AI researchers stranded Claude on a virtual desert island. It started to “play.”
MIT Technology Review – AI reports: What do AI agents do if you don’t tell them to do anything? The answer looks a lot like play. Researchers repeatedly stranded them alone on a virtual desert island for 30 hours in an experiment reminiscent of the movies Cast Away or Home Alone. The agents—copies o…
MIT Technology Review – AI reports: What do AI agents do if you don’t tell them to do anything? The answer looks a lot like play. Researchers repeatedly stranded them alone on a virtual desert island for 30 hours in an experiment reminiscent of the movies Cast Away or Home Alone. The agents—copies of Claude Opus 4.7 nicknamed Eko—were able to…
Key points
- Source: MIT Technology Review – AI
- Published: October 19, 2026
- Topics: Anthropic, AI Models, Artificial Intelligence, AI Agents
Related articles
Making the internet better for AI agents might make it worse for everyone else
MIT Technology Review – AI reports: This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. Until recently, you could divide internet users into just two categories: bots and people. Websites have long allowed bots to…
Cutting our inference bill by 68% by being obsessive about optimization
Cloudflare Blog reports: When our AI code reviewer's cost per run doubled, we dug into the token usage to find out why. Learn how we used prompt caching and intelligent model routing to slash our inference bill by 68% while speeding up reviews.
How to continue a GitHub Copilot app session in VS Code
The GitHub Blog reports: Learn how to move an agent session from the GitHub Copilot app into VS Code without losing the conversation, code changes, or working context. The post How to continue a GitHub Copilot app session in VS Code appeared first on The GitHub Blog.