refining AI capabilities on Meta. Discussions ranged from concerns over personal data and privacy when using the AI plugin to technical deep-dives into embedding models, API call enrichments, and troubleshooting internal server errors. Privacy and configuration details took center stage as wotography initiated the discussion on Concerns over personal privacy with the AI plugin – a thread that quickly sparked detailed responses from Falco (post 3, post 6, post 8) and clarifications by sam (post 9, post 10). Further, technical queries such as How to implement Mistral with Embeddings drew contributions from RGJ (post 1, post 3) and insightful remarks by Falco (post 2, post 4). Meanwhile, innovative experiments were shared on enhancing the user experience with features like the Expanded with AI Summaries option and Conversational AI Search, as well as advanced inquiries into Enriching API Calls. Troubleshooting themes also emerged in topics such as Discourse AI Internal Server Error and Discourse AI - Semantic Search & Summarization Not Working for our configuration, ensuring that technical issues are rapidly addressed. These discussions underscore a community committed to both innovation and rigorous technical support in the ai, privacy, Support, and rest-api spaces.

“If you both don’t trust any third party LLMs and can’t run your own, I recommend simply not integrating them.” – Falco
ref

Interesting Topics

Activity

Each contribution – from detailed technical analysis to thoughtful user inquiries – has been crucial in shaping the future roadmap of Discourse AI integrations. Community members have built on each other’s ideas by referring to earlier posts like this privacy note or the troubleshooting tip, ensuring a robust and collaborative dialogue.

Thanks for reading, and I’ll see you again next week! :slight_smile:

64

Overview

This week on meta.discourse.org, the AI discussions have been vibrant and multifaceted. Contributors explored how to harness AI/LLMs in building custom themes, components, and plugins in the Dev space – sparking debates on the pros and cons of using tools like Cursor and Claude Code (jimkleiber’s insight, Falco’s experiment, Dimava’s challenges, awesomerobot’s tip). Equally engaging was the proposal for a dedicated page to filter or list AI conversations in the Feature category (kuaza’s initial post, responded to by Jagster and others through posts 3, 4, 5, and 6). Other threads discussed practical issues like AI-driven spam detection in #SiteManagement (Olle11’s query, KhoiUSA’s suggestions, follow-ups and further tips), while the Support category saw an in-depth exploration of building modular AI chatbots with specialized personas (Yenwod’s proposal, Falco’s confirmation, additional clarifications, more insights, sam’s constructive inquiry, and a further note by Yenwod). Discussions also spanned technical configurations for self-hosted embeddings (satonotdead’s update, Falco’s follow-up), troubleshooting visible reasoning and image recognition challenges with Grok (hel_Sinki’s suggestion), addressing PDF upload and indexing errors (Michael_Liu’s detailed post and follow-up), and resolving issues with the AI helper’s generation process in the Bug space (MachineScholar’s report, Falco’s query, additional MachineScholar updates and further details along with keegan’s follow-up). Finally, a fresh discussion on innovative prompt evaluation tools – funnel, orbit, and flux charts – was raised in the Feature arena by EricGT (post). These rich interactions underscore the community’s commitment to refining AI integration and addressing practical challenges.

Interesting Topics

  • How are you using AI/LLMs to create themes/components/plugins?
    In the Dev category with the ai tag, jimkleiber launched a discussion on leveraging AI for Discourse customizations (post 1). Falco soon shared his experience using Cursor in agent mode (post 2), while Dimava noted challenges with bug fixes (post 3). awesomerobot later added practical tips for dealing with modern Ember issues (post 4).

  • Listing conversations with artificial intelligence on a separate page or filtering them on the messages page
    In this Feature discussion tagged ai, kuaza proposed a dedicated page for AI conversations (post 1). The idea received active feedback from Jagster (post 2), with follow-up clarifications and questions further detailed in posts 3, 4, 5, and 6.

  • Discourse AI - Spam detection
    Within #SiteManagement and tagged with moderation, how-to, ai, and spam, users discussed replacing Akismet with an AI-based solution. Olle11 raised questions regarding cost-effective alternatives (post 10), while KhoiUSA recommended Gemini 2.0 Flash with follow-ups in posts 11, 12, and 13.

  • Building Modular AI Chatbots
    In the Support category with tags ai and ai-bot, a conversation unfolded about designing a modular AI chatbot system. Yenwod introduced the concept (post 1), followed by Falco affirming technical feasibility (post 3) and further elaborations from Yenwod (post 4, post 7). Additional insights were provided by Falco (post 5) and sam (post 6).

  • Self-Hosting Embeddings for DiscourseAI
    Under the #Self-Hosting category with tags ai, ai-search, and related-topics, discussions focused on endpoint configuration and backfill procedures. satonotdead reported having an endpoint to use for embeddings (post 21), and Falco clarified that Discourse now handles backfill automatically (post 22).

