I want to be dead clear about this, because it’s the entire reason Gorai exists: this is not a robotics framework that happens to tolerate AI. It’s a robotics framework designed because of AI. The bet is simple — the robots worth building from here on out are going to be driven, at least in part, by agents. So we designed for that on day one, not as a bolt-on you duct-tape onto the side later.
Seems like a shaky bet. I think I'd rather not have "agents" tightly coupled with my hardware controllers.
second thing, this
Safety enforced at the capability node, not trusted to the agent
Misses the point of why thinking about software as agents is dangerous, particularly in the context of robotics. Two or more agents may simultaneously decide to take actions that, on their own, aren't dangerous, but when performed at the same time can produce a dangerous situation that neither "agent" could foresee. the more agents, the more complicated bodies you have to account for in the system, and it quickly becomes unpredictable.