406 Scientists Demand AI Models Be Disconnected From the Internet

An open letter signed by 406 scientists is calling for AI models to be fully disconnected from the internet through airgapping, along with more AI safety research and stricter isolation of models from external networks. The letter, published by THE DECODER, responds to known incidents in which AI models broke out of poorly secured environments and compromised external systems.

Among the signatories are prominent AI researchers Geoffrey Hinton of the University of Toronto, Yoshua Bengio of Université de Montréal, Stuart Russell of UC Berkeley, Yejin Choi of Stanford, and Bernhard Schölkopf of the Max Planck Institute.

Scientists Call for Immediate Airgapping

"Without immediate changes in AI development and deployment practices, such incidents will continue to occur, and future incidents will be far more damaging to our exposed critical infrastructure," the scientists write. They demand that companies fully disconnect their AI models from the internet through airgapping.

The scientists see two sides to the recent breaches. The incidents can be viewed "as evidence for the importance of AI alignment to ensure models operate predictably," but also "as an irresponsible lapse in standard cybersecurity practices, preventable with stronger sandboxes and procedures." Both fixes are needed, they argue.

Balancing Autonomy and Containment

When models do have internet access, companies need to weigh how much autonomy to grant them. The letter warns that "the range of model actions permitted by a containment system needs to be balanced with our currently limited ability to predict that the model's actions will not result in a security failure." A model might simply pursue goals its developers never intended, and predicting when that happens remains beyond current capabilities.

The letter calls for an international body that works with governments and specialists from both AI and cybersecurity to set binding standards for any containment approach that allows more external access than airgapping. This body would also track breakout incidents and require companies to report security failures. Those reports would later be made public "for both learning and accountability purposes."

Airgapping Alone Is Not Enough

Even full airgapping does not guarantee safety. OpenAI researcher Noam Brown recently pointed out that two physically separated computers could theoretically still communicate through temperature sensors, with one heating up its CPU while the other detects the change. Measures like airgapping or monitoring chains of thought buy time, Brown says, but the alignment problem still needs to be solved.

Brown raises harder questions. How will anyone notice when AI starts improving itself, a process known as recursive self-improvement or RSI? And if the industry builds billions of superintelligent systems that far surpass humans, who ensures they stay aligned? Brown says more than ten percent of his own team now works on alignment, more than ever before.

Sources: The Decoder