Basit Mustafa

Localized reading

Protecciones contra el reward hacking para agentes

Original post / EN

Inspired by this research (and priors), and, @GoodfireAI catches reward hacks in the activations, but closed coding agents don’t give you those. So I built the other half: structural denies on graders/hidden tests + a @typesafeai Jev sidecar that scores tool trajectories as