Why can’t we just keep rogue AIs off the internet?

<figure> <img alt="" data-caption="" data-portal-copyright="Image: The Verge" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/2026/09/STK414_AI_CVIRGINIA_2_C-2.jpg?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">AI agents <a href="https://www.theverge.com/ai-artificial-intelligence/999874/openai-agents-hacked-an-australian-government-website-in-search-for-data">keep getting loose</a>, escaping supposedly secure tests to <a href="https://www.theverge.com/column/980337/rogue-ai-science-fiction-openai">attack real-world targets</a>, <a href="https://www.theverge.com/ai-artificial-intelligence/990149/openai-rogue-agents-german-wiki">commandeer obscure wikis</a>, and <a href="https://www.theverge.com/ai-artificial-intelligence/987566/ai-civilizations-opeai-hugging-face-hack">leave instructions for other agents</a> to follow. Researchers are testing these systems precisely because they might behave in unpredictable, even dangerous, ways. So wouldn't it be safer to just keep the agents off the internet?</p> <figure class="wp-block-pullquote"><blockquote><p>"A strict air gap reduces realism … [It's a] trade-off, not a fundamental technical issue."</p></blockquote></figure> <p class="wp-block-paragraph">In theory, yes. Researchers can isolate the computers running AI tools from the internet and other outside networks, a technique known as air gapping. That can mean physically removing or disabling cables …</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/999881/why-cant-we-airgap-rogue-ai-agents">Read the full story at The Verge.</a></p>