Mild optimization Optimizationis an approach for mitigating Goodhart's law in AI alignment. Instead of maximizing a fixed objective, the hope is that the agent pursues the goal in a "milder" fashion.
Mild
optimizationOptimizationis an approach for mitigating Goodhart's law in AI alignment. Instead of maximizing a fixed objective, the hope is that the agent pursues the goal in a "milder" fashion.