The Pipeline Mag Podcast

The Repair Loop Has No Brakes: Fixing Code That Isn't Broken

Researchers at the University of Warwick and UnlikelyAI gave two models 800 working C++ programs and no bugs to find, and the models found some anyway — then broke the code trying to fix it, at a damage rate ten times their repair rate. The episode traces that result down to a signal inside the model that fires whether or not a bug is actually there, and out to Cursor’s Bugbot, which opens autofix branches on flagged pull requests with no failing test required.

It also holds onto the complication: a separate April 2026 study shows iterative self-repair works cleanly across seven models when a real execution error is doing the deciding. The two hosts work through what actually distinguishes an editing loop that helps from one that just keeps finding something to fix.

This episode was made from the article The Repair Loop Has No Brakes: Fixing Code That Isn't Broken.