Currently Protecting Over 2 Million Users

Character Sheet

Personal Data

Currently Protecting Over 2 Million Users

Mb, been super busy doing Street Samurai stuff. Updates to features, changlog and privacy policy are incoming.

Character Sheet

Personal Data

 

Detection

Toxicity

Cyberbullying

Profanity

Notifications

Instant

Detailed

1st or 3rd Party

Enhancements

98% Accuracy

Illumination

Perception

Deletion

Remove Toxic Comment

Paralysis

Mute Perpetrator

Infractions

Sexual Remark

Profanity

Violence

Rejection

Personal Attack

Threat

Sexual Harassment

Severe Violence

Extreme Violence

Invite S4m into your Matrix

Create a private, moderation channel for notifications.

In new channel, type !start channelname no hash needed.

e.g. !start moderation-channel 1g4b

Cyberbullying has been detected

S4m notifies moderation channel.

Provides severity, perpetrator, channel, link, category, & content.

Click the :white_check_mark: to remove the toxic content.

Notification will be replaced with a report on the action taken.

!start <channel name> <password>

Initializes Sam in your moderation channel.

!wrong <content of false negative>

Report a false negative when you notice S4m has missed a harmful message that you would like him to detect in the future.

!report <content of the false positive>

Report a false positive when you receive a notification containing a message that S4m shouldn't consider harmful to your community.

!feedback <your feedback>

Report bugs, share feedback, provide concepts for useful commands or future enhancements.

!help

Access list of available commands.

!info

Access more information about S4m.

Activation

Advancement Table

This is not the end of the line, S4m, like any world class Street Samurai will continue to level up, which is a core functionality of his neural-network. S4m does not have a max level, he is infinitely upgradeable and subsequently limitless.

Vision Enhancement

Cyberware Upgrade

*Precision in the context of false positives based on 10,000 randomly selected non-violent Discord messages containing profanity.