Bubsy Configuration
This is a work in progress but please visit https://bubsy.ai for latest information.
Bubsy currently has two features that can be configured: FUD Control and Spam Guard. Both features can be used to control the amount of negativity and spam in your communities.
Assisted FUD Control
FUD (Fear, Uncertainty, and Doubt) can range from fear-invoking questions to direct accusations and can harm the credibility of a project. To counter this, we have developed a model that understands and flags instances of negativity or fear-invoking questions. However, being an AI model, Bubsy can sometimes detect false positives. To address this, we have introduced a unique method that involves getting help from your community to eliminate false positives. How does it work? Whenever Bubsy flags someone for creating FUD, a timer initiates, notifying that the person will be muted for their negative message. The community has 15 seconds to prevent this from happening. If the community believes that the flag is justified, they don't have to do anything, and the member will be muted automatically. However, if the community believes it is a false positive, they have the option to stop this from happening.
Spam Guard
To counter the never-ending spam in Telegram communities, we have created a configurable model that can address spam such as excessive promotions, scam links, and more. Spammers are banned immediately.
Last updated