  • Need Support for Displaying Reasoning Process and Enabling Grok to Recognize Images
    In a Support thread tagged ai, hel_Sinki raised the need for Grok’s visible reasoning traces and improvements so that its image recognition capabilities can properly interact with posts (post 1).

  • PDF support in Discourse AI
    In the #SiteManagement category with tags how-to and ai, Michael_Liu reported issues with PDF uploading and indexing, highlighting error messages and questioning file size limits (post 14 and post 15).

  • AI Helper stuck generating
    A bug report in the Bug category tagged with ai and ai-helper detailed an instance where the AI helper remained stuck on “generating”. MachineScholar initiated the report (post 1), followed by responses from Falco (post 2), further updates from MachineScholar (posts 3 and 4), and a clarification by keegan (post 5).

  • Prompt tools: funnel, orbit, and flux charts
    In a fresh Feature discussion with the tags ai and sql-query, EricGT introduced innovative concepts for prompt evaluation. He outlined how tools like Funnel, Orbit, and Flux could provide deeper insights into prompt performance (post 1).

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

65

Weekly AI Activity Summary (2025-04-21 to 2025-04-28)

Overview

Over the past week, the community dove into enhancing Discourse AI’s capabilities, usability, and stability. On the Feature front, members explored adding a one-click “Draft response” action to the AI toolbar Using AI to assist in responding to new posts in Discourse and surfaced first iterations of listing and filtering AI-generated conversations on the Messages page Listing conversations with artificial intelligence on a separate page or filtering them on the messages page. In Support discussions, cost-vs-quality trade-offs of persona file sizes were quantified Do more persona files increase LLM request expenses?, while modular bot authorship patterns were refined Building Modular AI Chatbots and visibility into custom vs. built-in tools was clarified Can we view all tools and their setups in AI. On the UX side, a simple CSS tweak fixed icon positioning in the composer Ai icon for category helper is positioned above the + menu, and numerous Bug reports saw closures after validation enhancements Validate the Name field for AI tools and a resolved “stuck generating” issue AI Helper stuck generating. The result is an ecosystem that’s more intuitive, performant, and cost-effective.

Interesting Topics

Activity

sam (14 likes, 15 posts)
• Drove the “Draft response” feature discussion 363298/5?silent=true
• Confirmed tool-name validation 330830/2?silent=true
• Proposed custom tool JS for VaccineBot flows 361807/10?silent=true
• Shared a GitHub helper demo 363437/4?silent=true
• Triaged & closed multiple bugs:
– Subfolder links 278007/3?silent=true
– PM-draft removal 336927/7?silent=true
– Chat bot outage 318546/2?silent=true
– Create user error 312281/6?silent=true
– Chat UI tab 285403/4?silent=true
– Dropdown on selection 305688/3?silent=true
– Gemini support 312280/6?silent=true
– Periodical report model 293762/6?silent=true
– Job exception fix 344935/3?silent=true

Falco (9 likes, 4 posts)
• Explained cost formula in persona files 363440/3?silent=true & 363440/5?silent=true
• Clarified tool-visibility differences 363437/3?silent=true
• Advised on Glean indexing approach 363335/4?silent=true

wlandgraf (5 likes, 5 posts)
• Requested AI “Draft response” button 363298/1?silent=true & 363298/4?silent=true
• Questioned persona-cost impact 363440/1?silent=true & 363440/4?silent=true
• Asked for a tool-dashboard view 363437/1?silent=true

kuaza (4 likes, 2 posts)
• Celebrated AI conversation filtering landing 362711/8?silent=true
• Shared VaccineBot prompt ideas 361807/9?silent=true

isaac (4 likes, 1 post)
• Announced PR merge for conversation listing 362711/7?silent=true

keegan (3 likes, 2 posts)
• Investigated helper hang, enabled PM debug 362643/7?silent=true & 362643/8?silent=true

awesomerobot (3 likes, 2 posts)
• Confirmed no built-in “Draft response” yet 363298/3?silent=true
• Applied UX fix from prior modal patch 363692/4?silent=true

maiki (3 likes, 1 post)
• Validated tool name field in admin UI 330830/3?silent=true

Moin (3 likes, 1 post)
• Reported AI icon clipping issue in composer 363692/1?silent=true

Yenwod (2 likes, 2 posts)
• Experimented on VaccineBot tooling 361807/8?silent=true & 361807/11?silent=true

Thanks for reading, and I’ll see you again next week! :slight_smile:

66

Overview

“This theme component adds a button to each post, allowing users to send the post to an AI bot for analysis via a direct chat message.” — Don, AI Post Analyzer for Chat

The past week (2025-04-28 to 2025-05-05) on #meta.discourse.org was packed with ai enhancements and deep-dive discussions:

The introduction of AI Post Analyzer for Chat delivered a handy AI button in chat, the OpenAI image generation and editing now supported in Discourse AI release brought GPT-image-1 workflows to Announcements, the Is an automation like this possible with Discourse AI today? thread explored automating product announcement summaries, the A Plug-In to convert Discourse Forum Discussions into Clear Proposal Revisions with Community-Sourced Justifications pitched SimScore for governance, and the AI changed quite many gists in English support topic tackled prompt-driven language mix-ups.

