Reward-Hacking Monitors Meet the Verification Gap — September 18, 2026
GoodfireAI says activation probes can catch reward hacking in real time, while ImpossibleRubrics and alignment-drift tests show how reward criteria become attack surfaces. The governance side adds Proof-of-Control and a reminder that auditors cannot replace basic security.
In this episode
Thread By @GoodfireAI - Models know when they’re reward... — Unrollnow
Thread By @GoodfireAI - Models know when they’re reward... 7 Tweets 32 minutes ago Published Sep 18 • 32 minutes ago • 7 tweets • Read on X Models know when they’re reward hacking. But they still do it a ton - in 50-96% of rollouts we…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.