Also, their building up on top of a 'platform' is wonderful: funnel, exit nodes, sharing, ssh, drive etc.
I wonder if they can figure out a way to distribute compute eventually via their network (not just clunky ssh): 'my' storage is already shared with 'my' nodes, why not 'my' compute? :)
That was actually something we debated launching before Tailscale SSH but ended up doing Tailscale SSH first because the state problem for compute was annoying and we'd seen the App Engine etc progression through the problem space and knew it could be a time suck.
I still want to do it and we continue to brainstorm on the problem of state management and how to do it in an HA way, so you can run services where the compute bounces around some node in a set that's up and reachable on the tailnet but the state is durable and in sync between the nodes. It's a fun problem.
Looks like the layers are there for a Tailscale API: I could imagine writing a platform-independent Go 'app' that uses funnel+drive that could 'float' around the nodes.
Anyway, a fun problem (or worse, a solution looking for a problem as I couldn't immediately think of a problem that would require it just yet. May be distributed training and such)
I wonder if they can figure out a way to distribute compute eventually via their network (not just clunky ssh): 'my' storage is already shared with 'my' nodes, why not 'my' compute? :)
Seems like a great company/business.