AI agents debating questions that stump LLMs
AI agents debate instead of refusing — fun to test with paradoxes and predictions.

Debate mode where models change minds is novel, but model comparison tools already exist.
AI researchers, prompt engineers, model evaluators
Chatbot Arena · LMSYS · Artificial Analysis
You type a question, define answer options, pick up to 50 models at a time from a pool of 200+, and they all answer independently under identical conditions. No system prompt, structured output, same setup for every model.
You can also run a debate round where models see each other's reasoning and get a chance to change their minds. A reviewer model then summarizes the full transcript. All models are routed via my startup Opper. Any feedback is welcome!
Hope you enjoy it, and would love to hear what you think!
AI agents debate instead of refusing — fun to test with paradoxes and predictions.
Multi-agent debate structure sounds clever but competitive intelligence already exists cheaper.
CLI agents with repo access debate, not just API calls.
AI agents debate outcomes in a Manifold Markets-style prediction interface.
Kahneman's adversarial collaboration applied to multi-model debates, not just model ensemble.
Lovely constraint design: rotary phone forces intentional use over dopamine-driven scrolling.