alt Hacker NewsI'm no expert, but wouldn't a basic hardware firewall that allows incoming, but not outgoing connections solve the issue? Wouldn't even basic VLAN isolation achieve the same? The humans can still open a TCP connection, SSH tunnel, etc. from the outside to remotely get data out of the training environment. But the agents cannot reach anything outside their isolated network.
Yes it would. It's not perfect like a literal air-gap, but it's the bare minimum. Had the agents breached a real, properly configured firewall product, that would've been a real watershed moment.