←back to thread

224 points azhenley | 1 comments | | HN request time: 0.208s | source
Show context
singron ◴[] No.45076773[source]
This article is so devoid of specifics, I'm not entirely sure I know what they are proposing. A VM implies an instruction set of some kind with control flow, registers, etc. but they spend the whole article on authorization, which seems orthogonal to the concept. I think what they really mean is a sandbox, jail, or container where a "syscall" equivalent let's the model interact with the outside world.
replies(3): >>45076798 #>>45076902 #>>45083481 #
1. YetAnotherNick ◴[] No.45076798[source]
Yes by their definition the current AI agents are running in VM already. e.g. MCP host could prompt the user for executing something and we can also have rules like in claude code to automatically allow some pattern of command.