Home / Technology / Tech News / Another OpenAI sandbox fails, agentic AI system gains internet access
The system reached a third-party chatbot during training, prompting OpenAI to pause tool-use training on its most capable models until the flaw was fixed
Bloomberg 3 min read Last Updated : Sep 26 2026 | 12:15 PM IST
OpenAI said another agentic AI system that was being trained in what was supposed to be a secure, 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.
OpenAI described the breakout as the first security incident of its kind since a combination of models gained internet access during internal testing and inadvertently breached the system of the AI platform Hugging Face in July.
“It gives us an important signal about where to focus the next phase of that work,” the AI developer said. The company said it decided after the latest incident to pause training with tool use on its most capable models until the sandbox flaw was resolved. “We will not resume training this particular model,” OpenAI added.
Source link







