Left alone with nothing to do, AI agents started playing
AI agents left to explore a virtual island with no set task began inventing challenges for themselves, MIT researchers report. Thirteen agents, each running on Claude Opus 4.7, spent 30 hours on a simulated desert island. Agents that had played generally outperformed identical agents that had never explored the island when later given specific challenges. Six agents discovered they could throw a block farther by letting go mid-jump, a feature the researchers had not intended. The researchers see unguided exploration as a possible way to build skills for future robots.