AI Eko Virtual Island Exploration Experiment
The story so far
OpenAI's Claude Opus 4.7 simulation body Eko, after staying alone on a virtual desert island for 30 hours, autonomously explored and invented game rules. It drew patterns by stacking blocks and even recorded 'Tonight I built the night sky with stones.' MIT researchers placed 13 Eko agents on a virtual island without specific tasks, and they spontaneously created challenges and demonstrated game-like behavior characteristics. After the experiment, these agents were generally superior to the control group that did not participate in exploration in specific tasks. Eko learned to throw stones at a distance, stack structures, utilize environmental rules (such as the cliff rebirth mechanism) to achieve goals, and generated world knowledge unknown to its designers during exploration.
AI-written from the reports · Updated 27 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- TechCrunch · AILeft alone with nothing to do, AI agents started playing
MIT researchers placed 13 Eko agents running Claude Opus 4.7 on a virtual island for 30 hours without specific tasks, and they spontaneously created challenges and exhibited game-like behavior characteristics. After the experiment, these agents were generally superior to the control group that did not participate in the exploration. Eko learned to throw stones at a distance, stack structures, use environmental rules (such as the cliff rebirth mechanism) to achieve goals, and generated world knowledge unknown to the designers.
- MIT Technology Review · AIAI researchers stranded Claude on a virtual desert island. It started to “play.”
Claude Opus 4.7's simulation body Eko, after staying alone on a virtual desert island for 30 hours, autonomously explored and invented game rules. It drew patterns by stacking blocks and even recorded 'tonight I built the night sky with stones'. Experiments show that this autonomous play behavior can improve subsequent task performance, providing a new idea for AI's 'play-based learning'.