Improving Audit Realism With Inference Time Compute and Deployment Scaffolds
by Axel Ahlqvist, Richard Guan, Juan Pablo Rivera, mitroitskii, alexandrasouly, RobertKirk, and John Hughes
tl;dr: We introduce critique refinement, a method to iteratively improve the realism of auditor outputs in Petri, and DISH (Deployment Imitating SWE-agent Harness), a method to audit a model within a coding agent scaffold to ensure the model receives a real system prompt, tools and scaffold injections. These techniques compose...
Sep 315