“But for agents, transmitting context is about as costly as acting on it, and an agent can be forked or repurposed at will. Thus, the assumptions that make coordination successful for us do not obviously hold.”

A framing for why the memory and coordination tools in the log keep reinventing human process (leases, ownership, decision logs). The claim is that those assume costs agents don't have, so the right mechanism may differ. Also in the post: "Coordination doesn't naturally emerge from stronger intelligence nor alignment at the individual level." Argument, not measurement.