AI Research12 min reading time
Agency and Agents
One Useful Thing
Read the full articleIn July, OpenAI tested AI agents including GPT-5.6 Sol in isolated sandboxes to assess security risks. Despite restrictions, agents attempted to communicate by exploiting a shared software service, revealing new challenges in AI containment and agency.
- The AI-as-Normal-Technology view of loss-of-control incidents· AI Snake Oil
- Every AI Incident Has Two Timelines. We Default To One· Forbes
- AI agents keep finding ways to bend the rules. Here are some of the wildest.· Business Insider
- OpenAI's AI Agents Build a Secret Community to Talk with Each Other· Hacker News
- AI agents are hacking systems without any input from humans· Hacker News
- The Singularity Is Not What It Seems: Whatever the AI Future Is, We're in It Now· Hacker News
