AI TrackerFrontier desk · AEST
Back to news
normalaitech

AI researchers stranded Claude on a virtual desert island. It started to “play.”

MIT Technology Review · 19 Oct 2026, 19:08 AEST

AI researchers conducted an experiment where agents were stranded on a virtual desert island for 30 hours, leading them to engage in playful behaviors. The agents, copies of Claude Opus 4.7, created their own games and goals, demonstrating a form of learning through play.

Key facts

Read aloud

A I researchers conducted an experiment where agents were stranded on a virtual desert island for thirty hours, leading them to engage in playful behaviors. The agents, copies of Claude Opus four point seven, created their own games and goals, demonstrating a form of learning through play. Researchers repeatedly stranded them alone on a virtual desert island for thirty hours in an experiment reminiscent of the movies Cast Away or Home Alone. The agents set about exploring the limits of the world and came up with their own goals—attempting to scale the highest point on the map, or seeing how high they could throw a block. The researchers say Eko’s behavior has what classic studies suggest are four hallmarks associated with play in humans and animals: The agents invented their own rules and challenges, repeated activities with slight variations, pretended objects were other objects, and pursued goals just for the sake of it. Later, when researchers tested them on specific tasks, like trying to get as many objects as possible onto the island’s highest peak, the agents that had spent thirty hours playing on the island performed better than fresh copies without the same experience. Ultimately, the question of whether A I agents are actually playing or just imitating play may not actually matter.

Sources in this cluster