A Quantilizer is a proposed AI design that aims to reduce the harms from Goodhart’s law and specification gaming by selecting reasonably effective actions from a distribution of human-like actions, rather than maximizing over actions. It is more of a theoretical tool for exploring ways around these problems than a practical buildable design.
See also
Quantilizers: AI That Doesn’t Try Too Hard by Rob Miles
Quantilizers: A Safer Alternative to Maximizers for Limited Optimization by Jessica Taylor (original paper)