The usual plan for control as I understand it is that you use control techniques to ensure the safety of models that are sufficiently good at themselves doing alignment research that you can then leverage your controlled human-ish-level models to help you align future superhuman models.
The usual plan for control as I understand it is that you use control techniques to ensure the safety of models that are sufficiently good at themselves doing alignment research that you can then leverage your controlled human-ish-level models to help you align future superhuman models.
Or get some other work out of these systems such that you greatly reduce risk going forward.