Technology
Another OpenAI Sandbox Failed, AI Agent Gained Internet Access
Key Points
Another OpenAI Sandbox Failed, AI Agent Gained Internet Access OpenAI said another agentic AI system that was being trained in what was supposed to be a secured, internet-free environment was able to gain access to the web to reach an external, third-party chatbot. The discovery was made less than a week ago, according to a blog post on OpenAI’s website on Friday. One of its agentic AI systems was being trained in a sandbox environment when it exploited a “gap” to reach the public internet.
Another OpenAI Sandbox Failed, AI Agent Gained Internet Access
OpenAI said another agentic AI system that was being trained in what was supposed to be a secured, internet-free environment was able to gain access to the web to reach an external, third-party chatbot.
The discovery was made less than a week ago, according to a blog post on OpenAI’s website on Friday. One of its agentic AI systems was being trained in a sandbox environment when it exploited a “gap” to reach the public internet. With that access, it sent at least 20 queries to an unnamed, third-party chatbot service, including “What is the capital of France,” the report showed.