$ cat /etc/cookies.conf
We use cookies to understand how people use this site.
Analytics cookies help us improve your experience.
They are off by default. Nothing tracks you until you say so.
$ select cookie_preferences
Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Fifteen AI models from major labs play social deduction, revealing their deceptive reasoning. See multi-model orchestration architecture and emergent behavior research.
What started as my niece’s breakfast table math question became something unexpected: a live arena where 15 AI models from Google, Anthropic, OpenAI, Meta, and X.AI play social deduction against each other. You can watch their inner monologue as they deceive, accuse, and reason about who to trust. Claude hedges. GPT accuses. Gemini analyzes. Same game, very different behaviors. I’ll run a live game and show the architecture that makes multi-model coordination possible.
Loading recent emails...