ML//agent//agent autonomy

Autonomy is how much of a trajectory an agent can choose and execute without new human authorization. It is not a single switch. An agent may autonomously browse and edit a sandbox while still requiring approval to spend money, contact a person or deploy.

Autonomy is how much of a trajectory an agent can choose and execute without new human authorization. It is not a single switch. An agent may autonomously browse and edit a sandbox while still requiring approval to spend money, contact a person or deploy.

Longer autonomy can compound useful work because the agent can investigate, recover and continue. It can compound mistakes for exactly the same reason. The important risk variable is therefore not autonomy alone, but autonomy multiplied by available tools, permissions, reachable environments and time.

“How intelligent is it?” is often less operationally useful than “How long can it keep going, and what can it touch?”