Description

An interactive simulation where different AI models (Gemini 4 Argon, GPT-6 Astra, Claude Opus 5.5, and Qwen 3.5-9B) are given the full world state every 5 seconds to adjust helm and sails. The experiment tests autonomous decision-making in a physics-based environment, tracking the performance and failure modes of each model as they navigate a course.

Descriptions, tags, and model credits may be AI-generated or inferred from public sources and can be incomplete or wrong. Learn more.