Researchers say isolating AIs from the internet limits realistic testing
Physically isolating computers — known as air gapping — can make it harder for AI agents to reach external targets or for outside systems to enter a test environment. However, researchers interviewed by The Verge say the measure reduces the realism of evaluations, which often require external services, APIs and digital infrastructure, while increasing costs and slowing iterations. Applying it to every experiment could also delay the development of new models and may not be feasible at the scale of frontier AI labs.
Isolation would not eliminate every risk: agents could still compromise systems inside the environment or produce dangerous artifacts if they were moved outside it. The barrier could also be breached through methods such as USB devices or signals transmitted by internal components, although those routes are difficult. Researchers therefore describe air gapping as a trade-off between safety and realism, rather than a definitive technical solution.
Why it matters · editorial interpretation
Physical isolation may reduce attack paths, but researchers interviewed by The Verge say it also limits evaluations that depend on external services and makes iterations more costly and slower. This leaves labs with a practical trade-off between experimental safety and test realism, rather than a definitive solution.
Sources
ResearchSecurityAgents