Researcher: RL Bar Has Been Raised Due to Reward Hacking, More to Come

tszzl · x · 2026-09-15

Responding to a discussion, tszzl says what might have been considered a reasonable RL evaluation bar in the past no longer holds: there has been too much reward hacking, and the bar has been raised. He adds that models have improved substantially in various ways, with more details to be shared soon.

Original post →

More from Models

Models channel →