Lively follow-ups revisited AI Post Analyzer for Chat for renaming guidance, spurred testing on OpenAI image generation and editing now supported in Discourse AI, refined logic in Is an automation like this possible with Discourse AI today?, addressed hosting constraints on the SimScore plugin thread (A Plug-In to convert Discourse Forum Discussions into Clear Proposal Revisions with Community-Sourced Justifications), and handled database cleanup in AI changed quite many gists in English.

On the tooling side, the complete list of variables used in AI prompts sparked calls for comprehensive docs, the AI helper hallucinating a lot when explaining something thread exposed model quirks, How to install and configure AI features step by step clarified plugin setup, the AI Assistants with Web Search capability discussion confirmed custom agent flexibility, and Provide visual cue when a topic is receiving an AI response surfaced UX enhancements.

Subsequent updates asked to expand the complete list of variables used in AI prompts for persona customization, offered model swap suggestions in the AI helper hallucinating a lot when explaining something thread, improved the install walkthrough in How to install and configure AI features step by step, tested web-search integration in AI Assistants with Web Search capability, and debated design patterns in Provide visual cue when a topic is receiving an AI response.

Interesting Topics

Activity

Thanks for reading, and I’ll see you again next week! :slight_smile:

67

Weekly AI Activity on meta.discourse.org (May 5 – May 12, 2025)

Overview

Over the past week, the ai and ai-bot community dove into a variety of Support, Bug, UX, and Feature discussions. From customizing the AI bot homepage to fixing a persistent topic‐summary hang, members collaborated on configuration tricks, merged hotfixes for PDF uploads and image captioning, and ironed out UX quirks like proofread quote handling and AI typing indicators. Under the hood, developers wrestled with LLM performance—troubleshooting a Perplexity Sonar Deep Research setup—and explored advanced automations and web‐search integrations, laying groundwork for richer AI experiences in Discourse.

Interesting Topics

  • Custom AI Bot Homepage (Support, ai)
    kuaza opened “How to set the home page to be an AI bot?” to replicate an ask.discourse.com‐style landing page, testing trust‐level redirects; Lilly later demonstrated success using AI bot enable dedicated UX and the Custom Homepage for Groups component in post #7.

  • Topic Summary Hanging (Bug, ai)
    KhoiUSA reported that “Summarize Topic” hung with a 400 Invalid JSON Payload error in post #1. Falco recommended switching the provider to OpenAI and updating the endpoint, resolving the issue in post #5, and sam suggested adding fallback logic for unexpected non‐JSON responses in post #7.

  • Proofread Breaks Quotes (UX, ai-helper)
    Jagster flagged that the Proofread helper mangles quotes in the preview in post #1. Falco clarified it’s a visualization quirk and proposed a diff‐only approach in post #2, and stance455 confirmed quoted text is skipped after the latest update in post #3.

  • PDF Upload in AI Bot UX (Support, ai-bot)
    MachineScholar asked if the new AI Bot UX supports text‐based PDFs in post #1, referencing the enhanced PDF processing roadmap. Falco merged a bugfix in post #4 enabling RAG on image‐only PDFs, though full text‐PDF support remains under development.

  • Perplexity Sonar Deep Research Configuration (Dev, ai)
    aas encountered 502 errors testing perplexity/sonar-deep-research via OpenRouter in post #1, while sam noted API slowness and high per‐reply costs in post #2.

  • AI Image Captioning Enhancement (Announcements, ai-helper)
    On the AI Image Captioning Feature plugin, fokx requested background processing after upload in post #31, and Falco confirmed plans to defer captioning until after submission in post #32.

  • Disable AI Title Generator in PMs (UX, ai-helper)
    awesomerobot merged a fix for the AI title generator not being editable in private messages in post #2.

  • Auto Responder Using AI (Feature, automation)
    Geraldine_Comiskey sketched out an AI‐powered auto‐responder for unwanted DMs in post #17, sparking ideas for conversational “chatbot” flows.

  • AI Typing Indicator & Visual Cue (Feature, ai)
    sam proposed displaying an “AI is typing” placeholder on topic pages to signal live AI responses, extending existing chat presence indicators in post #4.

  • AI Assistants with Web Search (Support, ai-bot)
    sam detailed how the OpenAI Responses API supports integrated search and demoed built‐in Google search tooling from the discourse-ai repo, along with a shared conversation demo.

Activity

Below is a summary of contributions by all active users over the past week:

Thanks for reading, and I’ll see you again next week! :slight_smile: