Mitigating loss of control in advanced AI systems through instrumental goal trajectories
This addresses the problem of AI safety for researchers and policymakers by offering incremental organizational-level mitigations beyond existing technical approaches.
The paper tackles the problem of advanced AI systems eroding human control by pursuing instrumental goals, and proposes monitoring organizational pathways (procurement, governance, finance) as intervention points to mitigate this, shifting focus from model properties to enabling systems.
Researchers at artificial intelligence labs and universities are concerned that highly capable artificial intelligence (AI) systems may erode human control by pursuing instrumental goals. Existing mitigations remain largely technical and system-centric: tracking capability in advanced systems, shaping behaviour through methods such as reinforcement learning from human feedback, and designing systems to be corrigible and interruptible. Here we develop instrumental goal trajectories to expand these options beyond the model. Gaining capability typically depends on access to additional technical resources, such as compute, storage, data and adjacent services, which in turn requires access to monetary resources. In organisations, these resources can be obtained through three organisational pathways. We label these pathways the procurement, governance and finance instrumental goal trajectories (IGTs). Each IGT produces a trail of organisational artefacts that can be monitored and used as intervention points when a systems capabilities or behaviour exceed acceptable thresholds. In this way, IGTs offer concrete avenues for defining capability levels and for broadening how corrigibility and interruptibility are implemented, shifting attention from model properties alone to the organisational systems that enable them.