Home of S4m(bot) the most precise toxicity detection AI in cyberspace Illuminates toxic dialogue so moderators can react immediately.
S4m is a bot that offers state-of-the-art detection of toxic messages powered by our neurosymbolic AI along with a suite of moderation tools that empower moderators to maintain peace in their community. S4m has been developed by Samurai Labs - an Artificial Intelligence Lab dedicated to the detection and de-escalation of violent speech online.
S4m distinguishes real violence from friendly banter or harmless swearing and differentiates between various categories of violence, from personal attacks and insults to queerphobic content, racism, sexual harassment, and threats.
Invite S4m now to get free life-long access and have power over influencing the creation of its features.
Once you set up S4m in your moderation channel, you’ll be able to configure him manually using YAML or commands or utilize our community-adjusted moderation presets. S4m can act completely autonomously or wait for the moderators’ decision, depending on the severity and category of detected violence.
