Unwanted bots

AI-generated summary

The discussion addresses user concerns regarding the sudden appearance of multiple bot accounts on their Discourse instance. Andro reported these uncreated bots appearing after recent updates, despite not enabling AI features, and asked how to remove them. nickdb explained that these agents are part of the core build and were recently refactored from a single account into individual accounts for specific features, citing this pull request. While acknowledging that users who do not utilize AI might prefer to remove these dependencies, nickdb emphasized that the AI agent is becoming integral to platform security, particularly for anti-spam measures.

satonotdead expressed a preference for a single unified user for all AI bots, arguing that separating them by agent complicates usage in chat and personal messages. In response, nickdb suggested creating a custom agent bound to necessary built-in tools as an alternative. They defended the current task-specific approach, noting that it enhances accuracy and consistency, even while acknowledging the appeal of a simpler, less cluttered interface.

I have not enabled any Ai features as far as I am aware. But suddenly there are a whole lot of bot accounts i did not create. These appeared after the latest set of updates. Why did these get created and how can I get rid of them? I have no need of Ai for the forum.

They are part of the build whether you use them or not, recently a single account for the agent was broken out to individual ones for the relevant features.

Something I also noticed. If the system will let you, can’t see why you can’t remove them and their dependencies, if you will never use them.

It’s something that is becoming integral to the platform, I couldn’t imagine anti-spam without the AI agent..

I still think it would be great to be able to use just one user for all the AI bots.

Keeping them separated by agent makes using them from chat or personal message users extremely complicated.

You could just create your own agent and bind the required, built-in, discourse tools to it.

I am also a fan of the less-is-more philosophy but there is something to be said about the agentic approach, being task-specific. Makes accuracy and consistency better imo.