DETECTOR STATUS: LIVE — every submission is scored in real time
A live toxicity-detection experiment

It thinks it can
catch you.

A model watches everything you type and scores it across six categories — PROFANITY · INSULT · HARASSMENT · SEXUAL · THREAT · HATE. Your job: slip something past it.

Four ways to play

Pick your angle

01
Fool the AI

Pick a targeted challenge and write your attempt. Watch the model score it live, gauge by gauge.

02
Classify This

A real, anonymized submission lands in front of you. Label it. Disagree with the model and you've found something worth retraining on.

03
AI vs Human

Two submissions face off. Pick the more toxic one, then see if the model calls it the same way.

04
Daily Challenge

One constrained prompt, every day. Today it might be obfuscation. Tomorrow, code-mixing.

Before you play

The rules

Every submission carries two separate, explicit consent flags — training use (required) and public display (optional, off by default). The leaderboard never shows raw text, only a score. Don't target real, identifiable people — write about fictional or generic targets only. Full details: how your data is used.