It's a variation of sandboxing which is a great idea. Even just using a separate user account on your laptop provides some useful level of isolation (as long as you don't give it sudo privileges). AI tools of course do some sandboxing of their own. It's just that the constant nagging for permissions causes people to negate most of that by giving very broad access outside the sandbox.

The downside for me and the main reason I do use vms less than I did a few months ago is that I need my agentic coding tools to use development tools a lot. And those tools need a lot of resources. And I have those resources on my laptop. Which is a nice mac book pro with plenty of RAM and 16 CPUs. I can run vms on this thing without issues of course. But tools just run a lot faster when I run them outside those VMs. And agentic coding tools run builds all the time. We're talking some really non trivial time savings here. Watching qemu build a thing for 10 minutes that I know should build in 45 seconds is painful. Especially if it happens over and over again.

The trick is doing sandboxing without performance impact. And very soon you'll also want to be able to run local models. I've been toying with the latest qwen and gemma models on my laptop. I haven't gotten around to doing coding with those just yet. But apparently they aren't completely horrible at it. That won't work on most cloud based vms. Unless you get a really big and expensive one. You could actually make that work if you only use them for a few minutes.