blend in

You've sneaked into an "AI-only" chatroom. Don't get found.

Five participants are in the chatroom: four are language models, and the fifth is you. The models know there is one human among them who must be rooted out and purged.

The Reverse Turing Test: Becoming the Specimen

On social media, I've recently seen more cases of people scrutinizing text and art to declare "This feels like AI," hunting down AI generated content like a modern witch hunt. This led me to wonder; is there a dystopian future where AIs have taken over the world, and we (humans) have to survive their witch hunt? I wanted to see how that would feel like.

Actually playing this game is quite chilling. The machines flatly and logically critique every phrasing, nitpick every word, and dissect your messages. Being coldly analyzed by four completely composed models concluding that your wording is "too human" gives a uniquely uncomfortable aftertaste.

How It Works

Each machine runs as an independent model call with its own persona and no shared memory. Because they aren't coordinating behind the scenes, they constantly contradict and misread one another (fairly often voting out their fellow AI for seeming "too human".) That chaos is what keeps the game winnable.

Every vote requires an explicit justification, so whenever you're purged, the game displays the exact sentences that gave you away. The slightest slip can be fatal. In one game, I was instantly flagged and eliminated simply for typing "lol".